Initial commit

This commit is contained in:
Alex committed 2026-11-02 22:54:14 +08:00
commit 57fc3525eb
7311 files changed
+1291398

No files matched your search

@@ -0,0 +1,28 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
允许任何人以个人身份使用或分发本项目源代码,但仅限于学习和合法非盈利目的。
个人或组织如未获得版权持有人授权,不得将本项目以源代码或二进制形式用于商业行为。
使用本项目需满足以下条款,如使用过程中出现违反任意一项条款的情形,授权自动失效。
* 禁止将DrissionPage应用到任何可能违反当地法律规定和道德约束的项目中
* 禁止将DrissionPage用于任何可能有损他人利益的项目中
* 禁止将DrissionPage用于攻击与骚扰行为
* 遵守Robots协议,禁止将DrissionPage用于采集法律或系统Robots协议不允许的数据
使用DrissionPage发生的一切行为均由使用人自行负责。
因使用DrissionPage进行任何行为所产生的一切纠纷及后果均与版权持有人无关,
版权持有人不承担任何使用DrissionPage带来的风险和损失。
版权持有人不对DrissionPage可能存在的缺陷导致的任何损失负任何责任。
"""
from ._base.chromium import Chromium
from ._configs.chromium_options import ChromiumOptions
from ._configs.session_options import SessionOptions
from ._pages.chromium_page import ChromiumPage
from ._pages.session_page import SessionPage
from ._pages.web_page import WebPage
from .version import __version__
@@ -0,0 +1,17 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from ._base.chromium import Chromium
from ._configs.chromium_options import ChromiumOptions
from ._configs.session_options import SessionOptions
from ._pages.chromium_page import ChromiumPage
from ._pages.session_page import SessionPage
from ._pages.web_page import WebPage
from .version import __version__
__all__ = ['WebPage', 'ChromiumPage', 'Chromium', 'ChromiumOptions', 'SessionOptions', 'SessionPage', '__version__']
@@ -0,0 +1,362 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from abc import abstractmethod
from copy import copy
from pathlib import Path
from re import sub
from urllib.parse import quote
from DrissionGet import DrissionGet
from requests import Session
from .._configs.session_options import SessionOptions
from .._elements.none_element import NoneElement
from .._functions.elements import get_frame, get_eles
from .._functions.locator import get_loc
from .._functions.settings import Settings as _S
from .._functions.web import format_html
from ..errors import ElementNotFoundError, LocatorError
class BaseParser(object):
def __call__(self, locator):
return self.ele(locator)
def ele(self, locator, index=1, timeout=None):
return self._ele(locator, timeout, index=index, method='ele()')
def eles(self, locator, timeout=None):
return self._ele(locator, timeout, index=None)
def find(self, locators, any_one=True, first_ele=True, timeout=None):
if 'Session' in self._type:
timeout = 0
if timeout is None:
timeout = self.timeout
r = get_eles(locators, self, any_one, first_ele, timeout)
if any_one:
for ele in r:
if r[ele]:
return ele, r[ele]
return None, None
return r
# ----------------以下属性或方法待后代实现----------------
@property
def html(self):
return ''
def s_ele(self, locator=None):
pass
def s_eles(self, locator):
pass
def _ele(self, locator, timeout=None, index=1, raise_err=None, method=None):
pass
def _find_elements(self, locator, timeout, index=1, relative=False, raise_err=None):
pass
class BaseElement(BaseParser):
def __init__(self, owner=None):
self.owner = owner
self._type = 'BaseElement'
def get_frame(self, loc_or_ind, timeout=None):
if not isinstance(loc_or_ind, (int, str, tuple)):
raise ValueError(_S._lang.join(_S._lang.INCORRECT_TYPE_, 'loc_or_ind',
ALLOW_TYPE=_S._lang.LOC_OR_IND, CURR_VAL=loc_or_ind))
return get_frame(self, loc_ind_ele=loc_or_ind, timeout=timeout)
def _ele(self, locator, timeout=None, index=1, relative=False, raise_err=None, method=None):
if hasattr(locator, '_type'):
return locator
if timeout is None:
timeout = self.timeout
r = self._find_elements(locator, timeout=timeout, index=index, relative=relative, raise_err=raise_err)
if r or isinstance(r, list):
return r
if raise_err is True or (_S.raise_when_ele_not_found and raise_err is None):
raise ElementNotFoundError(METHOD=method, ARGS={'locator': locator, 'index': index, 'timeout': timeout})
r.method = method
r.args = {'locator': locator, 'index': index, 'timeout': timeout}
return r
@property
def timeout(self):
return self.owner.timeout if self.owner else 10
@property
def child_count(self):
return int(self._ele('xpath:count(./*)'))
# ----------------以下属性或方法由后代实现----------------
@property
def tag(self):
return
def parent(self, level_or_loc=1):
pass
def next(self, index=1):
pass
def nexts(self):
pass
class DrissionElement(BaseElement):
@property
def link(self):
return self.attr('href') or self.attr('src')
@property
def css_path(self):
return self._get_ele_path(xpath=False)
@property
def xpath(self):
return self._get_ele_path()
@property
def comments(self):
return self.eles('xpath:.//comment()')
def texts(self, text_node_only=False):
texts = self.eles('xpath:/text()') if text_node_only else [x if isinstance(x, str) else x.text
for x in self.eles('xpath:./text() | *')]
return [format_html(x.strip(' ').rstrip('\n')) for x in texts if x and sub('[\r\n\t ]', '', x) != '']
def parent(self, level_or_loc=1, index=1, timeout=None):
if isinstance(level_or_loc, int):
loc = f'xpath:./ancestor::*[{level_or_loc}]'
elif isinstance(level_or_loc, (tuple, str)):
loc = get_loc(level_or_loc, True)
if loc[0] == 'css selector':
raise LocatorError(_S._lang.UNSUPPORTED_CSS_SYNTAX)
loc = f'xpath:./ancestor::{loc[1].lstrip(". / ")}[{index}]'
else:
raise ValueError(_S._lang.join(_S._lang.INCORRECT_TYPE_, 'level_or_loc', ALLOW_TYPE='tuple, int, str',
CURR_VAL=level_or_loc))
return self._ele(loc, timeout=timeout, relative=True, raise_err=False, method='parent()')
def child(self, locator='', index=1, timeout=None, ele_only=True):
if isinstance(locator, int):
index = locator
locator = ''
if not locator:
loc = '*' if ele_only else 'node()'
else:
loc = get_loc(locator, True) # 把定位符转换为xpath
if loc[0] == 'css selector':
raise LocatorError(_S._lang.UNSUPPORTED_CSS_SYNTAX)
loc = loc[1].lstrip('./')
node = self._ele(f'xpath:./{loc}', timeout=timeout, index=index, relative=True, raise_err=False)
return node if node else NoneElement(self.owner, 'child()',
{'locator': locator, 'index': index, 'ele_only': ele_only})
def prev(self, locator='', index=1, timeout=None, ele_only=True):
return self._get_relative('prev()', 'preceding', True, locator, index, timeout, ele_only)
def next(self, locator='', index=1, timeout=None, ele_only=True):
return self._get_relative('next()', 'following', True, locator, index, timeout, ele_only)
def before(self, locator='', index=1, timeout=None, ele_only=True):
return self._get_relative('before()', 'preceding', False, locator, index, timeout, ele_only)
def after(self, locator='', index=1, timeout=None, ele_only=True):
return self._get_relative('after()', 'following', False, locator, index, timeout, ele_only)
def children(self, locator='', timeout=None, ele_only=True):
if not locator:
loc = '*' if ele_only else 'node()'
else:
loc = get_loc(locator, True) # 把定位符转换为xpath
if loc[0] == 'css selector':
raise LocatorError(_S._lang.UNSUPPORTED_CSS_SYNTAX)
loc = loc[1].lstrip('./')
loc = f'xpath:./{loc}'
nodes = self._ele(loc, timeout=timeout, index=None, relative=True)
return [e for e in nodes if not (isinstance(e, str) and sub('[ \n\t\r]', '', e) == '')]
def prevs(self, locator='', timeout=None, ele_only=True):
return self._get_relatives(locator=locator, direction='preceding', timeout=timeout, ele_only=ele_only)
def nexts(self, locator='', timeout=None, ele_only=True):
return self._get_relatives(locator=locator, direction='following', timeout=timeout, ele_only=ele_only)
def befores(self, locator='', timeout=None, ele_only=True):
return self._get_relatives(locator=locator, direction='preceding',
brother=False, timeout=timeout, ele_only=ele_only)
def afters(self, locator='', timeout=None, ele_only=True):
return self._get_relatives(locator=locator, direction='following',
brother=False, timeout=timeout, ele_only=ele_only)
def _get_relative(self, func, direction, brother, locator='', index=1, timeout=None, ele_only=True):
if isinstance(locator, int):
index = locator
locator = ''
node = self._get_relatives(index, locator, direction, brother, timeout, ele_only)
return node if node else NoneElement(self.owner, func,
{'locator': locator, 'index': index, 'ele_only': ele_only})
def _get_relatives(self, index=None, locator='', direction='following', brother=True, timeout=.5, ele_only=True):
brother = '-sibling' if brother else ''
if not locator:
loc = '*' if ele_only else 'node()'
else:
loc = get_loc(locator, True) # 把定位符转换为xpath
if loc[0] == 'css selector':
raise LocatorError(_S._lang.UNSUPPORTED_CSS_SYNTAX)
loc = loc[1].lstrip('./')
loc = f'xpath:./{direction}{brother}::{loc}'
if index is not None:
index = index if direction == 'following' else -index
nodes = self._ele(loc, timeout=timeout, index=index, relative=True, raise_err=False)
if isinstance(nodes, list):
nodes = [e for e in nodes if not (isinstance(e, str) and sub('[ \n\t\r]', '', e) == '')]
return nodes
# ----------------以下属性或方法由后代实现----------------
@property
def attrs(self):
return
@property
def text(self):
return
@property
def raw_text(self):
return
@abstractmethod
def attr(self, name):
return ''
def _get_ele_path(self, xpath=True):
return ''
def _find_elements(self, locator, timeout, index=1, relative=False, raise_err=None):
pass
class BasePage(BaseParser):
def __init__(self):
self._url = None
self._url_available = None
self.retry_times = 3
self.retry_interval = 2
self._DrissionGet = None
self._download_path = None
self._none_ele_return_value = False
self._none_ele_value = None
self._session = None
self._headers = None
self._session_options = None
self._type = 'BasePage'
@property
def title(self):
ele = self._ele('xpath://title', raise_err=False, method='title')
return ele.text if ele else None
@property
def url_available(self):
return self._url_available
@property
def download_path(self):
return self._download_path
@property
def download(self):
if self._DrissionGet is None:
if not self._session:
self._create_session()
self._DrissionGet = DrissionGet(driver=self, save_path=self.download_path)
return self._DrissionGet
def _before_connect(self, url, retry, interval):
is_file = False
if isinstance(url, Path) or ('://' not in url and ':\\\\' not in url):
p = Path(url)
if p.exists():
url = str(p.absolute())
is_file = True
self._url = url if is_file else quote(url, safe='-_.~!*\'"();:@&=+$,/\\?#[]%')
retry = retry if retry is not None else self.retry_times
interval = interval if interval is not None else self.retry_interval
return retry, interval, is_file
def _set_session_options(self, session_or_options=None):
if not session_or_options:
self._session_options = SessionOptions(session_or_options)
elif isinstance(session_or_options, SessionOptions):
self._session_options = session_or_options
elif isinstance(session_or_options, Session):
self._session_options = SessionOptions()
self._session = copy(session_or_options)
self._headers = self._session.headers
self._session.headers = None
def _create_session(self):
if not self._session_options:
self._set_session_options()
self._session, self._headers = self._session_options.make_session()
# ----------------以下属性或方法由后代实现----------------
@property
def url(self):
return
@property
def json(self):
return
@property
def user_agent(self):
return
@abstractmethod
def get(self, url, show_errmsg=False, retry=None, interval=None):
pass
def _ele(self, locator, timeout=None, index=1, raise_err=None, method=None):
if not locator:
raise ElementNotFoundError(METHOD=method, ARGS={'locator': locator, 'index': index, 'timeout': timeout})
if timeout is None:
timeout = self.timeout
r = self._find_elements(locator, timeout=timeout, index=index, raise_err=raise_err)
if r or isinstance(r, list):
return r
if raise_err is True or (_S.raise_when_ele_not_found and raise_err is None):
raise ElementNotFoundError(METHOD=method, ARGS={'locator': locator, 'index': index, 'timeout': timeout})
r.method = method
r.args = {'locator': locator, 'index': index, 'timeout': timeout}
return r
@@ -0,0 +1,449 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from abc import abstractmethod
from typing import Union, Tuple, List, Any, Optional, Dict
from DrissionGet import DrissionGet
from requests import Session
from requests.structures import CaseInsensitiveDict
from .._configs.session_options import SessionOptions
from .._elements.chromium_element import ChromiumElement
from .._elements.none_element import NoneElement
from .._elements.session_element import SessionElement
from .._functions.elements import SessionElementsList
from .._pages.chromium_frame import ChromiumFrame
from .._pages.chromium_page import ChromiumPage
from .._pages.session_page import SessionPage
from .._pages.web_page import WebPage
class BaseParser(object):
"""所有页面、元素类的基类"""
_type: str
timeout: float
def __call__(self, locator: Union[Tuple[str, str], str], index: int = 1): ...
def ele(self,
locator: Union[Tuple[str, str], str, BaseElement],
index: int = 1,
timeout: float = None): ...
def eles(self, locator: Union[Tuple[str, str], str], timeout=None): ...
def find(self,
locators: Union[str, List[str], tuple],
any_one: bool = True,
first_ele: bool = True,
timeout: float = None) -> Union[Dict[str, ChromiumElement], Dict[str, SessionElement],
Dict[str, List[ChromiumElement]], Dict[str, List[SessionElement]], Tuple[str, SessionElement],
Tuple[str, ChromiumElement]]:
"""传入多个定位符,获取多个ele
:param locators: 定位符组成的列表
:param any_one: 是否任何一个定位符找到结果即返回
:param first_ele: 每个定位符是否只获取第一个元素
:param timeout: 超时时间(秒)
:return: any_one为True时,返回一个找到的元素定位符和对象组成的元组,格式:(loc, ele),全都没找到返回(None, None)
any_one为False时,返回dict格式,key为定位符,value为找到的元素或列表
"""
...
# ----------------以下属性或方法待后代实现----------------
@property
def html(self) -> str: ...
def s_ele(self,
locator: Union[Tuple[str, str], str, BaseElement, None] = None,
index: int = 1) -> SessionElement: ...
def s_eles(self, locator: Union[Tuple[str, str], str]) -> SessionElementsList: ...
def _ele(self,
locator: Union[Tuple[str, str], str],
timeout: float = None,
index: Optional[int] = 1,
raise_err: bool = None,
method: str = None): ...
def _find_elements(self,
locator: Union[Tuple[str, str], str],
timeout: float,
index: Optional[int] = 1,
relative: bool = False,
raise_err: bool = None): ...
class BaseElement(BaseParser):
"""各元素类的基类"""
owner: BasePage = ...
def __init__(self, owner: BasePage = None): ...
@property
def timeout(self) -> float:
"""返回其查找元素时超时时间"""
...
@property
def child_count(self) -> int:
"""返回直接子元素的个数"""
...
# ----------------以下属性或方法由后代实现----------------
@property
def tag(self) -> str: ...
def parent(self, level_or_loc: Union[tuple, str, int] = 1): ...
def prev(self, index: int = 1) -> None: ...
def prevs(self) -> None: ...
def next(self, index: int = 1): ...
def nexts(self): ...
def get_frame(self, loc_or_ind, timeout=None) -> ChromiumFrame:
"""获取元素中一个frame对象
:param loc_or_ind: 定位符、iframe序号,序号从1开始,可传入负数获取倒数第几个
:param timeout: 查找元素超时时间(秒)
:return: ChromiumFrame对象
"""
...
def _ele(self,
locator: Union[Tuple[str, str], str],
timeout: float = None,
index: Optional[int] = 1,
relative: bool = False,
raise_err: bool = None,
method: str = None):
"""调用获取元素的方法
:param locator: 定位符
:param timeout: 超时时间(秒)
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param relative: 是否相对定位
:param raise_err: 找不到时是否抛出异常
:param method: 调用的方法名
:return: 元素对象或它们组成的列表
"""
...
class DrissionElement(BaseElement):
"""ChromiumElement 和 SessionElement的基类,但不是ShadowRoot的基类"""
def __init__(self, owner: BasePage = None): ...
@property
def link(self) -> str:
"""返回href或src绝对url"""
...
@property
def css_path(self) -> str:
"""返回css path路径"""
...
@property
def xpath(self) -> str:
"""返回xpath路径"""
...
@property
def comments(self) -> list:
"""返回元素注释文本组成的列表"""
...
def texts(self, text_node_only: bool = False) -> list:
"""返回元素内所有直接子节点的文本,包括元素和文本节点
:param text_node_only: 是否只返回文本节点
:return: 文本列表
"""
...
def parent(self,
level_or_loc: Union[tuple, str, int] = 1,
index: int = 1,
timeout: float = None) -> Union[DrissionElement, None]:
"""返回上面某一级父元素,可指定层数或用查询语法定位
:param level_or_loc: 第几级父元素,1开始,或定位符
:param index: 当level_or_loc传入定位符,使用此参数选择第几个结果,1开始
:param timeout: 时间(秒)
:return: 上级元素对象
"""
...
def child(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[DrissionElement, str, NoneElement]:
"""返回直接子元素元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param index: 第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 直接子元素或节点文本组成的列表
"""
...
def prev(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[DrissionElement, str, NoneElement]:
"""返回前面的一个兄弟元素,可用查询语法筛选,可指定返回筛选结果的第几个
:param locator: 用于筛选的查询语法
:param index: 前面第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 兄弟元素
"""
...
def next(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[DrissionElement, str, NoneElement]:
"""返回后面的一个兄弟元素,可用查询语法筛选,可指定返回筛选结果的第几个
:param locator: 用于筛选的查询语法
:param index: 后面第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 兄弟元素
"""
...
def before(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[DrissionElement, str, NoneElement]:
"""返回前面的一个兄弟元素,可用查询语法筛选,可指定返回筛选结果的第几个
:param locator: 用于筛选的查询语法
:param index: 前面第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素前面的某个元素或节点
"""
...
def after(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[DrissionElement, str, NoneElement]:
"""返回后面的一个兄弟元素,可用查询语法筛选,可指定返回筛选结果的第几个
:param locator: 用于筛选的查询语法
:param index: 后面第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素后面的某个元素或节点
"""
...
def children(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> List[Union[DrissionElement, str]]:
"""返回直接子元素元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 直接子元素或节点文本组成的列表
"""
...
def prevs(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> List[Union[DrissionElement, str]]:
"""返回前面全部兄弟元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 兄弟元素或节点文本组成的列表
"""
...
def nexts(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> List[Union[DrissionElement, str]]:
"""返回后面全部兄弟元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 兄弟元素或节点文本组成的列表
"""
...
def befores(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> List[Union[DrissionElement, str]]:
"""返回后面全部兄弟元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素前面的元素或节点组成的列表
"""
...
def afters(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> List[Union[DrissionElement, str]]:
"""返回前面全部兄弟元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素后面的元素或节点组成的列表
"""
...
def _get_relative(self,
func: str,
direction: str,
brother: bool,
locator: Union[Tuple[str, str], str] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> DrissionElement:
"""获取一个亲戚元素或节点,可用查询语法筛选,可指定返回筛选结果的第几个
:param func: 方法名称
:param direction: 方向,'following' 或 'preceding'
:param locator: 用于筛选的查询语法
:param index: 前面第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素前面的某个元素或节点
"""
...
def _get_relatives(self,
index: int = None,
locator: Union[Tuple[str, str], str] = '',
direction: str = 'following',
brother: bool = True,
timeout: float = 0.5,
ele_only: bool = True) -> List[Union[DrissionElement, str]]:
"""按要求返回兄弟元素或节点组成的列表
:param index: 获取第几个,该参数不为None时只获取该编号的元素
:param locator: 用于筛选的查询语法
:param direction: 'following' 或 'preceding',查找的方向
:param brother: 查找范围,在同级查找还是整个dom前后查找
:param timeout: 查找等待时间(秒)
:return: 元素对象或字符串
"""
...
# ----------------以下属性或方法由后代实现----------------
@property
def attrs(self) -> dict: ...
@property
def text(self) -> str: ...
@property
def raw_text(self) -> str: ...
@abstractmethod
def attr(self, name: str) -> str: ...
def _get_ele_path(self, xpath: bool = True) -> str: ...
class BasePage(BaseParser):
"""页面类的基类"""
_url_available: Optional[bool] = ...
retry_times: int = ...
retry_interval: float = ...
_download_path: Optional[str] = ...
_DrissionGet: Optional[DrissionGet] = ...
_none_ele_return_value: bool = ...
_none_ele_value: Any = ...
_page: Union[ChromiumPage, SessionPage, WebPage] = ...
_session: Optional[Session] = ...
_headers: Optional[CaseInsensitiveDict] = ...
_session_options: Optional[SessionOptions] = ...
def __init__(self): ...
@property
def title(self) -> Union[str, None]:
"""返回网页title"""
...
@property
def url_available(self) -> bool:
"""返回当前访问的url有效性"""
...
@property
def download_path(self) -> str:
"""返回默认下载路径"""
...
@property
def download(self) -> DrissionGet:
"""返回下载器对象"""
...
def _before_connect(self, url: str, retry: int, interval: float) -> tuple:
"""连接前的准备
:param url: 要访问的url
:param retry: 重试次数
:param interval: 重试间隔
:return: 重试次数、间隔、是否文件组成的tuple
"""
...
def _set_session_options(self, session_or_options: Union[Session, SessionOptions] = None) -> None:
"""启动配置
:param session_or_options: Session、SessionOptions对象
:return: None
"""
...
def _create_session(self) -> None:
"""创建内建Session对象"""
...
# ----------------以下属性或方法由后代实现----------------
@property
def url(self) -> str: ...
@property
def json(self) -> dict: ...
@property
def user_agent(self) -> str: ...
@abstractmethod
def get(self, url: str, show_errmsg: bool = False, retry: int = None, interval: float = None): ...
def _ele(self,
locator,
timeout: float = None,
index: Optional[int] = 1,
raise_err: bool = None,
method: str = None):
"""调用获取元素的方法
:param locator: 定位符
:param timeout: 超时时间(秒)
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param raise_err: 找不到时是否抛出异常
:param method: 调用的方法名
:return: 元素对象或它们组成的列表
"""
...
@@ -0,0 +1,537 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from pathlib import Path
from re import match
from shutil import rmtree
from threading import Lock
from time import sleep, perf_counter
from requests import Session
from websocket import WebSocketBadStatusException
from .driver import BrowserDriver, Driver
from .._configs.chromium_options import ChromiumOptions
from .._functions.browser import connect_browser
from .._functions.cookies import CookiesList
from .._functions.settings import Settings as _S
from .._functions.tools import PortFinder, raise_error
from .._pages.chromium_base import Timeout
from .._pages.chromium_tab import ChromiumTab
from .._pages.mix_tab import MixTab
from .._units.downloader import DownloadManager
from .._units.setter import BrowserSetter
from .._units.states import BrowserStates
from .._units.waiter import BrowserWaiter
from ..errors import BrowserConnectError, CDPError, PageDisconnectedError, IncorrectURLError
__ERROR__ = 'error'
class Chromium(object):
_BROWSERS = {}
_lock = Lock()
def __new__(cls, addr_or_opts=None, session_options=None):
opt = handle_options(addr_or_opts)
is_headless, browser_id, is_exists, ws_only = run_browser(opt)
with cls._lock:
if browser_id in cls._BROWSERS:
r = cls._BROWSERS[browser_id]
while not hasattr(r, '_driver'):
sleep(.05)
return r
r = object.__new__(cls)
r._chromium_options = opt
r._is_headless = is_headless
r._is_exists = is_exists
r._ws_only = ws_only
r.id = browser_id
cls._BROWSERS[browser_id] = r
return r
def __init__(self, addr_or_opts=None, session_options=None):
if hasattr(self, '_created'):
return
self._created = True
self._type = 'Chromium'
self._frames = {}
self._drivers = {}
self._all_drivers = {}
self._relation = {}
self._newest_tab_id = None
self._set = None
self._wait = None
self._states = None
self._timeouts = Timeout(**self._chromium_options.timeouts)
self._load_mode = self._chromium_options.load_mode
self._download_path = str(Path(self._chromium_options.download_path).absolute())
self._auto_handle_alert = None
self._none_ele_return_value = False
self._none_ele_value = None
self.retry_times = self._chromium_options.retry_times
self.retry_interval = self._chromium_options.retry_interval
self.address = self._chromium_options.address
self._ws_address = (self._chromium_options.ws_address if self._chromium_options.ws_address
else f'ws://{self.address}/devtools/browser/{self.id}')
self._disconnect_flag = False
self._driver = BrowserDriver(self.id, self._ws_address, self)
if (not self._ws_only
and (not self._chromium_options._ua_set and self._is_headless != self._chromium_options.is_headless)
or (self._is_exists and self._chromium_options._new_env)):
self.quit(3, True)
connect_browser(self._chromium_options)
s = Session()
s.trust_env = False
s.keep_alive = False
ws = s.get(f'http://{self.address}/json/version', headers={'Connection': 'close'})
self.id = ws.json()['webSocketDebuggerUrl'].split('/')[-1]
self._driver = BrowserDriver(self.id, self._ws_address, self)
ws.close()
s.close()
self._is_exists = False
self._frames = {}
self._drivers = {}
self._all_drivers = {}
self.version = self._run_cdp('Browser.getVersion')['product']
self._process_id = None
try:
r = self._run_cdp('SystemInfo.getProcessInfo')
for i in r.get('processInfo', []):
if i['type'] == 'browser':
self._process_id = i['id']
break
except:
pass
self._run_cdp('Target.setDiscoverTargets', discover=True)
self._driver.set_callback('Target.targetDestroyed', self._onTargetDestroyed)
self._driver.set_callback('Target.targetCreated', self._onTargetCreated)
self._dl_mgr = DownloadManager(self)
self._session_options = session_options
@property
def user_data_path(self):
return self._chromium_options.user_data_path
@property
def process_id(self):
return self._process_id
@property
def timeout(self):
return self._timeouts.base
@property
def timeouts(self):
return self._timeouts
@property
def load_mode(self):
return self._load_mode
@property
def download_path(self):
return self._download_path
@property
def set(self):
if self._set is None:
self._set = BrowserSetter(self)
return self._set
@property
def states(self):
if self._states is None:
self._states = BrowserStates(self)
return self._states
@property
def wait(self):
if self._wait is None:
self._wait = BrowserWaiter(self)
return self._wait
@property
def tabs_count(self):
j = self._run_cdp('Target.getTargets')['targetInfos'] # 不要改用get,避免卡死
return len([i for i in j if i['type'] in ('page', 'webview') and not i['url'].startswith('devtools://')])
@property
def tab_ids(self):
if self._ws_only:
return [i['targetId'] for i in self._run_cdp('Target.getTargets')['targetInfos']
if i['type'] in ('page', 'webview') and not i['url'].startswith('devtools://')]
else:
return [i['id'] for i in self._driver.get(f'http://{self.address}/json').json()
if i['type'] in ('page', 'webview') and not i['url'].startswith('devtools://')]
@property
def latest_tab(self):
return self._get_tab(id_or_num=self.tab_ids[0], as_id=not _S.singleton_tab_obj)
def cookies(self, all_info=False):
cks = self._run_cdp(f'Storage.getCookies')['cookies']
r = cks if all_info else [{'name': c['name'], 'value': c['value'], 'domain': c['domain']} for c in cks]
return CookiesList(r)
def new_tab(self, url=None, new_window=False, background=False, new_context=False):
return self._new_tab(True, url=url, new_window=new_window, background=background, new_context=new_context)
def get_tab(self, id_or_num=None, title=None, url=None, tab_type='page'):
t = self._get_tab(id_or_num=id_or_num, title=title, url=url, tab_type=tab_type, mix=True, as_id=False)
if t._type != 'MixTab':
raise RuntimeError(_S._lang.join(_S._lang.TAB_OBJ_EXISTS))
return t
def get_tabs(self, title=None, url=None, tab_type='page'):
return self._get_tabs(title=title, url=url, tab_type=tab_type, mix=True, as_id=False)
def close_tabs(self, tabs_or_ids, others=False):
if isinstance(tabs_or_ids, str):
tabs = {tabs_or_ids}
elif isinstance(tabs_or_ids, ChromiumTab):
tabs = {tabs_or_ids.tab_id}
elif isinstance(tabs_or_ids, (list, tuple)):
tabs = set(i.tab_id if isinstance(i, ChromiumTab) else i for i in tabs_or_ids)
else:
raise ValueError(_S._lang.join(_S._lang.INCORRECT_TYPE_, 'tabs_or_ids',
ALLOW_TYPE=_S._lang.TAB_OR_ID, CURR_VAL=tabs_or_ids))
all_tabs = set(self.tab_ids)
if others:
tabs = all_tabs - tabs
if len(all_tabs - tabs) > 0:
for tab in tabs:
self._close_tab(tab=tab)
else:
self.quit()
def _close_tab(self, tab):
if isinstance(tab, str):
tab = self.get_tab(tab)
tab._run_cdp('Target.closeTarget', targetId=tab.tab_id)
while tab.driver.is_running and tab.tab_id in self._all_drivers:
sleep(.01)
def activate_tab(self, id_ind_tab):
if isinstance(id_ind_tab, int):
id_ind_tab += -1 if id_ind_tab else 1
id_ind_tab = self.tab_ids[id_ind_tab]
elif isinstance(id_ind_tab, ChromiumTab):
id_ind_tab = id_ind_tab.tab_id
self._run_cdp('Target.activateTarget', targetId=id_ind_tab)
def reconnect(self):
self._disconnect_flag = True
self._driver.stop()
BrowserDriver.BROWSERS.pop(self.id)
self._driver = BrowserDriver(self.id, self._ws_address, self)
self._run_cdp('Target.setDiscoverTargets', discover=True)
self._driver.set_callback('Target.targetDestroyed', self._onTargetDestroyed)
self._driver.set_callback('Target.targetCreated', self._onTargetCreated)
self._disconnect_flag = False
def clear_cache(self, cache=True, cookies=True):
if cache:
self.latest_tab.run_cdp('Network.clearBrowserCache')
if cookies:
self._run_cdp('Storage.clearCookies')
def quit(self, timeout=5, force=False, del_data=False):
try:
self._run_cdp('Browser.close')
except PageDisconnectedError:
pass
self._driver.stop()
drivers = list(self._all_drivers.values())
for tab in drivers:
for driver in tab:
driver.stop()
if not self.address.startswith('127.0.0.1'):
return
if force:
pids = None
try:
pids = [pid['id'] for pid in self._run_cdp('SystemInfo.getProcessInfo')['processInfo']]
except:
pass
if pids:
from psutil import Process
for pid in pids:
try:
Process(pid).kill()
except:
pass
from os import popen
from platform import system
end_time = perf_counter() + timeout
while perf_counter() < end_time:
ok = True
for pid in pids:
txt = f'tasklist | findstr {pid}' if system().lower() == 'windows' else f'ps -ef | grep {pid}'
p = popen(txt)
sleep(.05)
try:
if f' {pid} ' in p.read():
ok = False
break
except TypeError:
pass
if ok:
break
if del_data and not self._chromium_options.is_auto_port and self._chromium_options.user_data_path:
path = Path(self._chromium_options.user_data_path)
rmtree(path, True)
def _new_tab(self, mix=True, url=None, new_window=False, background=False, new_context=False):
tab_type = MixTab if mix else ChromiumTab
tab = None
if new_context:
tab = self._run_cdp('Target.createBrowserContext')['browserContextId']
kwargs = {'url': ''}
if new_window:
kwargs['newWindow'] = True
if background:
kwargs['background'] = True
if tab:
kwargs['browserContextId'] = tab
if self.states.is_incognito and not new_context:
return _new_tab_by_js(self, url, tab_type, new_window)
else:
try:
tab = self._run_cdp('Target.createTarget', **kwargs)['targetId']
except CDPError:
return _new_tab_by_js(self, url, tab_type, new_window)
while self.states.is_alive:
if tab in self._drivers:
break
sleep(.01)
else:
raise BrowserConnectError(_S._lang.BROWSER_DISCONNECTED)
tab = tab_type(self, tab)
if url:
tab.get(url)
return tab
def _get_tab(self, id_or_num=None, title=None, url=None, tab_type='page', mix=True, as_id=False):
if id_or_num is not None:
if isinstance(id_or_num, int):
id_or_num = self.tab_ids[id_or_num - 1 if id_or_num > 0 else id_or_num]
elif isinstance(id_or_num, ChromiumTab):
return id_or_num.tab_id if as_id else ChromiumTab(self, id_or_num.tab_id)
else:
j = self._run_cdp('Target.getTargets')['targetInfos']
if id_or_num not in [i['targetId'] for i in j]:
raise RuntimeError(_S._lang.join(_S._lang.NO_SUCH_TAB, ARG=id_or_num, ALL_TABS=self.tab_ids))
elif title == url is None and tab_type == 'page':
id_or_num = self.tab_ids[0]
else:
tabs = self._get_tabs(title=title, url=url, tab_type=tab_type, as_id=True)
if tabs:
id_or_num = tabs[0]
else:
raise RuntimeError(_S._lang.join(_S._lang.NO_SUCH_TAB,
ARGS={'id_or_num': id_or_num, 'title': title, 'url': url,
'tab_type': tab_type}))
if as_id:
return id_or_num
with self._lock:
return MixTab(self, id_or_num) if mix else ChromiumTab(self, id_or_num)
def _get_tabs(self, title=None, url=None, tab_type='page', mix=True, as_id=False):
if self._ws_only:
tabs = self._run_cdp('Target.getTargets')['targetInfos']
_id = 'targetId'
else:
tabs = self._driver.get(f'http://{self.address}/json').json() # 不要改用cdp
_id = 'id'
if isinstance(tab_type, str):
tab_type = {tab_type}
elif isinstance(tab_type, (list, tuple, set)):
tab_type = set(tab_type)
elif tab_type is not None:
raise ValueError(_S._lang.join(_S._lang.INCORRECT_TYPE_, 'tab_type',
ALLOW_TYPE='set, list, tuple, str, None', CURR_VAL=tab_type))
tabs = [i for i in tabs if ((title is None or title in i['title']) and (url is None or url in i['url'])
and (tab_type is None or i['type'] in tab_type)
and i['title'] != 'chrome-extension://neajdppkdcdipfabeoofebfddakdcjhd/audio.html')]
if as_id:
return [tab[_id] for tab in tabs]
with self._lock:
if mix:
return [MixTab(self, tab[_id]) for tab in tabs]
else:
return [ChromiumTab(self, tab[_id]) for tab in tabs]
def _run_cdp(self, cmd, **cmd_args):
ignore = cmd_args.pop('_ignore', None)
r = self._driver.run(cmd, **cmd_args)
return r if __ERROR__ not in r else raise_error(r, self, ignore)
def _get_driver(self, tab_id, owner=None):
d = self._drivers.pop(tab_id, None)
if not d:
if self._ws_only:
d = Driver(tab_id, self._ws_address)
d.session_id = d.run('Target.attachToTarget', targetId=tab_id, flatten=True)['sessionId']
else:
d = Driver(tab_id, f'ws://{self.address}/devtools/page/{tab_id}')
d.owner = owner
self._all_drivers.setdefault(tab_id, set()).add(d)
return d
def _onTargetCreated(self, **kwargs):
if (kwargs['targetInfo']['type'] in ('page', 'webview')
and kwargs['targetInfo']['targetId'] not in self._all_drivers
and not kwargs['targetInfo']['url'].startswith('devtools://')):
try:
tab_id = kwargs['targetInfo']['targetId']
self._frames[tab_id] = tab_id
if self._ws_only:
d = Driver(tab_id, self._ws_address)
d.session_id = d.run('Target.attachToTarget', targetId=tab_id, flatten=True)['sessionId']
else:
d = Driver(tab_id, f'ws://{self.address}/devtools/page/{tab_id}')
self._relation[tab_id] = kwargs['targetInfo'].get('openerId', None)
self._drivers[tab_id] = d
self._all_drivers.setdefault(tab_id, set()).add(d)
self._newest_tab_id = tab_id
except WebSocketBadStatusException:
pass
def _onTargetDestroyed(self, **kwargs):
tab_id = kwargs['targetId']
self._dl_mgr.clear_tab_info(tab_id)
for key in [k for k, i in self._frames.items() if i == tab_id]:
self._frames.pop(key, None)
for d in self._all_drivers.get(tab_id, tuple()):
d.stop()
self._drivers.pop(tab_id, None)
self._all_drivers.pop(tab_id, None)
self._relation.pop(tab_id, None)
def _on_disconnect(self):
if not self._disconnect_flag:
Chromium._BROWSERS.pop(self.id, None)
if self._chromium_options.is_auto_port and self._chromium_options.user_data_path:
path = Path(self._chromium_options.user_data_path)
end_time = perf_counter() + 7
while perf_counter() < end_time:
if not path.exists():
break
try:
rmtree(path)
break
except (PermissionError, FileNotFoundError, OSError):
pass
sleep(.03)
def handle_options(addr_or_opts):
if not addr_or_opts:
_chromium_options = ChromiumOptions(addr_or_opts)
if _chromium_options.is_auto_port:
port, path = PortFinder(_chromium_options.tmp_path).get_port(_chromium_options.is_auto_port)
_chromium_options.set_address(f'127.0.0.1:{port}')
_chromium_options.set_user_data_path(path)
_chromium_options.auto_port(scope=_chromium_options.is_auto_port)
elif isinstance(addr_or_opts, ChromiumOptions):
if addr_or_opts.is_auto_port:
port, path = PortFinder(addr_or_opts.tmp_path).get_port(addr_or_opts.is_auto_port)
addr_or_opts._address = f'127.0.0.1:{port}'
addr_or_opts.set_user_data_path(path)
_chromium_options = addr_or_opts
elif isinstance(addr_or_opts, str) and ':' in addr_or_opts:
_chromium_options = ChromiumOptions()
_chromium_options.set_address(addr_or_opts)
elif isinstance(addr_or_opts, int):
_chromium_options = ChromiumOptions()
_chromium_options.set_local_port(addr_or_opts)
else:
raise ValueError(_S._lang.join(_S._lang.INCORRECT_VAL_, 'addr_or_opts',
ALLOW_TYPE=_S._lang.IP_OR_OPTIONS, CURR_VAL=addr_or_opts))
return _chromium_options
def run_browser(chromium_options):
if chromium_options.ws_address:
d = Driver('', chromium_options.ws_address)
browser_id = d.run('Target.getTargets')
if 'error' in browser_id:
raise BrowserConnectError(_S._lang.join(_S._lang.BROWSER_CONNECT_ERR2, INFO=browser_id['error']))
browser_id = browser_id['targetInfos'][0]['browserContextId']
is_headless = 'headless' in d.run('Browser.getVersion')['userAgent'].lower()
is_exists = True
d.stop()
if 'devtools/browser' not in chromium_options.ws_address:
return is_headless, browser_id, is_exists, True
else:
is_exists = connect_browser(chromium_options)
try:
s = Session()
s.trust_env = False
s.keep_alive = False
ws = s.get(f'http://{chromium_options.address}/json/version', headers={'Connection': 'close'}, timeout=2)
if not ws and not chromium_options.ws_address:
raise BrowserConnectError(_S._lang.BROWSER_CONNECT_ERR2)
json = ws.json()
if not chromium_options.ws_address:
browser_id = json['webSocketDebuggerUrl'].split('/')[-1]
is_headless = 'headless' in json['User-Agent'].lower()
ws.close()
s.close()
ws_only = False
except KeyError:
raise BrowserConnectError(_S._lang.BROWSER_NOT_FOR_CONTROL)
except:
if chromium_options.ws_address:
ws_only = True
else:
raise BrowserConnectError(_S._lang.BROWSER_CONNECT_ERR2)
return is_headless, browser_id, is_exists, ws_only
def _new_tab_by_js(browser: Chromium, url, tab_type, new_window):
mix = tab_type == MixTab
tab = browser._get_tab(mix=mix)
if url and not match(r'^.*?://.*', url):
raise IncorrectURLError(_S._lang.INVALID_URL, url=url)
url = f'"{url}"' if url else '""'
new = 'target="_new"' if new_window else 'target="_blank"'
tid = browser._newest_tab_id
tab.run_js(f'window.open({url}, {new})')
tid = browser.wait.new_tab(curr_tab=tid)
return browser._get_tab(tid, mix=mix)
@@ -0,0 +1,319 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from threading import Lock
from typing import List, Optional, Set, Dict, Union, Tuple, Literal, Any
from .driver import BrowserDriver, Driver
from .._configs.chromium_options import ChromiumOptions
from .._configs.session_options import SessionOptions
from .._functions.cookies import CookiesList
from .._pages.chromium_base import Timeout, ChromiumBase
from .._pages.chromium_tab import ChromiumTab
from .._pages.mix_tab import MixTab
from .._units.downloader import DownloadManager
from .._units.setter import BrowserSetter
from .._units.states import BrowserStates
from .._units.waiter import BrowserWaiter
class Chromium(object):
_BROWSERS: dict = ...
_lock: Lock = ...
id: str = ...
address: str = ...
_ws_address: str = ...
version: str = ...
retry_times: int = ...
retry_interval: float = ...
_set: Optional[BrowserSetter] = ...
_wait: Optional[BrowserWaiter] = ...
_states: Optional[BrowserStates] = ...
_chromium_options: ChromiumOptions = ...
_session_options: SessionOptions = ...
_driver: BrowserDriver = ...
_frames: dict = ...
_drivers: Dict[str, Driver] = ...
_all_drivers: Dict[str, Set[Driver]] = ...
_relation: Dict[str, Optional[str]] = ...
_process_id: Optional[int] = ...
_dl_mgr: DownloadManager = ...
_timeouts: Timeout = ...
_load_mode: str = ...
_download_path: str = ...
_auto_handle_alert: Optional[bool] = ...
_is_exists: bool = ...
_is_headless: bool = ...
_ws_only: bool = ...
_disconnect_flag: bool = ...
_none_ele_return_value: bool = ...
_none_ele_value: Any = ...
_newest_tab_id: Optional[str] = ...
def __new__(cls,
addr_or_opts: Union[str, int, ChromiumOptions] = None,
session_options: Union[SessionOptions, None, False] = None):
"""
:param addr_or_opts: 浏览器地址:端口、ws地址、ChromiumOptions对象或端口数字(int)
:param session_options: 使用双模Tab时使用的默认Session配置,为None使用ini文件配置,为False不从ini读取
"""
...
def __init__(self, addr_or_opts: Union[str, int, ChromiumOptions] = None,
session_options: Union[SessionOptions, None, False] = None):
"""
:param addr_or_opts: 浏览器地址:端口、ws地址、ChromiumOptions对象或端口数字(int)
:param session_options: 使用双模Tab时使用的默认Session配置,为None使用ini文件配置,为False不从ini读取
"""
...
@property
def user_data_path(self) -> str:
"""返回用户文件夹路径"""
...
@property
def process_id(self) -> Optional[int]:
"""返回浏览器进程id"""
...
@property
def timeout(self) -> float:
"""返回基础超时设置"""
...
@property
def timeouts(self) -> Timeout:
"""返回所有超时设置"""
...
@property
def load_mode(self) -> Literal['none', 'normal', 'eager']:
"""返回页面加载模式,包括 'none', 'normal', 'eager' 三种"""
...
@property
def download_path(self) -> str:
"""返回默认下载路径"""
...
@property
def set(self) -> BrowserSetter:
"""返回用于设置的对象"""
...
@property
def states(self) -> BrowserStates:
"""返回用于获取状态的对象"""
...
@property
def wait(self) -> BrowserWaiter:
"""返回用于等待的对象"""
...
@property
def tabs_count(self) -> int:
"""返回标签页数量,只统计page、webview类型"""
...
@property
def tab_ids(self) -> List[str]:
"""返回所有标签页id组成的列表,只统计page、webview类型"""
...
@property
def latest_tab(self) -> Union[MixTab, str]:
"""返回最新的标签页,最新标签页指最后创建或最后被激活的
当Settings.singleton_tab_obj==True时返回Tab对象,否则返回tab id"""
...
def cookies(self, all_info: bool = False) -> CookiesList:
"""以list格式返回所有域名的cookies
:param all_info: 是否返回所有内容,False则只返回name, value, domain
:return: cookies组成的列表
"""
...
def new_tab(self,
url: str = None,
new_window: bool = False,
background: bool = False,
new_context: bool = False) -> MixTab:
"""新建一个标签页
:param url: 新标签页跳转到的网址,为None时新建空标签页
:param new_window: 是否在新窗口打开标签页,隐身模式下无效
:param background: 是否不激活新标签页,隐身模式和访客模式及new_window为True时无效
:param new_context: 是否创建独立环境,隐身模式和访客模式下无效
:return: 新标签页对象
"""
...
def get_tab(self,
id_or_num: Union[str, int] = None,
title: str = None,
url: str = None,
tab_type: Union[str, list, tuple] = 'page',
as_id: bool = False) -> Union[MixTab, str]:
"""获取一个标签页对象,id_or_num不为None时,后面几个参数无效
:param id_or_num: 要获取的标签页id或序号,序号从1开始,可传入负数获取倒数第几个,不是视觉排列顺序,而是激活顺序
:param title: 要匹配title的文本,模糊匹配,为None则匹配所有
:param url: 要匹配url的文本,模糊匹配,为None则匹配所有
:param tab_type: tab类型,可用列表输入多个,如 'page', 'iframe' 等,为None则匹配所有
:param as_id: 是否返回标签页id而不是标签页对象
:return: Tab对象
"""
...
def get_tabs(self,
title: str = None,
url: str = None,
tab_type: Union[str, list, tuple] = 'page',
as_id: bool = False) -> List[MixTab, str]:
"""查找符合条件的tab,返回它们组成的列表,title和url是与关系
:param title: 要匹配title的文本
:param url: 要匹配url的文本
:param tab_type: tab类型,可用列表输入多个
:param as_id: 是否返回标签页id而不是标签页对象
:return: Tab对象列表
"""
...
def close_tabs(self,
tabs_or_ids: Union[str, ChromiumTab, List[Union[str, ChromiumTab]],
Tuple[Union[str, ChromiumTab]]],
others: bool = False) -> None:
"""关闭传入的标签页,可传入多个
:param tabs_or_ids: 指定的标签页对象或id,可用列表或元组传入多个
:param others: 是否关闭指定标签页之外的
:return: None
"""
...
def _close_tab(self, tab: Union[ChromiumBase, str]):
"""关闭一个标签页
:param tab: 标签页对象或id
:return: None
"""
def activate_tab(self, id_ind_tab: Union[int, str, ChromiumTab]) -> None:
"""使一个标签页显示到前端
:param id_ind_tab: 标签页id(str)、Tab对象或标签页序号(int),序号从1开始
:return: None
"""
...
def reconnect(self) -> None:
"""断开重连"""
...
def clear_cache(self, cache: bool = True, cookies: bool = True) -> None:
"""清除缓存,可选要清除的项
:param cache: 是否清除cache
:param cookies: 是否清除cookies
:return: None
"""
...
def quit(self, timeout: float = 5, force: bool = False, del_data: bool = False) -> None:
"""关闭浏览器
:param timeout: 等待浏览器关闭超时时间(秒)
:param force: 是否立刻强制终止进程
:param del_data: 是否删除用户文件夹
:return: None
"""
...
def _new_tab(self,
mix: bool = True,
url: str = None,
new_window: bool = False,
background: bool = False,
new_context: bool = False) -> Union[ChromiumTab, MixTab]:
"""新建一个标签页
:param mix: 是否创建MixTab
:param url: 新标签页跳转到的网址
:param new_window: 是否在新窗口打开标签页
:param background: 是否不激活新标签页,如new_window为True则无效
:param new_context: 是否创建新的上下文
:return: 新标签页对象
"""
...
def _get_tab(self,
id_or_num: Union[str, int] = None,
title: str = None,
url: str = None,
tab_type: Union[str, list, tuple] = 'page',
mix: bool = True,
as_id: bool = False) -> Union[ChromiumTab, str]:
"""获取一个标签页对象,id_or_num不为None时,后面几个参数无效
:param id_or_num: 要获取的标签页id或序号,序号从1开始,可传入负数获取倒数第几个,不是视觉排列顺序,而是激活顺序
:param title: 要匹配title的文本,模糊匹配,为None则匹配所有
:param url: 要匹配url的文本,模糊匹配,为None则匹配所有
:param tab_type: tab类型,可用列表输入多个,如 'page', 'iframe' 等,为None则匹配所有
:param mix: 是否返回可切换模式的Tab对象
:param as_id: 是否返回标签页id而不是标签页对象,mix=False时无效
:return: Tab对象
"""
...
def _get_tabs(self,
title: str = None,
url: str = None,
tab_type: Union[str, list, tuple] = 'page',
mix: bool = True,
as_id: bool = False) -> List[ChromiumTab, str]:
"""查找符合条件的tab,返回它们组成的列表,title和url是与关系
:param title: 要匹配title的文本
:param url: 要匹配url的文本
:param tab_type: tab类型,可用列表输入多个
:param mix: 是否返回可切换模式的Tab对象
:param as_id: 是否返回标签页id而不是标签页对象,mix=False时无效
:return: Tab对象列表
"""
...
def _run_cdp(self, cmd, **cmd_args) -> dict:
"""执行Chrome DevTools Protocol语句
:param cmd: 协议项目
:param cmd_args: 参数
:return: 执行的结果
"""
...
def _get_driver(self, tab_id: str, owner=None) -> Driver:
"""新建并返回指定tab id的Driver
:param tab_id: 标签页id
:param owner: 使用该驱动的对象
:return: Driver对象
"""
...
def _onTargetCreated(self, **kwargs): ...
def _onTargetDestroyed(self, **kwargs): ...
def _on_disconnect(self): ...
def handle_options(addr_or_opts):
"""设置浏览器启动属性
:param addr_or_opts: 'ip:port'、ChromiumOptions、Driver
:return: 返回ChromiumOptions对象
"""
...
def run_browser(chromium_options)->Tuple[bool, str, bool, bool]:
"""连接浏览器
:param chromium_options: ChromiumOptions对象
:return: 返回(是否无头, 浏览器id, 是否接管已存在, 是否只能用ws连接)
"""
...
@@ -0,0 +1,229 @@
# -*- coding: utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from json import dumps, loads, JSONDecodeError
from queue import Queue, Empty
from threading import Thread
from time import perf_counter, sleep
from requests import Session
from requests import adapters
from websocket import (WebSocketTimeoutException, WebSocketConnectionClosedException, create_connection,
WebSocketException, WebSocketBadStatusException)
from .._functions.settings import Settings as _S
from ..errors import PageDisconnectedError, BrowserConnectError
adapters.DEFAULT_RETRIES = 5
class Driver(object):
def __init__(self, _id, address, owner=None):
self.id = _id
self.address = address
self.owner = owner
self.alert_flag = False # 标记alert出现,跳过一条请求后复原
self._cur_id = 0
self._ws = None
self._recv_th = Thread(target=self._recv_loop)
self._handle_event_th = Thread(target=self._handle_event_loop)
self._recv_th.daemon = True
self._handle_event_th.daemon = True
self._handle_immediate_event_th = None
self.is_running = False
self.session_id = None
self.event_handlers = {}
self.immediate_event_handlers = {}
self.method_results = {}
self.event_queue = Queue()
self.immediate_event_queue = Queue()
self.start()
def _send(self, message, timeout=None):
self._cur_id += 1
ws_id = self._cur_id
message['id'] = ws_id
message_json = dumps(message)
end_time = perf_counter() + timeout if timeout is not None else None
self.method_results[ws_id] = Queue()
try:
self._ws.send(message_json)
if timeout == 0:
self.method_results.pop(ws_id, None)
return {'id': ws_id, 'result': {}}
except (OSError, WebSocketConnectionClosedException):
self.method_results.pop(ws_id, None)
return {'error': {'message': 'connection disconnected'}, 'type': 'connection_error'}
while self.is_running:
try:
result = self.method_results[ws_id].get(timeout=.2)
self.method_results.pop(ws_id, None)
return result
except Empty:
if self.alert_flag and message['method'].startswith(('Input.', 'Runtime.')):
return {'error': {'message': 'alert exists.'}, 'type': 'alert_exists'}
if timeout is not None and perf_counter() > end_time:
self.method_results.pop(ws_id, None)
return {'error': {'message': 'alert exists.'}, 'type': 'alert_exists'} \
if self.alert_flag else {'error': {'message': 'timeout'}, 'type': 'timeout'}
continue
return {'error': {'message': 'connection disconnected'}, 'type': 'connection_error'}
def _recv_loop(self):
while self.is_running:
try:
# self._ws.settimeout(1)
msg_json = self._ws.recv()
msg = loads(msg_json)
except WebSocketTimeoutException:
continue
except (WebSocketException, OSError, WebSocketConnectionClosedException, JSONDecodeError):
self._stop()
return
if 'method' in msg:
if msg['method'].startswith('Page.javascriptDialog'):
self.alert_flag = msg['method'].endswith('Opening')
function = self.immediate_event_handlers.get(msg['method'])
if function:
self._handle_immediate_event(function, msg['params'])
else:
self.event_queue.put(msg)
elif msg.get('id') in self.method_results:
self.method_results[msg['id']].put(msg)
def _handle_event_loop(self):
while self.is_running:
try:
event = self.event_queue.get(timeout=1)
except Empty:
continue
function = self.event_handlers.get(event['method'])
if function:
function(**event['params'])
self.event_queue.task_done()
def _handle_immediate_event_loop(self):
while not self.immediate_event_queue.empty():
function, kwargs = self.immediate_event_queue.get(timeout=1)
try:
function(**kwargs)
except PageDisconnectedError:
pass
def _handle_immediate_event(self, function, kwargs):
self.immediate_event_queue.put((function, kwargs))
if self._handle_immediate_event_th is None or not self._handle_immediate_event_th.is_alive():
self._handle_immediate_event_th = Thread(target=self._handle_immediate_event_loop)
self._handle_immediate_event_th.daemon = True
self._handle_immediate_event_th.start()
def run(self, _method, sessionId=None, **kwargs):
if not self.is_running:
return {'error': 'connection disconnected', 'type': 'connection_error'}
timeout = kwargs.pop('_timeout', _S.cdp_timeout)
if self.session_id:
result = self._send({'method': _method, 'params': kwargs, 'sessionId': self.session_id}, timeout=timeout)
elif sessionId:
result = self._send({'method': _method, 'params': kwargs, 'sessionId': sessionId}, timeout=timeout)
else:
result = self._send({'method': _method, 'params': kwargs}, timeout=timeout)
if 'result' not in result and 'error' in result:
kwargs['_timeout'] = timeout
return {'error': result['error']['message'], 'type': result.get('type', 'call_method_error'),
'method': _method, 'args': kwargs, 'data': result['error'].get('data')}
else:
return result['result']
def start(self):
self.is_running = True
try:
self._ws = create_connection(self.address, enable_multithread=True, suppress_origin=True)
except WebSocketBadStatusException as e:
if 'Handshake status 403 Forbidden' in str(e):
raise EnvironmentError(_S._lang.join(_S._lang.UPGRADE_WS))
else:
raise
except ConnectionRefusedError:
raise BrowserConnectError(_S._lang.BROWSER_NOT_EXIST)
self._recv_th.start()
self._handle_event_th.start()
return True
def stop(self):
self._stop()
while self._handle_event_th.is_alive() or self._recv_th.is_alive():
sleep(.01)
return True
def _stop(self):
if not self.is_running:
return False
self.is_running = False
if self._ws:
self._ws.close()
self._ws = None
self.event_handlers.clear()
self.method_results.clear()
self.event_queue.queue.clear()
if hasattr(self.owner, '_on_disconnect'):
self.owner._on_disconnect()
def set_callback(self, event, callback, immediate=False):
handler = self.immediate_event_handlers if immediate else self.event_handlers
if callback:
handler[event] = callback
else:
handler.pop(event, None)
class BrowserDriver(Driver):
BROWSERS = {}
def __new__(cls, _id, address, owner):
if _id in cls.BROWSERS:
return cls.BROWSERS[_id]
return object.__new__(cls)
def __init__(self, _id, address, owner):
if hasattr(self, '_created'):
return
self._created = True
BrowserDriver.BROWSERS[_id] = self
super().__init__(_id, address, owner)
def __repr__(self):
return f'<BrowserDriver {self.id}>'
@staticmethod
def get(url):
s = Session()
s.trust_env = False
s.keep_alive = False
r = s.get(url, headers={'Connection': 'close'})
r.close()
s.close()
return r
@@ -0,0 +1,114 @@
# -*- coding: utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from queue import Queue
from threading import Thread
from typing import Union, Callable, Dict, Optional
from requests import Response
from websocket import WebSocket
from .._base.chromium import Chromium
class Driver(object):
id: str
address: str
owner = ...
alert_flag: bool
_cur_id: int
_ws: Optional[WebSocket]
_recv_th: Thread
_handle_event_th: Thread
_handle_immediate_event_th: Optional[Thread]
session_id: Optional[str] = ...
is_running: bool
event_handlers: dict
immediate_event_handlers: dict
method_results: dict
event_queue: Queue
immediate_event_queue: Queue
def __init__(self, _id: str, address: str, owner=None):
"""
:param _id: 标签页id
:param address: 浏览器连接地址
:param owner: 创建这个驱动的对象
"""
...
def _send(self, message: dict, timeout: float = None) -> dict:
"""发送信息到浏览器,并返回浏览器返回的信息
:param message: 发送给浏览器的数据
:param timeout: 超时时间,为None表示无限
:return: 浏览器返回的数据
"""
...
def _recv_loop(self) -> None:
"""接收浏览器信息的守护线程方法"""
...
def _handle_event_loop(self) -> None:
"""当接收到浏览器信息,执行已绑定的方法"""
...
def _handle_immediate_event_loop(self): ...
def _handle_immediate_event(self, function: Callable, kwargs: dict):
"""处理立即执行的动作
:param function: 要运行下方法
:param kwargs: 方法参数
:return: None
"""
...
def run(self, _method: str, **kwargs) -> dict:
"""执行cdp方法
:param _method: cdp方法名
:param kwargs: cdp参数
:return: 执行结果
"""
...
def start(self) -> bool:
"""启动连接"""
...
def stop(self) -> bool:
"""中断连接"""
...
def _stop(self) -> None:
"""中断连接"""
...
def set_callback(self, event: str, callback: Union[Callable, None], immediate: bool = False) -> None:
"""绑定cdp event和回调方法
:param event: cdp event
:param callback: 绑定到cdp event的回调方法
:param immediate: 是否要立即处理的动作
:return: None
"""
...
class BrowserDriver(Driver):
BROWSERS: Dict[str, Driver] = ...
owner: Chromium = ...
def __new__(cls, _id: str, address: str, owner: Chromium): ...
def __init__(self, _id: str, address: str, owner: Chromium): ...
@staticmethod
def get(url) -> Response:
"""
:param url: 要访问的链接
:return: Response对象
"""
...
@@ -0,0 +1,439 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from pathlib import Path
from re import search
from urllib.parse import urlparse
from .options_manage import OptionsManager
from .._functions.settings import Settings as _S
class ChromiumOptions(object):
def __init__(self, read_file=True, ini_path=None):
self._user_data_path = None
self._user = 'Default'
self._prefs_to_del = []
self.clear_file_flags = False
self._is_headless = False
self._ua_set = False
self.ws_address = ''
if read_file is False:
ini_path = False
self.ini_path = None
elif ini_path:
ini_path = Path(ini_path).absolute()
if not ini_path.exists():
raise FileNotFoundError(_S._lang.join(_S._lang.INI_NOT_FOUND, PATH=ini_path))
self.ini_path = str(ini_path)
else:
self.ini_path = str(Path(__file__).parent / 'configs.ini')
om = OptionsManager(ini_path)
options = om.chromium_options
self._download_path = om.paths.get('download_path', '.') or '.'
self._tmp_path = om.paths.get('tmp_path', None) or None
self._arguments = options.get('arguments', [])
self._browser_path = options.get('browser_path', '')
self._extensions = options.get('extensions', [])
self._prefs = options.get('prefs', {})
self._flags = options.get('flags', {})
self._address = options.get('address', '')
self._load_mode = options.get('load_mode', 'normal')
self._system_user_path = options.get('system_user_path', False)
self._existing_only = options.get('existing_only', False)
self._new_env = options.get('new_env', False)
for i in self._arguments:
if i.startswith('--headless'):
self._is_headless = True
break
self._proxy = om.proxies.get('http', None) or om.proxies.get('https', None)
user_path = user = False
for arg in self._arguments:
if arg.startswith('--user-data-dir='):
self.set_user_data_path(arg[16:])
user_path = True
if arg.startswith('--profile-directory='):
self.set_user(arg[20:])
user = True
if user and user_path:
break
timeouts = om.timeouts
self._timeouts = {'base': timeouts['base'],
'page_load': timeouts['page_load'],
'script': timeouts['script']}
self._auto_port = options.get('auto_port', False)
others = om.others
self._retry_times = others.get('retry_times', 3)
self._retry_interval = others.get('retry_interval', 2)
return
def __repr__(self):
return f'<ChromiumOptions at {id(self)}>'
@property
def download_path(self):
return self._download_path
@property
def browser_path(self):
return self._browser_path
@property
def user_data_path(self):
return self._user_data_path
@property
def tmp_path(self):
return self._tmp_path
@property
def user(self):
return self._user
@property
def load_mode(self):
return self._load_mode
@property
def timeouts(self):
return self._timeouts
@property
def proxy(self):
return self._proxy
@property
def address(self):
return self._address
@property
def arguments(self):
return self._arguments
@property
def extensions(self):
return self._extensions
@property
def preferences(self):
return self._prefs
@property
def flags(self):
return self._flags
@property
def system_user_path(self):
return self._system_user_path
@property
def is_existing_only(self):
return self._existing_only
@property
def is_auto_port(self):
return self._auto_port
@property
def retry_times(self):
return self._retry_times
@property
def retry_interval(self):
return self._retry_interval
@property
def is_headless(self):
return self._is_headless
def set_retry(self, times=None, interval=None):
if times is not None:
self._retry_times = times
if interval is not None:
self._retry_interval = interval
return self
def set_argument(self, arg, value=None):
self.remove_argument(arg)
if value is not False:
if arg == '--headless':
if value == 'false':
self._is_headless = False
else:
if value is None:
value = 'new'
self._arguments.append(f'--headless={value}')
self._is_headless = True
else:
arg_str = arg if value is None else f'{arg}={value}'
self._arguments.append(arg_str)
elif arg == '--headless':
self._is_headless = False
return self
def remove_argument(self, value):
elements_to_delete = [arg for arg in self._arguments if arg == value or arg.startswith(f'{value}=')]
if not elements_to_delete:
return self
if len(elements_to_delete) == 1:
self._arguments.remove(elements_to_delete[0])
else:
self._arguments = [arg for arg in self._arguments if arg not in elements_to_delete]
return self
def add_extension(self, path):
self._extensions.append(path)
return self
def remove_extensions(self):
self._extensions = []
return self
def set_pref(self, arg, value):
self._prefs[arg] = value
return self
def remove_pref(self, arg):
self._prefs.pop(arg, None)
return self
def remove_pref_from_file(self, arg):
self._prefs_to_del.append(arg)
return self
def set_flag(self, flag, value=None):
if value is False:
self._flags.pop(flag, None)
else:
self._flags[flag] = value
return self
def clear_flags_in_file(self):
self.clear_file_flags = True
return self
def clear_flags(self):
self._flags = {}
return self
def clear_arguments(self):
self._arguments = []
return self
def clear_prefs(self):
self._prefs = {}
return self
def set_timeouts(self, base=None, page_load=None, script=None):
if base is not None:
self._timeouts['base'] = base
if page_load is not None:
self._timeouts['page_load'] = page_load
if script is not None:
self._timeouts['script'] = script
return self
def set_user(self, user='Default'):
self.set_argument('--profile-directory', user)
self._user = user
return self
def headless(self, on_off=True):
on_off = 'new' if on_off else on_off
return self.set_argument('--headless', on_off)
def no_imgs(self, on_off=True):
on_off = None if on_off else False
return self.set_argument('--blink-settings=imagesEnabled=false', on_off)
def no_js(self, on_off=True):
on_off = None if on_off else False
return self.set_argument('--disable-javascript', on_off)
def mute(self, on_off=True):
on_off = None if on_off else False
return self.set_argument('--mute-audio', on_off)
def incognito(self, on_off=True):
on_off = None if on_off else False
self.set_argument('--incognito', on_off)
return self.set_argument('--inprivate', on_off) # edge
def new_env(self, on_off=True):
self._new_env = on_off
return self
def ignore_certificate_errors(self, on_off=True):
on_off = None if on_off else False
return self.set_argument('--ignore-certificate-errors', on_off)
def set_user_agent(self, user_agent):
return self.set_argument('--user-agent', user_agent)
def set_proxy(self, proxy):
if search(r'.*?:.*?@.*?\..*', proxy):
print(_S._lang.UNSUPPORTED_USER_PROXY)
if proxy.lower().startswith('socks'):
print(_S._lang.UNSUPPORTED_SOCKS_PROXY)
self._proxy = proxy
return self.set_argument('--proxy-server', proxy)
def set_load_mode(self, value):
if value not in ('normal', 'eager', 'none'):
raise ValueError(_S._lang.join(_S._lang.INCORRECT_VAL_, 'value',
ALLOW_VAL="'normal', 'eager', 'none'", CURR_VAL=value))
self._load_mode = value.lower()
return self
def set_paths(self, browser_path=None, local_port=None, address=None, download_path=None,
user_data_path=None, cache_path=None):
"""快捷的路径设置函数,即将废弃
:param browser_path: 浏览器可执行文件路径
:param local_port: 本地端口号
:param address: 调试浏览器地址,例:127.0.0.1:9222
:param download_path: 下载文件路径
:param user_data_path: 用户数据路径
:param cache_path: 缓存路径
:return: 当前对象
"""
if browser_path is not None:
self.set_browser_path(browser_path)
if local_port is not None:
self.set_local_port(local_port)
if address is not None:
self.set_address(address)
if download_path is not None:
self.set_download_path(download_path)
if user_data_path is not None:
self.set_user_data_path(user_data_path)
if cache_path is not None:
self.set_cache_path(cache_path)
return self
def set_local_port(self, port):
self._address = f'127.0.0.1:{port}'
self._auto_port = False
self.ws_address = ''
return self
def set_address(self, address):
address = address.replace('localhost', '127.0.0.1')
self.ws_address = ''
if address.startswith('http'):
address = address.lstrip('htps:/')
elif address.startswith(('ws:', 'wss:')):
self.ws_address = address
address = urlparse(address).netloc
self._address = address
self._auto_port = False
return self
def set_browser_path(self, path):
self._browser_path = str(path)
return self
def set_download_path(self, path):
self._download_path = '.' if path is None else str(path)
return self
def set_tmp_path(self, path):
self._tmp_path = str(path)
return self
def set_user_data_path(self, path):
u = str(path)
self.set_argument('--user-data-dir', u)
self._user_data_path = u
self._auto_port = False
return self
def set_cache_path(self, path):
self.set_argument('--disk-cache-dir', str(path))
return self
def use_system_user_path(self, on_off=True):
self._system_user_path = on_off
return self
def auto_port(self, on_off=True, scope=None):
if on_off:
self._auto_port = scope if scope else (9600, 59600)
else:
self._auto_port = False
self._address = ''
self.ws_address = ''
return self
def existing_only(self, on_off=True):
self._existing_only = on_off
return self
def save(self, path=None):
if path == 'default':
path = (Path(__file__).parent / 'configs.ini').absolute()
elif path is None:
if self.ini_path:
path = Path(self.ini_path).absolute()
else:
path = (Path(__file__).parent / 'configs.ini').absolute()
else:
path = Path(path).absolute()
path = path / 'config.ini' if path.is_dir() else path
if path.exists():
om = OptionsManager(path)
else:
om = OptionsManager(self.ini_path or (Path(__file__).parent / 'configs.ini'))
# 设置chromium_options
attrs = ('address', 'browser_path', 'arguments', 'extensions', 'user', 'load_mode',
'auto_port', 'system_user_path', 'existing_only', 'flags', 'new_env')
for i in attrs:
om.set_item('chromium_options', i, self.__getattribute__(f'_{i}'))
# 设置代理
om.set_item('proxies', 'http', self._proxy or '')
om.set_item('proxies', 'https', self._proxy or '')
# 设置路径
om.set_item('paths', 'download_path', self._download_path or '')
om.set_item('paths', 'tmp_path', self._tmp_path or '')
# 设置timeout
om.set_item('timeouts', 'base', self._timeouts['base'])
om.set_item('timeouts', 'page_load', self._timeouts['page_load'])
om.set_item('timeouts', 'script', self._timeouts['script'])
# 设置重试
om.set_item('others', 'retry_times', self.retry_times)
om.set_item('others', 'retry_interval', self.retry_interval)
# 设置prefs
om.set_item('chromium_options', 'prefs', self._prefs)
path = str(path)
om.save(path)
return path
def save_to_default(self):
return self.save('default')
@@ -0,0 +1,399 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from pathlib import Path
from typing import Union, Any, Literal, Optional, Tuple
class ChromiumOptions(object):
ini_path: Optional[str] = ...
_user_data_path: Optional[str] = ...
_download_path: str = ...
_tmp_path: str = ...
_arguments: list = ...
_browser_path: str = ...
_user: str = ...
_load_mode: str = ...
_timeouts: dict = ...
_proxy: str = ...
_address: str = ...
_extensions: list = ...
_prefs: dict = ...
_flags: dict = ...
_prefs_to_del: list = ...
_new_env: bool = ...
clear_file_flags: bool = ...
_auto_port: Union[Tuple[int, int], False] = ...
_system_user_path: bool = ...
_existing_only: bool = ...
_retry_times: int = ...
_retry_interval: float = ...
_is_headless: bool = ...
_ua_set: bool = ...
ws_address: Optional[str] = ...
def __init__(self,
read_file: [bool, None] = True,
ini_path: Union[str, Path] = None):
"""
:param read_file: 是否从默认ini文件中读取配置信息
:param ini_path: ini文件路径,为None则读取默认ini文件
"""
...
@property
def download_path(self) -> str:
"""默认下载路径文件路径"""
...
@property
def browser_path(self) -> str:
"""浏览器启动文件路径"""
...
@property
def user_data_path(self) -> str:
"""返回用户数据文件夹路径"""
...
@property
def tmp_path(self) -> Optional[str]:
"""返回临时文件夹路径"""
...
@property
def user(self) -> str:
"""返回用户配置文件夹名称"""
...
@property
def load_mode(self) -> str:
"""返回页面加载策略,'normal', 'eager', 'none'"""
...
@property
def timeouts(self) -> dict:
"""返回timeouts设置"""
...
@property
def proxy(self) -> str:
"""返回代理设置"""
...
@property
def address(self) -> str:
"""返回浏览器地址,ip:port"""
...
@property
def arguments(self) -> list:
"""返回浏览器命令行设置列表"""
...
@property
def extensions(self) -> list:
"""以list形式返回要加载的插件路径"""
...
@property
def preferences(self) -> dict:
"""返回用户首选项配置"""
...
@property
def flags(self) -> dict:
"""返回实验项配置"""
...
@property
def system_user_path(self) -> bool:
"""返回是否使用系统安装的浏览器所使用的用户数据文件夹"""
...
@property
def is_existing_only(self) -> bool:
"""返回是否只接管现有浏览器方式"""
...
@property
def is_auto_port(self) -> Union[bool, Tuple[int, int]]:
"""返回是否使用自动端口和用户文件,如指定范围则返回范围tuple"""
...
@property
def retry_times(self) -> int:
"""返回连接失败时的重试次数"""
...
@property
def retry_interval(self) -> float:
"""返回连接失败时的重试间隔(秒)"""
...
@property
def is_headless(self) -> bool:
"""返回是否无头模式"""
...
def set_retry(self, times: int = None, interval: float = None) -> ChromiumOptions:
"""设置连接失败时的重试操作
:param times: 重试次数
:param interval: 重试间隔
:return: 当前对象
"""
...
def set_argument(self, arg: str, value: Union[str, None, bool] = None) -> ChromiumOptions:
"""设置浏览器配置的argument属性
:param arg: 属性名
:param value: 属性值,有值的属性传入值,没有的传入None,如传入False,删除该项
:return: 当前对象
"""
...
def remove_argument(self, value: str) -> ChromiumOptions:
"""移除一个argument项
:param value: 设置项名,有值的设置项传入设置名称即可
:return: 当前对象
"""
...
def add_extension(self, path: Union[str, Path]) -> ChromiumOptions:
"""添加插件
:param path: 插件路径,可指向文件夹
:return: 当前对象
"""
...
def remove_extensions(self) -> ChromiumOptions:
"""移除所有插件
:return: 当前对象
"""
...
def set_pref(self, arg: str, value: Any) -> ChromiumOptions:
"""设置Preferences文件中的用户设置项
:param arg: 设置项名称
:param value: 设置项值
:return: 当前对象
"""
...
def remove_pref(self, arg: str) -> ChromiumOptions:
"""删除用户首选项设置,不能删除已设置到文件中的项
:param arg: 设置项名称
:return: 当前对象
"""
...
def remove_pref_from_file(self, arg: str) -> ChromiumOptions:
"""删除用户配置文件中已设置的项
:param arg: 设置项名称
:return: 当前对象
"""
...
def set_flag(self, flag: str, value: Union[int, str, bool] = None) -> ChromiumOptions:
"""设置实验项
:param flag: 设置项名称
:param value: 设置项的值,为False则删除该项
:return: 当前对象
"""
...
def clear_flags_in_file(self) -> ChromiumOptions:
"""删除浏览器配置文件中已设置的实验项"""
...
def clear_flags(self) -> ChromiumOptions:
"""清空本对象已设置的flag参数"""
...
def clear_arguments(self) -> ChromiumOptions:
"""清空本对象已设置的argument参数"""
...
def clear_prefs(self) -> ChromiumOptions:
"""清空本对象已设置的pref参数"""
...
def set_timeouts(self,
base: float = None,
page_load: float = None,
script: float = None) -> ChromiumOptions:
"""设置超时时间,单位为秒
:param base: 默认超时时间
:param page_load: 页面加载超时时间
:param script: 脚本运行超时时间
:return: 当前对象
"""
...
def set_user(self, user: str = 'Default') -> ChromiumOptions:
"""设置使用哪个用户配置文件夹
:param user: 用户文件夹名称
:return: 当前对象
"""
...
def headless(self, on_off: bool = True) -> ChromiumOptions:
"""设置是否隐藏浏览器界面
:param on_off: 开或关
:return: 当前对象
"""
...
def no_imgs(self, on_off: bool = True) -> ChromiumOptions:
"""设置是否加载图片
:param on_off: 开或关
:return: 当前对象
"""
...
def no_js(self, on_off: bool = True) -> ChromiumOptions:
"""设置是否禁用js
:param on_off: 开或关
:return: 当前对象
"""
...
def mute(self, on_off: bool = True) -> ChromiumOptions:
"""设置是否静音
:param on_off: 开或关
:return: 当前对象
"""
...
def incognito(self, on_off: bool = True) -> ChromiumOptions:
"""设置是否使用无痕模式启动
:param on_off: 开或关
:return: 当前对象
"""
...
def new_env(self, on_off: bool = True) -> ChromiumOptions:
"""设置是否使用全新浏览器环境
:param on_off: 开或关
:return: 当前对象
"""
...
def ignore_certificate_errors(self, on_off=True) -> ChromiumOptions:
"""设置是否忽略证书错误
:param on_off: 开或关
:return: 当前对象
"""
...
def set_user_agent(self, user_agent: str) -> ChromiumOptions:
"""设置user agent
:param user_agent: user agent文本
:return: 当前对象
"""
...
def set_proxy(self, proxy: str) -> ChromiumOptions:
"""设置代理
:param proxy: 代理url和端口
:return: 当前对象
"""
...
def set_load_mode(self, value: Literal['normal', 'eager', 'none']) -> ChromiumOptions:
"""设置load_mode,可接收 'normal', 'eager', 'none'
normal:默认情况下使用, 等待所有资源下载完成
eager:DOM访问已准备就绪, 但其他资源 (如图像) 可能仍在加载中
none:完全不阻塞
:param value: 可接收 'normal', 'eager', 'none'
:return: 当前对象
"""
...
def set_local_port(self, port: Union[str, int]) -> ChromiumOptions:
"""设置本地启动端口,与set_address()和auto_port()互斥
:param port: 端口号
:return: 当前对象
"""
...
def set_address(self, address: str) -> ChromiumOptions:
"""设置浏览器地址,格式'ip:port',与auto_port()和set_local_port()互斥
:param address: 浏览器地址
:return: 当前对象
"""
...
def set_browser_path(self, path: Union[str, Path]) -> ChromiumOptions:
"""设置浏览器可执行文件路径
:param path: 浏览器路径
:return: 当前对象
"""
...
def set_download_path(self, path: Union[str, Path]) -> ChromiumOptions:
"""设置下载文件保存路径
:param path: 下载路径
:return: 当前对象
"""
...
def set_tmp_path(self, path: Union[str, Path]) -> ChromiumOptions:
"""设置临时文件文件保存路径
:param path: 下载路径
:return: 当前对象
"""
...
def set_user_data_path(self, path: Union[str, Path]) -> ChromiumOptions:
"""设置用户文件夹路径
:param path: 用户文件夹路径
:return: 当前对象
"""
...
def set_cache_path(self, path: Union[str, Path]) -> ChromiumOptions:
"""设置缓存路径
:param path: 缓存路径
:return: 当前对象
"""
...
def use_system_user_path(self, on_off: bool = True) -> ChromiumOptions:
"""设置是否使用系统安装的浏览器默认用户文件夹
:param on_off: 开或关
:return: 当前对象
"""
...
def auto_port(self,
on_off: bool = True,
scope: Tuple[int, int] = None) -> ChromiumOptions:
"""自动获取可用端口,与set_address()和set_local_port()互斥
:param on_off: 是否开启自动获取端口号
:param scope: 指定端口范围,不含最后的数字,为None则使用[9600-59600)
:return: 当前对象
"""
...
def existing_only(self, on_off: bool = True) -> ChromiumOptions:
"""设置只接管已有浏览器,不自动启动新的
:param on_off: 是否开启自动获取端口号
:return: 当前对象
"""
...
def save(self, path: Union[str, Path] = None) -> str:
"""保存设置到文件
:param path: ini文件的路径, None 保存到当前读取的配置文件,传入 'default' 保存到默认ini文件
:return: 保存文件的绝对路径
"""
...
def save_to_default(self) -> str:
"""保存当前配置到默认ini文件"""
...
@@ -0,0 +1,33 @@
[paths]
download_path =
tmp_path =
[chromium_options]
address = 127.0.0.1:9222
browser_path = chrome
arguments = ['--no-default-browser-check', '--disable-suggestions-ui', '--no-first-run', '--disable-infobars', '--disable-popup-blocking', '--hide-crash-restore-bubble', '--disable-features=PrivacySandboxSettings4']
extensions = []
prefs = {'profile.default_content_settings.popups': 0, 'profile.default_content_setting_values': {'notifications': 2}}
flags = {}
load_mode = normal
user = Default
auto_port = False
system_user_path = False
existing_only = False
new_env = False
[session_options]
headers = {'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/603.3.8 (KHTML, like Gecko) Version/10.1.2 Safari/603.3.8', 'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'connection': 'keep-alive', 'accept-charset': 'GB2312,utf-8;q=0.7,*;q=0.7'}
[timeouts]
base = 10
page_load = 30
script = 30
[proxies]
http =
https =
[others]
retry_times = 3
retry_interval = 2
@@ -0,0 +1,141 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from configparser import RawConfigParser, NoSectionError, NoOptionError
from pathlib import Path
from pprint import pprint
from .._functions.settings import Settings as _S
class OptionsManager(object):
def __init__(self, path=None):
if path is False:
self.ini_path = None
else:
default_configs = Path(__file__).parent / 'configs.ini'
if path is None:
dp_configs = Path('dp_configs.ini')
if dp_configs.exists():
self.ini_path = dp_configs
else:
self.ini_path = default_configs
elif path == 'default':
self.ini_path = default_configs
elif isinstance(path, Path):
self.ini_path = path
else:
self.ini_path = Path(path)
self._conf = RawConfigParser()
if path is not False and self.ini_path.exists():
self.file_exists = True
self._conf.read(self.ini_path, encoding='utf-8')
else:
self.file_exists = False
self._conf.add_section('paths')
self._conf.add_section('chromium_options')
self._conf.add_section('session_options')
self._conf.add_section('timeouts')
self._conf.add_section('proxies')
self._conf.add_section('others')
self.set_item('paths', 'download_path', '')
self.set_item('paths', 'tmp_path', '')
self.set_item('chromium_options', 'address', '127.0.0.1:9222')
self.set_item('chromium_options', 'browser_path', 'chrome')
self.set_item('chromium_options', 'arguments', "['--no-default-browser-check', '--disable-suggestions-ui', "
"'--no-first-run', '--disable-infobars', "
"'--disable-popup-blocking', '--hide-crash-restore-bubble', "
"'--disable-features=PrivacySandboxSettings4']")
self.set_item('chromium_options', 'extensions', '[]')
self.set_item('chromium_options', 'prefs', "{'profile.default_content_settings.popups': 0, "
"'profile.default_content_setting_values': "
"{'notifications': 2}}")
self.set_item('chromium_options', 'flags', '{}')
self.set_item('chromium_options', 'load_mode', 'normal')
self.set_item('chromium_options', 'user', 'Default')
self.set_item('chromium_options', 'auto_port', 'False')
self.set_item('chromium_options', 'system_user_path', 'False')
self.set_item('chromium_options', 'existing_only', 'False')
self.set_item('chromium_options', 'new_env', 'False')
self.set_item('session_options', 'headers', "{'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X "
"10_12_6) AppleWebKit/603.3.8 (KHTML, like Gecko) Version/10."
"1.2 Safari/603.3.8', 'accept': 'text/html,application/xhtml"
"+xml,application/xml;q=0.9,*/*;q=0.8', 'connection': "
"'keep-alive', 'accept-charset': 'GB2312,utf-8;q=0.7,*;q=0.7'}")
self.set_item('timeouts', 'base', '10')
self.set_item('timeouts', 'page_load', '30')
self.set_item('timeouts', 'script', '30')
self.set_item('proxies', 'http', '')
self.set_item('proxies', 'https', '')
self.set_item('others', 'retry_times', '3')
self.set_item('others', 'retry_interval', '2')
def __getattr__(self, item):
return self.get_option(item)
def get_value(self, section, item):
try:
return eval(self._conf.get(section, item))
except (SyntaxError, NameError):
return self._conf.get(section, item)
except NoSectionError and NoOptionError:
return None
def get_option(self, section):
items = self._conf.items(section)
option = dict()
for j in items:
try:
option[j[0]] = eval(self._conf.get(section, j[0]))
except Exception:
option[j[0]] = self._conf.get(section, j[0])
return option
def set_item(self, section, item, value):
self._conf.set(section, item, str(value))
self.__setattr__(f'_{section}', None)
return self
def remove_item(self, section, item):
self._conf.remove_option(section, item)
return self
def save(self, path=None):
default_path = (Path(__file__).parent / 'configs.ini').absolute()
if path == 'default':
path = default_path
elif path is None:
if self.ini_path is None:
raise RuntimeError(_S._lang.join(_S._lang.INI_NOT_SET))
path = self.ini_path.absolute()
else:
path = Path(path).absolute()
path = path / 'config.ini' if path.is_dir() else path
path.parent.mkdir(exist_ok=True, parents=True)
path = str(path)
self._conf.write(open(path, 'w', encoding='utf-8'))
print(f'{_S._lang.OPTIONS_HAVE_SAVED}: {path}')
if path == str(default_path):
print(_S._lang.AUTO_LOAD_TIP)
self.file_exists = True
return path
def save_to_default(self):
return self.save('default')
def show(self):
for i in self._conf.sections():
print(f'[{i}]')
pprint(self.get_option(i))
print()
@@ -0,0 +1,77 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from configparser import RawConfigParser
from pathlib import Path
from typing import Any, Optional, Union
class OptionsManager(object):
"""管理配置文件内容的类"""
ini_path: Optional[Path] = ...
file_exists: bool = ...
_conf: RawConfigParser = ...
def __init__(self, path: Union[Path, str] = None):
"""初始化,读取配置文件,如没有设置临时文件夹,则设置并新建
:param path: ini文件的路径,为None则找项目文件夹下的,找不到则读取模块文件夹下的
"""
...
def __getattr__(self, item) -> dict:
"""以dict形似返回获取大项信息
:param item: 项名
:return: None
"""
...
def get_value(self, section: str, item: str) -> Any:
"""获取配置的值
:param section: 段名
:param item: 项名
:return: 项值
"""
...
def get_option(self, section: str) -> dict:
"""把section内容以字典方式返回
:param section: 段名
:return: 段内容生成的字典
"""
...
def set_item(self, section: str, item: str, value: Any) -> None:
"""设置配置值
:param section: 段名
:param item: 项名
:param value: 项值
:return: None
"""
...
def remove_item(self, section: str, item: str) -> None:
"""删除配置值
:param section: 段名
:param item: 项名
:return: None
"""
...
def save(self, path: str = None) -> str:
"""保存配置文件
:param path: ini文件的路径,传入 'default' 保存到默认ini文件
:return: 保存路径
"""
...
def save_to_default(self) -> str:
"""保存当前配置到默认ini文件"""
...
def show(self) -> None:
"""打印所有设置信息"""
...
@@ -0,0 +1,371 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from copy import copy
from pathlib import Path
from requests import Session
from requests.structures import CaseInsensitiveDict
from .options_manage import OptionsManager
from .._functions.cookies import cookies_to_tuple, set_session_cookies
from .._functions.settings import Settings as _S
from .._functions.web import format_headers
class SessionOptions(object):
def __init__(self, read_file=True, ini_path=None):
self.ini_path = None
self._download_path = '.'
self._timeout = 10
self._del_set = set() # 记录要从ini文件删除的参数
if read_file is False:
ini_path = False
self.ini_path = None
elif ini_path:
ini_path = Path(ini_path).absolute()
if not ini_path.exists():
raise FileNotFoundError(_S._lang.join(_S._lang.INI_NOT_FOUND, PATH=ini_path))
self.ini_path = str(ini_path)
else:
self.ini_path = str(Path(__file__).parent / 'configs.ini')
om = OptionsManager(ini_path)
self._headers = None
self._cookies = None
self._auth = None
self._proxies = None
self._hooks = None
self._params = None
self._verify = None
self._cert = None
self._adapters = None
self._stream = None
self._trust_env = None
self._max_redirects = None
options = om.session_options
if options.get('headers', None) is not None:
self.set_headers(options['headers'])
if options.get('cookies', None) is not None:
self.set_cookies(options['cookies'])
if options.get('auth', None) is not None:
self._auth = options['auth']
if options.get('params', None) is not None:
self._params = options['params']
if options.get('verify', None) is not None:
self._verify = options['verify']
if options.get('cert', None) is not None:
self._cert = options['cert']
if options.get('stream', None) is not None:
self._stream = options['stream']
if options.get('trust_env', None) is not None:
self._trust_env = options['trust_env']
if options.get('max_redirects', None) is not None:
self._max_redirects = options['max_redirects']
self.set_proxies(om.proxies.get('http', None), om.proxies.get('https', None))
self._timeout = om.timeouts.get('base', 10)
self._download_path = om.paths.get('download_path', '.') or '.'
others = om.others
self._retry_times = others.get('retry_times', 3)
self._retry_interval = others.get('retry_interval', 2)
def __repr__(self):
return f'<SessionOptions at {id(self)}>'
# ===========须独立处理的项开始============
@property
def download_path(self):
return self._download_path
def set_download_path(self, path):
self._download_path = '.' if path is None else str(path)
return self
@property
def timeout(self):
return self._timeout
def set_timeout(self, second):
self._timeout = second
return self
@property
def proxies(self):
if self._proxies is None:
self._proxies = {}
return self._proxies
def set_proxies(self, http=None, https=None):
self._sets('proxies', {'http': http, 'https': https})
return self
@property
def retry_times(self):
return self._retry_times
@property
def retry_interval(self):
return self._retry_interval
def set_retry(self, times=None, interval=None):
if times is not None:
self._retry_times = times
if interval is not None:
self._retry_interval = interval
return self
# ===========须独立处理的项结束============
@property
def headers(self):
if self._headers is None:
self._headers = {}
return self._headers
def set_headers(self, headers):
if headers is None:
self._headers = None
self._del_set.add('headers')
else:
headers = format_headers(headers)
self._headers = {key.lower(): headers[key] for key in headers}
return self
def set_a_header(self, name, value):
if self._headers is None:
self._headers = {}
self._headers[name.lower()] = value
return self
def remove_a_header(self, name):
if self._headers is None:
return self
self._headers.pop(name.lower(), None)
return self
def clear_headers(self):
self._headers = None
self._del_set.add('headers')
@property
def cookies(self):
if self._cookies is None:
self._cookies = []
return self._cookies
def set_cookies(self, cookies):
cookies = cookies if cookies is None else list(cookies_to_tuple(cookies))
self._sets('cookies', cookies)
return self
@property
def auth(self):
return self._auth
def set_auth(self, auth):
self._sets('auth', auth)
return self
@property
def hooks(self):
if self._hooks is None:
self._hooks = {}
return self._hooks
def set_hooks(self, hooks):
self._hooks = hooks
return self
@property
def params(self):
if self._params is None:
self._params = {}
return self._params
def set_params(self, params):
self._sets('params', params)
return self
@property
def verify(self):
return self._verify
def set_verify(self, on_off):
self._sets('verify', on_off)
return self
@property
def cert(self):
return self._cert
def set_cert(self, cert):
self._sets('cert', cert)
return self
@property
def adapters(self):
if self._adapters is None:
self._adapters = []
return self._adapters
def add_adapter(self, url, adapter):
self._adapters.append((url, adapter))
return self
@property
def stream(self):
return self._stream
def set_stream(self, on_off):
self._sets('stream', on_off)
return self
@property
def trust_env(self):
return self._trust_env
def set_trust_env(self, on_off):
self._sets('trust_env', on_off)
return self
@property
def max_redirects(self):
return self._max_redirects
def set_max_redirects(self, times):
self._sets('max_redirects', times)
return self
def _sets(self, arg, val):
if val is None:
self.__setattr__(f'_{arg}', None)
self._del_set.add(arg)
else:
self.__setattr__(f'_{arg}', val)
if arg in self._del_set:
self._del_set.remove(arg)
def save(self, path=None):
if path == 'default':
path = (Path(__file__).parent / 'configs.ini').absolute()
elif path is None:
if self.ini_path:
path = Path(self.ini_path).absolute()
else:
path = (Path(__file__).parent / 'configs.ini').absolute()
else:
path = Path(path).absolute()
path = path / 'config.ini' if path.is_dir() else path
if path.exists():
om = OptionsManager(path)
else:
om = OptionsManager(self.ini_path or (Path(__file__).parent / 'configs.ini'))
options = session_options_to_dict(self)
for i in options:
if i not in ('download_path', 'timeout', 'proxies'):
om.set_item('session_options', i, options[i])
om.set_item('paths', 'download_path', self.download_path or '')
om.set_item('timeouts', 'base', self.timeout)
om.set_item('proxies', 'http', self.proxies.get('http', ''))
om.set_item('proxies', 'https', self.proxies.get('https', ''))
om.set_item('others', 'retry_times', self.retry_times)
om.set_item('others', 'retry_interval', self.retry_interval)
for i in self._del_set:
if i == 'download_path':
om.set_item('paths', 'download_path', '')
elif i == 'proxies':
om.set_item('proxies', 'http', '')
om.set_item('proxies', 'https', '')
else:
om.remove_item('session_options', i)
path = str(path)
om.save(path)
return path
def save_to_default(self):
return self.save('default')
def as_dict(self):
return session_options_to_dict(self)
def make_session(self):
s = Session()
h = CaseInsensitiveDict(self.headers) if self.headers else CaseInsensitiveDict()
if self.cookies:
set_session_cookies(s, self.cookies)
if self.adapters:
for url, adapter in self.adapters:
s.mount(url, adapter)
for i in ['auth', 'proxies', 'hooks', 'params', 'verify', 'cert', 'stream', 'trust_env', 'max_redirects']:
attr = self.__getattribute__(i)
if attr:
s.__setattr__(i, attr)
return s, h
def from_session(self, session, headers=None):
self._headers = CaseInsensitiveDict(copy(session.headers).update(headers)) if headers else session.headers
self._cookies = session.cookies
self._auth = session.auth
self._proxies = session.proxies
self._hooks = session.hooks
self._params = session.params
self._verify = session.verify
self._cert = session.cert
self._stream = session.stream
self._trust_env = session.trust_env
self._max_redirects = session.max_redirects
if session.adapters:
self._adapters = [(k, i) for k, i in session.adapters.items()]
return self
def session_options_to_dict(options):
if options in (False, None):
return SessionOptions(read_file=False).as_dict()
if isinstance(options, dict):
return options
re_dict = dict()
attrs = ['headers', 'cookies', 'proxies', 'params', 'verify', 'stream', 'trust_env', 'cert',
'max_redirects', 'timeout', 'download_path']
for attr in attrs:
val = options.__getattribute__(f'_{attr}')
if val is not None:
re_dict[attr] = val
return re_dict
@@ -0,0 +1,298 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from http.cookiejar import CookieJar, Cookie
from pathlib import Path
from typing import Any, Union, Tuple, Optional
from requests import Session
from requests.adapters import HTTPAdapter
from requests.auth import HTTPBasicAuth
from requests.cookies import RequestsCookieJar
from requests.structures import CaseInsensitiveDict
class SessionOptions(object):
"""requests的Session对象配置类"""
ini_path: Optional[str] = ...
_download_path: str = ...
_headers: Union[dict, CaseInsensitiveDict, None] = ...
_cookies: Union[list, RequestsCookieJar, None] = ...
_auth: Optional[tuple] = ...
_proxies: Optional[dict] = ...
_hooks: Optional[dict] = ...
_params: Union[dict, None] = ...
_verify: Optional[bool] = ...
_cert: Union[str, tuple, None] = ...
_adapters: Optional[list] = ...
_stream: Optional[bool] = ...
_trust_env: Optional[bool] = ...
_max_redirects: Optional[int] = ...
_timeout: float = ...
_del_set: set = ...
_retry_times: int = ...
_retry_interval: float = ...
def __init__(self,
read_file: [bool, None] = True,
ini_path: Union[str, Path] = None):
"""
:param read_file: 是否从文件读取配置
:param ini_path: ini文件路径
"""
...
@property
def download_path(self) -> str:
"""返回默认下载路径属性信息"""
...
def set_download_path(self, path: Union[str, Path]) -> SessionOptions:
"""设置默认下载路径
:param path: 下载路径
:return: 返回当前对象
"""
...
@property
def timeout(self) -> float:
"""返回timeout属性信息"""
...
def set_timeout(self, second: float) -> SessionOptions:
"""设置超时信息
:param second: 秒数
:return: 返回当前对象
"""
...
@property
def proxies(self) -> dict:
"""返回proxies设置信息"""
...
def set_proxies(self, http: Union[str, None], https: Union[str, None] = None) -> SessionOptions:
"""设置proxies参数
:param http: http代理地址
:param https: https代理地址
:return: 返回当前对象
"""
...
@property
def retry_times(self) -> int:
"""返回连接失败时的重试次数"""
...
@property
def retry_interval(self) -> float:
"""返回连接失败时的重试间隔(秒)"""
...
def set_retry(self, times: int = None, interval: float = None) -> SessionOptions:
"""设置连接失败时的重试操作
:param times: 重试次数
:param interval: 重试间隔
:return: 当前对象
"""
...
@property
def headers(self) -> dict:
"""返回headers设置信息"""
...
def set_headers(self, headers: Union[dict, str, None]) -> SessionOptions:
"""设置headers参数
:param headers: 参数值,传入None可在ini文件标记删除
:return: 返回当前对象
"""
...
def set_a_header(self, name: str, value: str) -> SessionOptions:
"""设置headers中一个项
:param name: 设置名称
:param value: 设置值
:return: 返回当前对象
"""
...
def remove_a_header(self, name: str) -> SessionOptions:
"""从headers中删除一个设置
:param name: 要删除的设置
:return: 返回当前对象
"""
...
def clear_headers(self) -> SessionOptions:
"""清空已设置的header参数"""
...
@property
def cookies(self) -> list:
"""以list形式返回cookies"""
...
def set_cookies(self, cookies: Union[Cookie, CookieJar, list, tuple, str, dict, None]) -> SessionOptions:
"""设置一个或多个cookies信息
:param cookies: cookies,可为Cookie, CookieJar, list, tuple, str, dict,传入None可在ini文件标记删除
:return: 返回当前对象
"""
...
@property
def auth(self) -> Union[Tuple[str, str], HTTPBasicAuth]:
"""返回认证设置信息"""
...
def set_auth(self, auth: Union[Tuple[str, str], HTTPBasicAuth, None]) -> SessionOptions:
"""设置认证元组或对象
:param auth: 认证元组或对象
:return: 返回当前对象
"""
...
@property
def hooks(self) -> dict:
"""返回回调方法"""
...
def set_hooks(self, hooks: Union[dict, None]) -> SessionOptions:
"""设置回调方法
:param hooks: 回调方法
:return: 返回当前对象
"""
...
@property
def params(self) -> dict:
"""返回连接参数设置信息"""
...
def set_params(self, params: Union[dict, None]) -> SessionOptions:
"""设置查询参数字典
:param params: 查询参数字典
:return: 返回当前对象
"""
...
@property
def verify(self) -> bool:
"""返回是否验证SSL证书设置"""
...
def set_verify(self, on_off: Union[bool, None]) -> SessionOptions:
"""设置是否验证SSL证书
:param on_off: 是否验证 SSL 证书
:return: 返回当前对象
"""
...
@property
def cert(self) -> Union[str, tuple]:
"""返回SSL证书设置信息"""
...
def set_cert(self, cert: Union[str, Tuple[str, str], None]) -> SessionOptions:
"""SSL客户端证书文件的路径(.pem格式),或('cert', 'key')元组
:param cert: 证书路径或元组
:return: 返回当前对象
"""
...
@property
def adapters(self) -> list:
"""返回适配器设置信息"""
...
def add_adapter(self, url: str, adapter: HTTPAdapter) -> SessionOptions:
"""添加适配器
:param url: 适配器对应url
:param adapter: 适配器对象
:return: 返回当前对象
"""
...
@property
def stream(self) -> bool:
"""返回是否使用流式响应内容设置信息"""
...
def set_stream(self, on_off: Union[bool, None]) -> SessionOptions:
"""设置是否使用流式响应内容
:param on_off: 是否使用流式响应内容
:return: 返回当前对象
"""
...
@property
def trust_env(self) -> bool:
"""返回是否信任环境设置信息"""
...
def set_trust_env(self, on_off: Union[bool, None]) -> SessionOptions:
"""设置是否信任环境
:param on_off: 是否信任环境
:return: 返回当前对象
"""
...
@property
def max_redirects(self) -> int:
"""返回最大重定向次数"""
...
def set_max_redirects(self, times: Union[int, None]) -> SessionOptions:
"""设置最大重定向次数
:param times: 最大重定向次数
:return: 返回当前对象
"""
...
def _sets(self, arg: str, val: Any) -> None:
"""给属性赋值或标记删除
:param arg: 属性名称
:param val: 参数值
:return: None
"""
...
def save(self, path: str = None) -> str:
"""保存设置到文件
:param path: ini文件的路径,传入 'default' 保存到默认ini文件
:return: 保存文件的绝对路径
"""
...
def save_to_default(self) -> str:
"""保存当前配置到默认ini文件"""
...
def as_dict(self) -> dict:
"""以字典形式返回本对象"""
...
def make_session(self) -> Tuple[Session, Optional[CaseInsensitiveDict]]:
"""根据内在的配置生成Session对象,headers从对象中分离"""
...
def from_session(self, session: Session, headers: CaseInsensitiveDict = None) -> SessionOptions:
"""从Session对象中读取配置
:param session: Session对象
:param headers: headers
:return: 当前对象
"""
...
def session_options_to_dict(options: Union[dict, SessionOptions, None]) -> Union[dict, None]:
"""把session配置对象转换为字典
:param options: session配置对象或字典
:return: 配置字典
"""
...
File diff suppressed because it is too large. Load diff
@@ -0,0 +1,980 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from pathlib import Path
from typing import Union, Tuple, List, Any, Literal, Optional
from .._base.base import DrissionElement, BaseElement
from .._elements.session_element import SessionElement
from .._functions.elements import SessionElementsList, ChromiumElementsList
from .._pages.chromium_base import ChromiumBase
from .._pages.chromium_frame import ChromiumFrame
from .._pages.chromium_page import ChromiumPage
from .._pages.chromium_tab import ChromiumTab
from .._pages.web_page import WebPage
from .._units.clicker import Clicker
from .._units.rect import ElementRect
from .._units.scroller import ElementScroller
from .._units.selector import SelectElement
from .._units.setter import ChromiumElementSetter
from .._units.states import ShadowRootStates, ElementStates
from .._units.waiter import ElementWaiter
PIC_TYPE = Literal['jpg', 'jpeg', 'png', 'webp', True]
class ChromiumElement(DrissionElement):
_tag: Optional[str] = ...
owner: ChromiumBase = ...
page: Union[ChromiumPage, WebPage] = ...
tab: Union[ChromiumPage, ChromiumTab] = ...
_node_id: int = ...
_obj_id: str = ...
_backend_id: int = ...
_doc_id: Optional[str] = ...
_scroll: Optional[ElementScroller] = ...
_clicker: Optional[Clicker] = ...
_select: Union[SelectElement, None, False] = ...
_wait: Optional[ElementWaiter] = ...
_rect: Optional[ElementRect] = ...
_set: Optional[ChromiumElementSetter] = ...
_states: Optional[ElementStates] = ...
_pseudo: Optional[Pseudo] = ...
def __init__(self,
owner: ChromiumBase,
node_id: int = None,
obj_id: str = None,
backend_id: int = None):
"""node_id、obj_id和backend_id必须至少传入一个
:param owner: 元素所在页面对象
:param node_id: cdp中的node id
:param obj_id: js中的object id
:param backend_id: backend id
"""
...
def __call__(self,
locator: Union[Tuple[str, str], str],
index: int = 1,
timeout: float = None) -> ChromiumElement:
"""在内部查找元素
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param timeout: 超时时间(秒)
:return: ChromiumElement对象或属性、文本
"""
...
def __repr__(self) -> str: ...
def __eq__(self, other: ChromiumElement) -> bool: ...
@property
def tag(self) -> str:
"""返回元素tag"""
...
@property
def html(self) -> str:
"""返回元素outerHTML文本"""
...
@property
def inner_html(self) -> str:
"""返回元素innerHTML文本"""
...
@property
def attrs(self) -> dict:
"""返回元素所有attribute属性"""
...
@property
def text(self) -> str:
"""返回元素内所有文本,文本已格式化"""
...
@property
def raw_text(self) -> str:
"""返回未格式化处理的元素内文本"""
...
@property
def set(self) -> ChromiumElementSetter:
"""返回用于设置元素属性的对象"""
...
@property
def states(self) -> ElementStates:
"""返回用于获取元素状态的对象"""
...
@property
def pseudo(self) -> Pseudo:
"""返回用于获取伪元素内容的对象"""
...
@property
def rect(self) -> ElementRect:
"""返回用于获取元素位置的对象"""
...
@property
def shadow_root(self) -> Union[None, ShadowRoot]:
"""返回当前元素的shadow_root元素对象"""
...
@property
def sr(self) -> Union[None, ShadowRoot]:
"""返回当前元素的shadow_root元素对象"""
...
@property
def scroll(self) -> ElementScroller:
"""用于滚动滚动条的对象"""
...
@property
def click(self) -> Clicker:
"""返回用于点击的对象"""
...
@property
def wait(self) -> ElementWaiter:
"""返回用于等待的对象"""
...
@property
def select(self) -> Union[SelectElement, False]:
"""返回专门处理下拉列表的Select类,非<select>元素返回False"""
...
@property
def value(self) -> str:
"""返回元素property属性的value值"""
...
def parent(self,
level_or_loc: Union[tuple, str, int] = 1,
index: int = 1,
timeout: float = 0) -> ChromiumElement:
"""返回上面某一级父元素,可指定层数或用查询语法定位
:param level_or_loc: 第几级父元素,1开始,或定位符
:param index: 当level_or_loc传入定位符,使用此参数选择第几个结果,1开始
:param timeout: 查找超时时间(秒)
:return: 上级元素对象
"""
...
def child(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[ChromiumElement, str]:
"""返回当前元素的一个符合条件的直接子元素,可用查询语法筛选,可指定返回筛选结果的第几个
:param locator: 用于筛选的查询语法
:param index: 第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 直接子元素或节点文本
"""
...
def prev(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[ChromiumElement, str]:
"""返回当前元素前面一个符合条件的同级元素,可用查询语法筛选,可指定返回筛选结果的第几个
:param locator: 用于筛选的查询语法
:param index: 前面第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 兄弟元素或节点文本
"""
...
def next(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[ChromiumElement, str]:
"""返回当前元素后面一个符合条件的同级元素,可用查询语法筛选,可指定返回筛选结果的第几个
:param locator: 用于筛选的查询语法
:param index: 第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 兄弟元素或节点文本
"""
...
def before(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[ChromiumElement, str]:
"""返回文档中当前元素前面符合条件的一个元素,可用查询语法筛选,可指定返回筛选结果的第几个
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param index: 前面第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素前面的某个元素或节点
"""
...
def after(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[ChromiumElement, str]:
"""返回文档中此当前元素后面符合条件的一个元素,可用查询语法筛选,可指定返回筛选结果的第几个
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param index: 第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素后面的某个元素或节点
"""
...
def children(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> Union[ChromiumElementsList, List[Union[ChromiumElement, str]]]:
"""返回当前元素符合条件的直接子元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 直接子元素或节点文本组成的列表
"""
...
def prevs(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> Union[ChromiumElementsList, List[Union[ChromiumElement, str]]]:
"""返回当前元素前面符合条件的同级元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 兄弟元素或节点文本组成的列表
"""
...
def nexts(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> Union[ChromiumElementsList, List[Union[ChromiumElement, str]]]:
"""返回当前元素后面符合条件的同级元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 兄弟元素或节点文本组成的列表
"""
...
def befores(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> Union[ChromiumElementsList, List[Union[ChromiumElement, str]]]:
"""返回文档中当前元素前面符合条件的元素或节点组成的列表,可用查询语法筛选
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素前面的元素或节点组成的列表
"""
...
def afters(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> Union[ChromiumElementsList, List[Union[ChromiumElement, str]]]:
"""返回文档中当前元素后面符合条件的元素或节点组成的列表,可用查询语法筛选
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素后面的元素或节点组成的列表
"""
...
def over(self, timeout: float = None) -> ChromiumElement:
"""获取覆盖在本元素上最上层的元素
:param timeout: 等待元素出现的超时时间(秒)
:return: 元素对象
"""
...
def offset(self,
locator: Optional[str] = None,
x: int = None,
y: int = None,
timeout: float = None) -> ChromiumElement:
"""获取相对本元素左上角左边指定偏移量位置的元素,如果offset_x和offset_y都是None,定位到元素中间点
:param locator: 定位符,只支持str,且不支持xpath和css方式
:param x: 横坐标偏移量,向右为正
:param y: 纵坐标偏移量,向下为正
:param timeout: 超时时间(秒),为None使用所在页面设置
:return: 元素对象
"""
...
def east(self, loc_or_pixel: Union[str, int, None] = None, index: int = 1) -> ChromiumElement:
"""获取元素右边某个指定元素
:param loc_or_pixel: 定位符,只支持str或int,且不支持xpath和css方式,传入int按像素距离获取
:param index: 第几个,从1开始
:return: 获取到的元素对象
"""
...
def south(self, loc_or_pixel: Union[str, int, None] = None, index: int = 1) -> ChromiumElement:
"""获取元素下方某个指定元素
:param loc_or_pixel: 定位符,只支持str或int,且不支持xpath和css方式,传入int按像素距离获取
:param index: 第几个,从1开始
:return: 获取到的元素对象
"""
...
def west(self, loc_or_pixel: Union[str, int, None] = None, index: int = 1) -> ChromiumElement:
"""获取元素左边某个指定元素
:param loc_or_pixel: 定位符,只支持str或int,且不支持xpath和css方式,传入int按像素距离获取
:param index: 第几个,从1开始
:return: 获取到的元素对象
"""
...
def north(self, loc_or_pixel: Union[str, int, None] = None, index: int = 1) -> ChromiumElement:
"""获取元素上方某个指定元素
:param loc_or_pixel: 定位符,只支持str或int,且不支持xpath和css方式,传入int按像素距离获取
:param index: 第几个,从1开始
:return: 获取到的元素对象
"""
...
def _get_relative_eles(self,
mode: str = 'north',
locator: Union[int, str] = None,
index: int = 1) -> ChromiumElement:
"""获取元素下方某个指定元素
:param locator: 定位符,只支持str或int,且不支持xpath和css方式
:param index: 第几个,从1开始
:return: 获取到的元素对象
"""
...
def check(self, uncheck: bool = False, by_js: bool = False) -> None:
"""选中或取消选中当前元素
:param uncheck: 是否取消选中
:param by_js: 是否用js执行
:return: None
"""
...
def attr(self, name: str) -> Union[str, None]:
"""返回一个attribute属性值
:param name: 属性名
:return: 属性值文本,没有该属性返回None
"""
...
def remove_attr(self, name: str) -> ChromiumElement:
"""删除元素一个attribute属性
:param name: 属性名
:return: None
"""
...
def property(self, name: str) -> Union[str, int, None]:
"""获取一个property属性值
:param name: 属性名
:return: 属性值文本
"""
...
def run_js(self, script: str, *args, as_expr: bool = False, timeout: float = None) -> Any:
"""对本元素执行javascript代码
:param script: js文本,文本中用this表示本元素
:param args: 参数,按顺序在js文本中对应arguments[0]、arguments[1]...
:param as_expr: 是否作为表达式运行,为True时args无效
:param timeout: js超时时间(秒),为None则使用页面timeouts.script设置
:return: 运行的结果
"""
...
def _run_js(self, script: str, *args, as_expr: bool = False, timeout: float = None) -> Any:
"""对本元素执行javascript代码
:param script: js文本,文本中用this表示本元素
:param args: 参数,按顺序在js文本中对应arguments[0]、arguments[1]...
:param as_expr: 是否作为表达式运行,为True时args无效
:param timeout: js超时时间(秒),为None则使用页面timeouts.script设置
:return: 运行的结果
"""
...
def run_async_js(self, script: str, *args, as_expr: bool = False) -> None:
"""以异步方式对本元素执行javascript代码
:param script: js文本,文本中用this表示本元素
:param args: 参数,按顺序在js文本中对应arguments[0]、arguments[1]...
:param as_expr: 是否作为表达式运行,为True时args无效
:return: None
"""
...
def ele(self,
locator: Union[Tuple[str, str], str],
index: int = 1,
timeout: float = None) -> ChromiumElement:
"""返回当前元素下级符合条件的一个元素、属性或节点文本
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 获取第几个元素,从1开始,可传入负数获取倒数第几个
:param timeout: 查找元素超时时间(秒),默认与元素所在页面等待时间一致
:return: ChromiumElement对象或属性、文本
"""
...
def eles(self,
locator: Union[Tuple[str, str], str],
timeout: float = None) -> ChromiumElementsList:
"""返回当前元素下级所有符合条件的子元素、属性或节点文本
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param timeout: 查找元素超时时间(秒),默认与元素所在页面等待时间一致
:return: ChromiumElement对象或属性、文本组成的列表
"""
...
def s_ele(self,
locator: Union[Tuple[str, str], str] = None,
index: int = 1,
timeout: float = None) -> SessionElement:
"""查找一个符合条件的元素,以SessionElement形式返回
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param timeout: 查找元素超时时间(秒),默认与元素所在页面等待时间一致
:return: SessionElement对象或属性、文本
"""
...
def s_eles(self,
locator: Union[Tuple[str, str], str] = None,
timeout: float = None) -> SessionElementsList:
"""查找所有符合条件的元素,以SessionElement列表形式返回
:param locator: 定位符
:param timeout: 查找元素超时时间(秒),默认与元素所在页面等待时间一致
:return: SessionElement或属性、文本组成的列表
"""
...
def _find_elements(self,
locator: Union[Tuple[str, str], str],
timeout: float,
index: Optional[int] = 1,
relative: bool = False,
raise_err: bool = False) -> Union[ChromiumElement, ChromiumFrame, ChromiumElementsList]:
"""返回当前元素下级符合条件的子元素、属性或节点文本,默认返回第一个
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param timeout: 查找元素超时时间(秒)
:param index: 第几个结果,从1开始,可传入负数获取倒数第几个,为None返回所有
:param relative: MixTab用的表示是否相对定位的参数
:param raise_err: 找不到元素是是否抛出异常,为None时根据全局设置
:return: ChromiumElement对象或文本、属性或其组成的列表
"""
...
def style(self, style: str, pseudo_ele: str = '') -> str:
"""返回元素样式属性值,可获取伪元素属性值
:param style: 样式属性名称
:param pseudo_ele: 伪元素名称(如有)
:return: 样式属性的值
"""
...
def src(self, timeout: float = None, base64_to_bytes: bool = True) -> Union[bytes, str, None]:
"""返回元素src资源,base64的可转为bytes返回,其它返回str
:param timeout: 等待资源加载的超时时间(秒)
:param base64_to_bytes: 为True时,如果是base64数据,转换为bytes格式
:return: 资源内容
"""
...
def save(self,
path: [str, bool] = None,
name: str = None,
timeout: float = None,
rename: bool = True) -> str:
"""保存图片或其它有src属性的元素的资源
:param path: 文件保存路径,为None时保存到当前文件夹
:param name: 文件名称,为None时从资源url获取
:param timeout: 等待资源加载的超时时间(秒)
:param rename: 遇到重名文件时是否自动重命名
:return: 返回保存路径
"""
...
def get_screenshot(self,
path: [str, Path] = None,
name: str = None,
as_bytes: PIC_TYPE = None,
as_base64: PIC_TYPE = None,
scroll_to_center: bool = True) -> Union[str, bytes]:
"""对当前元素截图,可保存到文件,或以字节方式返回
:param path: 文件保存路径
:param name: 完整文件名,后缀可选 'jpg','jpeg','png','webp'
:param as_bytes: 是否以字节形式返回图片,可选 'jpg','jpeg','png','webp',生效时path参数和as_base64参数无效
:param as_base64: 是否以base64字符串形式返回图片,可选 'jpg','jpeg','png','webp',生效时path参数无效
:param scroll_to_center: 截图前是否滚动到视口中央
:return: 图片完整路径或字节文本
"""
...
def input(self, vals: Any, clear: bool = False, by_js: bool = False) -> ChromiumElement:
"""输入文本或组合键,也可用于输入文件路径到input元素(路径间用\n间隔)
:param vals: 文本值或按键组合
:param clear: 输入前是否清空文本框
:param by_js: 是否用js方式输入,不能输入组合键
:return: None
"""
...
def clear(self, by_js: bool = False) -> ChromiumElement:
"""清空元素文本
:param by_js: 是否用js方式清空,为False则用全选+del模拟输入删除
:return: None
"""
...
def _input_focus(self) -> None:
"""输入前使元素获取焦点"""
...
def focus(self) -> ChromiumElement:
"""使元素获取焦点"""
...
def hover(self, offset_x: int = None, offset_y: int = None) -> ChromiumElement:
"""鼠标悬停,可接受偏移量,偏移量相对于元素左上角坐标。不传入offset_x和offset_y值时悬停在元素中点
:param offset_x: 相对元素左上角坐标的x轴偏移量
:param offset_y: 相对元素左上角坐标的y轴偏移量
:return: None
"""
...
def drag(self, offset_x: int = 0, offset_y: int = 0, duration: float = 0.5) -> ChromiumElement:
"""拖拽当前元素到相对位置
:param offset_x: x变化值
:param offset_y: y变化值
:param duration: 拖动用时,传入0即瞬间到达
:return: None
"""
...
def drag_to(self,
ele_or_loc: Union[Tuple[int, int], str, ChromiumElement],
duration: float = 0.5) -> ChromiumElement:
"""拖拽当前元素,目标为另一个元素或坐标元组(x, y)
:param ele_or_loc: 另一个元素或坐标元组,坐标为元素中点的坐标
:param duration: 拖动用时,传入0即瞬间到达
:return: None
"""
...
def _get_obj_id(self, node_id: int = None, backend_id: int = None) -> str: ...
def _get_node_id(self, obj_id: str = None, backend_id: int = None) -> int: ...
def _get_backend_id(self, node_id: int) -> int: ...
def _refresh_id(self) -> None:
"""根据backend id刷新其它id"""
...
def _get_ele_path(self, xpath: bool = True) -> str:
"""返获取绝对的css路径或xpath路径"""
...
def _set_file_input(self, files: Union[str, list, tuple]) -> None:
"""对上传控件写入路径
:param files: 文件路径列表或字符串,字符串时多个文件用回车分隔
:return: None
"""
...
class ShadowRoot(BaseElement):
owner: ChromiumBase = ...
tab: Union[ChromiumPage, ChromiumTab] = ...
_obj_id: str = ...
_node_id: int = ...
_backend_id: int = ...
parent_ele: ChromiumElement = ...
_states: Optional[ShadowRootStates] = ...
def __init__(self, parent_ele: ChromiumElement, obj_id: str = None, backend_id: int = None):
"""
:param parent_ele: shadow root 所在父元素
:param obj_id: js中的object id
:param backend_id: cdp中的backend id
"""
...
def __call__(self,
locator: Union[Tuple[str, str], str],
index: int = 1,
timeout: float = None) -> ChromiumElement:
"""在内部查找元素
例:ele2 = ele1('@id=ele_id')
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param timeout: 超时时间(秒)
:return: 元素对象或属性、文本
"""
...
def __repr__(self) -> str: ...
def __eq__(self, other: ShadowRoot) -> bool: ...
@property
def tag(self) -> str:
"""返回元素标签名"""
...
@property
def html(self) -> str:
"""返回outerHTML文本"""
...
@property
def inner_html(self) -> str:
"""返回内部的html文本"""
...
@property
def states(self) -> ShadowRootStates:
"""返回用于获取元素状态的对象"""
...
def run_js(self,
script: str,
*args,
as_expr: bool = False,
timeout: float = None) -> Any:
"""运行javascript代码
:param script: js文本
:param args: 参数,按顺序在js文本中对应arguments[0]、arguments[1]...
:param as_expr: 是否作为表达式运行,为True时args无效
:param timeout: js超时时间(秒),为None则使用页面timeouts.script设置
:return: 运行的结果
"""
...
def _run_js(self,
script: str,
*args,
as_expr: bool = False,
timeout: float = None) -> Any:
"""运行javascript代码
:param script: js文本
:param args: 参数,按顺序在js文本中对应arguments[0]、arguments[1]...
:param as_expr: 是否作为表达式运行,为True时args无效
:param timeout: js超时时间(秒),为None则使用页面timeouts.script设置
:return: 运行的结果
"""
...
def run_async_js(self,
script: str,
*args,
as_expr: bool = False,
timeout: float = None) -> None:
"""以异步方式执行js代码
:param script: js文本
:param args: 参数,按顺序在js文本中对应arguments[0]、arguments[1]...
:param as_expr: 是否作为表达式运行,为True时args无效
:param timeout: js超时时间(秒),为None则使用页面timeouts.script设置
:return: None
"""
...
def parent(self,
level_or_loc: Union[str, int] = 1,
index: int = 1,
timeout: float = 0) -> ChromiumElement:
"""返回上面某一级父元素,可指定层数或用查询语法定位
:param level_or_loc: 第几级父元素,或定位符
:param index: 当level_or_loc传入定位符,使用此参数选择第几个结果
:param timeout: 查找超时时间(秒)
:return: ChromiumElement对象
"""
...
def child(self,
locator: Union[Tuple[str, str], str] = '',
index: int = 1, timeout: float = None) -> ChromiumElement:
"""返回直接子元素元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param index: 第几个查询结果,1开始
:param timeout: 查找超时时间(秒)
:return: 直接子元素或节点文本组成的列表
"""
...
def next(self,
locator: Union[Tuple[str, str], str] = '',
index: int = 1, timeout: float = None) -> ChromiumElement:
"""返回当前元素后面一个符合条件的同级元素,可用查询语法筛选,可指定返回筛选结果的第几个
:param locator: 用于筛选的查询语法
:param index: 第几个查询结果,1开始
:param timeout: 查找超时时间(秒)
:return: ChromiumElement对象
"""
...
def before(self,
locator: Union[Tuple[str, str], str] = '',
index: int = 1, timeout: float = None) -> ChromiumElement:
"""返回文档中当前元素前面符合条件的一个元素,可用查询语法筛选,可指定返回筛选结果的第几个
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param index: 前面第几个查询结果,1开始
:param timeout: 查找超时时间(秒)
:return: 本元素前面的某个元素或节点
"""
...
def after(self,
locator: Union[Tuple[str, str], str] = '',
index: int = 1, timeout: float = None) -> ChromiumElement:
"""返回文档中此当前元素后面符合条件的一个元素,可用查询语法筛选,可指定返回筛选结果的第几个
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param index: 后面第几个查询结果,1开始
:param timeout: 查找超时时间(秒)
:return: 本元素后面的某个元素或节点
"""
...
def children(self, locator: Union[Tuple[str, str], str] = '', timeout: float = None) -> List[ChromiumElement]:
"""返回当前元素符合条件的直接子元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 查找超时时间(秒)
:return: 直接子元素或节点文本组成的列表
"""
...
def nexts(self, locator: Union[Tuple[str, str], str] = '', timeout: float = None) -> List[ChromiumElement]:
"""返回当前元素后面符合条件的同级元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 查找超时时间(秒)
:return: ChromiumElement对象组成的列表
"""
...
def befores(self, locator: Union[Tuple[str, str], str] = '', timeout: float = None) -> List[ChromiumElement]:
"""返回文档中当前元素前面符合条件的元素或节点组成的列表,可用查询语法筛选
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param timeout: 查找超时时间(秒)
:return: 本元素前面的元素或节点组成的列表
"""
...
def afters(self, locator: Union[Tuple[str, str], str] = '', timeout: float = None) -> List[ChromiumElement]:
"""返回文档中当前元素后面符合条件的元素或节点组成的列表,可用查询语法筛选
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param timeout: 查找超时时间(秒)
:return: 本元素后面的元素或节点组成的列表
"""
...
def ele(self,
locator: Union[Tuple[str, str], str],
index: int = 1,
timeout: float = None) -> ChromiumElement:
"""返回当前元素下级符合条件的一个元素
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 获取第几个元素,从1开始,可传入负数获取倒数第几个
:param timeout: 查找元素超时时间(秒),默认与元素所在页面等待时间一致
:return: ChromiumElement对象
"""
...
def eles(self,
locator: Union[Tuple[str, str], str],
timeout: float = None) -> ChromiumElementsList:
"""返回当前元素下级所有符合条件的子元素
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param timeout: 查找元素超时时间(秒),默认与元素所在页面等待时间一致
:return: ChromiumElement对象组成的列表
"""
...
def s_ele(self,
locator: Union[Tuple[str, str], str] = None,
index: int = 1,
timeout: float = None) -> SessionElement:
"""查找一个符合条件的元素以SessionElement形式返回,处理复杂页面时效率很高
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param timeout: 查找元素超时时间(秒),默认与元素所在页面等待时间一致
:return: SessionElement对象或属性、文本
"""
...
def s_eles(self, locator: Union[Tuple[str, str], str], timeout: float = None) -> SessionElementsList:
"""查找所有符合条件的元素以SessionElement列表形式返回,处理复杂页面时效率很高
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param timeout: 查找元素超时时间(秒),默认与元素所在页面等待时间一致
:return: SessionElement对象
"""
...
def _find_elements(self,
locator: Union[Tuple[str, str], str],
timeout: float,
index: Optional[int] = 1,
relative: bool = False,
raise_err: bool = None) -> Union[ChromiumElement, ChromiumFrame, str, ChromiumElementsList]:
"""返回当前元素下级符合条件的子元素、属性或节点文本,默认返回第一个
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param timeout: 查找元素超时时间(秒)
:param index: 第几个结果,从1开始,可传入负数获取倒数第几个,为None返回所有
:param relative: MixTab用的表示是否相对定位的参数
:param raise_err: 找不到元素是是否抛出异常,为None时根据全局设置
:return: ChromiumElement对象或其组成的列表
"""
...
def _get_node_id(self, obj_id: str) -> int: ...
def _get_obj_id(self, back_id: int) -> str: ...
def _get_backend_id(self, node_id: int) -> int: ...
def find_in_chromium_ele(ele: ChromiumElement,
locator: Union[str, Tuple[str, str]],
index: Optional[int] = 1,
timeout: float = None,
relative: bool = True) -> Union[ChromiumElement, List[ChromiumElement]]:
"""在chromium元素中查找
:param ele: ChromiumElement对象
:param locator: 元素定位元组
:param index: 第几个结果,从1开始,可传入负数获取倒数第几个,为None返回所有
:param timeout: 查找元素超时时间(秒)
:param relative: MixTab用于标记是否相对定位使用
:return: 返回ChromiumElement元素或它们组成的列表
"""
...
def find_by_xpath(ele: ChromiumElement,
xpath: str,
index: Optional[int],
timeout: float,
relative: bool = True) -> Union[ChromiumElement, List[ChromiumElement]]:
"""执行用xpath在元素中查找元素
:param ele: 在此元素中查找
:param xpath: 查找语句
:param index: 第几个结果,从1开始,可传入负数获取倒数第几个,为None返回所有
:param timeout: 超时时间(秒)
:param relative: 是否相对定位
:return: ChromiumElement或其组成的列表
"""
...
def find_by_css(ele: ChromiumElement,
selector: str,
index: Optional[int],
timeout: float) -> Union[ChromiumElement, List[ChromiumElement],]:
"""执行用css selector在元素中查找元素
:param ele: 在此元素中查找
:param selector: 查找语句
:param index: 第几个结果,从1开始,可传入负数获取倒数第几个,为None返回所有
:param timeout: 超时时间(秒)
:return: ChromiumElement或其组成的列表
"""
...
def make_chromium_eles(page: Union[ChromiumBase, ChromiumPage, WebPage, ChromiumTab, ChromiumFrame],
_ids: Union[tuple, list, str, int],
index: Optional[int] = 1,
is_obj_id: bool = True,
ele_only: bool = False
) -> Union[ChromiumElement, ChromiumFrame, ChromiumElementsList]:
"""根据node id或object id生成相应元素对象
:param page: ChromiumPage对象
:param _ids: 元素的id列表
:param index: 获取第几个,为None返回全部
:param is_obj_id: 传入的id是obj id还是node id
:param ele_only: 是否只返回ele,在页面查找元素时生效
:return: 浏览器元素对象或它们组成的列表,生成失败返回False
"""
...
def make_js_for_find_ele_by_xpath(xpath: str, type_txt: str, node_txt: str) -> str:
"""生成用xpath在元素中查找元素的js文本
:param xpath: xpath文本
:param type_txt: 查找类型
:param node_txt: 节点类型
:return: js文本
"""
...
def run_js(page_or_ele: Union[ChromiumBase, ChromiumElement, ShadowRoot],
script: str,
as_expr: bool,
timeout: float,
args: tuple = ...) -> Any:
"""运行javascript代码
:param page_or_ele: 页面对象或元素对象
:param script: js文本
:param as_expr: 是否作为表达式运行,为True时args无效
:param timeout: 超时时间(秒)
:param args: 参数,按顺序在js文本中对应arguments[0]、arguments[1]...
:return: js执行结果
"""
...
def parse_js_result(page: ChromiumBase,
ele: ChromiumElement,
result: dict,
end_time: float):
"""解析js返回的结果"""
...
def convert_argument(arg: Any) -> dict:
"""把参数转换成js能够接收的形式"""
...
class Pseudo(object):
_ele: ChromiumElement = ...
def __init__(self, ele: ChromiumElement):
"""
:param ele: ChromiumElement
"""
...
@property
def before(self) -> str:
"""返回当前元素的::before伪元素文本内容"""
...
@property
def after(self) -> str:
"""返回当前元素的::after伪元素文本内容"""
...
@@ -0,0 +1,52 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from .._functions.settings import Settings
from ..errors import ElementNotFoundError
class NoneElement(object):
def __init__(self, page=None, method=None, args=None):
if method and Settings.raise_when_ele_not_found: # 无传入method时不自动抛出,由调用者处理
raise ElementNotFoundError(METHOD=method, ARGS=args)
if page:
self._none_ele_value = page._none_ele_value
self._none_ele_return_value = page._none_ele_return_value
else:
self._none_ele_value = None
self._none_ele_return_value = False
self.method = method
self.args = {} if args is None else args
def __call__(self, *args, **kwargs):
if not self._none_ele_return_value:
raise ElementNotFoundError(METHOD=self.method, ARGS=self.args)
else:
return self
def __repr__(self):
return f'<NoneElement method={self.method}, {", ".join([f"{k}={v}" for k, v in self.args.items()])}>'
def __getattr__(self, item):
if not self._none_ele_return_value:
raise ElementNotFoundError(METHOD=self.method, ARGS=self.args)
elif item in ('ele', 's_ele', 'parent', 'child', 'next', 'prev', 'before', 'east', 'north', 'south', 'west',
'offset', 'over', 'after', 'get_frame', 'shadow_root', 'sr'):
return self
else:
if item in ('size', 'link', 'css_path', 'xpath', 'comments', 'texts', 'tag', 'html', 'inner_html',
'attrs', 'text', 'raw_text', 'value', 'attr', 'style', 'src', 'property'):
return self._none_ele_value
else:
raise ElementNotFoundError(METHOD=self.method, ARGS=self.args)
def __eq__(self, other):
return other is None
def __bool__(self):
return False
@@ -0,0 +1,38 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from typing import Any, Optional
from .._base.base import BasePage
class NoneElement(object):
_none_ele_value: Any = ...
_none_ele_return_value: Any = ...
method: Optional[str] = ...
args: Optional[dict] = ...
def __init__(self,
page: BasePage = None,
method: str = None,
args: dict = None):
"""
:param page: 元素所在页面
:param method: 查找元素的方法
:param args: 查找元素的参数
"""
...
def __call__(self, *args, **kwargs) -> NoneElement: ...
def __repr__(self) -> str: ...
def __getattr__(self, item: str) -> str: ...
def __eq__(self, other: Any) -> bool: ...
def __bool__(self) -> bool: ...
@@ -0,0 +1,298 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from html import unescape
from re import match, sub, DOTALL, search
from lxml.etree import tostring
from lxml.html import HtmlElement, fromstring
from .none_element import NoneElement
from .._base.base import DrissionElement, BasePage, BaseElement
from .._functions.elements import SessionElementsList
from .._functions.locator import get_loc
from .._functions.settings import Settings as _S
from .._functions.web import get_ele_txt, make_absolute_link
from ..errors import LocatorError
class SessionElement(DrissionElement):
def __init__(self, ele, owner=None):
"""初始化对象
:param ele: 被包装的HtmlElement元素
:param owner: 元素所在页面对象,如果是从 html 文本生成的元素,则为 None
"""
super().__init__(owner)
self._inner_ele = ele
self._type = 'SessionElement'
def __repr__(self):
attrs = [f"{k}='{v}'" for k, v in self.attrs.items()]
return f'<SessionElement {self.tag} {" ".join(attrs)}>'
def __call__(self, locator, index=1, timeout=None):
return self.ele(locator, index=index)
def __eq__(self, other):
return self.xpath == getattr(other, 'xpath', None)
@property
def inner_ele(self):
return self._inner_ele
@property
def tag(self):
return self._inner_ele.tag
@property
def html(self):
html = tostring(self._inner_ele, method="html").decode()
return unescape(html[:html.rfind('>') + 1]) # tostring()会把跟紧元素的文本节点也带上,因此要去掉
@property
def inner_html(self):
r = match(r'<.*?>(.*)</.*?>', self.html, flags=DOTALL)
return '' if not r else r.group(1)
@property
def attrs(self):
r = {}
for attr, val in self.inner_ele.items():
r[attr] = val if attr.lower in ('href', 'src') else self.attr(attr)
return r
@property
def text(self):
return get_ele_txt(self)
@property
def raw_text(self):
return str(self._inner_ele.text_content())
def parent(self, level_or_loc=1, index=1, timeout: float = None):
return super().parent(level_or_loc, index)
def child(self, locator='', index=1, timeout=None, ele_only=True):
return super().child(locator, index, timeout, ele_only=ele_only)
def prev(self, locator='', index=1, timeout=None, ele_only=True):
return super().prev(locator, index, timeout, ele_only=ele_only)
def next(self, locator='', index=1, timeout=None, ele_only=True):
return super().next(locator, index, timeout, ele_only=ele_only)
def before(self, locator='', index=1, timeout=None, ele_only=True):
return super().before(locator, index, timeout, ele_only=ele_only)
def after(self, locator='', index=1, timeout=None, ele_only=True):
return super().after(locator, index, timeout, ele_only=ele_only)
def children(self, locator='', timeout=0, ele_only=True):
return SessionElementsList(self.owner, super().children(locator, timeout, ele_only=ele_only))
def prevs(self, locator='', timeout=None, ele_only=True):
return SessionElementsList(self.owner, super().prevs(locator, timeout, ele_only=ele_only))
def nexts(self, locator='', timeout=None, ele_only=True):
return SessionElementsList(self.owner, super().nexts(locator, timeout, ele_only=ele_only))
def befores(self, locator='', timeout=None, ele_only=True):
return SessionElementsList(self.owner, super().befores(locator, timeout, ele_only=ele_only))
def afters(self, locator='', timeout=None, ele_only=True):
return SessionElementsList(self.owner, super().afters(locator, timeout, ele_only=ele_only))
def attr(self, name):
if name == 'href':
link = self.inner_ele.get('href')
if not link or link.lower().startswith(('javascript:', 'mailto:')):
return link
else:
return make_absolute_link(link, self.owner.url) if self.owner else link
elif name == 'src':
return make_absolute_link(self.inner_ele.get('src'),
self.owner.url) if self.owner else self.inner_ele.get('src')
elif name == 'text':
return self.text
elif name == 'innerText':
return self.raw_text
elif name in ('html', 'outerHTML'):
return self.html
elif name == 'innerHTML':
return self.inner_html
else:
return self.inner_ele.get(name.lower())
def ele(self, locator, index=1, timeout=None):
return self._ele(locator, index=index, method='ele()')
def eles(self, locator, timeout=None):
return self._ele(locator, index=None)
def s_ele(self, locator=None, index=1):
return self._ele(locator, index=index, method='s_ele()')
def s_eles(self, locator):
return self._ele(locator, index=None)
def _find_elements(self, locator, timeout, index=1, relative=False, raise_err=None):
return make_session_ele(self, locator, index=index)
def _get_ele_path(self, xpath=True):
if xpath:
return self._inner_ele.getroottree().getpath(self._inner_ele)
path_str = ''
ele = self
while ele:
id_ = ele.attr('id')
if id_:
path_str = f'>{ele.tag}#{id_}{path_str}'
else:
path_str = f'>{ele.tag}:nth-child({len(ele.eles("xpath:./preceding-sibling::*")) + 1}){path_str}'
ele = ele.parent()
return path_str[1:]
def make_session_ele(html_or_ele, loc=None, index=1, method=None):
# ---------------处理定位符---------------
if not loc:
if isinstance(html_or_ele, SessionElement):
return html_or_ele
loc = ('xpath', '.')
elif isinstance(loc, (str, tuple)):
loc = get_loc(loc)
else:
raise LocatorError(ALLOW_VAL=_S._lang.LOC_FORMAT, CURR_VAL=loc)
# ---------------根据传入对象类型获取页面对象和lxml元素对象---------------
the_type = getattr(html_or_ele, '_type', None)
# 直接传入html文本
if isinstance(html_or_ele, str):
page = None
html_or_ele = fromstring(html_or_ele)
# SessionElement
elif the_type == 'SessionElement':
page = html_or_ele.owner
loc_str = loc[1]
if loc[0] == 'xpath' and loc[1].lstrip().startswith('/'):
loc_str = f'.{loc[1]}'
html_or_ele = html_or_ele.inner_ele
# 若css以>开头,表示找元素的直接子元素,要用page以绝对路径才能找到
elif loc[0] == 'css selector' and loc[1].lstrip().startswith('>'):
loc_str = f'{html_or_ele.css_path}{loc[1]}'
if html_or_ele.owner:
html_or_ele = fromstring(html_or_ele.owner.html)
else: # 接收html文本,无page的情况
html_or_ele = fromstring(html_or_ele('xpath:/ancestor::*').html)
else:
html_or_ele = html_or_ele.inner_ele
loc = loc[0], loc_str
elif the_type == 'ChromiumElement':
loc_str = loc[1]
if loc[0] == 'xpath' and loc[1].lstrip().startswith('/'):
loc_str = f'.{loc[1]}'
elif loc[0] == 'css selector' and loc[1].lstrip().startswith('>'):
loc_str = f'{html_or_ele.css_path}{loc[1]}'
loc = loc[0], loc_str
# 获取整个页面html再定位到当前元素,以实现查找上级元素
page = html_or_ele.owner
xpath = html_or_ele.xpath
# ChromiumElement,兼容传入的元素在iframe内的情况
if html_or_ele._doc_id is None:
doc = html_or_ele._run_js('return this.ownerDocument;')
html_or_ele._doc_id = doc['objectId'] if doc else False
if html_or_ele._doc_id:
html = html_or_ele.owner._run_cdp('DOM.getOuterHTML', objectId=html_or_ele._doc_id)['outerHTML']
else:
html = html_or_ele.owner.html
html_or_ele = fromstring(html)
html_or_ele = html_or_ele.xpath(xpath)[0]
elif the_type == 'ChromiumFrame':
page = html_or_ele
html_or_ele = fromstring(html_or_ele.inner_html)
# 各种页面对象
elif isinstance(html_or_ele, BasePage):
page = html_or_ele
html = html_or_ele.html
if html.startswith('<?xml '):
html = sub(r'^<\?xml.*?>', '', html)
html_or_ele = fromstring(html)
# ShadowRoot
elif isinstance(html_or_ele, BaseElement):
page = html_or_ele.owner
html = html_or_ele.html
r = search(r'^<shadow_root>[ \n]*?<html>[ \n]*?(.*?)[ \n]*?</html>[ \n]*?</shadow_root>$', html)
if r:
html = r.group(1)
html_or_ele = fromstring(html)
else:
raise ValueError(_S._lang.join(_S._lang.INCORRECT_TYPE_, 'html_or_ele',
ALLOW_TYPE=_S._lang.HTML_ELE_TYPE, CURR_VAL=html_or_ele))
# ---------------执行查找-----------------
try:
if loc[0] == 'xpath': # 用lxml内置方法获取lxml的元素对象列表
eles = html_or_ele.xpath(loc[1])
else: # 用css selector获取元素对象列表
eles = html_or_ele.cssselect(loc[1])
if not isinstance(eles, list): # 结果不是列表,如数字
return eles
# 把lxml元素对象包装成SessionElement对象并按需要返回一个或全部
if index is None:
r = SessionElementsList(owner=page)
for e in eles:
if e != '\n':
r.append(SessionElement(e, page) if isinstance(e, HtmlElement) else e)
return r
else:
eles_count = len(eles)
if eles_count == 0 or abs(index) > eles_count:
return NoneElement(page, method=method, args={'locator': loc, 'index': index})
if index < 0:
index = eles_count + index + 1
ele = eles[index - 1]
if isinstance(ele, HtmlElement):
return SessionElement(ele, page)
elif isinstance(ele, str):
return ele
else:
return NoneElement(page, method=method, args={'locator': loc, 'index': index})
except Exception as e:
if 'Invalid expression' in str(e):
raise LocatorError(_S._lang.INVALID_XPATH_, loc)
elif 'Expected selector' in str(e):
raise LocatorError(_S._lang.INVALID_CSS_, loc)
raise e
@@ -0,0 +1,307 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from typing import Union, List, Tuple, Optional
from lxml.html import HtmlElement
from .._base.base import DrissionElement, BaseElement
from .._elements.chromium_element import ChromiumElement
from .._functions.elements import SessionElementsList
from .._pages.chromium_base import ChromiumBase
from .._pages.chromium_frame import ChromiumFrame
from .._pages.session_page import SessionPage
class SessionElement(DrissionElement):
"""静态元素对象"""
def __init__(self, ele: HtmlElement, owner: Union[SessionPage, None] = None):
self._inner_ele: HtmlElement = ...
self.owner: SessionPage = ...
self.page: SessionPage = ...
def __call__(self,
locator: Union[Tuple[str, str], str],
index: int = 1,
timeout: float = None) -> SessionElement:
"""在内部查找元素
例:ele2 = ele1('@id=ele_id')
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 第几个元素,从1开始,可传入负数获取倒数第几个
:param timeout: 不起实际作用
:return: SessionElement对象或属性、文本
"""
...
def __repr__(self) -> str: ...
def __eq__(self, other: SessionElement) -> bool: ...
@property
def inner_ele(self) -> HtmlElement: ...
@property
def tag(self) -> str:
"""返回元素类型"""
...
@property
def html(self) -> str:
"""返回outerHTML文本"""
...
@property
def inner_html(self) -> str:
"""返回元素innerHTML文本"""
...
@property
def attrs(self) -> dict:
"""返回元素所有属性及值"""
...
@property
def text(self) -> str:
"""返回元素内文本"""
...
@property
def raw_text(self) -> str:
"""返回未格式化处理的元素内文本"""
...
def parent(self,
level_or_loc: Union[tuple, str, int] = 1,
index: int = 1,
timeout: float = None) -> SessionElement:
"""返回上面某一级父元素,可指定层数或用查询语法定位
:param level_or_loc: 第几级父元素,或定位符
:param index: 当level_or_loc传入定位符,使用此参数选择第几个结果
:param timeout: 此参数不起实际作用
:return: 上级元素对象
"""
...
def child(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[SessionElement, str]:
"""返回当前元素的一个符合条件的直接子元素,可用查询语法筛选,可指定返回筛选结果的第几个
:param locator: 用于筛选的查询语法
:param index: 第几个查询结果,1开始
:param timeout: 此参数不起实际作用
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 直接子元素或节点文本
"""
...
def prev(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[SessionElement, str]:
"""返回当前元素前面一个符合条件的同级元素,可用查询语法筛选,可指定返回筛选结果的第几个
:param locator: 用于筛选的查询语法
:param index: 前面第几个查询结果,1开始
:param timeout: 此参数不起实际作用
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 同级元素
"""
...
def next(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[SessionElement, str]:
"""返回当前元素后面一个符合条件的同级元素,可用查询语法筛选,可指定返回筛选结果的第几个
:param locator: 用于筛选的查询语法
:param index: 第几个查询结果,1开始
:param timeout: 此参数不起实际作用
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 同级元素
"""
...
def before(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[SessionElement, str]:
"""返回文档中当前元素前面符合条件的一个元素,可用查询语法筛选,可指定返回筛选结果的第几个
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param index: 前面第几个查询结果,1开始
:param timeout: 此参数不起实际作用
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素前面的某个元素或节点
"""
...
def after(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[SessionElement, str]:
"""返回文档中此当前元素后面符合条件的一个元素,可用查询语法筛选,可指定返回筛选结果的第几个
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param index: 第几个查询结果,1开始
:param timeout: 此参数不起实际作用
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素后面的某个元素或节点
"""
...
def children(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> Union[SessionElementsList, List[Union[SessionElement, str]]]:
"""返回当前元素符合条件的直接子元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 此参数不起实际作用
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 直接子元素或节点文本组成的列表
"""
...
def prevs(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> Union[SessionElementsList, List[Union[SessionElement, str]]]:
"""返回当前元素前面符合条件的同级元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 此参数不起实际作用
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 同级元素或节点文本组成的列表
"""
...
def nexts(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> Union[SessionElementsList, List[Union[SessionElement, str]]]:
"""返回当前元素后面符合条件的同级元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 此参数不起实际作用
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 同级元素或节点文本组成的列表
"""
...
def befores(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> Union[SessionElementsList, List[Union[SessionElement, str]]]:
"""返回文档中当前元素前面符合条件的元素或节点组成的列表,可用查询语法筛选
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param timeout: 此参数不起实际作用
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素前面的元素或节点组成的列表
"""
...
def afters(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> Union[SessionElementsList, List[Union[SessionElement, str]]]:
"""返回文档中当前元素后面符合条件的元素或节点组成的列表,可用查询语法筛选
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param timeout: 此参数不起实际作用
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素后面的元素或节点组成的列表
"""
...
def attr(self, name: str) -> Optional[str]:
"""返回attribute属性值
:param name: 属性名
:return: 属性值文本,没有该属性返回None
"""
...
def ele(self,
locator: Union[Tuple[str, str], str],
index: int = 1,
timeout: float = None) -> SessionElement:
"""返回当前元素下级符合条件的一个元素、属性或节点文本
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 第几个元素,从1开始,可传入负数获取倒数第几个
:param timeout: 不起实际作用
:return: SessionElement对象或属性、文本
"""
...
def eles(self,
locator: Union[Tuple[str, str], str],
timeout: float = None) -> SessionElementsList:
"""返回当前元素下级所有符合条件的子元素、属性或节点文本
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param timeout: 不起实际作用
:return: SessionElement对象或属性、文本组成的列表
"""
...
def s_ele(self,
locator: Union[Tuple[str, str], str] = None,
index: int = 1) -> SessionElement:
"""返回当前元素下级符合条件的一个元素、属性或节点文本
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:return: SessionElement对象或属性、文本
"""
...
def s_eles(self, locator: Union[Tuple[str, str], str]) -> SessionElementsList:
"""返回当前元素下级所有符合条件的子元素、属性或节点文本
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:return: SessionElement对象或属性、文本组成的列表
"""
...
def _find_elements(self,
locator: Union[Tuple[str, str], str],
timeout: float,
index: Optional[int] = 1,
relative: bool = False,
raise_err: bool = None) -> Union[SessionElement, SessionElementsList]:
"""返回当前元素下级符合条件的子元素、属性或节点文本
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param timeout: 不起实际作用,用于和父类对应
:param index: 第几个结果,从1开始,可传入负数获取倒数第几个,为None返回所有
:param relative: MixTab用的表示是否相对定位的参数
:param raise_err: 找不到元素是是否抛出异常,为None时根据全局设置
:return: SessionElement对象
"""
...
def _get_ele_path(self, xpath: bool = True) -> str:
"""获取css路径或xpath路径
:param xpath: 用xpath还是css
:return: css路径或xpath路径
"""
...
def make_session_ele(html_or_ele: Union[str, SessionElement, SessionPage, ChromiumElement, BaseElement, ChromiumFrame,
ChromiumBase],
loc: Union[str, Tuple[str, str]] = None,
index: Optional[int] = 1,
method: Optional[str] = None) -> Union[SessionElement, SessionElementsList, str, float]:
"""从接收到的对象或html文本中查找元素,返回SessionElement对象
如要直接从html生成SessionElement而不在下级查找,loc输入None即可
:param html_or_ele: html文本、BaseParser对象
:param loc: 定位元组或字符串,为None时不在下级查找,返回根元素
:param index: 获取第几个元素,从1开始,可传入负数获取倒数第几个,None获取所有
:param method: 调用此方法的方法
:return: 返回SessionElement元素或列表,或属性文本
"""
...
@@ -0,0 +1,321 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from json import load, dump, JSONDecodeError
from os import environ
from pathlib import Path
from shutil import rmtree
from subprocess import Popen, DEVNULL
from tempfile import gettempdir
from time import perf_counter, sleep
from requests import Session
from .settings import Settings as _S
from .tools import port_is_using
from .._configs.options_manage import OptionsManager
from ..errors import BrowserConnectError
def connect_browser(option):
address = option.address.replace('localhost', '127.0.0.1')
if address.startswith('http'):
address = address.lstrip('htps:/')
browser_path = option.browser_path
ip, port = address.split(':')
using = port_is_using(ip, port)
if ip != '127.0.0.1' or using or option.is_existing_only:
if test_connect(ip, port):
return True
elif ip != '127.0.0.1':
raise BrowserConnectError(ADDRESS=address)
elif using:
raise BrowserConnectError(_S._lang.BROWSER_CONNECT_ERR1_, port, port, ADDRESS=address)
else: # option.is_existing_only
raise BrowserConnectError(_S._lang.BROWSER_CONNECT_ERR2, ADDRESS=address)
# ----------创建浏览器进程----------
args, user_path = get_launch_args(option)
if option._new_env:
rmtree(user_path, ignore_errors=True)
set_prefs(option)
set_flags(option)
try:
_run_browser(port, browser_path, args)
except FileNotFoundError: # 传入的路径找不到,主动在ini文件、注册表、系统变量中找
browser_path = get_chrome_path(option.ini_path)
if not browser_path:
raise FileNotFoundError(_S._lang.join(_S._lang.BROWSER_EXE_NOT_FOUND))
_run_browser(port, browser_path, args)
if not test_connect(ip, port):
raise BrowserConnectError(ADDRESS=address, TIP=_S._lang.BROWSER_CONNECT_ERR_INFO)
return False
def get_launch_args(opt):
# ----------处理arguments-----------
result = set()
user_path = False
for i in opt.arguments:
if i.startswith(('--disable-extensions-except=', '--load-extension=', '--remote-debugging-port=')):
continue
elif i.startswith('--user-data-dir') and not opt.system_user_path:
user_path = f'--user-data-dir={Path(i[16:]).absolute()}'
result.add(user_path)
continue
elif i.startswith('--user-agent='):
opt._ua_set = True
result.add(i)
if not user_path and not opt.system_user_path:
port = opt.address.split(':')[-1] if opt.address else '0'
p = Path(opt.tmp_path) if opt.tmp_path else Path(gettempdir()) / 'DrissionPage'
path = p / 'userData' / port
path.mkdir(parents=True, exist_ok=True)
user_path = path.absolute()
opt.set_user_data_path(user_path)
result.add(f'--user-data-dir={user_path}')
result = list(result)
# ----------处理插件extensions-------------
ext = [Path(e) for e in opt.extensions]
exts = []
if ext:
for e in ext:
if e.is_file():
raise ValueError(_S._lang.join(_S._lang.PLUGIN_NEED_FOLDER, str(e.absolute())))
elif not e.exists():
raise FileNotFoundError(_S._lang.join(_S._lang.EXT_NOT_FOUND, PATH=e))
else:
exts.append(str(e.absolute()))
ext = ','.join(set(exts))
result.append(f'--disable-extensions-except={ext}')
result.append(f'--load-extension={ext}')
return result, user_path
def set_prefs(opt):
if not opt.user_data_path or (not opt.preferences and not opt._prefs_to_del):
return
prefs = opt.preferences
del_list = opt._prefs_to_del
user = 'Default'
for arg in opt.arguments:
if arg.startswith('--profile-directory'):
user = arg.split('=')[-1].strip()
break
prefs_file = Path(opt.user_data_path) / user / 'Preferences'
if not prefs_file.exists():
prefs_file.parent.mkdir(parents=True, exist_ok=True)
with open(prefs_file, 'w') as f:
f.write('{}')
with open(prefs_file, "r", encoding='utf-8') as f:
try:
prefs_dict = load(f)
except JSONDecodeError:
prefs_dict = {}
for pref in prefs:
value = prefs[pref]
pref = pref.split('.')
_make_leave_in_dict(prefs_dict, pref, 0, len(pref))
_set_value_to_dict(prefs_dict, pref, value)
for pref in del_list:
_remove_arg_from_dict(prefs_dict, pref)
with open(prefs_file, 'w', encoding='utf-8') as f:
dump(prefs_dict, f)
def set_flags(opt):
if not opt.user_data_path or (not opt.clear_file_flags and not opt.flags):
return
state_file = Path(opt.user_data_path) / 'Local State'
if not state_file.exists():
state_file.parent.mkdir(parents=True, exist_ok=True)
with open(state_file, 'w') as f:
f.write('{}')
with open(state_file, "r", encoding='utf-8') as f:
try:
states_dict = load(f)
except JSONDecodeError:
states_dict = {}
states_dict.setdefault('browser', {}).setdefault('enabled_labs_experiments', [])
flags_list = [] if opt.clear_file_flags else states_dict['browser']['enabled_labs_experiments']
flags_dict = {}
for i in flags_list:
f = str(i).split('@', 1)
flags_dict[f[0]] = None if len(f) == 1 else f[1]
for k, i in opt.flags.items():
flags_dict[k] = i
states_dict['browser']['enabled_labs_experiments'] = [f'{k}@{i}' if i else k for k, i in flags_dict.items()]
with open(state_file, 'w', encoding='utf-8') as f:
dump(states_dict, f)
def test_connect(ip, port):
end_time = perf_counter() + _S.browser_connect_timeout
s = Session()
s.trust_env = False
s.keep_alive = False
while perf_counter() < end_time:
try:
r = s.get(f'http://{ip}:{port}/json', timeout=10, headers={'Connection': 'close'})
for tab in r.json():
if tab['type'] in ('page', 'webview'):
r.close()
s.close()
return True
r.close()
except Exception:
sleep(.2)
s.close()
return False
def _run_browser(port, path: str, args) -> Popen:
"""创建浏览器进程
:param port: 端口号
:param path: 浏览器路径
:param args: 启动参数
:return: 进程对象
"""
p = Path(path)
p = str(p / 'chrome') if p.is_dir() else str(path)
arguments = [p, f'--remote-debugging-port={port}']
arguments.extend(args)
try:
return Popen(arguments, shell=False, stdout=DEVNULL, stderr=DEVNULL)
except FileNotFoundError:
raise FileNotFoundError(_S._lang.join(_S._lang.BROWSER_NOT_FOUND))
def _make_leave_in_dict(target_dict: dict, src: list, num: int, end: int) -> None:
"""把prefs中a.b.c形式的属性转为a['b']['c']形式
:param target_dict: 要处理的字典
:param src: 属性层级列表[a, b, c]
:param num: 当前处理第几个
:param end: src长度
:return: None
"""
if num == end:
return
if src[num] not in target_dict:
target_dict[src[num]] = {}
num += 1
_make_leave_in_dict(target_dict[src[num - 1]], src, num, end)
def _set_value_to_dict(target_dict: dict, src: list, value) -> None:
"""把a.b.c形式的属性的值赋值到a['b']['c']形式的字典中
:param target_dict: 要处理的字典
:param src: 属性层级列表[a, b, c]
:param value: 属性值
:return: None
"""
src = "']['".join(src)
src = f"target_dict['{src}']=value"
exec(src)
def _remove_arg_from_dict(target_dict: dict, arg: str) -> None:
"""把a.b.c形式的属性从字典中删除
:param target_dict: 要处理的字典
:param arg: 层级属性,形式'a.b.c'
:return: None
"""
args = arg.split('.')
args = [f"['{i}']" for i in args]
src = ''.join(args)
src = f"target_dict{src}"
try:
exec(src)
src = ''.join(args[:-1])
src = f"target_dict{src}.pop({args[-1][1:-1]})"
exec(src)
except:
pass
def get_chrome_path(ini_path):
# -----------从ini文件中获取--------------
if ini_path and Path(ini_path).exists():
path = OptionsManager(ini_path).chromium_options.get('browser_path', None)
if path and Path(path).is_file():
return str(path)
# -----------使用which获取-----------
from shutil import which
path = (which('chrome') or which('chromium') or which('google-chrome') or which('google-chrome-stable')
or which('google-chrome-unstable') or which('google-chrome-beta'))
if path:
return path
# -----------从MAC和Linux默认路径获取-----------
from platform import system
sys = system().lower()
if sys in ('macos', 'darwin'):
p = '/Applications/Google Chrome.app/Contents/MacOS/Google Chrome'
return p if Path(p).exists() else None
elif sys == 'linux':
paths = ('/usr/bin/google-chrome', '/opt/google/chrome/google-chrome',
'/user/lib/chromium-browser/chromium-browser')
for p in paths:
if Path(p).exists():
return p
return None
elif sys != 'windows':
return None
# -----------从注册表中获取--------------
from winreg import OpenKey, EnumValue, CloseKey, HKEY_CURRENT_USER, HKEY_LOCAL_MACHINE, KEY_READ
txt = r'SOFTWARE\Microsoft\Windows\CurrentVersion\App Paths\chrome.exe'
try:
key = OpenKey(HKEY_CURRENT_USER, txt, reserved=0, access=KEY_READ)
k = EnumValue(key, 0)
CloseKey(key)
if k[1]:
return k[1]
except (FileNotFoundError, OSError):
try:
key = OpenKey(HKEY_LOCAL_MACHINE, txt, reserved=0, access=KEY_READ)
k = EnumValue(key, 0)
CloseKey(key)
if k[1]:
return k[1]
except (FileNotFoundError, OSError):
pass
# -----------从系统变量中获取--------------
for path in environ.get('PATH', '').split(';'):
path = Path(path) / 'chrome.exe'
try:
if path.exists():
return str(path)
except OSError:
pass
@@ -0,0 +1,60 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from typing import Union
from .._configs.chromium_options import ChromiumOptions
def connect_browser(option: ChromiumOptions) -> bool:
"""连接或启动浏览器
:param option: ChromiumOptions对象
:return: 返回是否接管的浏览器
"""
...
def get_launch_args(opt: ChromiumOptions) -> list:
"""从ChromiumOptions获取命令行启动参数
:param opt: ChromiumOptions
:return: 启动参数列表
"""
...
def set_prefs(opt: ChromiumOptions) -> None:
"""处理启动配置中的prefs项,目前只能对已存在文件夹配置
:param opt: ChromiumOptions
:return: None
"""
...
def set_flags(opt: ChromiumOptions) -> None:
"""处理启动配置中的flags项
:param opt: ChromiumOptions
:return: None
"""
...
def test_connect(ip: str, port: Union[int, str], timeout: float = 30) -> bool:
"""测试浏览器是否可用
:param ip: 浏览器ip
:param port: 浏览器端口
:param timeout: 超时时间(秒)
:return: None
"""
...
def get_chrome_path(ini_path: str) -> Union[str, None]:
"""从ini文件或系统变量中获取chrome可执行文件的路径
:param ini_path: ini文件路径
:return: 文件路径
"""
...
@@ -0,0 +1,18 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
class By:
ID = 'id'
XPATH = 'xpath'
LINK_TEXT = 'link text'
PARTIAL_LINK_TEXT = 'partial link text'
NAME = 'name'
TAG_NAME = 'tag name'
CLASS_NAME = 'class name'
CSS_SELECTOR = 'css selector'
@@ -0,0 +1,53 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from click import command, option
from .._functions.tools import configs_to_here as ch
from .._configs.chromium_options import ChromiumOptions
from .._pages.chromium_page import ChromiumPage
@command()
@option("-p", "--set-browser-path", help="设置浏览器路径")
@option("-u", "--set-user-path", help="设置用户数据路径")
@option("-c", "--configs-to-here", is_flag=True, help="复制默认配置文件到当前路径")
@option("-l", "--launch-browser", default=-1, help="启动浏览器,传入端口号,0表示用配置文件中的值")
def main(set_browser_path, set_user_path, configs_to_here, launch_browser):
if set_browser_path:
set_paths(browser_path=set_browser_path)
if set_user_path:
set_paths(user_data_path=set_user_path)
if configs_to_here:
ch()
if launch_browser >= 0:
port = f'127.0.0.1:{launch_browser}' if launch_browser else None
ChromiumPage(port)
def set_paths(browser_path=None, user_data_path=None):
"""快捷的路径设置函数
:param browser_path: 浏览器可执行文件路径
:param user_data_path: 用户数据路径
:return: None
"""
co = ChromiumOptions()
if browser_path is not None:
co.set_browser_path(browser_path)
if user_data_path is not None:
co.set_user_data_path(user_data_path)
co.save()
if __name__ == '__main__':
main()
@@ -0,0 +1,231 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from datetime import datetime
from http.cookiejar import Cookie, CookieJar
from tldextract import TLDExtract
from .settings import Settings as _S
def cookie_to_dict(cookie):
if isinstance(cookie, Cookie):
cookie_dict = cookie.__dict__.copy()
cookie_dict.pop('rfc2109', None)
cookie_dict.pop('_rest', None)
return cookie_dict
elif isinstance(cookie, dict):
cookie_dict = cookie
elif isinstance(cookie, str):
cookie_dict = {}
for attr in cookie.strip().rstrip(';,').split(',' if ',' in cookie else ';'):
attr_val = attr.strip().split('=', 1)
if attr_val[0] in ('domain', 'path', 'expires', 'max-age', 'HttpOnly', 'secure', 'expiry', 'name', 'value'):
cookie_dict[attr_val[0]] = attr_val[1] if len(attr_val) == 2 else ''
else:
cookie_dict['name'] = attr_val[0]
cookie_dict['value'] = attr_val[1] if len(attr_val) == 2 else ''
return cookie_dict
else:
raise ValueError(_S._lang.join(_S._lang.INCORRECT_TYPE_, 'cookie',
ALLOW_TYPE='Cookie, str, dict', CURR_TYPE=type(cookie)))
return cookie_dict
def cookies_to_tuple(cookies):
if isinstance(cookies, (list, tuple, CookieJar)):
cookies = tuple(cookie_to_dict(cookie) for cookie in cookies)
elif isinstance(cookies, str):
c_dict = {}
cookies = cookies.rstrip('; ')
cookies = cookies.split(';')
for attr in cookies:
attr_val = attr.strip().split('=', 1)
c_dict[attr_val[0]] = attr_val[1] if len(attr_val) == 2 else True
cookies = _dict_cookies_to_tuple(c_dict)
elif isinstance(cookies, dict):
cookies = _dict_cookies_to_tuple(cookies)
elif isinstance(cookies, Cookie):
cookies = (cookie_to_dict(cookies),)
else:
raise ValueError(_S._lang.join(_S._lang.INCORRECT_TYPE_, 'cookies',
ALLOW_TYPE='Cookie, CookieJar, list, tuple, str, dict', CURR_TYPE=type(cookies)))
return cookies
def set_session_cookies(session, cookies):
for cookie in cookies_to_tuple(cookies):
if cookie['value'] is None:
cookie['value'] = ''
kwargs = {x: cookie[x] for x in cookie
if x.lower() in ('version', 'port', 'domain', 'path', 'secure',
'expires', 'discard', 'comment', 'comment_url', 'rest')}
if 'expiry' in cookie:
kwargs['expires'] = cookie['expiry']
session.cookies.set(cookie['name'], cookie['value'], **kwargs)
def set_browser_cookies(browser, cookies):
c = []
for cookie in cookies_to_tuple(cookies):
if 'domain' not in cookie and 'url' not in cookie:
raise ValueError(_S._lang.join(_S._lang.NEED_DOMAIN2, cookie=cookie))
c.append(format_cookie(cookie))
browser._run_cdp('Storage.setCookies', cookies=c)
def set_tab_cookies(page, cookies):
for cookie in cookies_to_tuple(cookies):
cookie = format_cookie(cookie)
if cookie['name'].startswith('__Host-'):
if not page.url.startswith('http'):
cookie['name'] = cookie['name'].replace('__Host-', '__Secure-', 1)
else:
cookie['url'] = page.url
page._run_cdp_loaded('Network.setCookie', **cookie)
continue # 不用设置域名,可退出
if cookie.get('domain', None):
try:
page._run_cdp_loaded('Network.setCookie', **cookie)
if not is_cookie_in_driver(page, cookie):
page.browser.set.cookies(cookie)
continue
except Exception:
pass
url = page._browser_url
if not url.startswith('http'):
raise ValueError(_S._lang.join(_S._lang.DOMAIN_NOT_SET, cookie=cookie))
ex_url = TLDExtract(suffix_list_urls=["https://publicsuffix.org/list/public_suffix_list.dat",
f"file:///{_S.suffixes_list}"]).extract_str(url)
d_list = ex_url.subdomain.split('.')
d_list.append(f'{ex_url.domain}.{ex_url.suffix}' if ex_url.suffix else ex_url.domain)
tmp = [d_list[0]]
if len(d_list) > 1:
for i in d_list[1:]:
tmp.append('.')
tmp.append(i)
for i in range(len(tmp)):
cookie['domain'] = ''.join(tmp[i:])
page._run_cdp_loaded('Network.setCookie', **cookie)
if is_cookie_in_driver(page, cookie):
break
def is_cookie_in_driver(page, cookie):
if 'domain' in cookie:
for c in page.cookies(all_domains=True):
if cookie['name'] == c['name'] and cookie['value'] == c['value'] and cookie['domain'] == c.get('domain',
None):
return True
else:
for c in page.cookies(all_domains=True):
if cookie['name'] == c['name'] and cookie['value'] == c['value']:
return True
return False
def format_cookie(cookie):
if 'expiry' in cookie:
cookie['expires'] = int(cookie['expiry'])
cookie.pop('expiry')
if 'expires' in cookie:
if not cookie['expires']:
cookie.pop('expires')
elif isinstance(cookie['expires'], str):
if cookie['expires'].isdigit():
cookie['expires'] = int(cookie['expires'])
elif cookie['expires'].replace('.', '').isdigit():
cookie['expires'] = float(cookie['expires'])
else:
try:
cookie['expires'] = datetime.strptime(cookie['expires'], '%a, %d %b %Y %H:%M:%S GMT').timestamp()
except ValueError:
cookie.pop('expires')
if cookie['value'] is None:
cookie['value'] = ''
elif not isinstance(cookie['value'], str):
cookie['value'] = str(cookie['value'])
if cookie['name'].startswith('__Host-'):
cookie['path'] = '/'
cookie['secure'] = True
elif cookie['name'].startswith('__Secure-'):
cookie['secure'] = True
if 'sameSite' in cookie:
sameSite = cookie['sameSite']
if sameSite in (None, False) or sameSite not in ('None', 'Lax', 'Strict', 'no_restriction'):
cookie.pop('sameSite')
if 'priority' in cookie:
priority = cookie['priority']
if priority in (None, False):
cookie.pop('priority')
elif priority not in ('Low', 'Medium', 'High'):
raise ValueError(_S._lang.join(_S._lang.INCORRECT_VAL_, 'priority', ALLOW_VAL='"Low", "Medium", "High"',
CURR_VAL=priority, cookie=cookie))
if 'sourceScheme' in cookie:
sourceScheme = cookie['sourceScheme']
if sourceScheme in (None, False):
cookie.pop('sourceScheme')
elif sourceScheme not in ('Unset', 'NonSecure', 'Secure'):
raise ValueError(_S._lang.join(_S._lang.INCORRECT_VAL_, 'sourceScheme',
ALLOW_VAL='"Unset", "NonSecure", "Secure"', CURR_VAL=sourceScheme,
cookie=cookie))
return cookie
class CookiesList(list):
def as_dict(self):
return {c['name']: c['value'] for c in self}
def as_str(self):
return '; '.join([f'{c["name"]}={c["value"]}' for c in self])
def as_json(self):
from json import dumps
return dumps(self)
def _dict_cookies_to_tuple(cookies: dict):
"""把dict形式的cookies转换为tuple形式
:param cookies: 单个或多个cookies,单个时包含 'name' 和 'value'
:return: 多个dict格式cookies组成的列表
"""
if 'name' in cookies and 'value' in cookies: # 单个cookie
return (cookies,)
keys = ('domain', 'path', 'expires', 'max-age', 'HttpOnly', 'secure', 'expiry')
template = {k: v for k, v in cookies.items() if k in keys}
return tuple(dict(**{'name': k, 'value': v}, **template) for k, v in cookies.items() if k not in keys)
@@ -0,0 +1,94 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from http.cookiejar import Cookie
from typing import Union
from requests import Session
from requests.cookies import RequestsCookieJar
from .._base.chromium import Chromium
from .._pages.chromium_base import ChromiumBase
def cookie_to_dict(cookie: Union[Cookie, str, dict]) -> dict:
"""把Cookie对象转为dict格式
:param cookie: Cookie对象、字符串或字典
:return: cookie字典
"""
...
def cookies_to_tuple(cookies: Union[RequestsCookieJar, list, tuple, str, dict, Cookie]) -> tuple:
"""把cookies转为tuple格式
:param cookies: cookies信息,可为CookieJar, list, tuple, str, dict
:return: 返回tuple形式的cookies
"""
...
def set_session_cookies(session: Session,
cookies: Union[RequestsCookieJar, list, tuple, str, dict]) -> None:
"""设置Session对象的cookies
:param session: Session对象
:param cookies: cookies信息
:return: None
"""
...
def set_browser_cookies(browser: Chromium,
cookies: Union[RequestsCookieJar, list, tuple, str, dict]) -> None:
"""设置cookies值
:param browser: 页面对象
:param cookies: cookies信息
:return: None
"""
...
def set_tab_cookies(page: ChromiumBase,
cookies: Union[RequestsCookieJar, list, tuple, str, dict]) -> None:
"""设置cookies值
:param page: 页面对象
:param cookies: cookies信息
:return: None
"""
...
def is_cookie_in_driver(page: ChromiumBase, cookie: dict) -> bool:
"""查询cookie是否在浏览器内
:param page: BasePage对象
:param cookie: dict格式cookie
:return: bool
"""
...
def format_cookie(cookie: dict) -> dict:
"""设置cookie为可用格式
:param cookie: dict格式cookie
:return: 格式化后的cookie字典
"""
...
class CookiesList(list):
def as_dict(self) -> dict:
"""以dict格式返回,只包含name和value字段"""
...
def as_str(self) -> str:
"""以str格式返回,只包含name和value字段"""
...
def as_json(self) -> str:
"""以json格式返回"""
...
def __next__(self) -> dict: ...
@@ -0,0 +1,460 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from time import perf_counter, sleep
from .locator import is_str_loc, is_selenium_loc
from .._functions.settings import Settings as _S
from .._elements.none_element import NoneElement
from ..errors import LocatorError
class SessionElementsList(list):
def __init__(self, owner=None, *args):
super().__init__(*args)
self._owner = owner
def __getitem__(self, item):
cls = type(self)
if isinstance(item, slice):
return cls(self._owner, super().__getitem__(item))
elif isinstance(item, int):
return super().__getitem__(item)
else:
raise ValueError(_S._lang.join(_S._lang.INDEX_FORMAT, CURR_VAL=item))
@property
def get(self):
return Getter(self)
@property
def filter(self):
return SessionFilter(self)
@property
def filter_one(self):
return SessionFilterOne(self)
class ChromiumElementsList(SessionElementsList):
@property
def filter(self):
return ChromiumFilter(self)
@property
def filter_one(self):
return ChromiumFilterOne(self)
def search(self, displayed=None, checked=None, selected=None, enabled=None, clickable=None,
have_rect=None, have_text=None, tag=None):
return _search(self, displayed=displayed, checked=checked, selected=selected, enabled=enabled,
clickable=clickable, have_rect=have_rect, have_text=have_text, tag=tag)
def search_one(self, index=1, displayed=None, checked=None, selected=None, enabled=None, clickable=None,
have_rect=None, have_text=None, tag=None):
return _search_one(self, index=index, displayed=displayed, checked=checked, selected=selected,
enabled=enabled, clickable=clickable, have_rect=have_rect, have_text=have_text, tag=tag)
class SessionFilterOne(object):
def __init__(self, _list):
self._list = _list
self._index = 1
def __call__(self, index=1):
self._index = index
return self
def tag(self, name, equal=True):
num = 0
name = name.lower()
if equal:
for i in self._list:
if not isinstance(i, str) and i.tag == name:
num += 1
if self._index == num:
return i
else:
for i in self._list:
if not isinstance(i, str) and i.tag != name:
num += 1
if self._index == num:
return i
return NoneElement(self._list._owner, 'tag()', args={'name': name, 'equal': equal, 'index': self._index})
def attr(self, name, value, equal=True):
return self._get_attr(name, value, 'attr', equal=equal)
def text(self, text, fuzzy=True, contain=True):
num = 0
if contain:
for i in self._list:
t = i if isinstance(i, str) else i.raw_text
if (fuzzy and text in t) or (not fuzzy and text == t):
num += 1
if self._index == num:
return i
else:
for i in self._list:
t = i if isinstance(i, str) else i.raw_text
if (fuzzy and text not in t) or (not fuzzy and text != t):
num += 1
if self._index == num:
return i
return NoneElement(self._list._owner, 'text()',
args={'text': text, 'fuzzy': fuzzy, 'contain': contain, 'index': self._index})
def _get_attr(self, name, value, method, equal=True):
num = 0
if equal:
for i in self._list:
if not isinstance(i, str) and getattr(i, method)(name) == value:
num += 1
if self._index == num:
return i
else:
for i in self._list:
if not isinstance(i, str) and getattr(i, method)(name) != value:
num += 1
if self._index == num:
return i
return NoneElement(self._list._owner, f'{method}()',
args={'name': name, 'value': value, 'equal': equal, 'index': self._index})
class SessionFilter(SessionFilterOne):
def __iter__(self):
return iter(self._list)
def __next__(self):
return next(self._list)
def __len__(self):
return len(self._list)
def __getitem__(self, item):
return self._list[item]
@property
def get(self):
return self._list.get
def tag(self, name, equal=True):
self._list = _tag_all(self._list, SessionElementsList(owner=self._list._owner), name=name, equal=equal)
return self
def text(self, text, fuzzy=True, contain=True):
self._list = _text_all(self._list, SessionElementsList(owner=self._list._owner),
text=text, fuzzy=fuzzy, contain=contain)
return self
def _get_attr(self, name, value, method, equal=True):
self._list = _attr_all(self._list, SessionElementsList(owner=self._list._owner),
name=name, value=value, method=method, equal=equal)
return self
class ChromiumFilterOne(SessionFilterOne):
def displayed(self, equal=True):
return self._any_state('is_displayed', equal=equal)
def checked(self, equal=True):
return self._any_state('is_checked', equal=equal)
def selected(self, equal=True):
return self._any_state('is_selected', equal=equal)
def enabled(self, equal=True):
return self._any_state('is_enabled', equal=equal)
def clickable(self, equal=True):
return self._any_state('is_clickable', equal=equal)
def have_rect(self, equal=True):
return self._any_state('has_rect', equal=equal)
def style(self, name, value, equal=True):
return self._get_attr(name, value, 'style', equal=equal)
def property(self, name, value, equal=True):
return self._get_attr(name, value, 'property', equal=equal)
def _any_state(self, name, equal=True):
num = 0
if equal:
for i in self._list:
if not isinstance(i, str) and getattr(i.states, name):
num += 1
if self._index == num:
return i
else:
for i in self._list:
if not isinstance(i, str) and not getattr(i.states, name):
num += 1
if self._index == num:
return i
return NoneElement(self._list._owner, f'{name}()', args={'equal': equal, 'index': self._index})
class ChromiumFilter(ChromiumFilterOne):
def __iter__(self):
return iter(self._list)
def __next__(self):
return next(self._list)
def __len__(self):
return len(self._list)
def __getitem__(self, item):
return self._list[item]
@property
def get(self):
return self._list.get
def search_one(self, index=1, displayed=None, checked=None, selected=None, enabled=None, clickable=None,
have_rect=None, have_text=None, tag=None):
return _search_one(self._list, index=index, displayed=displayed, checked=checked, selected=selected,
enabled=enabled, clickable=clickable, have_rect=have_rect, have_text=have_text, tag=tag)
def search(self, displayed=None, checked=None, selected=None, enabled=None, clickable=None,
have_rect=None, have_text=None, tag=None):
return _search(self._list, displayed=displayed, checked=checked, selected=selected, enabled=enabled,
clickable=clickable, have_rect=have_rect, have_text=have_text, tag=tag)
def tag(self, name, equal=True):
self._list = _tag_all(self._list, ChromiumElementsList(owner=self._list._owner), name=name, equal=equal)
return self
def text(self, text, fuzzy=True, contain=True):
self._list = _text_all(self._list, ChromiumElementsList(owner=self._list._owner),
text=text, fuzzy=fuzzy, contain=contain)
return self
def _get_attr(self, name, value, method, equal=True):
self._list = _attr_all(self._list, ChromiumElementsList(owner=self._list._owner),
name=name, value=value, method=method, equal=equal)
return self
def _any_state(self, name, equal=True):
r = ChromiumElementsList(owner=self._list._owner)
if equal:
for i in self._list:
if not isinstance(i, str) and getattr(i.states, name):
r.append(i)
else:
for i in self._list:
if not isinstance(i, str) and not getattr(i.states, name):
r.append(i)
self._list = r
return self
class Getter(object):
def __init__(self, _list):
self._list = _list
def links(self):
return [e.link for e in self._list if not isinstance(e, str)]
def texts(self):
return [e if isinstance(e, str) else e.text for e in self._list]
def attrs(self, name):
return [e.attr(name) for e in self._list if not isinstance(e, str)]
def get_eles(locators, owner, any_one=False, first_ele=True, timeout=10):
if is_selenium_loc(locators):
locators = (locators,)
res = {loc: None for loc in locators}
if timeout == 0:
for loc in locators:
ele = owner._ele(loc, timeout=0, raise_err=False, index=1 if first_ele else None, method='find()')
res[loc] = ele
if ele and any_one:
return res
return res
end_time = perf_counter() + timeout
while perf_counter() <= end_time:
for loc in locators:
if res[loc]:
continue
ele = owner._ele(loc, timeout=0, raise_err=False, index=1 if first_ele else None, method='find()')
res[loc] = ele
if ele and any_one:
return res
if all(res.values()):
return res
sleep(.05)
return res
def get_frame(owner, loc_ind_ele, timeout=None):
if isinstance(loc_ind_ele, str):
if is_str_loc(loc_ind_ele):
xpath = loc_ind_ele
else:
xpath = f'xpath://*[(name()="iframe" or name()="frame") and (@name="{loc_ind_ele}" or @id="{loc_ind_ele}")]'
ele = owner._ele(xpath, timeout=timeout)
if ele and ele._type != 'ChromiumFrame':
raise LocatorError(_S._lang.LOC_NOT_FOR_FRAME, LOCATOR=loc_ind_ele)
r = ele
elif isinstance(loc_ind_ele, tuple):
ele = owner._ele(loc_ind_ele, timeout=timeout)
if ele and ele._type != 'ChromiumFrame':
raise LocatorError(_S._lang.LOC_NOT_FOR_FRAME, LOCATOR=loc_ind_ele)
r = ele
elif isinstance(loc_ind_ele, int):
ele = owner._ele('@|tag():iframe@|tag():frame', timeout=timeout, index=loc_ind_ele)
if ele and ele._type != 'ChromiumFrame':
raise LocatorError(_S._lang.LOC_NOT_FOR_FRAME, LOCATOR=loc_ind_ele)
r = ele
elif getattr(loc_ind_ele, '_type', None) == 'ChromiumFrame':
r = loc_ind_ele
else:
raise ValueError(_S._lang.join(_S._lang.INCORRECT_VAL_, 'loc_ind_ele',
ALLOW_VAL=_S._lang.FRAME_LOC_FORMAT, CURR_VAL=loc_ind_ele))
if isinstance(r, NoneElement):
r.method = 'get_frame()'
r.args = {'loc_ind_ele': loc_ind_ele}
return r
def _attr_all(src_list, aim_list, name, value, method, equal=True):
if equal:
for i in src_list:
if not isinstance(i, str) and getattr(i, method)(name) == value:
aim_list.append(i)
else:
for i in src_list:
if not isinstance(i, str) and getattr(i, method)(name) != value:
aim_list.append(i)
return aim_list
def _tag_all(src_list, aim_list, name, equal=True):
name = name.lower()
if equal:
for i in src_list:
if not isinstance(i, str) and i.tag == name:
aim_list.append(i)
else:
for i in src_list:
if not isinstance(i, str) and i.tag != name:
aim_list.append(i)
return aim_list
def _text_all(src_list, aim_list, text, fuzzy=True, contain=True):
"""以是否含有指定文本为条件筛选元素
:param text: 用于匹配的文本
:param fuzzy: 是否模糊匹配
:param contain: 是否包含该字符串,False表示不包含
:return: 筛选结果
"""
if contain:
for i in src_list:
t = i if isinstance(i, str) else i.raw_text
if (fuzzy and text in t) or (not fuzzy and text == t):
aim_list.append(i)
else:
for i in src_list:
t = i if isinstance(i, str) else i.raw_text
if (fuzzy and text not in t) or (not fuzzy and text != t):
aim_list.append(i)
return aim_list
def _search(_list, displayed=None, checked=None, selected=None, enabled=None, clickable=None,
have_rect=None, have_text=None, tag=None):
"""或关系筛选元素
:param displayed: 是否显示,bool,None为忽略该项
:param checked: 是否被选中,bool,None为忽略该项
:param selected: 是否被选择,bool,None为忽略该项
:param enabled: 是否可用,bool,None为忽略该项
:param clickable: 是否可点击,bool,None为忽略该项
:param have_rect: 是否拥有大小和位置,bool,None为忽略该项
:param have_text: 是否含有文本,bool,None为忽略该项
:param tag: 元素类型
:return: 筛选结果
"""
r = ChromiumElementsList(owner=_list._owner)
for i in _list:
if not isinstance(i, str) and (
(displayed is not None and (displayed is True and i.states.is_displayed)
or (displayed is False and not i.states.is_displayed))
or (checked is not None and (checked is True and i.states.is_checked)
or (checked is False and not i.states.is_checked))
or (selected is not None and (selected is True and i.states.is_selected)
or (selected is False and not i.states.is_selected))
or (enabled is not None and (enabled is True and i.states.is_enabled)
or (enabled is False and not i.states.is_enabled))
or (clickable is not None and (clickable is True and i.states.is_clickable)
or (clickable is False and not i.states.is_clickable))
or (have_rect is not None and (have_rect is True and i.states.has_rect)
or (have_rect is False and not i.states.has_rect))
or (have_text is not None and (have_text is True and i.raw_text)
or (have_text is False and not i.raw_text))
or (tag is not None and i.tag == tag.lower())):
r.append(i)
return ChromiumFilter(r)
def _search_one(_list, index=1, displayed=None, checked=None, selected=None, enabled=None, clickable=None,
have_rect=None, have_text=None, tag=None):
"""或关系筛选元素,获取一个结果
:param index: 元素序号,从1开始
:param displayed: 是否显示,bool,None为忽略该项
:param checked: 是否被选中,bool,None为忽略该项
:param selected: 是否被选择,bool,None为忽略该项
:param enabled: 是否可用,bool,None为忽略该项
:param clickable: 是否可点击,bool,None为忽略该项
:param have_rect: 是否拥有大小和位置,bool,None为忽略该项
:param have_text: 是否含有文本,bool,None为忽略该项
:param tag: 元素类型
:return: 筛选结果
"""
num = 0
for i in _list:
if not isinstance(i, str) and (
(displayed is not None and (displayed is True and i.states.is_displayed)
or (displayed is False and not i.states.is_displayed))
or (checked is not None and (checked is True and i.states.is_checked)
or (checked is False and not i.states.is_checked))
or (selected is not None and (selected is True and i.states.is_selected)
or (selected is False and not i.states.is_selected))
or (enabled is not None and (enabled is True and i.states.is_enabled)
or (enabled is False and not i.states.is_enabled))
or (clickable is not None and (clickable is True and i.states.is_clickable)
or (clickable is False and not i.states.is_clickable))
or (have_rect is not None and (have_rect is True and i.states.has_rect)
or (have_rect is False and not i.states.has_rect))
or (have_text is not None and (have_text is True and i.raw_text)
or (have_text is False and not i.raw_text))
or (tag is not None and i.tag == tag.lower())):
num += 1
if num == index:
return i
return NoneElement(_list._owner, method='filter()', args={'displayed': displayed, 'checked': checked,
'selected': selected, 'enabled': enabled,
'clickable': clickable, 'have_rect': have_rect,
'have_text': have_text, 'tag': tag})
@@ -0,0 +1,588 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from typing import Union, List, Optional, Iterable, Dict
from .._base.base import BaseParser
from .._elements.chromium_element import ChromiumElement
from .._elements.session_element import SessionElement
from .._pages.chromium_base import ChromiumBase
from .._pages.chromium_frame import ChromiumFrame
from .._pages.session_page import SessionPage
class SessionElementsList(list):
_owner: SessionPage = ...
def __init__(self,
owner: SessionPage = None,
*args):
"""
:param owner: 产生元素列表的页面
:param args:
"""
...
def __next__(self) -> SessionElement: ...
def __getitem__(self, _i) -> Union[SessionElement, SessionElementsList]: ...
def __iter__(self) -> List[SessionElement]: ...
@property
def get(self) -> Getter:
"""返回用于属性的对象"""
...
@property
def filter(self) -> SessionFilter:
"""返回用于筛选多个元素的对象"""
...
@property
def filter_one(self) -> SessionFilterOne:
"""用于筛选单个元素的对象"""
...
class ChromiumElementsList(SessionElementsList):
_owner: ChromiumBase = ...
def __init__(self,
owner: ChromiumBase = None,
*args):
"""
:param owner: 产生元素列表的页面
:param args:
"""
...
def __next__(self) -> ChromiumElement: ...
def __getitem__(self, _i) -> Union[ChromiumElement, ChromiumElementsList]: ...
def __iter__(self) -> List[ChromiumElement]: ...
@property
def filter(self) -> ChromiumFilter:
"""返回用于筛选多个元素的对象"""
...
@property
def filter_one(self) -> ChromiumFilterOne:
"""用于筛选单个元素的对象"""
...
def search(self,
displayed: Optional[bool] = None,
checked: Optional[bool] = None,
selected: Optional[bool] = None,
enabled: Optional[bool] = None,
clickable: Optional[bool] = None,
have_rect: Optional[bool] = None,
have_text: Optional[bool] = None,
tag: str = None) -> ChromiumFilter:
"""或关系筛选元素
:param displayed: 是否显示,bool,None为忽略该项
:param checked: 是否被选中,bool,None为忽略该项
:param selected: 是否被选择,bool,None为忽略该项
:param enabled: 是否可用,bool,None为忽略该项
:param clickable: 是否可点击,bool,None为忽略该项
:param have_rect: 是否拥有大小和位置,bool,None为忽略该项
:param have_text: 是否含有文本,bool,None为忽略该项
:param tag: 指定的元素类型
:return: 筛选结果
"""
...
def search_one(self,
index: int = 1,
displayed: Optional[bool] = None,
checked: Optional[bool] = None,
selected: Optional[bool] = None,
enabled: Optional[bool] = None,
clickable: Optional[bool] = None,
have_rect: Optional[bool] = None,
have_text: Optional[bool] = None,
tag: str = None) -> ChromiumElement:
"""或关系筛选元素,获取一个结果
:param index: 元素序号,从1开始
:param displayed: 是否显示,bool,None为忽略该项
:param checked: 是否被选中,bool,None为忽略该项
:param selected: 是否被选择,bool,None为忽略该项
:param enabled: 是否可用,bool,None为忽略该项
:param clickable: 是否可点击,bool,None为忽略该项
:param have_rect: 是否拥有大小和位置,bool,None为忽略该项
:param have_text: 是否含有文本,bool,None为忽略该项
:param tag: 指定的元素类型
:return: 筛选结果
"""
...
class SessionFilterOne(object):
_list: SessionElementsList = ...
_index: int = ...
def __init__(self, _list: SessionElementsList):
"""
:param _list: 元素列表对象
"""
...
def __call__(self, index: int = 1) -> SessionFilterOne:
"""返回结果中第几个元素
:param index: 元素序号,从1开始
:return: 对象自身
"""
...
def tag(self, name: str, equal: bool = True) -> SessionElement:
"""筛选某种元素
:param name: 标签页名称
:param equal: True表示匹配这种元素,False表示匹配非这种元素
:return: 筛选结果
"""
...
def attr(self, name: str, value: str, equal: bool = True) -> SessionElement:
"""以是否拥有某个attribute值为条件筛选元素
:param name: 属性名称
:param value: 属性值
:param equal: True表示匹配name值为value值的元素,False表示匹配name值不为value值的
:return: 筛选结果
"""
...
def text(self, text: str, fuzzy: bool = True, contain: bool = True) -> SessionElement:
"""以是否含有指定文本为条件筛选元素
:param text: 用于匹配的文本
:param fuzzy: 是否模糊匹配
:param contain: 是否包含该字符串,False表示不包含
:return: 筛选结果
"""
...
def _get_attr(self,
name: str,
value: str,
method: str,
equal: bool = True) -> SessionElement:
"""返回通过某个方法可获得某个值的元素
:param name: 属性名称
:param value: 属性值
:param method: 方法名称
:return: 筛选结果
"""
...
class SessionFilter(SessionFilterOne):
def __iter__(self) -> Iterable[SessionElement]: ...
def __next__(self) -> SessionElement: ...
def __len__(self) -> int: ...
def __getitem__(self, item: int) -> SessionElement: ...
@property
def get(self) -> Getter:
"""返回用于获取元素属性的对象"""
...
def tag(self, name: str, equal: bool = True) -> SessionFilter:
"""筛选某种元素
:param name: 标签页名称
:param equal: True表示匹配这种元素,False表示匹配非这种元素
:return: 筛选结果
"""
...
def attr(self, name: str, value: str, equal: bool = True) -> SessionFilter:
"""以是否拥有某个attribute值为条件筛选元素
:param name: 属性名称
:param value: 属性值
:param equal: True表示匹配name值为value值的元素,False表示匹配name值不为value值的
:return: 筛选结果
"""
...
def text(self, text: str, fuzzy: bool = True, contain: bool = True) -> SessionFilter:
"""以是否含有指定文本为条件筛选元素
:param text: 用于匹配的文本
:param fuzzy: 是否模糊匹配
:param contain: 是否包含该字符串,False表示不包含
:return: 筛选结果
"""
...
def _get_attr(self,
name: str,
value: str,
method: str,
equal: bool = True) -> SessionFilter:
"""返回通过某个方法可获得某个值的元素
:param name: 属性名称
:param value: 属性值
:param method: 方法名称
:return: 筛选结果
"""
...
class ChromiumFilterOne(SessionFilterOne):
_list: ChromiumElementsList = ...
def __init__(self, _list: ChromiumElementsList):
"""
:param _list: 元素列表对象
"""
...
def __call__(self, index: int = 1) -> ChromiumFilterOne:
"""返回结果中第几个元素
:param index: 元素序号,从1开始
:return: 对象自身
"""
...
def tag(self, name: str, equal: bool = True) -> SessionElement:
"""筛选某种元素
:param name: 标签页名称
:param equal: True表示匹配这种元素,False表示匹配非这种元素
:return: 筛选结果
"""
...
def attr(self, name: str, value: str, equal: bool = True) -> ChromiumElement:
"""以是否拥有某个attribute值为条件筛选元素
:param name: 属性名称
:param value: 属性值
:param equal: True表示匹配name值为value值的元素,False表示匹配name值不为value值的
:return: 筛选结果
"""
...
def text(self,
text: str,
fuzzy: bool = True,
contain: bool = True) -> ChromiumElement:
"""以是否含有指定文本为条件筛选元素
:param text: 用于匹配的文本
:param fuzzy: 是否模糊匹配
:param contain: 是否包含该字符串,False表示不包含
:return: 筛选结果
"""
...
def displayed(self, equal: bool = True) -> ChromiumElement:
"""以是否显示为条件筛选元素
:param equal: 是否匹配显示的元素,False匹配不显示的
:return: 筛选结果
"""
...
def checked(self, equal: bool = True) -> ChromiumElement:
"""以是否被选中为条件筛选元素
:param equal: 是否匹配被选中的元素,False匹配不被选中的
:return: 筛选结果
"""
...
def selected(self, equal: bool = True) -> ChromiumElement:
"""以是否被选择为条件筛选元素,用于<select>元素项目
:param equal: 是否匹配被选择的元素,False匹配不被选择的
:return: 筛选结果
"""
...
def enabled(self, equal: bool = True) -> ChromiumElement:
"""以是否可用为条件筛选元素
:param equal: 是否匹配可用的元素,False表示匹配disabled状态的
:return: 筛选结果
"""
...
def clickable(self, equal: bool = True) -> ChromiumElement:
"""以是否可点击为条件筛选元素
:param equal: 是否匹配可点击的元素,False表示匹配不是可点击的
:return: 筛选结果
"""
...
def have_rect(self, equal: bool = True) -> ChromiumElement:
"""以是否有大小为条件筛选元素
:param equal: 是否匹配有大小的元素,False表示匹配没有大小的
:return: 筛选结果
"""
...
def style(self, name: str, value: str, equal: bool = True) -> ChromiumElement:
"""以是否拥有某个style值为条件筛选元素
:param name: 属性名称
:param value: 属性值
:param equal: True表示匹配name值为value值的元素,False表示匹配name值不为value值的
:return: 筛选结果
"""
...
def property(self,
name: str,
value: str, equal: bool = True) -> ChromiumElement:
"""以是否拥有某个property值为条件筛选元素
:param name: 属性名称
:param value: 属性值
:param equal: True表示匹配name值为value值的元素,False表示匹配name值不为value值的
:return: 筛选结果
"""
...
def _get_attr(self,
name: str,
value: str,
method: str, equal: bool = True) -> ChromiumElement:
"""返回通过某个方法可获得某个值的元素
:param name: 属性名称
:param value: 属性值
:param method: 方法名称
:return: 筛选结果
"""
...
def _any_state(self, name: str, equal: bool = True) -> ChromiumElement:
"""
:param name: 状态名称
:param equal: 是否是指定状态,False表示否定状态
:return: 选中的列表
"""
...
class ChromiumFilter(ChromiumFilterOne):
def __iter__(self) -> Iterable[ChromiumElement]: ...
def __next__(self) -> ChromiumElement: ...
def __len__(self) -> int: ...
def __getitem__(self, item: int) -> ChromiumElement: ...
@property
def get(self) -> Getter:
"""返回用于获取元素属性的对象"""
...
def tag(self, name: str, equal: bool = True) -> ChromiumFilter:
"""筛选某种元素
:param name: 标签页名称
:param equal: True表示匹配这种元素,False表示匹配非这种元素
:return: 筛选结果
"""
...
def attr(self, name: str, value: str, equal: bool = True) -> ChromiumFilter:
"""以是否拥有某个attribute值为条件筛选元素
:param name: 属性名称
:param value: 属性值
:param equal: True表示匹配name值为value值的元素,False表示匹配name值不为value值的
:return: 筛选结果
"""
...
def text(self, text: str, fuzzy: bool = True, contain: bool = True) -> ChromiumFilter:
"""以是否含有指定文本为条件筛选元素
:param text: 用于匹配的文本
:param fuzzy: 是否模糊匹配
:param contain: 是否包含该字符串,False表示不包含
:return: 筛选结果
"""
...
def displayed(self, equal: bool = True) -> ChromiumFilter:
"""以是否显示为条件筛选元素
:param equal: 是否匹配显示的元素,False匹配不显示的
:return: 筛选结果
"""
...
def checked(self, equal: bool = True) -> ChromiumFilter:
"""以是否被选中为条件筛选元素
:param equal: 是否匹配被选中的元素,False匹配不被选中的
:return: 筛选结果
"""
...
def selected(self, equal: bool = True) -> ChromiumFilter:
"""以是否被选择为条件筛选元素,用于<select>元素项目
:param equal: 是否匹配被选择的元素,False匹配不被选择的
:return: 筛选结果
"""
...
def enabled(self, equal: bool = True) -> ChromiumFilter:
"""以是否可用为条件筛选元素
:param equal: 是否匹配可用的元素,False表示匹配disabled状态的
:return: 筛选结果
"""
...
def clickable(self, equal: bool = True) -> ChromiumFilter:
"""以是否可点击为条件筛选元素
:param equal: 是否匹配可点击的元素,False表示匹配不是可点击的
:return: 筛选结果
"""
...
def have_rect(self, equal: bool = True) -> ChromiumFilter:
"""以是否有大小为条件筛选元素
:param equal: 是否匹配有大小的元素,False表示匹配没有大小的
:return: 筛选结果
"""
...
def style(self, name: str, value: str, equal: bool = True) -> ChromiumFilter:
"""以是否拥有某个style值为条件筛选元素
:param name: 属性名称
:param value: 属性值
:param equal: True表示匹配name值为value值的元素,False表示匹配name值不为value值的
:return: 筛选结果
"""
...
def property(self,
name: str,
value: str, equal: bool = True) -> ChromiumFilter:
"""以是否拥有某个property值为条件筛选元素
:param name: 属性名称
:param value: 属性值
:param equal: True表示匹配name值为value值的元素,False表示匹配name值不为value值的
:return: 筛选结果
"""
...
def search_one(self,
index: int = 1,
displayed: Optional[bool] = None,
checked: Optional[bool] = None,
selected: Optional[bool] = None,
enabled: Optional[bool] = None,
clickable: Optional[bool] = None,
have_rect: Optional[bool] = None,
have_text: Optional[bool] = None,
tag: str = None) -> ChromiumElement:
"""或关系筛选元素,获取一个结果
:param index: 元素序号,从1开始
:param displayed: 是否显示,bool,None为忽略该项
:param checked: 是否被选中,bool,None为忽略该项
:param selected: 是否被选择,bool,None为忽略该项
:param enabled: 是否可用,bool,None为忽略该项
:param clickable: 是否可点击,bool,None为忽略该项
:param have_rect: 是否拥有大小和位置,bool,None为忽略该项
:param have_text: 是否含有文本,bool,None为忽略该项
:param tag: 指定的元素类型
:return: 筛选结果
"""
...
def search(self,
displayed: Optional[bool] = None,
checked: Optional[bool] = None,
selected: Optional[bool] = None,
enabled: Optional[bool] = None,
clickable: Optional[bool] = None,
have_rect: Optional[bool] = None,
have_text: Optional[bool] = None,
tag: str = None) -> ChromiumFilter:
"""或关系筛选元素
:param displayed: 是否显示,bool,None为忽略该项
:param checked: 是否被选中,bool,None为忽略该项
:param selected: 是否被选择,bool,None为忽略该项
:param enabled: 是否可用,bool,None为忽略该项
:param clickable: 是否可点击,bool,None为忽略该项
:param have_rect: 是否拥有大小和位置,bool,None为忽略该项
:param have_text: 是否含有文本,bool,None为忽略该项
:param tag: 指定的元素类型
:return: 筛选结果
"""
...
def _get_attr(self,
name: str,
value: str,
method: str, equal: bool = True) -> ChromiumFilter:
"""返回通过某个方法可获得某个值的元素
:param name: 属性名称
:param value: 属性值
:param method: 方法名称
:return: 筛选结果
"""
...
def _any_state(self, name: str, equal: bool = True) -> ChromiumFilter:
"""
:param name: 状态名称
:param equal: 是否是指定状态,False表示否定状态
:return: 选中的列表
"""
...
class Getter(object):
_list: SessionElementsList = ...
def __init__(self, _list: SessionElementsList):
"""
:param _list: 元素列表对象
"""
...
def links(self) -> List[str]:
"""返回所有元素的link属性组成的列表"""
...
def texts(self) -> List[str]:
"""返回所有元素的text属性组成的列表"""
...
def attrs(self, name: str) -> List[str]:
"""返回所有元素指定的attr属性组成的列表
:param name: 属性名称
:return: 属性文本组成的列表
"""
...
def get_eles(locators: Union[str, tuple, List[Union[str, tuple]]],
owner: BaseParser,
any_one: bool = False,
first_ele: bool = True,
timeout: float = 10) -> Union[Dict[str, ChromiumElement], Dict[str, SessionElement],
Dict[str, List[ChromiumElement]], Dict[str, List[SessionElement]]]:
"""传入多个定位符,获取多个ele
:param locators: 定位符或它们组成的列表
:param owner: 页面或元素对象
:param any_one: 是否找到任何一个即返回
:param first_ele: 每个定位符是否只获取第一个元素
:param timeout: 超时时间(秒)
:return: 多个定位符组成的dict,first_only为False返回列表,否则为元素,无结果的返回False
"""
...
def get_frame(owner: BaseParser,
loc_ind_ele: Union[str, int, tuple, ChromiumFrame, ChromiumElement],
timeout: float = None) -> ChromiumFrame:
"""获取页面中一个frame对象
:param owner: 要在其中查找元素的对象
:param loc_ind_ele: 定位符、iframe序号、ChromiumFrame对象,序号从1开始,可传入负数获取倒数第几个
:param timeout: 查找元素超时时间(秒)
:return: ChromiumFrame对象
"""
...
@@ -0,0 +1,436 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from platform import system
from ..errors import AlertExistsError
modifierBit = {'\ue00a': 1, '\ue009': 2, '\ue03d': 4, '\ue008': 8}
sys = system().lower()
class Keys:
"""特殊按键"""
NULL = '\ue000'
CANCEL = '\ue001' # ^break
HELP = '\ue002'
BACKSPACE = '\ue003'
TAB = '\ue004'
CLEAR = '\ue005'
RETURN = '\ue006'
ENTER = '\ue007'
SHIFT = '\ue008'
CONTROL = '\ue009'
CTRL = '\ue009'
ALT = '\ue00a'
PAUSE = '\ue00b'
ESCAPE = '\ue00c'
SPACE = '\ue00d'
PAGE_UP = '\ue00e'
PAGE_DOWN = '\ue00f'
END = '\ue010'
HOME = '\ue011'
LEFT = '\ue012'
UP = '\ue013'
RIGHT = '\ue014'
DOWN = '\ue015'
INSERT = '\ue016'
DELETE = '\ue017'
DEL = '\ue017'
SEMICOLON = '\ue018'
EQUALS = '\ue019'
META = '\ue03d'
COMMAND = '\ue03d'
CTRL_COMM = '\ue03d' if sys in ('macos', 'darwin') else '\ue009'
CTRL_A = (CTRL_COMM, 'a')
CTRL_C = (CTRL_COMM, 'c')
CTRL_X = (CTRL_COMM, 'x')
CTRL_V = (CTRL_COMM, 'v')
CTRL_Z = (CTRL_COMM, 'z')
CTRL_Y = (CTRL_COMM, 'y')
NUMPAD0 = '\ue01a' # number pad keys
NUMPAD1 = '\ue01b'
NUMPAD2 = '\ue01c'
NUMPAD3 = '\ue01d'
NUMPAD4 = '\ue01e'
NUMPAD5 = '\ue01f'
NUMPAD6 = '\ue020'
NUMPAD7 = '\ue021'
NUMPAD8 = '\ue022'
NUMPAD9 = '\ue023'
MULTIPLY = '\ue024'
ADD = '\ue025'
# SEPARATOR = '\ue026'
SUBTRACT = '\ue027'
DECIMAL = '\ue028'
DIVIDE = '\ue029'
F1 = '\ue031' # function keys
F2 = '\ue032'
F3 = '\ue033'
F4 = '\ue034'
F5 = '\ue035'
F6 = '\ue036'
F7 = '\ue037'
F8 = '\ue038'
F9 = '\ue039'
F10 = '\ue03a'
F11 = '\ue03b'
F12 = '\ue03c'
# ZENKAKU_HANKAKU = '\ue040'
keyDefinitions = {
'0': {'keyCode': 48, 'key': '0', 'code': 'Digit0'},
'1': {'keyCode': 49, 'key': '1', 'code': 'Digit1'},
'2': {'keyCode': 50, 'key': '2', 'code': 'Digit2'},
'3': {'keyCode': 51, 'key': '3', 'code': 'Digit3'},
'4': {'keyCode': 52, 'key': '4', 'code': 'Digit4'},
'5': {'keyCode': 53, 'key': '5', 'code': 'Digit5'},
'6': {'keyCode': 54, 'key': '6', 'code': 'Digit6'},
'7': {'keyCode': 55, 'key': '7', 'code': 'Digit7'},
'8': {'keyCode': 56, 'key': '8', 'code': 'Digit8'},
'9': {'keyCode': 57, 'key': '9', 'code': 'Digit9'},
'a': {'keyCode': 65, 'key': 'a', 'code': 'KeyA'},
'b': {'keyCode': 66, 'key': 'b', 'code': 'KeyB'},
'c': {'keyCode': 67, 'key': 'c', 'code': 'KeyC'},
'd': {'keyCode': 68, 'key': 'd', 'code': 'KeyD'},
'e': {'keyCode': 69, 'key': 'e', 'code': 'KeyE'},
'f': {'keyCode': 70, 'key': 'f', 'code': 'KeyF'},
'g': {'keyCode': 71, 'key': 'g', 'code': 'KeyG'},
'h': {'keyCode': 72, 'key': 'h', 'code': 'KeyH'},
'i': {'keyCode': 73, 'key': 'i', 'code': 'KeyI'},
'j': {'keyCode': 74, 'key': 'j', 'code': 'KeyJ'},
'k': {'keyCode': 75, 'key': 'k', 'code': 'KeyK'},
'l': {'keyCode': 76, 'key': 'l', 'code': 'KeyL'},
'm': {'keyCode': 77, 'key': 'm', 'code': 'KeyM'},
'n': {'keyCode': 78, 'key': 'n', 'code': 'KeyN'},
'o': {'keyCode': 79, 'key': 'o', 'code': 'KeyO'},
'p': {'keyCode': 80, 'key': 'p', 'code': 'KeyP'},
'q': {'keyCode': 81, 'key': 'q', 'code': 'KeyQ'},
'r': {'keyCode': 82, 'key': 'r', 'code': 'KeyR'},
's': {'keyCode': 83, 'key': 's', 'code': 'KeyS'},
't': {'keyCode': 84, 'key': 't', 'code': 'KeyT'},
'u': {'keyCode': 85, 'key': 'u', 'code': 'KeyU'},
'v': {'keyCode': 86, 'key': 'v', 'code': 'KeyV'},
'w': {'keyCode': 87, 'key': 'w', 'code': 'KeyW'},
'x': {'keyCode': 88, 'key': 'x', 'code': 'KeyX'},
'y': {'keyCode': 89, 'key': 'y', 'code': 'KeyY'},
'z': {'keyCode': 90, 'key': 'z', 'code': 'KeyZ'},
' ': {'keyCode': 32, 'key': ' ', 'code': 'Space'},
'*': {'keyCode': 106, 'key': '*', 'code': 'NumpadMultiply', 'location': 3},
'+': {'keyCode': 107, 'key': '+', 'code': 'NumpadAdd', 'location': 3},
'-': {'keyCode': 109, 'key': '-', 'code': 'NumpadSubtract', 'location': 3},
'/': {'keyCode': 111, 'key': '/', 'code': 'NumpadDivide', 'location': 3},
';': {'keyCode': 186, 'key': ';', 'code': 'Semicolon'},
'=': {'keyCode': 187, 'key': '=', 'code': 'Equal'},
',': {'keyCode': 188, 'key': ',', 'code': 'Comma'},
'.': {'keyCode': 190, 'key': '.', 'code': 'Period'},
'`': {'keyCode': 192, 'key': '`', 'code': 'Backquote'},
'[': {'keyCode': 219, 'key': '[', 'code': 'BracketLeft'},
'\\': {'keyCode': 220, 'key': '\\', 'code': 'Backslash'},
']': {'keyCode': 221, 'key': ']', 'code': 'BracketRight'},
'\'': {'keyCode': 222, 'key': '\'', 'code': 'Quote'},
')': {'keyCode': 48, 'key': ')', 'code': 'Digit0'},
'!': {'keyCode': 49, 'key': '!', 'code': 'Digit1'},
'@': {'keyCode': 50, 'key': '@', 'code': 'Digit2'},
'#': {'keyCode': 51, 'key': '#', 'code': 'Digit3'},
'$': {'keyCode': 52, 'key': '$', 'code': 'Digit4'},
'%': {'keyCode': 53, 'key': '%', 'code': 'Digit5'},
'^': {'keyCode': 54, 'key': '^', 'code': 'Digit6'},
'&': {'keyCode': 55, 'key': '&', 'code': 'Digit7'},
'(': {'keyCode': 57, 'key': '(', 'code': 'Digit9'},
'A': {'keyCode': 65, 'key': 'A', 'code': 'KeyA'},
'B': {'keyCode': 66, 'key': 'B', 'code': 'KeyB'},
'C': {'keyCode': 67, 'key': 'C', 'code': 'KeyC'},
'D': {'keyCode': 68, 'key': 'D', 'code': 'KeyD'},
'E': {'keyCode': 69, 'key': 'E', 'code': 'KeyE'},
'F': {'keyCode': 70, 'key': 'F', 'code': 'KeyF'},
'G': {'keyCode': 71, 'key': 'G', 'code': 'KeyG'},
'H': {'keyCode': 72, 'key': 'H', 'code': 'KeyH'},
'I': {'keyCode': 73, 'key': 'I', 'code': 'KeyI'},
'J': {'keyCode': 74, 'key': 'J', 'code': 'KeyJ'},
'K': {'keyCode': 75, 'key': 'K', 'code': 'KeyK'},
'L': {'keyCode': 76, 'key': 'L', 'code': 'KeyL'},
'M': {'keyCode': 77, 'key': 'M', 'code': 'KeyM'},
'N': {'keyCode': 78, 'key': 'N', 'code': 'KeyN'},
'O': {'keyCode': 79, 'key': 'O', 'code': 'KeyO'},
'P': {'keyCode': 80, 'key': 'P', 'code': 'KeyP'},
'Q': {'keyCode': 81, 'key': 'Q', 'code': 'KeyQ'},
'R': {'keyCode': 82, 'key': 'R', 'code': 'KeyR'},
'S': {'keyCode': 83, 'key': 'S', 'code': 'KeyS'},
'T': {'keyCode': 84, 'key': 'T', 'code': 'KeyT'},
'U': {'keyCode': 85, 'key': 'U', 'code': 'KeyU'},
'V': {'keyCode': 86, 'key': 'V', 'code': 'KeyV'},
'W': {'keyCode': 87, 'key': 'W', 'code': 'KeyW'},
'X': {'keyCode': 88, 'key': 'X', 'code': 'KeyX'},
'Y': {'keyCode': 89, 'key': 'Y', 'code': 'KeyY'},
'Z': {'keyCode': 90, 'key': 'Z', 'code': 'KeyZ'},
':': {'keyCode': 186, 'key': ':', 'code': 'Semicolon'},
'<': {'keyCode': 188, 'key': '<', 'code': 'Comma'},
'_': {'keyCode': 189, 'key': '_', 'code': 'Minus'},
'>': {'keyCode': 190, 'key': '>', 'code': 'Period'},
'?': {'keyCode': 191, 'key': '?', 'code': 'Slash'},
'~': {'keyCode': 192, 'key': '~', 'code': 'Backquote'},
'{': {'keyCode': 219, 'key': '{', 'code': 'BracketLeft'},
'|': {'keyCode': 220, 'key': '|', 'code': 'Backslash'},
# '\ue026': {'keyCode': 220, 'key': '|', 'code': 'Backslash'},
'}': {'keyCode': 221, 'key': '}', 'code': 'BracketRight'},
'"': {'keyCode': 222, 'key': '"', 'code': 'Quote'},
'\n': {'keyCode': 13, 'code': 'Enter', 'key': 'Enter', 'text': '\r'},
'\ue007': {'keyCode': 13, 'code': 'Enter', 'key': 'Enter', 'text': '\r'},
'\ue006': {'keyCode': 13, 'code': 'NumpadEnter', 'key': 'Enter', 'text': '\r', 'location': 3},
'\ue003': {'keyCode': 8, 'code': 'Backspace', 'key': 'Backspace'},
'\ue00d': {'keyCode': 32, 'code': 'Space', 'key': ' '},
# 'PageUp': {'keyCode': 33, 'shiftKeyCode': 105, 'key': 'PageUp', 'code': 'Numpad9', 'shiftKey': '9', 'location': 3},
'\ue00e': {'keyCode': 33, 'code': 'PageUp', 'key': 'PageUp'},
# 'PageDown': {'keyCode': 34, 'shiftKeyCode': 99, 'key': 'PageDown', 'code': 'Numpad3', 'shiftKey': '3', 'location': 3},
'\ue00f': {'keyCode': 34, 'code': 'PageDown', 'key': 'PageDown'},
'\ue008': {'keyCode': 16, 'code': 'ShiftLeft', 'key': 'Shift', 'location': 1},
# 'ShiftRight': {'keyCode': 16, 'code': 'ShiftRight', 'key': 'Shift', 'location': 2},
'\ue009': {'keyCode': 17, 'code': 'ControlLeft', 'key': 'Control', 'location': 1},
# 'ControlRight': {'keyCode': 17, 'code': 'ControlRight', 'key': 'Control', 'location': 2},
'\ue00a': {'keyCode': 18, 'code': 'AltLeft', 'key': 'Alt', 'location': 1},
# 'AltRight': {'keyCode': 18, 'code': 'AltRight', 'key': 'Alt', 'location': 2},
'\ue03d': {'keyCode': 91, 'key': 'Meta', 'code': 'MetaLeft'},
'\r': {'keyCode': 13, 'code': 'Enter', 'key': 'Enter', 'text': '\r'},
'\ue011': {'keyCode': 36, 'code': 'Home', 'key': 'Home'},
# 'Numpad7': {'keyCode': 36, 'shiftKeyCode': 103, 'key': 'Home', 'code': 'Numpad7', 'shiftKey': '7', 'location': 3},
'\ue012': {'keyCode': 37, 'code': 'ArrowLeft', 'key': 'ArrowLeft'},
# 'Numpad4': {'keyCode': 37, 'shiftKeyCode': 100, 'key': 'ArrowLeft', 'code': 'Numpad4', 'shiftKey': '4', 'location': 3},
# 'Numpad8': {'keyCode': 38, 'shiftKeyCode': 104, 'key': 'ArrowUp', 'code': 'Numpad8', 'shiftKey': '8', 'location': 3},
'\ue013': {'keyCode': 38, 'code': 'ArrowUp', 'key': 'ArrowUp'},
'\ue014': {'keyCode': 39, 'code': 'ArrowRight', 'key': 'ArrowRight'},
# 'Numpad6': {'keyCode': 39, 'shiftKeyCode': 102, 'key': 'ArrowRight', 'code': 'Numpad6', 'shiftKey': '6', 'location': 3},
# 'Numpad2': {'keyCode': 40, 'shiftKeyCode': 98, 'key': 'ArrowDown', 'code': 'Numpad2', 'shiftKey': '2', 'location': 3},
'\ue015': {'keyCode': 40, 'code': 'ArrowDown', 'key': 'ArrowDown'},
'\ue001': {'keyCode': 3, 'code': 'Abort', 'key': 'Cancel'},
'\ue002': {'keyCode': 6, 'code': 'Help', 'key': 'Help'},
'\ue004': {'keyCode': 9, 'code': 'Tab', 'key': 'Tab'},
'\ue005': {'keyCode': 12, 'shiftKeyCode': 101, 'key': 'Clear', 'code': 'Numpad5', 'shiftKey': '5', 'location': 3},
'\ue00b': {'keyCode': 19, 'code': 'Pause', 'key': 'Pause'},
# 'CapsLock': {'keyCode': 20, 'code': 'CapsLock', 'key': 'CapsLock'},
'\ue00c': {'keyCode': 27, 'code': 'Escape', 'key': 'Escape'},
# 'Convert': {'keyCode': 28, 'code': 'Convert', 'key': 'Convert'},
# 'NonConvert': {'keyCode': 29, 'code': 'NonConvert', 'key': 'NonConvert'},
'\ue010': {'keyCode': 35, 'code': 'End', 'key': 'End'},
# 'Numpad1': {'keyCode': 35, 'shiftKeyCode': 97, 'key': 'End', 'code': 'Numpad1', 'shiftKey': '1', 'location': 3},
# 'Select': {'keyCode': 41, 'code': 'Select', 'key': 'Select'},
# 'Open': {'keyCode': 43, 'code': 'Open', 'key': 'Execute'},
# 'PrintScreen': {'keyCode': 44, 'code': 'PrintScreen', 'key': 'PrintScreen'},
'\ue016': {'keyCode': 45, 'code': 'Insert', 'key': 'Insert'},
# 'Numpad0': {'keyCode': 45, 'shiftKeyCode': 96, 'key': 'Insert', 'code': 'Numpad0', 'shiftKey': '0', 'location': 3},
'\ue017': {'keyCode': 46, 'code': 'Delete', 'key': 'Delete'},
'\ue028': {'keyCode': 46, 'shiftKeyCode': 110, 'code': 'NumpadDecimal', 'key': '\u0000', 'shiftKey': '.',
'location': 3},
'\ue01a': {'keyCode': 48, 'code': 'Digit0', 'shiftKey': ')', 'key': '0'},
'\ue01b': {'keyCode': 49, 'code': 'Digit1', 'shiftKey': '!', 'key': '1'},
'\ue01c': {'keyCode': 50, 'code': 'Digit2', 'shiftKey': '@', 'key': '2'},
'\ue01d': {'keyCode': 51, 'code': 'Digit3', 'shiftKey': '#', 'key': '3'},
'\ue01e': {'keyCode': 52, 'code': 'Digit4', 'shiftKey': '$', 'key': '4'},
'\ue01f': {'keyCode': 53, 'code': 'Digit5', 'shiftKey': '%', 'key': '5'},
'\ue020': {'keyCode': 54, 'code': 'Digit6', 'shiftKey': '^', 'key': '6'},
'\ue021': {'keyCode': 55, 'code': 'Digit7', 'shiftKey': '&', 'key': '7'},
'\ue022': {'keyCode': 56, 'code': 'Digit8', 'shiftKey': '*', 'key': '8'},
'\ue023': {'keyCode': 57, 'code': 'Digit9', 'shiftKey': r'\(', 'key': '9'},
'\ue024': {'keyCode': 106, 'code': 'NumpadMultiply', 'key': '*', 'location': 3},
'\ue025': {'keyCode': 107, 'code': 'NumpadAdd', 'key': '+', 'location': 3},
'\ue027': {'keyCode': 109, 'code': 'NumpadSubtract', 'key': '-', 'location': 3},
'\ue029': {'keyCode': 111, 'code': 'NumpadDivide', 'key': '/', 'location': 3},
'\ue031': {'keyCode': 112, 'code': 'F1', 'key': 'F1'},
'\ue032': {'keyCode': 113, 'code': 'F2', 'key': 'F2'},
'\ue033': {'keyCode': 114, 'code': 'F3', 'key': 'F3'},
'\ue034': {'keyCode': 115, 'code': 'F4', 'key': 'F4'},
'\ue035': {'keyCode': 116, 'code': 'F5', 'key': 'F5'},
'\ue036': {'keyCode': 117, 'code': 'F6', 'key': 'F6'},
'\ue037': {'keyCode': 118, 'code': 'F7', 'key': 'F7'},
'\ue038': {'keyCode': 119, 'code': 'F8', 'key': 'F8'},
'\ue039': {'keyCode': 120, 'code': 'F9', 'key': 'F9'},
'\ue03a': {'keyCode': 121, 'code': 'F10', 'key': 'F10'},
'\ue03b': {'keyCode': 122, 'code': 'F11', 'key': 'F11'},
'\ue03c': {'keyCode': 123, 'code': 'F12', 'key': 'F12'},
'\ue018': {'keyCode': 186, 'code': 'Semicolon', 'shiftKey': ':', 'key': ';'},
'\ue019': {'keyCode': 187, 'code': 'NumpadEqual', 'key': '=', 'location': 3},
'\u0000': {'keyCode': 46, 'key': '\u0000', 'code': 'NumpadDecimal', 'location': 3},
# 'KeyA': {'keyCode': 65, 'code': 'KeyA', 'shiftKey': 'A', 'key': 'a'},
# 'KeyB': {'keyCode': 66, 'code': 'KeyB', 'shiftKey': 'B', 'key': 'b'},
# 'KeyC': {'keyCode': 67, 'code': 'KeyC', 'shiftKey': 'C', 'key': 'c'},
# 'KeyD': {'keyCode': 68, 'code': 'KeyD', 'shiftKey': 'D', 'key': 'd'},
# 'KeyE': {'keyCode': 69, 'code': 'KeyE', 'shiftKey': 'E', 'key': 'e'},
# 'KeyF': {'keyCode': 70, 'code': 'KeyF', 'shiftKey': 'F', 'key': 'f'},
# 'KeyG': {'keyCode': 71, 'code': 'KeyG', 'shiftKey': 'G', 'key': 'g'},
# 'KeyH': {'keyCode': 72, 'code': 'KeyH', 'shiftKey': 'H', 'key': 'h'},
# 'KeyI': {'keyCode': 73, 'code': 'KeyI', 'shiftKey': 'I', 'key': 'i'},
# 'KeyJ': {'keyCode': 74, 'code': 'KeyJ', 'shiftKey': 'J', 'key': 'j'},
# 'KeyK': {'keyCode': 75, 'code': 'KeyK', 'shiftKey': 'K', 'key': 'k'},
# 'KeyL': {'keyCode': 76, 'code': 'KeyL', 'shiftKey': 'L', 'key': 'l'},
# 'KeyM': {'keyCode': 77, 'code': 'KeyM', 'shiftKey': 'M', 'key': 'm'},
# 'KeyN': {'keyCode': 78, 'code': 'KeyN', 'shiftKey': 'N', 'key': 'n'},
# 'KeyO': {'keyCode': 79, 'code': 'KeyO', 'shiftKey': 'O', 'key': 'o'},
# 'KeyP': {'keyCode': 80, 'code': 'KeyP', 'shiftKey': 'P', 'key': 'p'},
# 'KeyQ': {'keyCode': 81, 'code': 'KeyQ', 'shiftKey': 'Q', 'key': 'q'},
# 'KeyR': {'keyCode': 82, 'code': 'KeyR', 'shiftKey': 'R', 'key': 'r'},
# 'KeyS': {'keyCode': 83, 'code': 'KeyS', 'shiftKey': 'S', 'key': 's'},
# 'KeyT': {'keyCode': 84, 'code': 'KeyT', 'shiftKey': 'T', 'key': 't'},
# 'KeyU': {'keyCode': 85, 'code': 'KeyU', 'shiftKey': 'U', 'key': 'u'},
# 'KeyV': {'keyCode': 86, 'code': 'KeyV', 'shiftKey': 'V', 'key': 'v'},
# 'KeyW': {'keyCode': 87, 'code': 'KeyW', 'shiftKey': 'W', 'key': 'w'},
# 'KeyX': {'keyCode': 88, 'code': 'KeyX', 'shiftKey': 'X', 'key': 'x'},
# 'KeyY': {'keyCode': 89, 'code': 'KeyY', 'shiftKey': 'Y', 'key': 'y'},
# 'KeyZ': {'keyCode': 90, 'code': 'KeyZ', 'shiftKey': 'Z', 'key': 'z'},
# 'MetaLeft': {'keyCode': 91, 'code': 'MetaLeft', 'key': 'Meta'},
# 'MetaRight': {'keyCode': 92, 'code': 'MetaRight', 'key': 'Meta'},
# 'ContextMenu': {'keyCode': 93, 'code': 'ContextMenu', 'key': 'ContextMenu'},
# 'F13': {'keyCode': 124, 'code': 'F13', 'key': 'F13'},
# 'F14': {'keyCode': 125, 'code': 'F14', 'key': 'F14'},
# 'F15': {'keyCode': 126, 'code': 'F15', 'key': 'F15'},
# 'F16': {'keyCode': 127, 'code': 'F16', 'key': 'F16'},
# 'F17': {'keyCode': 128, 'code': 'F17', 'key': 'F17'},
# 'F18': {'keyCode': 129, 'code': 'F18', 'key': 'F18'},
# 'F19': {'keyCode': 130, 'code': 'F19', 'key': 'F19'},
# 'F20': {'keyCode': 131, 'code': 'F20', 'key': 'F20'},
# 'F21': {'keyCode': 132, 'code': 'F21', 'key': 'F21'},
# 'F22': {'keyCode': 133, 'code': 'F22', 'key': 'F22'},
# 'F23': {'keyCode': 134, 'code': 'F23', 'key': 'F23'},
# 'F24': {'keyCode': 135, 'code': 'F24', 'key': 'F24'},
# 'NumLock': {'keyCode': 144, 'code': 'NumLock', 'key': 'NumLock'},
# 'ScrollLock': {'keyCode': 145, 'code': 'ScrollLock', 'key': 'ScrollLock'},
# 'AudioVolumeMute': {'keyCode': 173, 'code': 'AudioVolumeMute', 'key': 'AudioVolumeMute'},
# 'AudioVolumeDown': {'keyCode': 174, 'code': 'AudioVolumeDown', 'key': 'AudioVolumeDown'},
# 'AudioVolumeUp': {'keyCode': 175, 'code': 'AudioVolumeUp', 'key': 'AudioVolumeUp'},
# 'MediaTrackNext': {'keyCode': 176, 'code': 'MediaTrackNext', 'key': 'MediaTrackNext'},
# 'MediaTrackPrevious': {'keyCode': 177, 'code': 'MediaTrackPrevious', 'key': 'MediaTrackPrevious'},
# 'MediaStop': {'keyCode': 178, 'code': 'MediaStop', 'key': 'MediaStop'},
# 'MediaPlayPause': {'keyCode': 179, 'code': 'MediaPlayPause', 'key': 'MediaPlayPause'},
# 'Equal': {'keyCode': 187, 'code': 'Equal', 'shiftKey': '+', 'key': '='},
# 'Comma': {'keyCode': 188, 'code': 'Comma', 'shiftKey': '<', 'key': ','},
# 'Minus': {'keyCode': 189, 'code': 'Minus', 'shiftKey': '_', 'key': '-'},
# 'Period': {'keyCode': 190, 'code': 'Period', 'shiftKey': '>', 'key': '.'},
# 'Slash': {'keyCode': 191, 'code': 'Slash', 'shiftKey': '?', 'key': '/'},
# 'Backquote': {'keyCode': 192, 'code': 'Backquote', 'shiftKey': '~', 'key': '`'},
# 'BracketLeft': {'keyCode': 219, 'code': 'BracketLeft', 'shiftKey': '{', 'key': '['},
# 'Backslash': {'keyCode': 220, 'code': 'Backslash', 'shiftKey': '|', 'key': '\\'},
# 'BracketRight': {'keyCode': 221, 'code': 'BracketRight', 'shiftKey': '}', 'key': ']'},
# 'Quote': {'keyCode': 222, 'code': 'Quote', 'shiftKey': '"', 'key': '\''},
# 'AltGraph': {'keyCode': 225, 'code': 'AltGraph', 'key': 'AltGraph'},
# 'Props': {'keyCode': 247, 'code': 'Props', 'key': 'CrSel'},
# 'Cancel': {'keyCode': 3, 'key': 'Cancel', 'code': 'Abort'},
# 'Clear': {'keyCode': 12, 'key': 'Clear', 'code': 'Numpad5', 'location': 3},
# 'Shift': {'keyCode': 16, 'key': 'Shift', 'code': 'ShiftLeft'},
# 'Control': {'keyCode': 17, 'key': 'Control', 'code': 'ControlLeft'},
# 'Alt': {'keyCode': 18, 'key': 'Alt', 'code': 'AltLeft'},
# 'Accept': {'keyCode': 30, 'key': 'Accept'},
# 'ModeChange': {'keyCode': 31, 'key': 'ModeChange'},
# 'Print': {'keyCode': 42, 'key': 'Print'},
# 'Execute': {'keyCode': 43, 'key': 'Execute', 'code': 'Open'},
# 'Attn': {'keyCode': 246, 'key': 'Attn'},
# 'CrSel': {'keyCode': 247, 'key': 'CrSel', 'code': 'Props'},
# 'ExSel': {'keyCode': 248, 'key': 'ExSel'},
# 'EraseEof': {'keyCode': 249, 'key': 'EraseEof'},
# 'Play': {'keyCode': 250, 'key': 'Play'},
# 'ZoomOut': {'keyCode': 251, 'key': 'ZoomOut'},
# 'Power': {'key': 'Power', 'code': 'Power'},
# 'Eject': {'key': 'Eject', 'code': 'Eject'},
}
def keys_to_typing(value):
typing = []
modifier = 0
for val in value:
if val in ('\ue009', '\ue008', '\ue00a', '\ue03d'):
modifier |= modifierBit.get(val, 0)
continue
if isinstance(val, (int, float)):
val = str(val)
for i in range(len(val)):
typing.append(val[i])
else:
for i in range(len(val)):
typing.append(val[i])
return modifier, ''.join(typing)
def make_input_data(modifiers, key, key_up=False):
data = keyDefinitions.get(key)
if not data:
return None
result = {'modifiers': modifiers, 'autoRepeat': False, '_ignore': AlertExistsError}
shift = modifiers & 8
if shift and data.get('shiftKey'):
result['key'] = data['shiftKey']
result['text'] = data['shiftKey']
elif 'key' in data:
result['key'] = data['key']
if len(result.get('key', '')) == 1: # type: ignore
result['text'] = data['key']
sys_text = 'windowsVirtualKeyCode' if sys == 'windows' else 'nativeVirtualKeyCode'
if shift and data.get('shiftKeyCode'):
result[sys_text] = data['shiftKeyCode']
elif 'keyCode' in data:
result[sys_text] = data['keyCode']
if 'code' in data:
result['code'] = data['code']
if 'location' in data:
result['location'] = data['location']
result['isKeypad'] = data['location'] == 3
else:
result['location'] = 0
result['isKeypad'] = False
if shift and data.get('shiftText'):
result['text'] = data['shiftText']
result['unmodifiedText'] = data['shiftText']
elif 'text' in data:
result['text'] = data['text']
result['unmodifiedText'] = data['text']
if modifiers & ~8:
result['text'] = ''
result['type'] = 'keyUp' if key_up else ('keyDown' if result.get('text') else 'rawKeyDown')
return result
def send_key(page, modifier, key):
data = make_input_data(modifier, key)
if data:
page._run_cdp('Input.dispatchKeyEvent', **data)
data['type'] = 'keyUp'
page._run_cdp('Input.dispatchKeyEvent', **data)
else:
page._run_cdp('Input.insertText', text=key, _ignore=AlertExistsError)
def input_text_or_keys(page, text_or_keys):
if not isinstance(text_or_keys, (tuple, list)):
text_or_keys = (str(text_or_keys),)
modifier, text_or_keys = keys_to_typing(text_or_keys)
if modifier != 0: # 包含修饰符
for key in text_or_keys:
send_key(page, modifier, key)
return
if text_or_keys.endswith(('\n', '\ue007', '\ue006')):
page._run_cdp('Input.insertText', text=text_or_keys[:-1], _ignore=AlertExistsError)
send_key(page, modifier, '\n')
else:
page._run_cdp('Input.insertText', text=text_or_keys, _ignore=AlertExistsError)
@@ -0,0 +1,122 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from typing import Tuple, Union, Any
from .._pages.chromium_base import ChromiumBase
class Keys:
"""特殊按键"""
CTRL_A: tuple
CTRL_C: tuple
CTRL_X: tuple
CTRL_V: tuple
CTRL_Z: tuple
CTRL_Y: tuple
NULL: str
CANCEL: str
HELP: str
BACKSPACE: str
TAB: str
CLEAR: str
RETURN: str
ENTER: str
SHIFT: str
CONTROL: str
CTRL: str
ALT: str
PAUSE: str
ESCAPE: str
SPACE: str
PAGE_UP: str
PAGE_DOWN: str
END: str
HOME: str
LEFT: str
UP: str
RIGHT: str
DOWN: str
INSERT: str
DELETE: str
DEL: str
SEMICOLON: str
EQUALS: str
NUMPAD0: str
NUMPAD1: str
NUMPAD2: str
NUMPAD3: str
NUMPAD4: str
NUMPAD5: str
NUMPAD6: str
NUMPAD7: str
NUMPAD8: str
NUMPAD9: str
MULTIPLY: str
ADD: str
SUBTRACT: str
DECIMAL: str
DIVIDE: str
F1: str
F2: str
F3: str
F4: str
F5: str
F6: str
F7: str
F8: str
F9: str
F10: str
F11: str
F12: str
META: str
COMMAND: str
keyDefinitions: dict = ...
modifierBit: dict = ...
def keys_to_typing(value: Union[str, int, list, tuple]) -> Tuple[int, str]:
"""把要输入的内容连成字符串,去掉其中 ctrl 等键。
返回的modifier表示是否有按下组合键"""
...
def make_input_data(modifiers: int,
key: str,
key_up: bool = False) -> dict:
"""
:param modifiers: 功能键设置
:param key: 按键字符
:param key_up: 是否提起
:return: None
"""
...
def send_key(page: ChromiumBase, modifier: int, key: str) -> None:
"""发送一个字,在键盘中的字符触发按键,其它直接发送文本
:param page: 动作所在页面
:param modifier: 功能键信息
:param key: 要是输入的按键
:return: None
"""
...
def input_text_or_keys(page: ChromiumBase, text_or_keys: Any) -> None:
"""输入文本,也可输入组合键,组合键用tuple形式输入
:param page: ChromiumBase对象
:param text_or_keys: 文本值或按键组合
:return: self
"""
...
@@ -0,0 +1,549 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from re import split
from .by import By
from .._functions.settings import Settings as _S
from ..errors import LocatorError
def locator_to_tuple(loc):
loc = _preprocess(loc)
# 多属性查找
if loc.startswith(('@@', '@|', '@!')) and loc not in ('@@', '@|', '@!'):
args = _get_args(loc)
# 单属性查找
elif loc.startswith('@') and loc != '@':
arg = _get_arg(loc[1:])
arg.append(False)
args = {'and': True, 'args': [arg]}
# 根据tag name查找
elif loc.startswith(('tag:', 'tag=', 'tag^', 'tag$')) and loc not in ('tag:', 'tag=', 'tag^', 'tag$'):
at_ind = loc.find('@')
if at_ind == -1:
args = {'and': True, 'args': [['tag()', '=', loc[4:].lower(), False]]}
else:
args_str = loc[at_ind:]
if args_str.startswith(('@@', '@|', '@!')):
args = _get_args(args_str)
args['args'].append([f'tag()', '=', loc[4:at_ind].lower(), False])
else: # t:div@aa=bb的格式
arg = _get_arg(loc[at_ind + 1:])
arg.append(False)
args = {'and': True, 'args': [['tag()', '=', loc[4:at_ind].lower(), False], arg]}
# 根据文本查找
elif loc.startswith(('text=', 'text:', 'text^', 'text$')):
args = {'and': True, 'args': [['text()', loc[4], loc[5:], False]]}
# 根据文本模糊查找
else:
args = {'and': True, 'args': [['text()', '=', loc, False]]}
return args
def _get_args(text: str = '') -> dict:
"""解析定位参数字符串生成dict格式数据
:param text: 待处理的字符串
:return: 格式: {'and': bool, 'args': ['属性名称', '匹配方式', '属性值', 是否否定]}
"""
arg_list = []
args = split(r'(@!|@@|@\|)', text)[1:]
if '@@' in args and '@|' in args:
raise LocatorError(_S._lang.SYMBOL_CONFLICT, VALUE=text)
_and = '@|' not in args
for k in range(0, len(args) - 1, 2):
arg = _get_arg(args[k + 1])
if arg:
arg.append(True if args[k] == '@!' else False) # 是否去除某个属性
arg_list.append(arg)
return {'and': _and, 'args': arg_list}
def _get_arg(text) -> list:
"""解析arg=abc格式字符串,生成格式:['属性名称', '匹配方式', '属性值', 是否否定],不是式子的返回None"""
r = split(r'([:=$^])', text, maxsplit=1)
if not r[0]:
return [None, None, None, None]
# !=时只有属性名没有属性内容,查询是否存在该属性
name = r[0] if r[0] != 'tx()' else 'text()'
name = name if name != 't()' else 'teg()'
return [name, None, None] if len(r) != 3 else [name, r[1], r[2]]
def is_str_loc(text):
return text.startswith(('.', '#', '@', 't:', 't=', 'tag:', 'tag=', 'tx:', 'tx=', 'tx^', 'tx$', 'text:', 'text=',
'text^', 'text$', 'xpath:', 'xpath=', 'x:', 'x=', 'css:', 'css=', 'c:', 'c='))
def is_selenium_loc(loc):
return (isinstance(loc, tuple) and len(loc) == 2 and loc[0].lower() in (
'id', 'xpath', 'link text', 'partial link text', 'name', 'tag name', 'class name', 'css selector')
and isinstance(loc[1], str))
def get_loc(loc, translate_css=False, css_mode=False):
if isinstance(loc, tuple):
loc = translate_css_loc(loc) if css_mode else translate_loc(loc)
elif isinstance(loc, str):
loc = str_to_css_loc(loc) if css_mode else str_to_xpath_loc(loc)
else:
raise LocatorError(ALLOW_TYPE=_S._lang.LOC_FORMAT, CURR_VAL=loc)
if loc[0] == 'css selector' and translate_css:
from lxml.cssselect import CSSSelector, ExpressionError
try:
path = str(CSSSelector(loc[1], translator='html').path)
path = path[20:] if path.startswith('descendant-or-self::') else path
loc = 'xpath', path
except ExpressionError:
pass
return loc
def str_to_xpath_loc(loc):
loc_by = 'xpath'
loc = _preprocess(loc)
# 多属性查找
if loc.startswith(('@@', '@|', '@!')) and loc not in ('@@', '@|', '@!'):
loc_str = _make_multi_xpath_str('*', loc)[1]
# 单属性查找
elif loc.startswith('@') and loc != '@':
loc_str = _make_single_xpath_str('*', loc)[1]
# 根据tag name查找
elif loc.startswith(('tag:', 'tag=', 'tag^', 'tag$')) and loc not in ('tag:', 'tag=', 'tag^', 'tag$'):
at_ind = loc.find('@')
if at_ind == -1:
loc_str = f'//*[name()="{loc[4:]}"]'
elif loc[at_ind:].startswith(('@@', '@|', '@!')):
loc_str = _make_multi_xpath_str(loc[4:at_ind], loc[at_ind:])[1]
else:
loc_str = _make_single_xpath_str(loc[4:at_ind], loc[at_ind:])[1]
# 根据文本查找
elif loc.startswith('text='):
loc_str = f'//*[text()={_quotes_escape(loc[5:])}]'
elif loc.startswith('text:') and loc != 'text:':
loc_str = f'//*/text()[contains(., {_quotes_escape(loc[5:])})]/..'
elif loc.startswith('text^') and loc != 'text^':
loc_str = f'//*/text()[starts-with(., {_quotes_escape(loc[5:])})]/..'
elif loc.startswith('text$') and loc != 'text$':
loc_str = (f'//*/text()[substring(., string-length(.) - string-length({_quotes_escape(loc[5:])}) +1) = '
f'{_quotes_escape(loc[5:])}]/..')
# 用xpath查找
elif loc.startswith(('xpath:', 'xpath=')) and loc not in ('xpath:', 'xpath='):
loc_str = loc[6:]
# 用css selector查找
elif loc.startswith(('css:', 'css=')) and loc not in ('css:', 'css='):
loc_by = 'css selector'
loc_str = loc[4:]
# 根据文本模糊查找
elif loc:
loc_str = f'//*/text()[contains(., {_quotes_escape(loc)})]/..'
else:
loc_str = '//*'
return loc_by, loc_str
def str_to_css_loc(loc):
loc_by = 'css selector'
loc = _preprocess(loc)
# 多属性查找
if loc.startswith(('@@', '@|', '@!')) and loc not in ('@@', '@|', '@!'):
loc_str = _make_multi_css_str('*', loc)[1]
# 单属性查找
elif loc.startswith('@') and loc != '@':
loc_by, loc_str = _make_single_css_str('*', loc)
# 根据tag name查找
elif loc.startswith(('tag:', 'tag=', 'tag^', 'tag$')) and loc not in ('tag:', 'tag=', 'tag^', 'tag$'):
at_ind = loc.find('@')
if at_ind == -1:
loc_str = loc[4:]
elif loc[at_ind:].startswith(('@@', '@|', '@!')):
loc_by, loc_str = _make_multi_css_str(loc[4:at_ind], loc[at_ind:])
else:
loc_by, loc_str = _make_single_css_str(loc[4:at_ind], loc[at_ind:])
# 根据文本查找
elif loc.startswith(('text=', 'text:', 'text^', 'text$', 'xpath=', 'xpath:')):
loc_by, loc_str = str_to_xpath_loc(loc)
# 用css selector查找
elif loc.startswith(('css:', 'css=')) and loc not in ('css:', 'css='):
loc_str = loc[4:]
# 根据文本模糊查找
elif loc:
loc_by, loc_str = str_to_xpath_loc(loc)
else:
loc_str = '*'
return loc_by, loc_str
def _make_single_xpath_str(tag: str, text: str) -> tuple:
"""生成单属性xpath语句
:param tag: 标签名
:param text: 待处理的字符串
:return: xpath字符串
"""
arg_list = [] if tag == '*' else [f'name()="{tag}"']
arg_str = txt_str = ''
if text == '@':
arg_str = 'not(@*)'
else:
r = split(r'([:=$^])', text, maxsplit=1)
len_r = len(r)
len_r0 = len(r[0])
if len_r == 3 and len_r0 > 1:
if r[0] in ('@tag()', '@t()'):
arg_str = f'name()="{r[2].lower()}"'
else:
symbol = r[1]
if symbol == '=': # 精确查找
arg = 'text()' if r[0] in ('@text()', '@tx()') else r[0]
arg_str = f'{arg}={_quotes_escape(r[2])}'
elif symbol == '^': # 匹配开头
if r[0] in ('@text()', '@tx()'):
txt_str = f'/text()[starts-with(., {_quotes_escape(r[2])})]/..'
arg_str = ''
else:
arg_str = f"starts-with({r[0]},{_quotes_escape(r[2])})"
elif symbol == '$': # 匹配结尾
if r[0] in ('@text()', '@tx()'):
txt_str = (f'/text()[substring(., string-length(.) - string-length('
f'{_quotes_escape(r[2])}) +1) = {_quotes_escape(r[2])}]/..')
arg_str = ''
else:
arg_str = (f'substring({r[0]}, string-length({r[0]}) - string-length('
f'{_quotes_escape(r[2])}) +1) = {_quotes_escape(r[2])}')
elif symbol == ':': # 模糊查找
if r[0] in ('@text()', '@tx()'):
txt_str = f'/text()[contains(., {_quotes_escape(r[2])})]/..'
arg_str = ''
else:
arg_str = f"contains({r[0]},{_quotes_escape(r[2])})"
else:
raise LocatorError(_S._lang.INCORRECT_SIGN_, symbol)
elif len_r != 3 and len_r0 > 1:
if r[0] in ('@tag()', '@t()'):
arg_str = ''
else:
arg_str = 'normalize-space(text())' if r[0] in ('@text()', '@tx()') else f'{r[0]}'
if arg_str:
arg_list.append(arg_str)
arg_str = ' and '.join(arg_list)
return 'xpath', f'//*[{arg_str}]{txt_str}' if arg_str else f'//*{txt_str}'
def _make_multi_xpath_str(tag: str, text: str) -> tuple:
"""生成多属性查找的xpath语句
:param tag: 标签名
:param text: 待处理的字符串
:return: xpath字符串
"""
arg_list = []
args = split(r'(@!|@@|@\|)', text)[1:]
if '@@' in args and '@|' in args:
raise LocatorError(_S._lang.SYMBOL_CONFLICT, VALUE=text)
_and = '@|' not in args
tags = [] if tag == '*' else [f'name()="{tag}"']
tags_connect = ' or '
for k in range(0, len(args) - 1, 2):
r = split(r'([:=$^])', args[k + 1], maxsplit=1)
arg_str = ''
len_r = len(r)
if not r[0]: # 不查询任何属性
arg_str = 'not(@*)'
else:
ignore = True if args[k] == '@!' else False # 是否去除某个属性
if len_r != 3: # 只有属性名没有属性内容,查询是否存在该属性
if r[0] in ('tag()', 't()'):
continue
arg_str = 'normalize-space(text())' if r[0] in ('text()', 'tx()') else f'@{r[0]}'
elif len_r == 3: # 属性名和内容都有
if r[0] in ('tag()', 't()'):
if ignore:
tags.append(f'not(name()="{r[2]}")')
tags_connect = ' and '
else:
tags.append(f'name()="{r[2]}"')
continue
symbol = r[1]
if r[0] in ('text()', 'tx()'):
arg = '.'
txt = r[2]
else:
arg = f'@{r[0]}'
txt = r[2]
if symbol == '=':
arg_str = f'{arg}={_quotes_escape(txt)}'
elif symbol == ':':
arg_str = f'contains({arg},{_quotes_escape(txt)})'
elif symbol == '^':
arg_str = f'starts-with({arg},{_quotes_escape(txt)})'
elif symbol == '$':
arg_str = (f'substring({arg}, string-length({arg}) - string-length('
f'{_quotes_escape(txt)}) +1) = {_quotes_escape(txt)}')
else:
raise LocatorError(_S._lang.INCORRECT_SIGN_, symbol)
if arg_str and ignore:
arg_str = f'not({arg_str})'
if arg_str:
arg_list.append(arg_str)
arg_str = ' and '.join(arg_list) if _and else ' or '.join(arg_list)
if tags:
condition = f' and ({arg_str})' if arg_str else ''
arg_str = f'({tags_connect.join(tags)}){condition}'
return 'xpath', f'//*[{arg_str}]' if arg_str else f'//*'
def _quotes_escape(search_str: str) -> str:
"""将"转义,不知何故不能直接用 斜杠 来转义
:param search_str: 查询字符串
:return: 把"转义后的字符串
"""
if '"' not in search_str:
return f'"{search_str}"'
parts = search_str.split('"')
parts_num = len(parts)
search_str = 'concat('
for key, i in enumerate(parts):
search_str += f'"{i}"'
search_str += ',' + '\'"\',' if key < parts_num - 1 else ''
search_str += ',"")'
return search_str
def _make_multi_css_str(tag: str, text: str) -> tuple:
"""生成多属性查找的css selector语句
:param tag: 标签名
:param text: 待处理的字符串
:return: css selector字符串
"""
arg_list = []
args = split(r'(@!|@@|@\|)', text)[1:]
if '@@' in args and '@|' in args:
raise LocatorError(_S._lang.SYMBOL_CONFLICT, LOCATOR=text)
_and = '@|' not in args
for k in range(0, len(args) - 1, 2):
r = split(r'([:=$^])', args[k + 1], maxsplit=1)
if not r[0] or r[0].startswith(('text()', 'tx()')):
return _make_multi_xpath_str(tag, text)
arg_str = ''
len_r = len(r)
ignore = True if args[k] == '@!' else False # 是否去除某个属性
if len_r != 3: # 只有属性名没有属性内容,查询是否存在该属性
if r[0] in ('tag()', 't()'):
continue
arg_str = f'[{r[0]}]'
elif len_r == 3: # 属性名和内容都有
if r[0] in ('tag()', 't()'):
if tag == '*':
tag = f':not({r[2].lower()})' if ignore else f'{r[2]}'
else:
tag += f',:not({r[2].lower()})' if ignore else f',{r[2]}'
continue
d = {'=': '', '^': '^', '$': '$', ':': '*'}
arg_str = f'[{r[0]}{d[r[1]]}={css_trans(r[2])}]'
if arg_str and ignore:
arg_str = f':not({arg_str})'
if arg_str:
arg_list.append(arg_str)
if _and:
return 'css selector', f'{tag}{"".join(arg_list)}'
return 'css selector', f'{tag}{("," + tag).join(arg_list)}'
def _make_single_css_str(tag: str, text: str) -> tuple:
"""生成单属性css selector语句
:param tag: 标签名
:param text: 待处理的字符串
:return: css selector字符串
"""
if text == '@' or text.startswith(('@text()', '@tx()')):
return _make_single_xpath_str(tag, text)
r = split(r'([:=$^])', text, maxsplit=1)
if r[0] in ('@tag()', '@t()'):
return 'css selector', r[2]
if len(r) == 3:
d = {'=': '', '^': '^', '$': '$', ':': '*'}
arg_str = f'[{r[0][1:]}{d[r[1]]}={css_trans(r[2])}]'
else:
arg_str = f'[{css_trans(r[0][1:])}]'
return 'css selector', f'{tag}{arg_str}'
def translate_loc(loc):
if len(loc) != 2:
raise LocatorError(_S._lang.LOC_LEN, LOCATOR=loc)
loc_by = By.XPATH
loc_0 = loc[0].lower()
if loc_0 == By.XPATH:
loc_str = loc[1]
elif loc_0 == By.CSS_SELECTOR:
loc_by = loc_0
loc_str = loc[1]
elif loc_0 == By.ID:
loc_str = f'//*[@id="{loc[1]}"]'
elif loc_0 == By.CLASS_NAME:
loc_str = f'//*[@class="{loc[1]}"]'
elif loc_0 == By.LINK_TEXT:
loc_str = f'//a[text()="{loc[1]}"]'
elif loc_0 == By.NAME:
loc_str = f'//*[@name="{loc[1]}"]'
elif loc_0 == By.TAG_NAME:
loc_str = f'//*[name()="{loc[1]}"]'
elif loc_0 == By.PARTIAL_LINK_TEXT:
loc_str = f'//a[contains(text(),"{loc[1]}")]'
else:
raise LocatorError(_S._lang.INVALID_LOC, LOCATOR=loc)
return loc_by, loc_str
def translate_css_loc(loc):
if len(loc) != 2:
raise LocatorError(_S._lang.LOC_LEN, LOCATOR=loc)
loc_by = By.CSS_SELECTOR
loc_0 = loc[0].lower()
if loc_0 == By.XPATH:
loc_by = By.XPATH
loc_str = loc[1]
elif loc_0 == By.CSS_SELECTOR:
loc_by = loc_0
loc_str = loc[1]
elif loc_0 == By.ID:
loc_str = f'#{css_trans(loc[1])}'
elif loc_0 == By.CLASS_NAME:
loc_str = f'.{css_trans(loc[1])}'
elif loc_0 == By.LINK_TEXT:
loc_by = By.XPATH
loc_str = f'//a[text()="{css_trans(loc[1])}"]'
elif loc_0 == By.NAME:
loc_str = f'*[@name={css_trans(loc[1])}]'
elif loc_0 == By.TAG_NAME:
loc_str = loc[1]
elif loc_0 == By.PARTIAL_LINK_TEXT:
loc_by = By.XPATH
loc_str = f'//a[contains(text(),"{loc[1]}")]'
else:
raise LocatorError(_S._lang.INVALID_LOC, LOCATOR=loc)
return loc_by, loc_str
def css_trans(txt):
c = ('!', '"', '#', '$', '%', '&', '\'', '(', ')', '*', '+', ',', '-', '.', '/', ':', ';', '<', '=', '>', '?', '@',
'[', '\\', ']', '^', '`', ',', '{', '|', '}', '~', ' ')
return ''.join([fr'\{i}' if i in c else i for i in txt])
def _preprocess(loc):
"""对缩写进行处理,替换回完整写法"""
if loc.startswith('.'):
if loc.startswith(('.=', '.:', '.^', '.$')):
loc = loc.replace('.', '@class', 1)
else:
loc = loc.replace('.', '@class=', 1)
elif loc.startswith('#'):
if loc.startswith(('#=', '#:', '#^', '#$')):
loc = loc.replace('#', '@id', 1)
else:
loc = loc.replace('#', '@id=', 1)
elif loc.startswith(('t:', 't=')):
loc = f'tag:{loc[2:]}'
elif loc.startswith(('tx:', 'tx=', 'tx^', 'tx$')):
loc = f'text{loc[2:]}'
elif loc.startswith(('c:', 'c=')):
loc = f'css:{loc[2:]}'
elif loc.startswith(('x:', 'x=')):
loc = f'xpath:{loc[2:]}'
return loc
@@ -0,0 +1,78 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from typing import Union
def locator_to_tuple(loc: str) -> dict:
"""解析定位字符串生成dict格式数据
:param loc: 待处理的字符串
:return: 格式: {'and': bool, 'args': ['属性名称', '匹配方式', '属性值', 是否否定]}
"""
...
def is_str_loc(text: str) -> bool:
"""返回text是否定位符"""
...
def is_selenium_loc(loc: tuple) -> bool:
"""返回tuple是否selenium的定位符"""
...
def get_loc(loc: Union[tuple, str],
translate_css: bool = False,
css_mode: bool = False) -> tuple:
"""接收本库定位语法或selenium定位元组,转换为标准定位元组,可翻译css selector为xpath
:param loc: 本库定位语法或selenium定位元组
:param translate_css: 是否翻译css selector为xpath,用于相对定位
:param css_mode: 是否尽量用css selector方式
:return: DrissionPage定位元组
"""
...
def str_to_xpath_loc(loc: str) -> tuple:
"""处理元素查找语句
:param loc: 查找语法字符串
:return: 匹配符元组
"""
...
def str_to_css_loc(loc: str) -> tuple:
"""处理元素查找语句
:param loc: 查找语法字符串
:return: 匹配符元组
"""
...
def translate_loc(loc: tuple) -> tuple:
"""把By类型的loc元组转换为css selector或xpath类型的
:param loc: By类型的loc元组
:return: css selector或xpath类型的loc元组
"""
...
def translate_css_loc(loc: tuple) -> tuple:
"""把By类型的loc元组转换为css selector或xpath类型的
:param loc: By类型的loc元组
:return: css selector或xpath类型的loc元组
"""
...
def css_trans(txt: str) -> str:
"""css字符串中特殊字符转义
:param txt: 要处理的文本
:return: 处理后的文本
"""
...
@@ -0,0 +1,67 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from pathlib import Path
from .texts import get_txt_class
class Settings(object):
raise_when_ele_not_found = False
raise_when_click_failed = False
raise_when_wait_failed = False
singleton_tab_obj = True
cdp_timeout = 30
browser_connect_timeout = 30
auto_handle_alert = None
_lang = get_txt_class(None)
suffixes_list = str(Path(__file__).parent.absolute() / 'suffixes.dat').replace('\\', '/')
@classmethod
def set_raise_when_ele_not_found(cls, on_off=True):
cls.raise_when_ele_not_found = on_off
return cls
@classmethod
def set_raise_when_click_failed(cls, on_off=True):
cls.raise_when_click_failed = on_off
return cls
@classmethod
def set_raise_when_wait_failed(cls, on_off=True):
cls.raise_when_wait_failed = on_off
return cls
@classmethod
def set_singleton_tab_obj(cls, on_off=True):
cls.singleton_tab_obj = on_off
return cls
@classmethod
def set_cdp_timeout(cls, second):
cls.cdp_timeout = second
return cls
@classmethod
def set_browser_connect_timeout(cls, second):
cls.browser_connect_timeout = second
return cls
@classmethod
def set_auto_handle_alert(cls, accept=True):
cls.auto_handle_alert = accept
return cls
@classmethod
def set_language(cls, code):
cls._lang = get_txt_class(code)
return cls
@classmethod
def set_suffixes_list(cls, path):
cls.suffixes_list = str(Path(path).absolute()).replace('\\', '/')
return cls
@@ -0,0 +1,95 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from pathlib import Path
from typing import Optional, Union, Literal
from .texts import Texts
class Settings(object):
raise_when_ele_not_found: bool = ...
raise_when_click_failed: bool = ...
raise_when_wait_failed: bool = ...
singleton_tab_obj: bool = ...
cdp_timeout: float = ...
browser_connect_timeout: float = ...
auto_handle_alert: Optional[bool] = ...
_lang: Texts = ...
suffixes_list: str = ...
@classmethod
def set_raise_when_ele_not_found(cls, on_off: bool = True) -> Settings:
"""设置找不到元素时是否立即抛出异常
:param on_off: bool表示开或关
:return: None
"""
...
@classmethod
def set_raise_when_click_failed(cls, on_off: bool = True) -> Settings:
"""设置点击失败时是否立即抛出异常
:param on_off: bool表示开或关
:return: None
"""
...
@classmethod
def set_raise_when_wait_failed(cls, on_off: bool = True) -> Settings:
"""设置等待失败时是否立即抛出异常
:param on_off: bool表示开或关
:return: None
"""
...
@classmethod
def set_singleton_tab_obj(cls, on_off: bool = True) -> Settings:
"""设置是否开启tab单例模式
:param on_off: bool表示开或关
:return: None
"""
...
@classmethod
def set_cdp_timeout(cls, second: float) -> Settings:
"""设置csp执行超时时间(秒)
:param second: 超时秒数
:return: None
"""
...
@classmethod
def set_browser_connect_timeout(cls, second: float) -> Settings:
"""设置等待浏览器连接超时时间(秒)
:param second: 超时秒数
:return: None
"""
...
@classmethod
def set_auto_handle_alert(cls, accept: Optional[bool] = True) -> Settings:
"""设置是否自动处理js弹出信息
:param accept: None为不处理,True为接受,False为取消
:return: None
"""
...
@classmethod
def set_language(cls, code: Literal['zh_cn', 'en']) -> Settings:
"""设置报错和提示信息使用的语言
:param code: 表示语言的文本'zh_cn', 'en'
:return: None
"""
...
@classmethod
def set_suffixes_list(cls, path: Union[str, Path]) -> Settings:
"""设置用于识别域名后缀的文件路径
:param path: 文件路径
:return: None
"""
...
File diff suppressed because it is too large. Load diff
@@ -0,0 +1,397 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from locale import getlocale
from ..version import __version__
def get_txt_class(lang=None):
languages = {
'zh_cn': Texts,
'cn': Texts,
'en': English,
}
if lang is None:
locale = str(getlocale()[0]).lower()
if locale.startswith('zh') or 'chinese' in locale:
lang = 'zh_cn'
elif locale.startswith('en') or 'english' in locale:
lang = 'en'
else:
lang = 'zh_cn'
else:
lang = lang.lower()
lang = languages.get(lang, None)
if lang is None:
raise ValueError(f'lang must be one of {languages.keys()}')
return lang
class Texts(object):
# --------- 参数名 ---------
VERSION = '版本'
INFO = '详情'
METHOD = '方法'
ARGS = '参数'
ARG = '参数'
BROWSER_VER = '浏览器版本'
PATH = '路径'
VALUE = '值'
ALLOW_VAL = '允许值'
CURR_VAL = '当前值'
ALLOW_TYPE = '允许类型'
CURR_TYPE = '当前类型'
TIP = '提示'
ADDRESS = '地址'
LOCATOR = '定位符'
ALL_TABS = '所有标签页'
# --------- 异常默认文本 ---------
ELEMENTNOTFOUNDERROR = '没有找到元素。'
ALERTEXISTSERROR = '存在未处理的提示框。'
CONTEXTLOSTERROR = '页面被刷新,请操作前尝试等待页面刷新或加载完成。'
ELEMENTLOSTERROR = '元素对象已失效。可能是页面整体刷新,或js局部刷新把元素替换或去除了。'
CDPERROR = '方法调用错误。'
PAGEDISCONNECTEDERROR = '与页面的连接已断开。'
JAVASCRIPTERROR = 'JavaScript运行错误。'
NORECTERROR = '该元素没有位置及大小。'
BROWSERCONNECTERROR = '浏览器连接失败。'
NORESOURCEERROR = '该元素无可保存的内容或保存失败。'
CANNOTCLICKERROR = '该元素无法滚动到视口或被遮挡,无法点击。'
GETDOCUMENTERROR = '获取文档失败。'
WAITTIMEOUTERROR = '等待失败。'
INCORRECTURLERROR = '无效的url。'
LOCATORERROR = '定位符格式不正确。',
STORAGEERROR = '无法操作当前存储数据。'
COOKIEFORMATERROR = 'cookie格式不正确。'
TARGETNOTFOUNDERROR = '找不到指定页面。'
# --------- 异常信息 ---------
NO_AVAILABLE_PORT_FOUND = '未找到可用端口。'
WIN_SYS_ONLY = '该方法只能在Windows系统使用。'
NEED_LIB_ = '请先安装{}。'
INVALID_URL = '无效的url,也许要加上"http://"?'
INVALID_HEADER_NAME = '无效的header项名。'
NOT_A_FUNCTION = '传入的js无法解析成函数。'
METHOD_NOT_FOUND = '没有找到对应功能,方法错误或你的浏览器太旧。'
NO_RESPONSE = '超时,可能是浏览器卡了。'
UNKNOWN_ERR = '出现未知错误。'
FEEDBACK = ('出现这个错误可能意味着程序有bug,请把错误信息和重现方法告知作者,谢谢。\n'
'报告网站: https://gitee.com/g1879/DrissionPage/issues')
INI_NOT_FOUND = 'ini文件不存在。'
EXT_NOT_FOUND = '插件路径不存在。'
WAITING_FAILED_ = '等待{}失败(等待{}秒)。'
GET_OBJ_FAILED = '获取对象失败。'
INCORRECT_VAL_ = '{}参数值错误。'
INCORRECT_TYPE_ = '{}参数类型错误。'
CONNECT_ERR = '连接异常。'
BROWSER_CONNECT_ERR1_ = '浏览器连接失败,请检查{}端口是否浏览器,且已添加"--remote-debugging-port={}"启动项。'
BROWSER_CONNECT_ERR2 = '浏览器连接失败,请确认浏览器已启动。'
BROWSER_EXE_NOT_FOUND = '无法找到浏览器可执行文件路径,请手动配置。'
BROWSER_NOT_FOUND = '未找到浏览器。'
BROWSER_NOT_EXIST = '浏览器未开启或已关闭。'
BROWSER_DISCONNECTED = '浏览器已关闭或链接已断开。'
BROWSER_NOT_FOR_CONTROL = '浏览器版本太旧或此浏览器不支持接管。'
UNSUPPORTED_CSS_SYNTAX = '此css selector语法不受支持,请换成xpath。'
UNSUPPORTED_ARG_TYPE_ = '不支持参数{}的类型: {}。'
UPGRADE_WS = '请升级websocket-client库。'
INI_NOT_SET = 'ini_path未设置。'
INVALID_XPATH_ = '无效的xpath语句: {}'
INVALID_CSS_ = '无效的css selector语句: {}'
INDEX_FORMAT = '序号必须是数字或切片。'
LOC_NOT_FOR_FRAME = '该定位符不是指向frame元素。'
NEED_DOWNLOAD_PATH = '此功能需显式设置下载路径。'
GET_WINDOW_SIZE_FAILED = '获取窗口信息失败。'
SET_FAILED_ = '{}设置失败。'
NOT_LISTENING = '监听未启动或已停止。'
NOT_BLOB = '该链接非blob类型。'
CANNOT_INPUT_FILE = '该输入框无法接管,请改用对<input>元素输入路径的方法设置。'
NO_SUCH_KEY_ = '没有这个按键: {}'
NO_NEW_TAB = '没有等到新标签页。'
NO_SUCH_TAB = '没有找到指定标签页。'
NEED_DOMAIN = '需设置domain或url值。如设置url值,需以http开头。'
NEED_DOMAIN2 = 'cookie必须带有"domain"或"url"字段。'
NEED_ARG_ = '{}必须设置。'
SAVE_PATH_MUST_BE_FOLDER = 'save_path必须为文件夹。'
GET_PDF_FAILED = '保存失败,可能浏览器版本不支持。'
GET_BLOB_FAILED = '无法获取该资源。'
NO_SRC_ATTR = '元素没有src值或该值为空。'
D_MODE_ONLY = 'url、domain、path参数只有d模式下有效。'
S_MODE_ONLY = '以下参数在s模式下才会生效:'
STATUS_CODE_ = '状态码: {}'
TAB_OBJ_EXISTS = '该标签页已有非MixTab版本,如需多对象共用标签页请设置Settings.set_singleton_tab_obj(False)。'
ONLY_ENGLISH = '转换成视频仅支持英文路径和文件名。'
SELECT_ONLY = 'select方法只能在<select>元素使用。'
MULTI_SELECT_ONLY = '只能在多选菜单执行此操作。'
OPTION_NOT_FOUND = '没有找到指定选项。'
STR_FOR_SINGLE_SELECT = '单选列表只能传入str格式。'
JS_RUNTIME_ERR = 'js运行环境出错。'
TIMEOUT_ = '{}超时(等待{}秒)'
JS_RESULT_ERR = 'js结果解析错误。'
S_MODE_GET_FAILED = 's模式访问失败,请设置go=False,自行构造连接参数进行访问。'
ZERO_PAGE_SIZE = '页面大小为0,请尝试等待页面加载完成。'
CONTENT_IS_EMPTY = '返回内容为空。'
FIND_ELE_ERR = '查找元素异常。'
SYMBOL_CONFLICT = '@@和@|不能同时出现在一个定位语句中。'
INVALID_LOC = '无法识别的定位符。'
LOC_LEN = '定位符长度必须为2。'
INCORRECT_SIGN_ = '符号不正确: {}'
DOMAIN_NOT_SET = '未设置域名,请设置cookie的domain参数或先访问一个网站。'
PLUGIN_NEED_FOLDER = '插件需解压为文件夹:{}'
NEED_FILES_OR_TEXT_ARG = 'files参数和text参数必须至少输入一个。'
# --------- 参数内容 ---------
ELE_DISPLAYED = '元素显示'
ELE_LOADED = '元素加载'
PAGE_LOADED = '页面加载'
NEW_TAB = '新标签页'
DATA_PACKET = '数据包'
ELE_HIDDEN_DEL = '元素隐藏或被删除'
ELE_DEL = '元素被删除'
ELE_HAS_RECT = '元素拥有大小及位置'
ELE_HIDDEN = '元素隐藏'
ELE_CLICKABLE = '元素可点击'
ELE_COVERED = '元素被覆盖'
ELE_NOT_COVERED = '元素不被覆盖'
ELE_AVAILABLE = '元素可用'
ELE_NOT_AVAILABLE = '元素不可用'
ELE_STOP_MOVING = '元素停止运动'
ELE_STATE_CHANGED_ = '等待元素状态改变失败(等待{}秒)。'
RUN_BY_ADMIN = '尝试用管理员权限运行。'
BROWSER_CONNECT_ERR_INFO = ('\n1、用户文件夹没有和已打开的浏览器冲突\n'
'2、如为无界面系统,请添加\'--headless=new\'启动参数\n'
'3、如果是Linux系统,尝试添加\'--no-sandbox\'启动参数\n'
'可使用ChromiumOptions设置端口和用户文件夹路径。')
# ALLOW
LOC_OR_IND = '定位符(str或长度为2的tuple)或序号'
STR_ONLY = 'str格式且不支持xpath和css形式'
LOC_FORMAT = 'str或长度为2的tuple'
ELE_OR_LOC = '定位符(str或长度为2的tuple)或元素'
FRAME_LOC_FORMAT = '定位符、iframe序号、id、name、ChromiumFrame对象'
SET_DOWNLOAD_PATH = '使用set.download_path()方法、配置对象或ini文件均可。'
SET_WINDOW_NORMAL = '浏览器全屏或最小化状态时请先调用set.window.normal()恢复正常状态。'
HTML_ELE_TYPE = '元素、页面对象或html文本'
ELE_LOC_FORMAT = '(x, y)格式坐标,或ChromiumElement对象'
IP_OR_OPTIONS = 'ip:port格式字符串或ChromiumOptions类型'
TAB_OR_ID = '标签页对象或id'
RUN_JS = '执行js'
PAGE_CONNECT = '页面连接'
NEW_ELE_INFO = 'str格式的html文本,或tuple格式(tag, {name: value})。'
DICT_TO_NEW_ELE = '此网页不支持html格式新建元素,请用dict传入html_or_info参数。'
# --------- print ---------
RETRY = '重试'
OPTIONS_HAVE_SAVED = '配置已保存到文件'
AUTO_LOAD_TIP = '以后程序可自动从文件加载配置'
STOP_RECORDING = '停止录制'
START_RECORD = '开始录制'
CHOOSE_RECORD_TARGET = '请手动选择要录制的目标。'
UNSUPPORTED_USER_PROXY = '你似乎在设置使用账号密码的代理,暂时不支持这种代理,可自行用插件实现需求。'
UNSUPPORTED_SOCKS_PROXY = '你似乎在设置使用socks代理,暂时不支持这种代理,可自行用插件实现需求。'
NOT_SUPPORT_DOWNLOAD = '浏览器版本太低无法使用下载管理功能。'
FILE_NAME = '文件名'
FOLDER_PATH = '目录路径'
UNKNOWN = '未知'
DOWNLOAD_COMPLETED = '下载完成'
COMPLETED_AND_RENAME = '完成并重命名'
OVERWROTE = '已覆盖'
DOWNLOAD_CANCELED = '下载取消'
SKIPPED = '已跳过'
@classmethod
def get(cls, item):
return getattr(cls, item, item) if isinstance(item, str) and item.isupper() else item
@classmethod
def join(cls, *args, **kwargs):
kwargs['VERSION'] = __version__
main = ('\n' + args[0].format(*[i for i in args[1:]])) if args else ''
msg = ('\n' + '\n'.join([f'{cls.get(k)}: {v}' for k, v in kwargs.items()]))
return f'{main}{msg}'
class English(Texts):
# --------- 参数名 ---------
VERSION = 'Version'
INFO = 'Information'
METHOD = 'Method'
ARGS = 'Arguments'
ARG = 'Argument'
BROWSER_VER = 'Browser Version'
PATH = 'Path'
VALUE = 'Value'
ALLOW_VAL = 'Allow Value'
CURR_VAL = 'Current Value'
ALLOW_TYPE = 'Allow Type'
CURR_TYPE = 'Current Type'
TIP = 'Tip'
ADDRESS = 'Address'
LOCATOR = 'Locator'
ALL_TABS = 'All Tabs'
# --------- 异常默认文本 ---------
ELEMENTNOTFOUNDERROR = 'No element found.'
ALERTEXISTSERROR = 'An unprocessed dialog box exists.'
CONTEXTLOSTERROR = 'The page is refreshed. Please wait until the page is refreshed or loaded.'
ELEMENTLOSTERROR = ('The element object is invalid. This may be an overall refresh of the page, or a partial js '
'refresh to replace or remove elements.')
CDPERROR = 'Method call error.'
PAGEDISCONNECTEDERROR = 'The connection to the page has been disconnected.'
JAVASCRIPTERROR = 'JavaScript running error.'
NORECTERROR = 'This element has no location or size.'
BROWSERCONNECTERROR = 'The browser connection fails.'
NORESOURCEERROR = 'The element has no saved content or failed to save.'
CANNOTCLICKERROR = 'The element does not scroll to the viewport or is blocked and cannot be clicked.'
GETDOCUMENTERROR = 'Failed to obtain the document. Procedure'
WAITTIMEOUTERROR = 'Wait for failure.'
INCORRECTURLERROR = 'Invalid url.'
LOCATORERROR = 'Invalid locator format.',
STORAGEERROR = 'Cannot manipulate the currently stored data.'
COOKIEFORMATERROR = 'The cookie format is incorrect.'
TARGETNOTFOUNDERROR = 'The specified page cannot be found.'
PLUGIN_NEED_FOLDER = 'The plugin needs to be decompressed into a folder:{}'
NEED_FILES_OR_TEXT_ARG = 'At least one of the "files" parameter and the "text" parameter must be entered.'
# --------- 异常信息 ---------
NO_AVAILABLE_PORT_FOUND = 'No available port found.'
WIN_SYS_ONLY = 'This method can be used only on Windows.'
NEED_LIB_ = 'Please install {} first.'
INVALID_URL = 'Invalid url, maybe add "http://"?'
INVALID_HEADER_NAME = 'Invalid header name.'
NOT_A_FUNCTION = 'The passed js cannot be parsed into a function.'
METHOD_NOT_FOUND = 'The function is not found, the method is wrong or your browser is too old.'
NO_RESPONSE = 'Time out. Maybe the browser is stuck.'
UNKNOWN_ERR = 'An unknown error occurred.'
FEEDBACK = ('This error may mean that there is a bug in the program, please inform the author of the error '
'message and how to reproduce it, thank you.\n'
'Report url: https://gitee.com/g1879/DrissionPage/issues')
INI_NOT_FOUND = 'The ini file does not exist.'
EXT_NOT_FOUND = 'The plug-in path does not exist.'
WAITING_FAILED_ = 'Wait for {} failed ({} seconds).'
GET_OBJ_FAILED = 'Failed to obtain the object. Procedure'
INCORRECT_VAL_ = 'The {} parameter value is incorrect.'
INCORRECT_TYPE_ = 'The {} parameter type is incorrect.'
CONNECT_ERR = 'The connection is abnormal.'
BROWSER_CONNECT_ERR1_ = ('Browser connect failed, check whether the port {} is a browser and '
'"--remote-debugging-port={}" startup item is added.')
BROWSER_CONNECT_ERR2 = 'The browser connection failed. Please ensure that the browser is started.'
BROWSER_EXE_NOT_FOUND = 'The browser executable file path cannot be found. Please configure it manually.'
BROWSER_NOT_FOUND = 'Browser not found.'
BROWSER_NOT_EXIST = 'The browser is not started or closed.'
BROWSER_DISCONNECTED = 'The browser is closed or the link is broken.'
BROWSER_NOT_FOR_CONTROL = 'The browser version is too old or this browser does not support takeover.'
UNSUPPORTED_CSS_SYNTAX = 'This css selector syntax is not supported, please replace it with xpath.'
UNSUPPORTED_ARG_TYPE_ = 'The type of parameter {} is not supported: {}.'
UPGRADE_WS = 'Upgrade the websocket-client library.'
INI_NOT_SET = 'ini_path is not set.'
INVALID_XPATH_ = 'Invalid xpath statement: {}'
INVALID_CSS_ = 'Invalid css selector statement: {}'
INDEX_FORMAT = 'The serial number must be a number or slice.'
LOC_NOT_FOR_FRAME = 'This locator does not point to the frame element.'
NEED_DOWNLOAD_PATH = 'You need to explicitly set the download path for this function.'
GET_WINDOW_SIZE_FAILED = 'Failed to obtain window information. Procedure'
SET_FAILED_ = 'The argument {} setting failed.'
NOT_LISTENING = 'Listening is not started or stopped.'
NOT_BLOB = 'The link is not of blob type.'
CANNOT_INPUT_FILE = 'This input field cannot handle. Instead, set the input path to the <input> element.'
NO_SUCH_KEY_ = 'There is no button: {}'
NO_NEW_TAB = 'Failed to wait for new tab.'
NO_SUCH_TAB = 'The specified tab was not found.'
NEED_DOMAIN = 'You need to set a domain or url value. If the url value is set, it must start with http.'
NEED_DOMAIN2 = 'The cookie must have a "domain" or "url" field.'
NEED_ARG_ = '{} must be set.'
SAVE_PATH_MUST_BE_FOLDER = 'save_path must be a folder.'
GET_PDF_FAILED = 'The save fails because the browser version may not support it.'
GET_BLOB_FAILED = 'The resource cannot be retrieved.'
NO_SRC_ATTR = 'The element does not have a src value or the value is empty.'
D_MODE_ONLY = 'The url, domain, and path parameters are valid only in d mode.'
S_MODE_ONLY = 'The following parameters take effect only in s mode:'
STATUS_CODE_ = 'Status Code: {}'
TAB_OBJ_EXISTS = ('There is already a non-mixtab version of this tab. If multiple objects are common, '
'use Settings.set_singleton_tab_obj(False).')
ONLY_ENGLISH = 'Only English path and file name are supported when converting to video.'
SELECT_ONLY = 'The select method can only be used on <select> elements.'
MULTI_SELECT_ONLY = 'You can only do this from the multiple select element.'
OPTION_NOT_FOUND = 'The specified option was not found.'
STR_FOR_SINGLE_SELECT = 'Single-choice select element can only be passed in str format.'
JS_RUNTIME_ERR = 'The js runtime environment is faulty.'
TIMEOUT_ = 'Wait for {} timeout ({} seconds).'
JS_RESULT_ERR = 'js result parsing error.'
S_MODE_GET_FAILED = 'S mode access fails, please set go=False and construct connection parameters for access.'
ZERO_PAGE_SIZE = 'The page size is 0, please try to wait for the page to load.'
CONTENT_IS_EMPTY = 'The returned content is empty.'
FIND_ELE_ERR = 'Find element exceptions.'
SYMBOL_CONFLICT = '"@@" and "@|" cannot appear in the same location statement.'
INVALID_LOC = 'Unrecognized locator.'
LOC_LEN = 'The length of the locator must be 2.'
INCORRECT_SIGN_ = 'Incorrect symbol: {}'
DOMAIN_NOT_SET = 'No domain name is set, please set the domain parameter of the cookie or visit a website first.'
# --------- 参数内容 ---------
ELE_DISPLAYED = 'element display'
ELE_LOADED = 'element loaded'
PAGE_LOADED = 'page loaded'
NEW_TAB = 'new tab'
DATA_PACKET = 'data packet'
ELE_HIDDEN_DEL = 'element is hidden or deleted'
ELE_DEL = 'element be deleted'
ELE_HAS_RECT = 'element has size and position'
ELE_HIDDEN = 'element hidden'
ELE_CLICKABLE = 'element clickable'
ELE_COVERED = 'element is covered'
ELE_NOT_COVERED = 'element is not covered'
ELE_AVAILABLE = 'element available'
ELE_NOT_AVAILABLE = 'element not available'
ELE_STOP_MOVING = 'element stop moving'
ELE_STATE_CHANGED_ = 'Failed to wait for element state change ({} seconds).'
RUN_BY_ADMIN = 'Try to run with administrator rights.'
BROWSER_CONNECT_ERR_INFO = ('\n1, the user folder does not conflict with the open browser \n'
'2, if no interface system, please add \'--headless=new\' startup parameter \n'
'3, if the system is Linux, try adding \'--no-sandbox\' boot parameter \n'
'The port and user folder paths can be set using ChromiumOptions.')
# ALLOW
LOC_OR_IND = 'A locator (str or tuple of length 2) or serial number.'
STR_ONLY = 'Str format and not support xpath or css selector.'
LOC_FORMAT = 'str or tuple of length 2'
ELE_OR_LOC = 'A locator (str or tuple of length 2) or element.'
FRAME_LOC_FORMAT = 'locator, iframe serial number, id, name, ChromiumFrame object'
SET_DOWNLOAD_PATH = 'Use the set.download_path() method, configuration object, or ini file.'
SET_WINDOW_NORMAL = ('When the browser is in full screen or minimized state, call set.window.normal() '
'first to restore the normal state.')
HTML_ELE_TYPE = 'Element, Tab object, or html text'
ELE_LOC_FORMAT = '(x, y) format coordinates, or ChromiumElement objects'
IP_OR_OPTIONS = 'ip:port format character string or ChromiumOptions type'
TAB_OR_ID = 'Tab object or tab id'
RUN_JS = 'run js'
PAGE_CONNECT = 'Page connection'
NEW_ELE_INFO = 'html text, or tuple format: (tag, {name: value}).'
DICT_TO_NEW_ELE = ('This page does not support new elements in html format. Please pass the html_or_info '
'parameter with dict.')
# --------- print ---------
RETRY = 'Retry'
OPTIONS_HAVE_SAVED = 'The configuration is saved to a file'
AUTO_LOAD_TIP = 'Later the program can automatically load the configuration from the file'
STOP_RECORDING = 'Stop recording.'
START_RECORD = 'Start recording.'
CHOOSE_RECORD_TARGET = 'Manually select the target you want to record.'
UNSUPPORTED_USER_PROXY = ('You seem to be setting up a proxy that uses the account password, which is not '
'supported for the time being, and can be implemented by the plug-in itself.')
UNSUPPORTED_SOCKS_PROXY = ('You seem to be setting up the use of socks proxy, this proxy is not supported for the '
'time being, you can use your own plug-in to achieve the requirements.')
NOT_SUPPORT_DOWNLOAD = 'The browser version is too low to use the download management function.'
FILE_NAME = 'File Name'
FOLDER_PATH = 'Folder Path'
UNKNOWN = 'Unknown'
DOWNLOAD_COMPLETED = 'Complete'
COMPLETED_AND_RENAME = 'Renamed'
OVERWROTE = 'Overwrote'
DOWNLOAD_CANCELED = 'Canceled'
SKIPPED = 'Skipped'
@@ -0,0 +1,199 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from pathlib import Path
from platform import system
from shutil import rmtree
from tempfile import gettempdir
from threading import Lock
from time import perf_counter, sleep
from .._configs.options_manage import OptionsManager
from .._functions.settings import Settings as _S
from ..errors import (ContextLostError, ElementLostError, PageDisconnectedError, NoRectError, BrowserConnectError,
AlertExistsError, IncorrectURLError, StorageError, CookieFormatError, JavaScriptError, CDPError)
class PortFinder(object):
used_port = set()
prev_time = 0
lock = Lock()
checked_paths = set()
def __init__(self, path=None):
tmp = Path(path) if path else Path(gettempdir()) / 'DrissionPage'
self.tmp_dir = tmp / 'autoPortData'
self.tmp_dir.mkdir(parents=True, exist_ok=True)
if str(self.tmp_dir.absolute()) not in PortFinder.checked_paths:
for i in self.tmp_dir.iterdir():
if i.is_dir() and not port_is_using('127.0.0.1', i.name):
rmtree(i, ignore_errors=True)
PortFinder.checked_paths.add(str(self.tmp_dir.absolute()))
def get_port(self, scope=None):
from random import randint
with PortFinder.lock:
if PortFinder.prev_time and perf_counter() - PortFinder.prev_time > 60:
PortFinder.used_port.clear()
if scope in (True, None):
scope = (9600, 59600)
max_times = scope[1] - scope[0]
times = 0
while times < max_times:
times += 1
port = randint(*scope)
if port in PortFinder.used_port or port_is_using('127.0.0.1', port):
continue
path = self.tmp_dir / str(port)
if path.exists():
try:
rmtree(path)
except:
continue
PortFinder.used_port.add(port)
PortFinder.prev_time = perf_counter()
return port, str(path)
raise BrowserConnectError(_S._lang.NO_AVAILABLE_PORT_FOUND)
def port_is_using(ip, port):
from socket import socket, AF_INET, SOCK_STREAM
s = socket(AF_INET, SOCK_STREAM)
s.settimeout(.1)
result = s.connect_ex((ip, int(port)))
s.close()
return result == 0
def clean_folder(folder_path, ignore=None):
ignore = [] if not ignore else ignore
p = Path(folder_path)
for f in p.iterdir():
if f.name not in ignore:
if f.is_file():
f.unlink()
elif f.is_dir():
rmtree(f, True)
def show_or_hide_browser(tab, hide=True):
if not tab.browser.address.startswith(('127.0.0.1', 'localhost')):
return
if system().lower() != 'windows':
raise EnvironmentError(_S._lang.WIN_SYS_ONLY)
try:
from win32gui import ShowWindow
from win32con import SW_HIDE, SW_SHOW
except (ImportError, ModuleNotFoundError):
raise EnvironmentError(_S._lang.join(_S._lang.NEED_LIB_, 'pypiwin32', TIP='pip install pypiwin32'))
pid = tab.browser.process_id
if not pid:
return None
hds = get_hwnds_from_pid(pid, tab.title)
sw = SW_HIDE if hide else SW_SHOW
for hd in hds:
ShowWindow(hd, sw)
def get_browser_progress_id(progress, address):
if progress:
return progress.pid
from os import popen
port = address.split(':')[-1]
txt = ''
progresses = popen(f'netstat -nao | findstr :{port}').read().split('\n')
for progress in progresses:
if 'LISTENING' in progress:
txt = progress
break
if not txt:
return None
return txt.split(' ')[-1]
def get_hwnds_from_pid(pid, title):
try:
from win32gui import IsWindow, GetWindowText, EnumWindows
from win32process import GetWindowThreadProcessId
except (ImportError, ModuleNotFoundError):
raise EnvironmentError(_S._lang.join(_S._lang.NEED_LIB_, 'win32gui, win32process',
TIP='pip install pypiwin32\npip install win32process'))
def callback(hwnd, hds):
if IsWindow(hwnd) and title in GetWindowText(hwnd):
_, found_pid = GetWindowThreadProcessId(hwnd)
if str(found_pid) == str(pid):
hds.append(hwnd)
return True
hwnds = []
EnumWindows(callback, hwnds)
return hwnds
def wait_until(function, kwargs=None, timeout=10):
if kwargs is None:
kwargs = {}
end_time = perf_counter() + timeout
while perf_counter() < end_time:
value = function(**kwargs)
if value:
return value
sleep(.01)
raise TimeoutError
def configs_to_here(save_name=None):
om = OptionsManager('default')
save_name = f'{save_name}.ini' if save_name is not None else 'dp_configs.ini'
om.save(save_name)
def raise_error(result, browser, ignore=None, user=False):
error = result['error']
if error in ('Cannot find context with specified id', 'Inspected target navigated or closed',
'No frame with given id found'):
r = ContextLostError()
elif error in ('Could not find node with given id', 'Could not find object with given id',
'No node with given id found', 'Node with given id does not belong to the document',
'No node found for given backend id'):
r = ElementLostError()
elif error in ('connection disconnected', 'No target with given id found'):
r = PageDisconnectedError()
elif error == 'alert exists.':
r = AlertExistsError()
elif error in ('Node does not have a layout object', 'Could not compute box model.'):
r = NoRectError()
elif error == 'Cannot navigate to invalid URL':
r = IncorrectURLError(_S._lang.INVALID_URL, url=result["args"]["url"])
elif error == 'Frame corresponds to an opaque origin and its storage key cannot be serialized':
r = StorageError()
elif error == 'Sanitizing cookie failed':
r = CookieFormatError(cookies=result["args"])
elif error == 'Invalid header name':
r = ValueError(_S._lang.join(_S._lang.INVALID_HEADER_NAME, headers=result["args"]["headers"]))
elif error == 'Given expression does not evaluate to a function':
r = JavaScriptError(_S._lang.NOT_A_FUNCTION, JS=result["args"]["functionDeclaration"])
elif error.endswith("' wasn't found"):
r = RuntimeError(_S._lang.join(_S._lang.METHOD_NOT_FOUND, BROWSER_VER=browser.version, METHOD=result["method"]))
elif result['type'] == 'timeout':
r = TimeoutError(_S._lang.join(_S._lang.NO_RESPONSE, INFO=result["error"],
METHOD=result["method"], ARGS=result["args"]))
elif result['type'] == 'call_method_error' and not user:
r = CDPError(_S._lang.UNKNOWN_ERR, INFO=result["error"], METHOD=result["method"],
ARGS=result["args"], TIP=_S._lang.FEEDBACK)
else:
r = RuntimeError(_S._lang.join(_S._lang.UNKNOWN_ERR, INFO=result, TIP=_S._lang.FEEDBACK))
if not ignore or not isinstance(r, ignore):
raise r
@@ -0,0 +1,110 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from os import popen
from pathlib import Path
from threading import Lock
from typing import Union, Tuple
from .._base.chromium import Chromium
from .._pages.chromium_base import ChromiumBase
class PortFinder(object):
used_port: set = ...
prev_time: float = ...
lock: Lock = ...
tmp_dir: Path = ...
checked_paths: set = ...
def __init__(self, path: Union[str, Path] = None):
"""
:param path: 临时文件保存路径,为None时使用系统临时文件夹
"""
...
@staticmethod
def get_port(scope: Tuple[int, int] = None) -> Tuple[int, str]:
"""查找一个可用端口
:param scope: 指定端口范围,不含最后的数字,为None则使用[9600-59600)
:return: 可以使用的端口和用户文件夹路径组成的元组
"""
...
def port_is_using(ip: str, port: Union[str, int]) -> bool:
"""检查端口是否被占用
:param ip: 浏览器地址
:param port: 浏览器端口
:return: bool
"""
...
def clean_folder(folder_path: Union[str, Path], ignore: Union[tuple, list] = None) -> None:
"""清空一个文件夹,除了ignore里的文件和文件夹
:param folder_path: 要清空的文件夹路径
:param ignore: 忽略列表
:return: None
"""
...
def show_or_hide_browser(tab: ChromiumBase, hide: bool = True) -> None:
"""执行显示或隐藏浏览器窗口
:param tab: ChromiumTab对象
:param hide: 是否隐藏
:return: None
"""
...
def get_browser_progress_id(progress: Union[popen, None], address: str) -> Union[str, None]:
"""获取浏览器进程id
:param progress: 已知的进程对象,没有时传入None
:param address: 浏览器管理地址,含端口
:return: 进程id或None
"""
...
def get_hwnds_from_pid(pid: Union[str, int], title: str) -> list:
"""通过PID查询句柄ID
:param pid: 进程id
:param title: 窗口标题
:return: 进程句柄组成的列表
"""
...
def wait_until(function: callable, kwargs: dict = None, timeout: float = 10):
"""等待传入的方法返回值不为假
:param function: 要执行的方法
:param kwargs: 方法参数
:param timeout: 超时时间(秒)
:return: 执行结果,超时抛出TimeoutError
"""
...
def configs_to_here(save_name: Union[Path, str] = None) -> None:
"""把默认ini文件复制到当前目录
:param save_name: 指定文件名,为None则命名为'dp_configs.ini'
:return: None
"""
...
def raise_error(result: dict, browser: Chromium, ignore=None, user: bool = False) -> None:
"""抛出error对应报错
:param result: 包含error的dict
:param browser: 浏览器对象
:param ignore: 要忽略的错误
:param user: 是否用户调用的
:return: None
"""
...
@@ -0,0 +1,318 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from html import unescape
from os.path import sep
from pathlib import Path
from re import sub
from urllib.parse import urlparse, urljoin, urlunparse
from DrissionRecord.tools import make_valid_name
from requests.structures import CaseInsensitiveDict
from .._functions.settings import Settings as _S
def get_ele_txt(e):
# 前面无须换行的元素
nowrap_list = ('br', 'sub', 'sup', 'em', 'strong', 'a', 'font', 'b', 'span', 's', 'i', 'del', 'ins', 'img', 'td',
'th', 'abbr', 'bdi', 'bdo', 'cite', 'code', 'data', 'dfn', 'kbd', 'mark', 'q', 'rp', 'rt', 'ruby',
'samp', 'small', 'time', 'u', 'var', 'wbr', 'button', 'slot', 'content')
# 后面添加换行的元素
wrap_after_list = ('p', 'div', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'ol', 'li', 'blockquote', 'header',
'footer', 'address' 'article', 'aside', 'main', 'nav', 'section', 'figcaption', 'summary')
# 不获取文本的元素
noText_list = ('script', 'style', 'video', 'audio', 'iframe', 'embed', 'noscript', 'canvas', 'template')
# 用/t分隔的元素
tab_list = ('td', 'th')
if e.tag in noText_list:
return e.raw_text
def get_node_txt(ele, pre=False) -> list:
tag = ele.tag
if tag == 'br':
return [True]
if not pre and tag == 'pre':
pre = True
str_list = []
if tag in noText_list and not pre: # 标签内的文本不返回
return str_list
nodes = ele.eles('xpath:./text() | *')
prev_ele = ''
for el in nodes:
if isinstance(el, str): # 字符节点
if pre:
str_list.append(el)
else:
if sub('[ \n\t\r]', '', el) != '': # 字符除了回车和空格还有其它内容
txt = el
if not pre:
txt = txt.replace('\r\n', ' ').replace('\n', ' ')
txt = sub(r' {2,}', ' ', txt)
str_list.append(txt)
else: # 元素节点
if el.tag not in nowrap_list and str_list and str_list[-1] != '\n': # 元素间换行的情况
str_list.append('\n')
if el.tag in tab_list and prev_ele in tab_list: # 表格的行
str_list.append('\t')
str_list.extend(get_node_txt(el, pre))
prev_ele = el.tag
if tag in wrap_after_list and str_list and str_list[-1] not in ('\n', True): # 有些元素后面要添加回车
str_list.append('\n')
return str_list
re_str = get_node_txt(e)
if re_str and re_str[-1] == '\n':
re_str.pop()
l = len(re_str)
if l > 1:
r = []
for i in range(l - 1):
i1 = re_str[i]
i2 = re_str[i + 1]
if i1 is True:
r.append('\n')
continue
elif i2 is True:
r.append(i1)
continue
elif i1.endswith(' ') and i2.startswith(' '):
i1 = i1[:-1]
r.append(i1)
r.append('\n' if re_str[-1] is True else re_str[-1])
re_str = ''.join(r)
elif not l:
re_str = ''
else:
re_str = re_str[0] if re_str[0] is not True else '\n'
return format_html(re_str.strip())
def format_html(text):
return unescape(text).replace('\xa0', ' ') if text else text
def location_in_viewport(page, loc_x, loc_y):
js = f'''function(){{let x = {loc_x}; let y = {loc_y};
const scrollLeft = document.documentElement.scrollLeft;
const scrollTop = document.documentElement.scrollTop;
const vWidth = document.documentElement.clientWidth;
const vHeight = document.documentElement.clientHeight;
if (x< scrollLeft || y < scrollTop || x > vWidth + scrollLeft || y > vHeight + scrollTop){{return false;}}
return true;}}'''
return page._run_js(js)
def offset_scroll(ele, offset_x, offset_y):
loc_x, loc_y = ele.rect.location
cp_x, cp_y = ele.rect.click_point
lx = loc_x + offset_x if offset_x else cp_x
ly = loc_y + offset_y if offset_y else cp_y
if not location_in_viewport(ele.owner, lx, ly):
clientWidth = ele.owner._run_js('return document.body.clientWidth;')
clientHeight = ele.owner._run_js('return document.body.clientHeight;')
ele.owner.scroll.to_location(lx - clientWidth // 2, ly - clientHeight // 2)
cl_x, cl_y = ele.rect.viewport_location
ccp_x, ccp_y = ele.rect.viewport_click_point
cx = cl_x + offset_x if offset_x else ccp_x
cy = cl_y + offset_y if offset_y else ccp_y
return cx, cy
def make_absolute_link(link, baseURI=None):
if not link:
return link
link = link.strip().replace('\\', '/')
parsed = urlparse(link)._asdict()
# if baseURI:
# baseURI = baseURI.rstrip('/\\')
# 是相对路径,与页面url拼接并返回
if not parsed['netloc']:
return urljoin(baseURI, link) if baseURI else link
# 是绝对路径但缺少协议,从页面url获取协议并修复
if not parsed['scheme'] and baseURI:
parsed['scheme'] = urlparse(baseURI).scheme
parsed = tuple(v for v in parsed.values())
return urlunparse(parsed)
# 绝对路径且不缺协议,直接返回
return link
def is_js_func(func):
func = func.strip()
if (func.startswith('function') or func.startswith('async ')) and func.endswith('}'):
return True
# elif '=>' in func:
# return True
return False
def get_blob(page, url, as_bytes=True):
if not url.startswith('blob'):
raise ValueError(_S._lang.join(_S._lang.NOT_BLOB, url=url))
js = """
function fetchData(url) {
return new Promise((resolve, reject) => {
let xhr = new XMLHttpRequest();
xhr.responseType = 'blob';
xhr.onload = function() {
let reader = new FileReader();
reader.onloadend = function(){resolve(reader.result);}
reader.readAsDataURL(xhr.response);
};
xhr.open('GET', url, true);
xhr.send();
});
}
"""
try:
result = page._run_js(js, url)
except:
raise RuntimeError(_S._lang.join(_S._lang.GET_BLOB_FAILED))
if as_bytes:
from base64 import b64decode
return b64decode(result.split(',', 1)[-1])
else:
return result
def save_page(tab, path=None, name=None, as_pdf=False, kwargs=None):
if name:
if name.endswith('.pdf'):
name = name[:-4]
as_pdf = True
elif name.endswith('.mhtml'):
name = name[:-6]
as_pdf = False
if path:
path = Path(path)
if path.suffix.lower() == '.mhtml':
name = path.stem
path = path.parent
as_pdf = False
elif path.suffix.lower() == '.pdf':
name = path.stem
path = path.parent
as_pdf = True
return get_pdf(tab, path, name, kwargs) if as_pdf else get_mhtml(tab, path, name)
def get_mhtml(page, path=None, name=None):
r = page._run_cdp('Page.captureSnapshot')['data']
if path is None and name is None:
return r
path = path or '.'
Path(path).mkdir(parents=True, exist_ok=True)
name = make_valid_name(name or page.title)
with open(f'{path}{sep}{name}.mhtml', 'w', encoding='utf-8', newline='\n') as f:
f.write(r.replace('\r\n', '\n'))
return r
def get_pdf(page, path=None, name=None, kwargs=None):
if not kwargs:
kwargs = {}
kwargs['transferMode'] = 'ReturnAsBase64'
if 'printBackground' not in kwargs:
kwargs['printBackground'] = True
try:
r = page._run_cdp('Page.printToPDF', **kwargs)['data']
except:
raise RuntimeError(_S._lang.join(_S._lang.GET_PDF_FAILED))
from base64 import b64decode
r = b64decode(r)
if path is None and name is None:
return r
path = path or '.'
Path(path).mkdir(parents=True, exist_ok=True)
name = make_valid_name(name or page.title)
with open(f'{path}{sep}{name}.pdf', 'wb', newline='\n') as f:
f.write(r)
return r
def tree(ele_or_page, text=False, show_js=False, show_css=False):
def _tree(obj, last_one=True, body=''):
list_ele = obj.children()
length = len(list_ele)
body_unit = ' ' if last_one else '│ '
tail = '├───'
new_body = body + body_unit
if length > 0:
new_last_one = False
for i in range(length):
if i == length - 1:
tail = '└───'
new_last_one = True
e = list_ele[i]
attrs = ' '.join([f"{k}='{v}'" for k, v in e.attrs.items()])
show_text = f'{new_body}{tail}<{e.tag} {attrs}>'.replace('\n', ' ')
if text:
t = e('x:/text()')
if t:
t = t.replace('\n', ' ')
if (e.tag not in ('script', 'style') or (e.tag == 'script' and show_js)
or (e.tag == 'style' and show_css)):
if text is not True:
t = t[:text]
show_text = f'{show_text} {t}'
print(show_text)
_tree(e, new_last_one, new_body)
ele = ele_or_page.s_ele()
attrs = ' '.join([f"{k}='{v}'" for k, v in ele.attrs.items()])
show_text = f'<{ele.tag} {attrs}>'.replace('\n', ' ')
if text:
t = ele('x:/text()')
if t:
t = t.replace('\n', ' ')
if (ele.tag not in ('script', 'style') or (ele.tag == 'script' and show_js)
or (ele.tag == 'style' and show_css)):
if text is not True:
t = t[:text]
show_text = f'{show_text} {t}'
print(show_text)
_tree(ele)
def format_headers(txt):
if isinstance(txt, (dict, CaseInsensitiveDict)):
for k, v in txt.items():
if v not in (None, False, True):
txt[k] = str(v)
for i in (':method', ':scheme', ':authority', ':path'):
txt.pop(i, None)
return txt
headers = {}
for header in txt.split('\n'):
if header:
name, value = header.split(': ', maxsplit=1)
if name not in (':method', ':scheme', ':authority', ':path'):
headers[name] = value
return headers
@@ -0,0 +1,140 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from pathlib import Path
from typing import Union, Optional, Tuple
from .._base.base import DrissionElement, BaseParser
from .._elements.chromium_element import ChromiumElement
from .._pages.chromium_base import ChromiumBase
from .._pages.chromium_page import ChromiumPage
from .._pages.chromium_tab import ChromiumTab
def get_ele_txt(e: DrissionElement) -> str:
"""获取元素内所有文本
:param e: 元素对象
:return: 元素内所有文本
"""
...
def format_html(text: str) -> str:
"""处理html编码字符
:param text: html文本
:return: 格式化后的html文本
"""
...
def location_in_viewport(page: ChromiumBase, loc_x: float, loc_y: float) -> bool:
"""判断给定的坐标是否在视口中 |n
:param page: ChromePage对象
:param loc_x: 页面绝对坐标x
:param loc_y: 页面绝对坐标y
:return: bool
"""
...
def offset_scroll(ele: ChromiumElement, offset_x: float, offset_y: float) -> Tuple[int, int]:
"""接收元素及偏移坐标,把坐标滚动到页面中间,返回该点坐标
有偏移量时以元素左上角坐标为基准,没有时以click_point为基准
:param ele: 元素对象
:param offset_x: 偏移量x
:param offset_y: 偏移量y
:return: 相对坐标
"""
...
def make_absolute_link(link: str, baseURI: str = None) -> str:
"""获取绝对url
:param link: 超链接
:param baseURI: 页面或iframe的url
:return: 绝对链接
"""
...
def is_js_func(func: str) -> bool:
"""检查文本是否js函数"""
...
def get_blob(page: ChromiumBase, url: str, as_bytes: bool = True) -> bytes:
"""获取知道blob资源
:param page: 资源所在页面对象
:param url: 资源url
:param as_bytes: 是否以字节形式返回
:return: 资源内容
"""
...
def save_page(tab: Union[ChromiumPage, ChromiumTab],
path: Union[Path, str, None] = None,
name: Optional[str] = None,
as_pdf: bool = False,
kwargs: dict = None) -> Union[bytes, str]:
"""把当前页面保存为文件,如果path和name参数都为None,只返回文本
:param tab: Tab或Page对象
:param path: 保存路径,为None且name不为None时保存在当前路径
:param name: 文件名,为None且path不为None时用title属性值
:param as_pdf: 为Ture保存为pdf,否则为mhtml且忽略kwargs参数
:param kwargs: pdf生成参数
:return: as_pdf为True时返回bytes,否则返回文件文本
"""
...
def get_mhtml(page: Union[ChromiumPage, ChromiumTab],
path: Optional[Path] = None,
name: Optional[str] = None) -> Union[bytes, str]:
"""把当前页面保存为mhtml文件,如果path和name参数都为None,只返回mhtml文本
:param page: 要保存的页面对象
:param path: 保存路径,为None且name不为None时保存在当前路径
:param name: 文件名,为None且path不为None时用title属性值
:return: mhtml文本
"""
...
def get_pdf(page: Union[ChromiumPage, ChromiumTab],
path: Optional[Path] = None,
name: Optional[str] = None,
kwargs: dict = None) -> Union[bytes, str]:
"""把当前页面保存为pdf文件,如果path和name参数都为None,只返回字节
:param page: 要保存的页面对象
:param path: 保存路径,为None且name不为None时保存在当前路径
:param name: 文件名,为None且path不为None时用title属性值
:param kwargs: pdf生成参数
:return: pdf文本
"""
...
def tree(ele_or_page: BaseParser,
text: Union[int, bool] = False,
show_js: bool = False,
show_css: bool = False) -> None:
"""把页面或元素对象DOM结构打印出来
:param ele_or_page: 页面或元素对象
:param text: 是否打印文本,输入数字可指定打印文本长度上线
:param show_js: 打印文本时是否包含<script>内文本,text参数为False时无效
:param show_css: 打印文本时是否包含<style>内文本,text参数为False时无效
:return: None
"""
...
def format_headers(txt: str) -> dict:
"""从浏览器复制的文本生成dict格式headers,文本用换行分隔
:param txt: 从浏览器复制的原始文本格式headers
:return: dict格式headers
"""
...
@@ -0,0 +1,950 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from json import loads, JSONDecodeError
from os.path import sep
from pathlib import Path
from re import findall
from threading import Thread
from time import perf_counter, sleep
from DrissionRecord.tools import make_valid_name
from .._base.base import BasePage
from .._elements.chromium_element import run_js, make_chromium_eles
from .._elements.none_element import NoneElement
from .._elements.session_element import make_session_ele
from .._functions.cookies import CookiesList
from .._functions.elements import SessionElementsList, get_frame, ChromiumElementsList
from .._functions.locator import get_loc
from .._functions.settings import Settings as _S
from .._functions.tools import raise_error
from .._functions.web import location_in_viewport
from .._units.actions import Actions
from .._units.console import Console
from .._units.listener import Listener
from .._units.rect import TabRect
from .._units.screencast import Screencast
from .._units.scroller import PageScroller
from .._units.setter import ChromiumBaseSetter
from .._units.states import PageStates
from .._units.waiter import BaseWaiter
from ..errors import (ContextLostError, CDPError, PageDisconnectedError, ElementLostError, JavaScriptError,
BrowserConnectError, LocatorError)
__ERROR__ = 'error'
class ChromiumBase(BasePage):
def __init__(self, browser, target_id=None):
super().__init__()
self._browser = browser
self._is_loading = None
self._root_id = None # object id
self._set = None
self._screencast = None
self._actions = None
self._states = None
self._has_alert = False
self._ready_state = None
self._rect = None
self._wait = None
self._scroll = None
self._console = None
self._upload_list = None
self._doc_got = False # 用于在LoadEventFired和FrameStoppedLoading间标记是否已获取doc
self._auto_handle_alert = None
self._load_end_time = 0
self._init_jss = []
self._disconnect_flag = False
self._type = 'ChromiumBase'
if not hasattr(self, '_listener'):
self._listener = None
self._d_set_runtime_settings()
self._connect_browser(target_id)
def __call__(self, locator, index=1, timeout=None):
return self.ele(locator, index, timeout)
def _d_set_runtime_settings(self):
pass
def _connect_browser(self, target_id=None):
self._is_reading = False
if not target_id:
if self.browser._ws_only:
tabs = self._run_cdp('Target.getTargets')['targetInfos']
_id = 'targetId'
else:
tabs = self.browser._driver.get(f'http://{self.browser.address}/json').json()
_id = 'id'
tabs = [(i[_id], i['url']) for i in tabs
if i['type'] in ('page', 'webview') and not i['url'].startswith('devtools://')]
dialog = None
if len(tabs) > 1:
for k, t in enumerate(tabs):
if t[1] == 'chrome://privacy-sandbox-dialog/notice':
dialog = k
elif not target_id:
target_id = t[0]
if target_id and dialog is not None:
break
if dialog is not None:
close_privacy_dialog(self, tabs[dialog][0])
else:
target_id = tabs[0][0]
self._driver_init(target_id)
if self._js_ready_state == 'complete' and self._ready_state is None:
self._get_document()
self._ready_state = 'complete'
def _driver_init(self, target_id):
self._is_loading = True
self._driver = self.browser._get_driver(target_id, self)
self._alert = Alert(self._auto_handle_alert)
self._driver.set_callback('Page.javascriptDialogOpening', self._on_alert_open, immediate=True)
self._driver.set_callback('Page.javascriptDialogClosed', self._on_alert_close)
self._driver.run('Page.enable')
self._driver.run('DOM.enable')
self._driver.run('Emulation.setFocusEmulationEnabled', enabled=True)
r = self._run_cdp('Page.getFrameTree')
for i in findall(r"'id': '(.*?)'", str(r)):
self.browser._frames[i] = self.tab_id
if not hasattr(self, '_frame_id'):
self._frame_id = r['frameTree']['frame']['id']
self._driver.set_callback('Page.frameStartedLoading', self._onFrameStartedLoading)
self._driver.set_callback('Page.frameNavigated', self._onFrameNavigated)
self._driver.set_callback('Page.domContentEventFired', self._onDomContentEventFired)
self._driver.set_callback('Page.loadEventFired', self._onLoadEventFired)
self._driver.set_callback('Page.frameStoppedLoading', self._onFrameStoppedLoading)
self._driver.set_callback('Page.frameAttached', self._onFrameAttached)
self._driver.set_callback('Page.frameDetached', self._onFrameDetached)
def _get_document(self, timeout=10):
if self._is_reading:
return
self._is_reading = True
timeout = max(timeout, 2)
end_time = perf_counter() + timeout
while perf_counter() < end_time:
try:
b_id = self._run_cdp('DOM.getDocument', _timeout=timeout)['root']['backendNodeId']
timeout = end_time - perf_counter()
timeout = 1 if timeout <= 1 else timeout
self._root_id = self._run_cdp('DOM.resolveNode', backendNodeId=b_id,
_timeout=timeout)['object']['objectId']
result = True
break
except PageDisconnectedError:
result = False
break
except:
timeout = end_time - perf_counter()
timeout = .5 if timeout <= 0 else timeout
sleep(.05)
else:
result = False
if result:
r = self._run_cdp('Page.getFrameTree', _ignore=PageDisconnectedError)
for i in findall(r"'id': '(.*?)'", str(r)):
self.browser._frames[i] = self.tab_id
self._is_loading = False
self._is_reading = False
return result
def _onFrameDetached(self, **kwargs):
self.browser._frames.pop(kwargs['frameId'], None)
def _onFrameAttached(self, **kwargs):
self.browser._frames[kwargs['frameId']] = self.tab_id
def _onFrameStartedLoading(self, **kwargs):
self.browser._frames[kwargs['frameId']] = self.tab_id
if kwargs['frameId'] == self._frame_id:
self._doc_got = False
self._ready_state = 'connecting'
self._is_loading = True
self._load_end_time = perf_counter() + self.timeouts.page_load
if self._load_mode == 'eager':
t = Thread(target=self._wait_to_stop)
t.daemon = True
t.start()
def _onFrameNavigated(self, **kwargs):
if kwargs['frame']['id'] == self._frame_id:
self._doc_got = False
self._ready_state = 'loading'
self._is_loading = True
if kwargs.get('type', None) == 'BackForwardCacheRestore':
self._get_document()
def _onDomContentEventFired(self, **kwargs):
if self._load_mode == 'eager':
self._run_cdp('Page.stopLoading')
if self._get_document(self._load_end_time - perf_counter() - .1):
self._doc_got = True
self._ready_state = 'interactive'
def _onLoadEventFired(self, **kwargs):
if self._doc_got is False and self._get_document(self._load_end_time - perf_counter() - .1):
self._doc_got = True
self._ready_state = 'complete'
def _onFrameStoppedLoading(self, **kwargs):
self.browser._frames[kwargs['frameId']] = self.tab_id
if kwargs['frameId'] == self._frame_id:
if self._doc_got is False:
self._get_document(self._load_end_time - perf_counter() - .1)
self._ready_state = 'complete'
def _onFileChooserOpened(self, **kwargs):
if self._upload_list:
if 'backendNodeId' not in kwargs:
raise RuntimeError(_S._lang.join(_S._lang.CANNOT_INPUT_FILE))
files = self._upload_list if kwargs['mode'] == 'selectMultiple' else self._upload_list[:1]
self._run_cdp('DOM.setFileInputFiles', files=files, backendNodeId=kwargs['backendNodeId'])
self.driver.set_callback('Page.fileChooserOpened', None)
self._run_cdp('Page.setInterceptFileChooserDialog', enabled=False)
self._upload_list = None
def _wait_to_stop(self):
end_time = perf_counter() + self.timeouts.page_load
while perf_counter() < end_time:
sleep(.02)
if self._ready_state in ('interactive', 'complete') and self._is_loading:
self.stop_loading()
# ----------挂件----------
@property
def wait(self):
if self._wait is None:
self._wait = BaseWaiter(self)
return self._wait
@property
def set(self):
if self._set is None:
self._set = ChromiumBaseSetter(self)
return self._set
@property
def screencast(self):
if self._screencast is None:
self._screencast = Screencast(self)
return self._screencast
@property
def actions(self):
if self._actions is None:
self._actions = Actions(self)
self.wait.doc_loaded()
return self._actions
@property
def listen(self):
if self._listener is None:
self._listener = Listener(self)
return self._listener
@property
def states(self):
if self._states is None:
self._states = PageStates(self)
return self._states
@property
def scroll(self):
self.wait.doc_loaded()
if self._scroll is None:
self._scroll = PageScroller(self)
return self._scroll
@property
def rect(self):
# self.wait.doc_loaded()
if self._rect is None:
self._rect = TabRect(self)
return self._rect
@property
def console(self):
if self._console is None:
self._console = Console(self)
return self._console
@property
def timeout(self):
return self._timeouts.base
@property
def timeouts(self):
return self._timeouts
# ----------挂件结束----------
@property
def browser(self):
return self._browser
@property
def driver(self):
if self._driver is None:
raise BrowserConnectError(_S._lang.BROWSER_DISCONNECTED)
return self._driver
@property
def title(self):
return self._run_cdp_loaded('Target.getTargetInfo', targetId=self._target_id)['targetInfo']['title']
@property
def url(self):
return self._run_cdp_loaded('Target.getTargetInfo', targetId=self._target_id)['targetInfo']['url']
@property
def _browser_url(self):
return self.url
@property
def html(self):
self.wait.doc_loaded()
return self._run_cdp('DOM.getOuterHTML', objectId=self._root_id)['outerHTML']
@property
def json(self):
try:
return loads(self('t:pre', timeout=.5).text)
except JSONDecodeError:
return None
@property
def tab_id(self):
return self.driver.id
@property
def _target_id(self):
return self.driver.id
@property
def active_ele(self):
return self._run_js_loaded('return document.activeElement;')
@property
def load_mode(self):
return self._load_mode
@property
def user_agent(self):
return self._run_cdp('Runtime.evaluate', expression='navigator.userAgent;')['result']['value']
@property
def upload_list(self):
return self._upload_list
@property
def session(self):
if self._session is None:
self._create_session()
return self._session
@property
def _js_ready_state(self):
try:
return self._run_cdp('Runtime.evaluate', expression='document.readyState;', _timeout=3)['result']['value']
except ContextLostError:
return None
except TimeoutError:
return 'timeout'
def run_cdp(self, cmd, **cmd_args):
r = self.driver.run(cmd, **cmd_args)
return r if __ERROR__ not in r else raise_error(r, self.browser, user=True)
def run_cdp_loaded(self, cmd, **cmd_args):
self.wait.doc_loaded()
r = self.driver.run(cmd, **cmd_args)
return r if __ERROR__ not in r else raise_error(r, self.browser, user=True)
def _run_cdp(self, cmd, **cmd_args):
ignore = cmd_args.pop('_ignore', None)
r = self.driver.run(cmd, **cmd_args)
return r if __ERROR__ not in r else raise_error(r, self.browser, ignore)
def _run_cdp_loaded(self, cmd, **cmd_args):
self.wait.doc_loaded()
return self._run_cdp(cmd, **cmd_args)
def run_js(self, script, *args, as_expr=False, timeout=None):
return self._run_js(script, *args, as_expr=as_expr, timeout=timeout)
def run_js_loaded(self, script, *args, as_expr=False, timeout=None):
self.wait.doc_loaded()
return self._run_js(script, *args, as_expr=as_expr, timeout=timeout)
def _run_js(self, script, *args, as_expr=False, timeout=None):
return run_js(self, script, as_expr, self.timeouts.script if timeout is None else timeout, args)
def _run_js_loaded(self, script, *args, as_expr=False, timeout=None):
self.wait.doc_loaded()
return run_js(self, script, as_expr, self.timeouts.script if timeout is None else timeout, args)
def run_async_js(self, script, *args, as_expr=False):
run_js(self, script, as_expr, 0, args)
def get(self, url, show_errmsg=False, retry=None, interval=None, timeout=None):
retry, interval, is_file = self._before_connect(url, retry, interval)
self._url_available = self._d_connect(self._url, times=retry, interval=interval,
show_errmsg=show_errmsg, timeout=timeout)
return self._url_available
def cookies(self, all_domains=False, all_info=False):
txt = 'Storage' if all_domains else 'Network'
cookies = self._run_cdp_loaded(f'{txt}.getCookies')['cookies']
if all_info:
r = cookies
else:
r = [{'name': cookie['name'], 'value': cookie['value'], 'domain': cookie['domain']} for cookie in cookies]
return CookiesList(r)
def ele(self, locator, index=1, timeout=None):
return self._ele(locator, timeout=timeout, index=index, method='ele()')
def eles(self, locator, timeout=None):
return self._ele(locator, timeout=timeout, index=None)
def s_ele(self, locator=None, index=1, timeout=None):
if timeout is None:
timeout = self.timeout
return (NoneElement(self, method='s_ele()', args={'locator': locator, 'index': index, 'timeout': timeout})
if locator and not self.wait.eles_loaded(locator, timeout=timeout)
else make_session_ele(self, locator, index=index, method='s_ele()'))
def s_eles(self, locator, timeout=None):
return (make_session_ele(self, locator, index=None)
if self.wait.eles_loaded(locator, timeout=timeout) else SessionElementsList())
def _find_elements(self, locator, timeout, index=1, relative=False, raise_err=None):
if isinstance(locator, (str, tuple)):
loc = get_loc(locator)[1]
elif locator._type in ('ChromiumElement', 'ChromiumFrame'):
return locator
else:
raise LocatorError(_S._lang.join(ALLOW_TYPE=_S._lang.ELE_OR_LOC, CURR_VAL=locator))
self.wait.doc_loaded()
end_time = perf_counter() + timeout
search_ids = []
timeout = .5 if timeout <= 0 else timeout
result = self.driver.run('DOM.performSearch', query=loc, _timeout=timeout, includeUserAgentShadowDOM=True)
if not result or __ERROR__ in result:
num = 0
else:
num = result['resultCount']
search_ids.append(result['searchId'])
while True:
if num > 0:
from_index = index_arg = 0
if index is None:
end_index = num
index_arg = None
elif index < 0:
from_index = index + num
end_index = from_index + 1
else:
from_index = index - 1
end_index = from_index + 1
if from_index <= num - 1:
nIds = self._driver.run('DOM.getSearchResults', searchId=result['searchId'],
fromIndex=from_index, toIndex=end_index)
if __ERROR__ not in nIds:
if nIds['nodeIds'][0] != 0:
r = make_chromium_eles(self, _ids=nIds['nodeIds'], index=index_arg,
is_obj_id=False, ele_only=True)
if r is not False:
break
elif nIds[__ERROR__] == 'connection disconnected':
raise PageDisconnectedError
if perf_counter() >= end_time:
return NoneElement(self) if index is not None else ChromiumElementsList(owner=self)
sleep(.01)
timeout = end_time - perf_counter()
timeout = .5 if timeout <= 0 else timeout
result = self.driver.run('DOM.performSearch', query=loc, _timeout=timeout, includeUserAgentShadowDOM=True)
if result and __ERROR__ not in result:
num = result['resultCount']
search_ids.append(result['searchId'])
elif result and result[__ERROR__] == 'connection disconnected':
raise PageDisconnectedError
for _id in search_ids:
self._driver.run('DOM.discardSearchResults', searchId=_id)
return r
def refresh(self, ignore_cache=False):
self._is_loading = True
self._run_cdp('Page.reload', ignoreCache=ignore_cache)
self.wait.load_start()
def forward(self, steps=1):
self._forward_or_back(steps)
def back(self, steps=1):
self._forward_or_back(-steps)
def _forward_or_back(self, steps):
if steps == 0:
return
history = self._run_cdp('Page.getNavigationHistory')
index = history['currentIndex']
history = history['entries']
direction = 1 if steps > 0 else -1
curr_url = history[index]['url']
nid = None
for num in range(abs(steps)):
for i in history[index::direction]:
index += direction
if i['url'] != curr_url:
nid = i['id']
curr_url = i['url']
break
if nid:
self._is_loading = True
self._run_cdp('Page.navigateToHistoryEntry', entryId=nid)
def stop_loading(self):
try:
self._run_cdp('Page.stopLoading')
end_time = perf_counter() + 5
while self._ready_state != 'complete' and perf_counter() < end_time:
sleep(.02)
except (PageDisconnectedError, CDPError):
pass
finally:
self._ready_state = 'complete'
def remove_ele(self, loc_or_ele):
if not loc_or_ele:
return
ele = self._ele(loc_or_ele, raise_err=False)
if ele:
self._run_cdp('DOM.removeNode', nodeId=ele._node_id, _ignore=ElementLostError)
def add_ele(self, html_or_info, insert_to=None, before=None):
if isinstance(html_or_info, str):
insert_to = self.ele(insert_to) if insert_to else self.ele('t:body')
args = [html_or_info, insert_to]
if before:
args.append(insert_to.ele(before))
js = '''
ele = document.createElement(null);
arguments[1].insertBefore(ele, arguments[2]);
ele.outerHTML = arguments[0];
return arguments[2].previousElementSibling;
'''
else:
js = '''
ele = document.createElement(null);
arguments[1].appendChild(ele);
ele.outerHTML = arguments[0];
return arguments[1].lastElementChild;
'''
elif isinstance(html_or_info, tuple):
args = [html_or_info[0], html_or_info[1]]
txt = ''
if insert_to:
args.append(self.ele(insert_to))
if before:
args.append(self.ele(before))
txt = '''
arguments[2].insertBefore(ele, arguments[3]);
'''
else:
txt = '''
arguments[2].appendChild(ele);
'''
js = f'''
ele = document.createElement(arguments[0]);
for(let k in arguments[1]){{
if(k=="innerHTML"){{ele.innerHTML=arguments[1][k]}}
else if(k=="innerText"){{ele.innerText=arguments[1][k]}}
else{{ele.setAttribute(k, arguments[1][k]);}}
}}
{txt}
return ele;
'''
else:
raise ValueError(_S._lang.join(_S._lang.INCORRECT_VAL_, 'html_or_info', ALLOW_TYPE='html, tuple',
TIP=_S._lang.NEW_ELE_INFO, CURR_VAL=html_or_info))
try:
ele = self._run_js(js, *args)
except JavaScriptError:
raise RuntimeError(_S._lang.join(_S._lang.DICT_TO_NEW_ELE))
return ele
def get_frame(self, loc_ind_ele, timeout=None):
return get_frame(self, loc_ind_ele=loc_ind_ele, timeout=timeout)
def get_frames(self, locator=None, timeout=None):
locator = locator or 'xpath://*[name()="iframe" or name()="frame"]'
frames = self._ele(locator, timeout=timeout, index=None, raise_err=False)
return ChromiumElementsList(self, frames)
def session_storage(self, item=None):
js = f'sessionStorage.getItem("{item}")' if item else 'sessionStorage'
return self._run_js_loaded(js, as_expr=True)
def local_storage(self, item=None):
js = f'localStorage.getItem("{item}")' if item else 'localStorage'
return self._run_js_loaded(js, as_expr=True)
def get_screenshot(self, path=None, name=None, as_bytes=None, as_base64=None,
full_page=False, left_top=None, right_bottom=None):
return self._get_screenshot(path=path, name=name, as_bytes=as_bytes, as_base64=as_base64,
full_page=full_page, left_top=left_top, right_bottom=right_bottom)
def add_init_js(self, script):
js_id = self._run_cdp('Page.addScriptToEvaluateOnNewDocument', source=script,
includeCommandLineAPI=True)['identifier']
self._init_jss.append(js_id)
return js_id
def remove_init_js(self, script_id=None):
if script_id is None:
for js_id in self._init_jss:
self._run_cdp('Page.removeScriptToEvaluateOnNewDocument', identifier=js_id)
self._init_jss.clear()
elif script_id in self._init_jss:
self._run_cdp('Page.removeScriptToEvaluateOnNewDocument', identifier=script_id)
self._init_jss.remove(script_id)
def clear_cache(self, session_storage=True, local_storage=True, cache=True, cookies=True):
if session_storage and local_storage and cache and cookies:
self._run_cdp_loaded("Storage.clearDataForOrigin", origin="*", storageTypes="all")
if session_storage or local_storage:
self._run_cdp_loaded('DOMStorage.enable')
i = self._run_cdp('Storage.getStorageKeyForFrame', frameId=self._frame_id)['storageKey']
if session_storage:
self._run_cdp('DOMStorage.clear', storageId={'storageKey': i, 'isLocalStorage': False})
if local_storage:
self._run_cdp('DOMStorage.clear', storageId={'storageKey': i, 'isLocalStorage': True})
self._run_cdp_loaded('DOMStorage.disable')
if cache:
self._run_cdp_loaded('Network.clearBrowserCache')
if cookies:
self._run_cdp_loaded('Network.clearBrowserCookies')
def disconnect(self):
if self._driver:
self._disconnect_flag = True
self._driver.stop()
self.browser._all_drivers.get(self._driver.id, set()).discard(self._driver)
self._disconnect_flag = False
def reconnect(self, wait=0):
t_id = self._target_id
self.disconnect()
sleep(wait)
self.browser.reconnect()
self._driver = self.browser._get_driver(t_id, self)
self._driver_init(t_id)
self._get_document()
def handle_alert(self, accept=True, send=None, timeout=None, next_one=False):
if not isinstance(accept, bool):
return self._handle_alert(accept=accept, send=send, timeout=timeout, next_one=next_one)
r = self._handle_alert(accept=accept, send=send, timeout=timeout, next_one=next_one)
while self._has_alert:
sleep(.0001)
return r
def _handle_alert(self, accept=True, send=None, timeout=None, next_one=False):
if next_one:
self._alert.handle_next = accept
self._alert.next_text = send
return
if timeout is None:
timeout = self.timeout
timeout = .1 if timeout <= 0 else timeout
end_time = perf_counter() + timeout
while not self._alert.activated and perf_counter() < end_time:
sleep(.01)
if not self._alert.activated:
return False
res_text = self._alert.text
if not isinstance(accept, bool):
return res_text
d = {'accept': accept, '_timeout': 0}
if self._alert.type == 'prompt' and send is not None:
d['promptText'] = send
self.driver.run('Page.handleJavaScriptDialog', **d)
return res_text
def _on_alert_open(self, **kwargs):
self._alert.activated = True
self._alert.text = kwargs['message']
self._alert.type = kwargs['type']
self._alert.defaultPrompt = kwargs.get('defaultPrompt', None)
self._alert.response_accept = None
self._alert.response_text = None
self._has_alert = True
if self._alert.auto is not None:
if self._alert.auto != 'close':
self._handle_alert(self._alert.auto)
elif _S.auto_handle_alert is not None:
self._handle_alert(_S.auto_handle_alert)
elif self._alert.handle_next is not None:
self._handle_alert(self._alert.handle_next, self._alert.next_text)
self._alert.handle_next = None
def _on_alert_close(self, **kwargs):
self._alert.activated = False
self._alert.text = None
self._alert.type = None
self._alert.defaultPrompt = None
self._alert.response_accept = kwargs.get('result')
self._alert.response_text = kwargs['userInput']
self._has_alert = False
def _wait_loaded(self, timeout=None):
if timeout is None:
timeout = self.timeouts.page_load
end_time = perf_counter() + timeout
while perf_counter() < end_time:
if self._ready_state == 'complete':
return True
elif self._load_mode == 'eager' and self._ready_state in ('interactive',
'complete') and not self._is_loading:
return True
sleep(.01)
try:
self.stop_loading()
except CDPError:
pass
return False
def _d_connect(self, to_url, times=0, interval=1, show_errmsg=False, timeout=None):
err = None
self._is_loading = True
timeout = timeout if timeout is not None else self.timeouts.page_load
for t in range(times + 1):
err = None
end_time = perf_counter() + timeout
try:
result = self._run_cdp('Page.navigate', frameId=self._frame_id, url=to_url, _timeout=timeout)
if 'errorText' in result:
err = ConnectionError(_S._lang.join(_S._lang.CONNECT_ERR, INFO=result['errorText']))
except TimeoutError:
err = TimeoutError(_S._lang.join(_S._lang.TIMEOUT_, _S._lang.PAGE_CONNECT, timeout))
if err:
if t < times:
sleep(interval)
if show_errmsg:
print(f'{_S._lang.RETRY}{t + 1} {to_url}')
end_time1 = end_time - perf_counter()
while self._ready_state not in ('loading', 'complete') and perf_counter() < end_time1: # 等待出错信息显示
sleep(.01)
self.stop_loading()
continue
if self._load_mode == 'none':
return True
yu = end_time - perf_counter()
ok = self._wait_loaded(1 if yu <= 0 else yu)
if not ok:
err = TimeoutError(_S._lang.join(_S._lang.TIMEOUT_, _S._lang.PAGE_CONNECT, timeout))
if t < times:
sleep(interval)
if show_errmsg:
print(f'{_S._lang.RETRY}{t + 1} {to_url}')
continue
if not err:
break
if err:
if show_errmsg:
raise err if err is not None else ConnectionError(_S._lang.join(_S._lang.CONNECT_ERR))
return False
return True
def _get_screenshot(self, path=None, name=None, as_bytes=None, as_base64=None,
full_page=False, left_top=None, right_bottom=None, ele=None):
if as_bytes:
if as_bytes is True:
pic_type = 'png'
else:
if as_bytes not in ('jpg', 'jpeg', 'png', 'webp'):
raise ValueError(_S._lang.join(_S._lang.INCORRECT_VAL_, 'as_bytes',
ALLOW_VAL='"jpg", "jpeg", "png", "webp"', CURR_VAL=as_bytes))
pic_type = 'jpeg' if as_bytes == 'jpg' else as_bytes
elif as_base64:
if as_base64 is True:
pic_type = 'png'
else:
if as_base64 not in ('jpg', 'jpeg', 'png', 'webp'):
raise ValueError(_S._lang.join(_S._lang.INCORRECT_VAL_, 'as_base64',
ALLOW_VAL='"jpg", "jpeg", "png", "webp"', CURR_VAL=as_base64))
pic_type = 'jpeg' if as_base64 == 'jpg' else as_base64
else:
path = str(path).rstrip('\\/') if path else '.'
if not path.endswith(('.jpg', '.jpeg', '.png', '.webp')):
if not name:
name = f'{self.title}.jpg'
elif not name.endswith(('.jpg', '.jpeg', '.png', '.webp')):
name = f'{name}.jpg'
path = f'{path}{sep}{make_valid_name(name)}'
path = Path(path)
pic_type = path.suffix.lower()
pic_type = 'jpeg' if pic_type == '.jpg' else pic_type[1:]
if full_page:
width, height = self.rect.size
if width == 0 or height == 0:
raise RuntimeError(_S._lang.join(_S._lang.ZERO_PAGE_SIZE))
vp = {'x': 0, 'y': 0, 'width': width, 'height': height, 'scale': 1}
args = {'format': pic_type, 'captureBeyondViewport': True, 'clip': vp}
else:
if left_top or right_bottom:
if not left_top:
left_top = (0, 0)
if not right_bottom:
right_bottom = self.rect.size
x, y = left_top
w = right_bottom[0] - x
h = right_bottom[1] - y
v = not (location_in_viewport(self, x, y) and
location_in_viewport(self, right_bottom[0], right_bottom[1]))
if v and (self._run_js('return document.body.scrollHeight > window.innerHeight;') and
not self._run_js('return document.body.scrollWidth > window.innerWidth;')):
x += 10
vp = {'x': x, 'y': y, 'width': w, 'height': h, 'scale': 1}
args = {'format': pic_type, 'captureBeyondViewport': v, 'clip': vp}
else:
args = {'format': pic_type}
if pic_type == 'jpeg':
args['quality'] = 100
png = self._run_cdp_loaded('Page.captureScreenshot', **args)['data']
if as_base64:
return png
from base64 import b64decode
png = b64decode(png)
if as_bytes:
return png
path.parent.mkdir(parents=True, exist_ok=True)
with open(path, 'wb') as f:
f.write(png)
return str(path.absolute())
class Timeout(object):
def __init__(self, base=None, page_load=None, script=None):
self.base = 10 if base is None else base
self.page_load = 30 if page_load is None else page_load
self.script = 30 if script is None else script
def __repr__(self):
return str({'base': self.base, 'page_load': self.page_load, 'script': self.script})
@property
def as_dict(self):
return {'base': self.base, 'page_load': self.page_load, 'script': self.script}
class Alert(object):
def __init__(self, auto=None):
self.activated = False
self.text = None
self.type = None
self.defaultPrompt = None
self.response_accept = None
self.response_text = None
self.handle_next = None
self.next_text = None
self.auto = auto
def close_privacy_dialog(page, tid):
"""关闭隐私声明弹窗
:param page: ChromiumBase对象
:param tid: tab id
:return: None
"""
try:
driver = page.browser._get_driver(tid)
driver.run('Runtime.enable')
driver.run('DOM.enable')
driver.run('DOM.getDocument')
sid = driver.run('DOM.performSearch', query='//*[name()="privacy-sandbox-notice-dialog-app"]',
includeUserAgentShadowDOM=True)['searchId']
r = driver.run('DOM.getSearchResults', searchId=sid, fromIndex=0, toIndex=1)['nodeIds'][0]
end_time = perf_counter() + 3
while perf_counter() < end_time:
try:
r = driver.run('DOM.describeNode', nodeId=r)['node']['shadowRoots'][0]['backendNodeId']
break
except KeyError:
pass
sleep(.05)
driver.run('DOM.discardSearchResults', searchId=sid)
r = driver.run('DOM.resolveNode', backendNodeId=r)['object']['objectId']
r = driver.run('Runtime.callFunctionOn', objectId=r,
functionDeclaration='function(){return this.getElementById("ackButton");}')['result']['objectId']
driver.run('Runtime.callFunctionOn', objectId=r, functionDeclaration='function(){return this.click();}')
driver.close()
except:
pass
@@ -0,0 +1,681 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from pathlib import Path
from typing import Union, Tuple, Any, Optional, Literal
from requests import Session
from .chromium_page import ChromiumPage
from .chromium_tab import ChromiumTab
from .mix_tab import MixTab
from .web_page import WebPage
from .._base.base import BasePage
from .._base.chromium import Chromium
from .._base.driver import Driver
from .._elements.chromium_element import ChromiumElement
from .._elements.session_element import SessionElement
from .._functions.cookies import CookiesList
from .._functions.elements import SessionElementsList, ChromiumElementsList
from .._pages.chromium_frame import ChromiumFrame
from .._units.actions import Actions
from .._units.console import Console
from .._units.listener import Listener
from .._units.rect import TabRect, FrameRect
from .._units.screencast import Screencast
from .._units.scroller import Scroller, PageScroller
from .._units.setter import ChromiumBaseSetter
from .._units.states import PageStates
from .._units.waiter import BaseWaiter
PIC_TYPE = Literal['jpg', 'jpeg', 'png', 'webp', True]
class ChromiumBase(BasePage):
"""标签页、Frame、Page基类"""
_tab: Union[ChromiumTab, MixTab, ChromiumFrame, ChromiumPage, WebPage] = ...
_browser: Chromium = ...
_driver: Optional[Driver] = ...
_frame_id: str = ...
_is_reading: bool = ...
_is_timeout: bool = ...
_timeouts: Timeout = ...
_first_run: bool = ...
_is_loading: Optional[bool] = ...
_load_mode: str = ...
_scroll: Optional[Scroller] = ...
_url: str = ...
_root_id: Optional[str] = ...
_upload_list: Optional[list] = ...
_wait: Optional[BaseWaiter] = ...
_set: Optional[ChromiumBaseSetter] = ...
_screencast: Optional[Screencast] = ...
_actions: Optional[Actions] = ...
_listener: Optional[Listener] = ...
_states: Optional[PageStates] = ...
_alert: Alert = ...
_has_alert: bool = ...
_auto_handle_alert: Optional[bool] = ...
_doc_got: bool = ...
_load_end_time: float = ...
_init_jss: list = ...
_ready_state: Optional[str] = ...
_rect: Optional[TabRect] = ...
_console: Optional[Console] = ...
_disconnect_flag: bool = ...
_type: str = ...
def __init__(self,
browser: Chromium,
tab_id: str = None):
"""
:param browser: Chromium
:param tab_id: 要控制的tab id,不指定默认为激活的标签页
"""
...
def __call__(self,
locator: Union[Tuple[str, str], str, ChromiumElement],
index: int = 1,
timeout: float = None) -> ChromiumElement:
"""在内部查找元素
例:ele = page('@id=ele_id')
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 获取第几个元素,从1开始,可传入负数获取倒数第几个
:param timeout: 超时时间(秒)
:return: ChromiumElement对象
"""
...
def _d_set_runtime_settings(self) -> None: ...
def _connect_browser(self, target_id: str = None) -> None:
"""连接浏览器,在第一次时运行
:param target_id: 要控制的target id,不指定默认为激活的标签页
:return: None
"""
...
def _driver_init(self, target_id: str) -> None:
"""新建页面、页面刷新后要进行的cdp参数初始化
:param target_id: 要跳转到的target id
:return: None
"""
...
def _get_document(self, timeout: float = 10) -> bool:
"""获取页面文档
:param timeout: 超时时间(秒)
:return: 是否获取成功
"""
...
def _onFrameDetached(self, **kwargs) -> None: ...
def _onFrameAttached(self, **kwargs) -> None: ...
def _onFrameStartedLoading(self, **kwargs):
"""页面开始加载时执行"""
...
def _onFrameNavigated(self, **kwargs):
"""页面跳转时执行"""
...
def _onDomContentEventFired(self, **kwargs):
"""在页面刷新、变化后重新读取页面内容"""
...
def _onLoadEventFired(self, **kwargs):
"""在页面刷新、变化后重新读取页面内容"""
...
def _onFrameStoppedLoading(self, **kwargs):
"""页面加载完成后执行"""
...
def _onFileChooserOpened(self, **kwargs):
"""文件选择框打开时执行"""
...
def _wait_to_stop(self):
"""eager策略超时时使页面停止加载"""
...
@property
def wait(self) -> BaseWaiter:
"""返回用于等待的对象"""
...
@property
def set(self) -> ChromiumBaseSetter:
"""返回用于设置的对象"""
...
@property
def screencast(self) -> Screencast:
"""返回用于录屏的对象"""
...
@property
def actions(self) -> Actions:
"""返回用于执行动作链的对象"""
...
@property
def listen(self) -> Listener:
"""返回用于聆听数据包的对象"""
...
@property
def states(self) -> PageStates:
"""返回用于获取状态信息的对象"""
...
@property
def scroll(self) -> PageScroller:
"""返回用于滚动滚动条的对象"""
...
@property
def rect(self) -> Union[TabRect, FrameRect]:
"""返回获取窗口坐标和大小的对象"""
...
@property
def console(self) -> Console:
"""返回获取控制台信息的对象"""
...
@property
def timeout(self) -> float:
"""返回timeout设置"""
...
@property
def timeouts(self) -> Timeout:
"""返回timeouts设置"""
...
@property
def browser(self) -> Chromium:
"""返回浏览器对象"""
...
@property
def driver(self) -> Driver:
"""返回用于控制浏览器的Driver对象"""
...
@property
def title(self) -> str:
"""返回当前页面title"""
...
@property
def url(self) -> str:
"""返回当前页面url"""
...
@property
def _browser_url(self) -> str:
"""用于被MixTab覆盖"""
...
@property
def html(self) -> str:
"""返回当前页面html文本"""
...
@property
def json(self) -> Union[dict, None]:
"""当返回内容是json格式时,返回对应的字典,非json格式时返回None"""
...
@property
def tab_id(self) -> str:
"""返回当前标签页id"""
...
@property
def _target_id(self) -> str:
"""返回当前标签页id"""
...
@property
def active_ele(self) -> ChromiumElement:
"""返回当前焦点所在元素"""
...
@property
def load_mode(self) -> Literal['none', 'normal', 'eager']:
"""返回页面加载策略,有3种:'none'、'normal'、'eager'"""
...
@property
def user_agent(self) -> str:
"""返回user agent"""
...
@property
def upload_list(self) -> list:
"""返回等待上传文件列表"""
...
@property
def session(self) -> Session:
"""返回用于转换模式或download的Session对象"""
...
@property
def _js_ready_state(self) -> str:
"""返回js获取的ready state信息"""
...
def run_cdp(self, cmd: str, **cmd_args) -> dict:
"""执行Chrome DevTools Protocol语句
:param cmd: 协议项目
:param cmd_args: 参数
:return: 执行的结果
"""
...
def run_cdp_loaded(self, cmd: str, **cmd_args) -> dict:
"""执行Chrome DevTools Protocol语句,执行前等待页面加载完毕
:param cmd: 协议项目
:param cmd_args: 参数
:return: 执行的结果
"""
...
def _run_cdp(self, cmd: str, **cmd_args) -> dict:
"""执行Chrome DevTools Protocol语句
:param cmd: 协议项目
:param cmd_args: 参数
:return: 执行的结果
"""
...
def _run_cdp_loaded(self, cmd: str, **cmd_args) -> dict:
"""执行Chrome DevTools Protocol语句,执行前等待页面加载完毕
:param cmd: 协议项目
:param cmd_args: 参数
:return: 执行的结果
"""
...
def run_js(self, script: Union[str, Path], *args, as_expr: bool = False, timeout: float = None) -> Any:
"""运行javascript代码
:param script: js文本或js文件路径
:param args: 参数,按顺序在js文本中对应arguments[0]、arguments[1]...
:param as_expr: 是否作为表达式运行,为True时args无效
:param timeout: js超时时间(秒),为None则使用页面timeouts.script设置
:return: 运行的结果
"""
...
def run_js_loaded(self, script: Union[str, Path], *args, as_expr: bool = False, timeout: float = None) -> Any:
"""运行javascript代码,执行前等待页面加载完毕
:param script: js文本或js文件路径
:param args: 参数,按顺序在js文本中对应arguments[0]、arguments[1]...
:param as_expr: 是否作为表达式运行,为True时args无效
:param timeout: js超时时间(秒),为None则使用页面timeouts.script属性值
:return: 运行的结果
"""
...
def _run_js(self, script: Union[str, Path], *args, as_expr: bool = False, timeout: float = None) -> Any:
"""运行javascript代码
:param script: js文本或js文件路径
:param args: 参数,按顺序在js文本中对应arguments[0]、arguments[1]...
:param as_expr: 是否作为表达式运行,为True时args无效
:param timeout: js超时时间(秒),为None则使用页面timeouts.script设置
:return: 运行的结果
"""
...
def _run_js_loaded(self, script: Union[str, Path], *args, as_expr: bool = False, timeout: float = None) -> Any:
"""运行javascript代码,执行前等待页面加载完毕
:param script: js文本或js文件路径
:param args: 参数,按顺序在js文本中对应arguments[0]、arguments[1]...
:param as_expr: 是否作为表达式运行,为True时args无效
:param timeout: js超时时间(秒),为None则使用页面timeouts.script属性值
:return: 运行的结果
"""
...
def run_async_js(self, script: Union[str, Path], *args, as_expr: bool = False) -> None:
"""以异步方式执行js代码或js文件路径
:param script: js文本
:param args: 参数,按顺序在js文本中对应arguments[0]、arguments[1]...
:param as_expr: 是否作为表达式运行,为True时args无效
:return: None
"""
...
def get(self, url: str, show_errmsg: bool = False, retry: int = None,
interval: float = None, timeout: float = None) -> Union[None, bool]:
"""访问url
:param url: 目标url
:param show_errmsg: 是否显示和抛出异常
:param retry: 重试次数,为None时使用页面对象retry_times属性值
:param interval: 重试间隔(秒),为None时使用页面对象retry_interval属性值
:param timeout: 连接超时时间(秒),为None时使用页面对象timeouts.page_load属性值
:return: 目标url是否可用
"""
...
def cookies(self, all_domains: bool = False, all_info: bool = False) -> CookiesList:
"""返回cookies信息
:param all_domains: 是否返回所有域的cookies
:param all_info: 是否返回所有信息,为False时只返回name、value、domain
:return: cookies信息
"""
...
def ele(self,
locator: Union[Tuple[str, str], str, ChromiumElement, ChromiumFrame],
index: int = 1,
timeout: float = None) -> ChromiumElement:
"""获取一个符合条件的元素对象
:param locator: 定位符或元素对象
:param index: 获取第几个元素,从1开始,可传入负数获取倒数第几个
:param timeout: 查找超时时间(秒),默认与页面等待时间一致
:return: ChromiumElement对象
"""
...
def eles(self,
locator: Union[Tuple[str, str], str],
timeout: float = None) -> ChromiumElementsList:
"""获取所有符合条件的元素对象
:param locator: 定位符或元素对象
:param timeout: 查找超时时间(秒),默认与页面等待时间一致
:return: ChromiumElement对象组成的列表
"""
...
def s_ele(self,
locator: Union[Tuple[str, str], str] = None,
index: int = 1,
timeout: float = None) -> SessionElement:
"""查找一个符合条件的元素以SessionElement形式返回,处理复杂页面时效率很高
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param timeout: 查找元素超时时间(秒),默认与页面等待时间一致
:return: SessionElement对象或属性、文本
"""
...
def s_eles(self,
locator: Union[Tuple[str, str], str],
timeout: float = None) -> SessionElementsList:
"""查找所有符合条件的元素以SessionElement列表形式返回
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param timeout: 查找元素超时时间(秒),默认与页面等待时间一致
:return: SessionElement对象组成的列表
"""
...
def _find_elements(self,
locator: Union[Tuple[str, str], str, ChromiumElement, ChromiumFrame],
timeout: float,
index: Optional[int] = 1,
relative: bool = False,
raise_err: bool = None) -> Union[ChromiumElement, ChromiumFrame, ChromiumElementsList]:
"""执行元素查找
:param locator: 定位符或元素对象
:param timeout: 查找超时时间(秒)
:param index: 第几个结果,从1开始,可传入负数获取倒数第几个,为None返回所有
:param relative: MixTab用的表示是否相对定位的参数
:param raise_err: 找不到元素是是否抛出异常,为None时根据全局设置
:return: ChromiumElement对象或元素对象组成的列表
"""
...
def refresh(self, ignore_cache: bool = False) -> None:
"""刷新当前页面
:param ignore_cache: 是否忽略缓存
:return: None
"""
...
def forward(self, steps: int = 1) -> None:
"""在浏览历史中前进若干步
:param steps: 前进步数
:return: None
"""
...
def back(self, steps: int = 1) -> None:
"""在浏览历史中后退若干步
:param steps: 后退步数
:return: None
"""
...
def _forward_or_back(self, steps: int) -> None:
"""执行浏览器前进或后退,会跳过url相同的历史记录
:param steps: 步数
:return: None
"""
...
def stop_loading(self) -> None:
"""页面停止加载"""
...
def remove_ele(self, loc_or_ele: Union[ChromiumElement, ChromiumFrame, str, Tuple[str, str]]) -> None:
"""从页面上删除一个元素
:param loc_or_ele: 元素对象或定位符
:return: None
"""
...
def add_ele(self,
html_or_info: Union[str, Tuple[str, dict]],
insert_to: Union[ChromiumElement, str, Tuple[str, str], None] = None,
before: Union[ChromiumElement, str, Tuple[str, str], None] = None) -> Union[
ChromiumElement, ChromiumFrame]:
"""新建一个元素
:param html_or_info: 新元素的html文本或信息。信息格式为:(tag, {attr1: value, ...})
:param insert_to: 插入到哪个元素中,可接收元素对象和定位符,为None且为html添加到body,不为html不插入
:param before: 在哪个子节点前面插入,可接收对象和定位符,为None插入到父元素末尾
:return: 元素对象
"""
...
def get_frame(self,
loc_ind_ele: Union[str, int, tuple, ChromiumFrame, ChromiumElement],
timeout: float = None) -> ChromiumFrame:
"""获取页面中一个frame对象
:param loc_ind_ele: 定位符、iframe序号、ChromiumFrame对象,序号从1开始,可传入负数获取倒数第几个
:param timeout: 查找元素超时时间(秒)
:return: ChromiumFrame对象
"""
...
def get_frames(self,
locator: Union[str, tuple] = None,
timeout: float = None) -> ChromiumElementsList:
"""获取所有符合条件的frame对象
:param locator: 定位符,为None时返回所有
:param timeout: 查找超时时间(秒)
:return: ChromiumFrame对象组成的列表
"""
...
def session_storage(self, item: str = None) -> Union[str, dict, None]:
"""返回sessionStorage信息,不设置item则获取全部
:param item: 要获取的项,不设置则返回全部
:return: sessionStorage一个或所有项内容
"""
...
def local_storage(self, item: str = None) -> Union[str, dict, None]:
"""返回localStorage信息,不设置item则获取全部
:param item: 要获取的项目,不设置则返回全部
:return: localStorage一个或所有项内容
"""
...
def get_screenshot(self, path: [str, Path] = None, name: str = None, as_bytes: PIC_TYPE = None,
as_base64: PIC_TYPE = None, full_page: bool = False, left_top: Tuple[int, int] = None,
right_bottom: Tuple[int, int] = None) -> Union[str, bytes]:
"""对页面进行截图,可对整个网页、可见网页、指定范围截图。对可视范围外截图需要90以上版本浏览器支持
:param path: 保存路径
:param name: 完整文件名,后缀可选 'jpg','jpeg','png','webp'
:param as_bytes: 是否以字节形式返回图片,可选 'jpg','jpeg','png','webp',生效时path参数和as_base64参数无效
:param as_base64: 是否以base64字符串形式返回图片,可选 'jpg','jpeg','png','webp',生效时path参数无效
:param full_page: 是否整页截图,为True截取整个网页,为False截取可视窗口
:param left_top: 截取范围左上角坐标
:param right_bottom: 截取范围右下角角坐标
:return: 图片完整路径或字节文本
"""
...
def add_init_js(self, script: str) -> str:
"""添加初始化脚本,在页面加载任何脚本前执行
:param script: js文本
:return: 添加的脚本的id
"""
...
def remove_init_js(self, script_id: str = None) -> None:
"""删除初始化脚本,js_id传入None时删除所有
:param script_id: 脚本的id
:return: None
"""
...
def clear_cache(self, session_storage: bool = True, local_storage: bool = True, cache: bool = True,
cookies: bool = True) -> None:
"""清除缓存,可选要清除的项
:param session_storage: 是否清除sessionStorage
:param local_storage: 是否清除localStorage
:param cache: 是否清除cache
:param cookies: 是否清除cookies
:return: None
"""
...
def disconnect(self) -> None:
"""断开与页面的连接,不关闭页面"""
...
def reconnect(self, wait: float = 0) -> None:
"""断开与页面原来的页面,重新建立连接
:param wait: 断开后等待若干秒再连接
:return: None
"""
...
def handle_alert(self,
accept: Optional[bool] = True,
send: str = None,
timeout: float = None,
next_one: bool = False) -> Union[str, False]:
"""处理提示框,可以自动等待提示框出现
:param accept: True表示确认,False表示取消,为None不会按按钮但依然返回文本值
:param send: 处理prompt提示框时可输入文本
:param timeout: 等待提示框出现的超时时间(秒),为None则使用self.timeout属性的值
:param next_one: 是否处理下一个出现的提示框,为True时timeout参数无效
:return: 提示框内容文本,未等到提示框则返回False
"""
...
def _handle_alert(self,
accept: Optional[bool] = True,
send: str = None,
timeout: float = None,
next_one: bool = False) -> Union[str, False]:
"""处理提示框,可以自动等待提示框出现
:param accept: True表示确认,False表示取消,其它值不会按按钮但依然返回文本值
:param send: 处理prompt提示框时可输入文本
:param timeout: 等待提示框出现的超时时间(秒),为None则使用self.timeout属性的值
:param next_one: 是否处理下一个出现的提示框,为True时timeout参数无效
:return: 提示框内容文本,未等到提示框则返回False
"""
...
def _on_alert_open(self, **kwargs):
"""alert出现时触发的方法"""
...
def _on_alert_close(self, **kwargs):
"""alert关闭时触发的方法"""
...
def _wait_loaded(self, timeout: float = None) -> bool:
"""等待页面加载完成,超时触发停止加载
:param timeout: 超时时间(秒)
:return: 是否成功,超时返回False
"""
...
def _d_connect(self, to_url: str, times: int = 0, interval: float = 1, show_errmsg: bool = False,
timeout: float = None) -> Union[bool, None]:
"""尝试连接,重试若干次
:param to_url: 要访问的url
:param times: 重试次数
:param interval: 重试间隔(秒)
:param show_errmsg: 是否抛出异常
:param timeout: 连接超时时间(秒)
:return: 是否成功,返回None表示不确定
"""
...
def _get_screenshot(self, path: [str, Path] = None, name: str = None, as_bytes: PIC_TYPE = None,
as_base64: PIC_TYPE = None, full_page: bool = False, left_top: Tuple[float, float] = None,
right_bottom: Tuple[float, float] = None, ele: ChromiumElement = None) -> Union[str, bytes]:
"""对页面进行截图,可对整个网页、可见网页、指定范围截图。对可视范围外截图需要90以上版本浏览器支持
:param path: 保存路径
:param name: 完整文件名,后缀可选 'jpg','jpeg','png','webp'
:param as_bytes: 是否以字节形式返回图片,可选 'jpg','jpeg','png','webp',生效时path参数和as_base64参数无效
:param as_base64: 是否以base64字符串形式返回图片,可选 'jpg','jpeg','png','webp',生效时path参数无效
:param full_page: 是否整页截图,为True截取整个网页,为False截取可视窗口
:param left_top: 截取范围左上角坐标
:param right_bottom: 截取范围右下角角坐标
:param ele: 为异域iframe内元素截图设置
:return: 图片完整路径或字节文本
"""
...
class Timeout(object):
"""用于保存d模式timeout信息的类"""
base: float = ...
page_load: float = ...
script: float = ...
def __init__(self, base=None, page_load=None, script=None):
"""
:param base: 默认超时时间
:param page_load: 页面加载超时时间
:param script: js超时时间
"""
...
@property
def as_dict(self) -> dict:
"""以dict格式返回timeout设置"""
...
class Alert(object):
"""用于保存alert信息的类"""
activated: Optional[bool] = ...
text: Optional[str] = ...
type: Optional[str] = ...
defaultPrompt: Optional[str] = ...
response_accept: Optional[str] = ...
response_text: Optional[str] = ...
handle_next: Optional[bool] = ...
next_text: Optional[str] = ...
auto: Optional[bool] = ...
def __init__(self, auto: bool = None): ...
@@ -0,0 +1,457 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from copy import copy
from re import search, findall, DOTALL
from time import sleep, perf_counter
from .._elements.chromium_element import ChromiumElement
from .._functions.settings import Settings as _S
from .._pages.chromium_base import ChromiumBase
from .._units.listener import FrameListener
from .._units.rect import FrameRect
from .._units.scroller import FrameScroller
from .._units.setter import ChromiumFrameSetter
from .._units.states import FrameStates
from .._units.waiter import FrameWaiter
from ..errors import ContextLostError, ElementLostError, PageDisconnectedError, JavaScriptError
class ChromiumFrame(ChromiumBase):
_Frames = {}
def __new__(cls, owner, ele, info=None):
fid = info['node']['frameId'] if info else owner._run_cdp('DOM.describeNode',
backendNodeId=ele._backend_id)['node']['frameId']
if _S.singleton_tab_obj and fid in cls._Frames:
r = cls._Frames[fid]
while not hasattr(r, '_type') or r._type != 'ChromiumFrame':
sleep(.01)
return r
r = object.__new__(cls)
cls._Frames[fid] = r
return r
def __init__(self, owner, ele, info=None):
if _S.singleton_tab_obj and hasattr(self, '_created'):
return
self._created = True
self._tab = owner._tab
self._target_page = owner
self._backend_id = ele._backend_id
self._frame_ele = ele
self._reloading = False
try:
node = info['node'] if info else owner._run_cdp('DOM.describeNode', backendNodeId=ele._backend_id)['node']
self._frame_id = node['frameId']
if self._is_inner_frame():
self._is_diff_domain = False
self.doc_ele = ChromiumElement(self._target_page, backend_id=node['contentDocument']['backendNodeId'])
super().__init__(owner.browser, owner.driver.id)
else:
self._is_diff_domain = True
delattr(self, '_frame_id')
super().__init__(owner.browser, node['frameId'])
obj_id = super()._run_js('document;', as_expr=True)['objectId']
self.doc_ele = ChromiumElement(self, obj_id=obj_id)
except Exception as e:
ChromiumFrame._Frames.pop(self._frame_id, None)
raise e
self._type = 'ChromiumFrame'
def __call__(self, locator, index=1, timeout=None):
return self.ele(locator, index=index, timeout=timeout)
def __repr__(self):
attrs = [f"{k}='{v}'" for k, v in self._frame_ele.attrs.items()]
return f'<ChromiumFrame {self.frame_ele.tag} {" ".join(attrs)}>'
def __eq__(self, other):
return self._frame_id == getattr(other, '_frame_id', None)
def _d_set_runtime_settings(self):
if not hasattr(self, '_timeouts'):
self._timeouts = copy(self._target_page.timeouts)
self.retry_times = self._target_page.retry_times
self.retry_interval = self._target_page.retry_interval
self._download_path = self._target_page.download_path
self._auto_handle_alert = self._target_page._auto_handle_alert
self._load_mode = self._target_page._load_mode if not self._is_diff_domain else 'normal'
def _driver_init(self, target_id, is_init=True):
try:
super()._driver_init(target_id)
except:
if not self.browser._ws_only:
self.browser._driver.get(f'http://{self._browser.address}/json')
super()._driver_init(target_id)
self._driver.set_callback('Inspector.detached', self._onInspectorDetached, immediate=True)
self._driver.set_callback('Page.frameDetached', None)
self._driver.set_callback('Page.frameDetached', self._onFrameDetached, immediate=True)
def _reload(self):
self._is_loading = True
self._reloading = True
self._doc_got = False
self._driver.stop()
try:
self._frame_ele = ChromiumElement(self._target_page, backend_id=self._backend_id)
end_time = perf_counter() + 2
while perf_counter() < end_time:
node = self._target_page._run_cdp('DOM.describeNode', backendNodeId=self._frame_ele._backend_id)['node']
if 'frameId' in node:
break
sleep(.05)
else:
return
except (ElementLostError, PageDisconnectedError):
return
if self._is_inner_frame():
self._is_diff_domain = False
self.doc_ele = ChromiumElement(self._target_page, backend_id=node['contentDocument']['backendNodeId'])
self._frame_id = node['frameId']
if self._listener:
self._listener._to_target(self._target_page.tab_id, self._browser._ws_address, self)
super().__init__(self._browser, self._target_page.tab_id)
else:
self._is_diff_domain = True
if self._listener:
self._listener._to_target(node['frameId'], self._browser.address, self)
end_time = perf_counter() + self.timeouts.page_load
super().__init__(self._browser, node['frameId'])
timeout = end_time - perf_counter()
if timeout <= 0:
timeout = .5
self._wait_loaded(timeout)
self._is_loading = False
self._reloading = False
def _get_document(self, timeout=10):
if self._is_reading:
return
self._is_reading = True
try:
if self._is_diff_domain is False:
node = self._target_page._run_cdp('DOM.describeNode', backendNodeId=self._backend_id)['node']
self.doc_ele = ChromiumElement(self._target_page, backend_id=node['contentDocument']['backendNodeId'])
else:
timeout = max(timeout, 2)
b_id = self._run_cdp('DOM.getDocument', _timeout=timeout)['root']['backendNodeId']
self.doc_ele = ChromiumElement(self, backend_id=b_id)
self._root_id = self.doc_ele._obj_id
r = self._run_cdp('Page.getFrameTree', _ignore=PageDisconnectedError)
for i in findall(r"'id': '(.*?)'", str(r)):
self.browser._frames[i] = self.tab_id
return True
except:
return False
finally:
if not self._reloading: # 阻止reload时标识
self._is_loading = False
self._is_reading = False
def _onInspectorDetached(self, **kwargs):
# 异域转同域或退出
self._reload()
def _onFrameDetached(self, **kwargs):
# 同域变异域
self.browser._frames.pop(kwargs['frameId'], None)
ChromiumFrame._Frames.pop(kwargs['frameId'], None)
if kwargs['frameId'] == self._frame_id:
self._reload()
# ----------挂件----------
@property
def scroll(self):
self.wait.doc_loaded()
if self._scroll is None:
self._scroll = FrameScroller(self)
return self._scroll
@property
def set(self):
if self._set is None:
self._set = ChromiumFrameSetter(self)
return self._set
@property
def states(self):
if self._states is None:
self._states = FrameStates(self)
return self._states
@property
def wait(self):
if self._wait is None:
self._wait = FrameWaiter(self)
return self._wait
@property
def rect(self):
if self._rect is None:
self._rect = FrameRect(self)
return self._rect
@property
def listen(self):
if self._listener is None:
self._listener = FrameListener(self)
return self._listener
# ----------挂件结束----------
@property
def _obj_id(self):
return self.frame_ele._obj_id
@property
def _node_id(self):
return self.frame_ele._node_id
@property
def owner(self):
return self.frame_ele.owner
@property
def frame_ele(self):
return self._frame_ele
@property
def tag(self):
return self.frame_ele.tag
@property
def url(self):
try:
return self.doc_ele._run_js('return this.location.href;')
except JavaScriptError:
return None
@property
def html(self):
tag = self.tag
out_html = self._target_page._run_cdp('DOM.getOuterHTML', backendNodeId=self.frame_ele._backend_id)['outerHTML']
sign = search(rf'<{tag}.*?>', out_html, DOTALL).group(0)
return f'{sign}{self.inner_html}</{tag}>'
@property
def inner_html(self):
return self.doc_ele._run_js('return this.documentElement.outerHTML;')
@property
def link(self):
return self.frame_ele.link
@property
def title(self):
r = self._ele('t:title', raise_err=False)
return r.text if r else None
@property
def attrs(self):
return self.frame_ele.attrs
@property
def active_ele(self):
return self.doc_ele._run_js('return this.activeElement;')
@property
def xpath(self):
return self.frame_ele.xpath
@property
def css_path(self):
return self.frame_ele.css_path
@property
def tab(self):
return self._tab
@property
def tab_id(self):
return self.tab.tab_id
@property
def download_path(self):
return self._download_path
@property
def sr(self):
return self.frame_ele.sr
@property
def shadow_root(self):
return self.frame_ele.sr
@property
def child_count(self):
return int(self._ele('xpath:count(./*)'))
@property
def _js_ready_state(self):
if self._is_diff_domain:
return super()._js_ready_state
else:
try:
return self.doc_ele._run_js('return this.readyState;')
except ContextLostError:
try:
node = self._run_cdp('DOM.describeNode', backendNodeId=self.frame_ele._backend_id)['node']
doc = ChromiumElement(self._target_page, backend_id=node['contentDocument']['backendNodeId'])
return doc._run_js('return this.readyState;')
except:
return None
def refresh(self):
self.doc_ele._run_js('this.location.reload();')
def property(self, name):
return self.frame_ele.property(name)
def attr(self, name):
return self.frame_ele.attr(name)
def remove_attr(self, name):
self.frame_ele.remove_attr(name)
def style(self, style, pseudo_ele=''):
return self.frame_ele.style(style=style, pseudo_ele=pseudo_ele)
def run_js(self, script, *args, as_expr=False, timeout=None):
return self._run_js(script, *args, as_expr=as_expr, timeout=timeout)
def _run_js(self, script, *args, as_expr=False, timeout=None):
if script.startswith('this.scrollIntoView'):
return self.frame_ele._run_js(script, *args, as_expr=as_expr, timeout=timeout)
else:
return self.doc_ele._run_js(script, *args, as_expr=as_expr, timeout=timeout)
def parent(self, level_or_loc=1, index=1, timeout=0):
return self.frame_ele.parent(level_or_loc, index, timeout=timeout)
def prev(self, locator='', index=1, timeout=0, ele_only=True):
return self.frame_ele.prev(locator, index, timeout, ele_only=ele_only)
def next(self, locator='', index=1, timeout=0, ele_only=True):
return self.frame_ele.next(locator, index, timeout, ele_only=ele_only)
def before(self, locator='', index=1, timeout=None, ele_only=True):
return self.frame_ele.before(locator, index, timeout, ele_only=ele_only)
def after(self, locator='', index=1, timeout=None, ele_only=True):
return self.frame_ele.after(locator, index, timeout, ele_only=ele_only)
def prevs(self, locator='', timeout=0, ele_only=True):
return self.frame_ele.prevs(locator, timeout, ele_only=ele_only)
def nexts(self, locator='', timeout=0, ele_only=True):
return self.frame_ele.nexts(locator, timeout, ele_only=ele_only)
def befores(self, locator='', timeout=None, ele_only=True):
return self.frame_ele.befores(locator, timeout, ele_only=ele_only)
def afters(self, locator='', timeout=None, ele_only=True):
return self.frame_ele.afters(locator, timeout, ele_only=ele_only)
def get_screenshot(self, path=None, name=None, as_bytes=None, as_base64=None):
return self.frame_ele.get_screenshot(path=path, name=name, as_bytes=as_bytes, as_base64=as_base64)
def _get_screenshot(self, path=None, name=None, as_bytes: [bool, str] = None, as_base64: [bool, str] = None,
full_page=False, left_top=None, right_bottom=None, ele=None):
if not self._is_diff_domain:
return super().get_screenshot(path=path, name=name, as_bytes=as_bytes, as_base64=as_base64,
full_page=full_page, left_top=left_top, right_bottom=right_bottom)
if as_bytes:
if as_bytes is True:
pic_type = 'png'
else:
if as_bytes not in ('jpg', 'jpeg', 'png', 'webp'):
raise ValueError(_S._lang.join(_S._lang.INCORRECT_VAL_, 'as_bytes',
ALLOW_VAL='"jpg", "jpeg", "png", "webp"', CURR_VAL=as_bytes))
pic_type = 'jpeg' if as_bytes == 'jpg' else as_bytes
elif as_base64:
if as_base64 is True:
pic_type = 'png'
else:
if as_base64 not in ('jpg', 'jpeg', 'png', 'webp'):
raise ValueError(_S._lang.join(_S._lang.INCORRECT_VAL_, 'as_base64',
ALLOW_VAL='"jpg", "jpeg", "png", "webp"', CURR_VAL=as_base64))
pic_type = 'jpeg' if as_base64 == 'jpg' else as_base64
else:
path = str(path).rstrip('\\/') if path else '.'
if path and path.endswith(('.jpg', '.jpeg', '.png', '.webp')):
pic_type = path.rsplit('.', 1)[-1]
elif name and name.endswith(('.jpg', '.jpeg', '.png', '.webp')):
pic_type = name.rsplit('.', 1)[-1]
else:
pic_type = 'jpeg'
if pic_type == 'jpg':
pic_type = 'jpeg'
self.frame_ele.scroll.to_see(center=True)
self.scroll.to_see(ele, center=True)
cx, cy = ele.rect.viewport_location
w, h = ele.rect.size
img_data = f'data:image/{pic_type};base64,{self.frame_ele.get_screenshot(as_base64=True)}'
body = self.tab('t:body')
first_child = body('c::first-child')
if not isinstance(first_child, ChromiumElement):
first_child = first_child.frame_ele
js = f'''
img = document.createElement('img');
img.src = "{img_data}";
img.style.setProperty("z-index",9999999);
img.style.setProperty("position","fixed");
arguments[0].insertBefore(img, this);
return img;'''
new_ele = first_child._run_js(js, body)
new_ele.scroll.to_see(center=True)
top = int(self.frame_ele.style('border-top').split('px')[0])
left = int(self.frame_ele.style('border-left').split('px')[0])
r = self.tab._run_cdp('Page.getLayoutMetrics')['visualViewport']
sx = r['pageX']
sy = r['pageY']
r = self.tab.get_screenshot(path=path, name=name, as_bytes=as_bytes, as_base64=as_base64,
left_top=(cx + left + sx, cy + top + sy),
right_bottom=(cx + w + left + sx, cy + h + top + sy))
self.tab.remove_ele(new_ele)
return r
def _find_elements(self, locator, timeout, index=1, relative=False, raise_err=None):
if isinstance(locator, ChromiumElement):
return locator
self.wait.doc_loaded()
return self.doc_ele._ele(locator, index=index, timeout=timeout,
raise_err=raise_err) if index is not None else self.doc_ele.eles(locator, timeout)
def _is_inner_frame(self):
return self._frame_id in str(self._target_page._run_cdp('Page.getFrameTree')['frameTree'])
@@ -0,0 +1,458 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from pathlib import Path
from typing import Union, Tuple, List, Any, Optional, Literal
from .chromium_base import ChromiumBase
from .chromium_tab import ChromiumTab
from .mix_tab import MixTab
from .._elements.chromium_element import ChromiumElement, ShadowRoot
from .._functions.elements import ChromiumElementsList
from .._units.listener import FrameListener
from .._units.rect import FrameRect
from .._units.scroller import FrameScroller
from .._units.setter import ChromiumFrameSetter
from .._units.states import FrameStates
from .._units.waiter import FrameWaiter
class ChromiumFrame(ChromiumBase):
_Frames: dict = ...
_target_page: Union[ChromiumTab, ChromiumFrame] = ...
_tab: Union[MixTab, ChromiumTab] = ...
_set: ChromiumFrameSetter = ...
_frame_ele: ChromiumElement = ...
_backend_id: int = ...
_doc_ele: ChromiumElement = ...
_is_diff_domain: bool = ...
doc_ele: ChromiumElement = ...
_states: FrameStates = ...
_reloading: bool = ...
_rect: Optional[FrameRect] = ...
_listener: FrameListener = ...
def __init__(self,
owner: Union[ChromiumTab, ChromiumFrame],
ele: ChromiumElement,
info: dict = None):
"""
:param owner: frame所在的页面对象
:param ele: frame所在元素
:param info: frame所在元素信息
"""
...
def __call__(self,
locator: Union[Tuple[str, str], str],
index: int = 1,
timeout: float = None) -> ChromiumElement:
"""在内部查找元素
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param timeout: 超时时间(秒)
:return: ChromiumElement对象或属性、文本
"""
...
def __repr__(self) -> str: ...
def __eq__(self, other: ChromiumFrame) -> bool: ...
def _d_set_runtime_settings(self) -> None:
"""重写设置浏览器运行参数方法"""
...
def _driver_init(self, target_id: str, is_init: bool = True) -> None:
"""避免出现服务器500错误
:param target_id: 要跳转到的target id
:return: None
"""
...
def _reload(self) -> None:
"""重新获取document"""
...
def _get_document(self, timeout: float = 10) -> bool:
"""刷新cdp使用的document数据
:param timeout: 超时时间(秒)
:return: 是否获取成功
"""
...
def _onFrameStoppedLoading(self, **kwargs): ...
def _onInspectorDetached(self, **kwargs): ...
@property
def scroll(self) -> FrameScroller:
"""返回用于滚动的对象"""
...
@property
def set(self) -> ChromiumFrameSetter:
"""返回用于设置的对象"""
...
@property
def states(self) -> FrameStates:
"""返回用于获取状态信息的对象"""
...
@property
def wait(self) -> FrameWaiter:
"""返回用于等待的对象"""
...
@property
def rect(self) -> FrameRect:
"""返回获取坐标和大小的对象"""
...
@property
def listen(self) -> FrameListener:
"""返回用于聆听数据包的对象"""
...
@property
def _obj_id(self) -> str: ...
@property
def _node_id(self) -> int: ...
@property
def owner(self) -> ChromiumBase:
"""返回所属页面对象"""
...
@property
def frame_ele(self) -> ChromiumElement:
"""返回总页面上的frame元素"""
...
@property
def tag(self) -> str:
"""返回元素tag"""
...
@property
def url(self) -> str:
"""返回frame当前访问的url"""
...
@property
def html(self) -> str:
"""返回元素outerHTML文本"""
...
@property
def inner_html(self) -> str:
"""返回元素innerHTML文本"""
...
@property
def link(self) -> str:
"""返回href或src绝对url"""
...
@property
def title(self) -> str:
"""返回页面title"""
...
@property
def attrs(self) -> dict:
"""返回frame元素所有attribute属性"""
...
@property
def active_ele(self) -> ChromiumElement:
"""返回当前焦点所在元素"""
...
@property
def xpath(self) -> str:
"""返回frame的xpath绝对路径"""
...
@property
def css_path(self) -> str:
"""返回frame的css selector绝对路径"""
...
@property
def tab(self) -> Union[ChromiumTab, MixTab]:
"""返回frame所在的tab对象"""
...
@property
def tab_id(self) -> str:
"""返回frame所在tab的id"""
...
@property
def download_path(self) -> str:
"""返回下载文件保存路径"""
...
@property
def sr(self) -> Union[None, ShadowRoot]:
"""返回iframe的shadow-root元素对象"""
...
@property
def shadow_root(self) -> Union[None, ShadowRoot]:
"""返回iframe的shadow-root元素对象"""
...
@property
def child_count(self) -> int:
"""返回直接子元素的个数"""
...
@property
def _js_ready_state(self) -> Literal['loading', 'interactive', 'complete']:
"""返回当前页面加载状态"""
...
def refresh(self) -> None:
"""刷新frame页面"""
...
def property(self, name: str) -> Union[str, None]:
"""返回frame元素一个property属性值
:param name: 属性名
:return: 属性值文本,没有该属性返回None
"""
...
def attr(self, name: str) -> Union[str, None]:
"""返回frame元素一个attribute属性值
:param name: 属性名
:return: 属性值文本,没有该属性返回None
"""
...
def remove_attr(self, name: str) -> None:
"""删除frame元素attribute属性
:param name: 属性名
:return: None
"""
...
def style(self, style: str, pseudo_ele: str = '') -> str:
"""返回frame元素样式属性值,可获取伪元素属性值
:param style: 样式属性名称
:param pseudo_ele: 伪元素名称(如有)
:return: 样式属性的值
"""
...
def run_js(self,
script: str,
*args,
as_expr: bool = False,
timeout: float = None) -> Any:
"""运行javascript代码
:param script: js文本
:param args: 参数,按顺序在js文本中对应arguments[0]、arguments[1]...
:param as_expr: 是否作为表达式运行,为True时args无效
:param timeout: js超时时间(秒),为None则使用页面timeouts.script设置
:return: 运行的结果
"""
...
def _run_js(self,
script: str,
*args,
as_expr: bool = False,
timeout: float = None) -> Any:
"""运行javascript代码
:param script: js文本
:param args: 参数,按顺序在js文本中对应arguments[0]、arguments[1]...
:param as_expr: 是否作为表达式运行,为True时args无效
:param timeout: js超时时间(秒),为None则使用页面timeouts.script设置
:return: 运行的结果
"""
...
def parent(self,
level_or_loc: Union[Tuple[str, str], str, int] = 1,
index: int = 1,
timeout: float = 0) -> ChromiumElement:
"""返回上面某一级父元素,可指定层数或用查询语法定位
:param level_or_loc: 第几级父元素,1开始,或定位符
:param index: 当level_or_loc传入定位符,使用此参数选择第几个结果,1开始
:param timeout: 查找超时时间(秒)
:return: 上级元素对象
"""
...
def prev(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = 0,
ele_only: bool = True) -> Union[ChromiumElement, str]:
"""返回当前元素前面一个符合条件的同级元素,可用查询语法筛选,可指定返回筛选结果的第几个
:param locator: 用于筛选的查询语法
:param index: 前面第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 同级元素或节点
"""
...
def next(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = 0,
ele_only: bool = True) -> Union[ChromiumElement, str]:
"""返回当前元素后面一个符合条件的同级元素,可用查询语法筛选,可指定返回筛选结果的第几个
:param locator: 用于筛选的查询语法
:param index: 后面第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 同级元素或节点
"""
...
def before(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[ChromiumElement, str]:
"""返回文档中当前元素前面符合条件的一个元素,可用查询语法筛选,可指定返回筛选结果的第几个
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param index: 前面第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素前面的某个元素或节点
"""
...
def after(self,
locator: Union[Tuple[str, str], str, int] = '',
index: int = 1,
timeout: float = None,
ele_only: bool = True) -> Union[ChromiumElement, str]:
"""返回文档中此当前元素后面符合条件的一个元素,可用查询语法筛选,可指定返回筛选结果的第几个
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param index: 后面第几个查询结果,1开始
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素后面的某个元素或节点
"""
...
def prevs(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = 0,
ele_only: bool = True) -> List[Union[ChromiumElement, str]]:
"""返回当前元素前面符合条件的同级元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 同级元素或节点文本组成的列表
"""
...
def nexts(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = 0,
ele_only: bool = True) -> List[Union[ChromiumElement, str]]:
"""返回当前元素后面符合条件的同级元素或节点组成的列表,可用查询语法筛选
:param locator: 用于筛选的查询语法
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 同级元素或节点文本组成的列表
"""
...
def befores(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> List[Union[ChromiumElement, str]]:
"""返回文档中当前元素前面符合条件的元素或节点组成的列表,可用查询语法筛选
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素前面的元素或节点组成的列表
"""
...
def afters(self,
locator: Union[Tuple[str, str], str] = '',
timeout: float = None,
ele_only: bool = True) -> List[Union[ChromiumElement, str]]:
"""返回文档中当前元素后面符合条件的元素或节点组成的列表,可用查询语法筛选
查找范围不限同级元素,而是整个DOM文档
:param locator: 用于筛选的查询语法
:param timeout: 查找节点的超时时间(秒)
:param ele_only: 是否只获取元素,为False时把文本、注释节点也纳入
:return: 本元素前面的元素或节点组成的列表
"""
...
def get_screenshot(self,
path: [str, Path] = None,
name: str = None,
as_bytes: [bool, str] = None,
as_base64: [bool, str] = None) -> Union[str, bytes]:
"""对页面进行截图,可对整个网页、可见网页、指定范围截图。对可视范围外截图需要90以上版本浏览器支持
:param path: 文件保存路径
:param name: 完整文件名,后缀可选 'jpg','jpeg','png','webp'
:param as_bytes: 是否以字节形式返回图片,可选 'jpg','jpeg','png','webp',生效时path参数和as_base64参数无效
:param as_base64: 是否以base64字符串形式返回图片,可选 'jpg','jpeg','png','webp',生效时path参数无效
:return: 图片完整路径或字节文本
"""
...
def _get_screenshot(self,
path: [str, Path] = None,
name: str = None,
as_bytes: [bool, str] = None,
as_base64: [bool, str] = None,
full_page: bool = False,
left_top: Tuple[int, int] = None,
right_bottom: Tuple[int, int] = None,
ele: ChromiumElement = None) -> Union[str, bytes]:
"""实现截图
:param path: 文件保存路径
:param name: 完整文件名,后缀可选 'jpg','jpeg','png','webp'
:param as_bytes: 是否以字节形式返回图片,可选 'jpg','jpeg','png','webp',生效时path参数和as_base64参数无效
:param as_base64: 是否以base64字符串形式返回图片,可选 'jpg','jpeg','png','webp',生效时path参数无效
:param full_page: 是否整页截图,为True截取整个网页,为False截取可视窗口
:param left_top: 截取范围左上角坐标
:param right_bottom: 截取范围右下角角坐标
:param ele: 为异域iframe内元素截图设置
:return: 图片完整路径或字节文本
"""
...
def _find_elements(self,
locator: Union[Tuple[str, str], str, ChromiumElement, ChromiumFrame],
timeout: float,
index: Optional[int] = 1,
relative: bool = False,
raise_err: bool = None) -> Union[ChromiumElement, ChromiumFrame, None, ChromiumElementsList]:
"""在frame内查找单个元素
:param locator: 定位符或元素对象
:param timeout: 查找超时时间(秒)
:param index: 第几个结果,从1开始,可传入负数获取倒数第几个,为None返回所有
:param relative: MixTab用的表示是否相对定位的参数
:param raise_err: 找不到元素是是否抛出异常,为None时根据全局设置
:return: ChromiumElement对象
"""
...
def _is_inner_frame(self) -> bool:
"""返回当前frame是否同域"""
...
@@ -0,0 +1,131 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from time import sleep
from .._base.chromium import Chromium
from .._functions.settings import Settings
from .._functions.web import save_page
from .._pages.chromium_base import ChromiumBase
from .._units.setter import ChromiumPageSetter
from .._units.waiter import ChromiumPageWaiter
class ChromiumPage(ChromiumBase):
_PAGES = {}
def __new__(cls, addr_or_opts=None, tab_id=None, timeout=None):
# 即将废弃timeout
browser = Chromium(addr_or_opts=addr_or_opts)
if browser.id in cls._PAGES:
r = cls._PAGES[browser.id]
while not hasattr(r, '_frame_id'):
sleep(.05)
return r
r = object.__new__(cls)
r._browser = browser
cls._PAGES[browser.id] = r
return r
def __init__(self, addr_or_opts=None, tab_id=None, timeout=None):
# 即将废弃timeout
if hasattr(self, '_created'):
return
self._created = True
self.tab = self
super().__init__(self.browser, tab_id)
self._type = 'ChromiumPage'
self.set.timeouts(base=timeout) # 即将废弃
self._tab = self
self._browser._dl_mgr._page_id = self.tab_id
def __repr__(self):
return f'<ChromiumPage browser_id={self.browser.id} tab_id={self.tab_id}>'
def _d_set_runtime_settings(self):
"""设置运行时用到的属性"""
self._timeouts = self.browser.timeouts
self._load_mode = self.browser._load_mode
self._download_path = self.browser.download_path
self.retry_times = self.browser.retry_times
self.retry_interval = self.browser.retry_interval
self._auto_handle_alert = self.browser._auto_handle_alert
@property
def set(self):
if self._set is None:
self._set = ChromiumPageSetter(self)
return self._set
@property
def wait(self):
if self._wait is None:
self._wait = ChromiumPageWaiter(self)
return self._wait
@property
def browser(self):
return self._browser
@property
def tabs_count(self):
return self.browser.tabs_count
@property
def tab_ids(self):
return self.browser.tab_ids
@property
def latest_tab(self):
return self.browser._get_tab(id_or_num=self.tab_ids[0], as_id=not Settings.singleton_tab_obj)
@property
def process_id(self):
return self.browser.process_id
@property
def browser_version(self):
return self._browser.version
@property
def address(self):
return self.browser.address
@property
def download_path(self):
return self.browser.download_path
def save(self, path=None, name=None, as_pdf=False, **kwargs):
return save_page(self, path, name, as_pdf, kwargs)
def get_tab(self, id_or_num=None, title=None, url=None, tab_type='page', as_id=False):
return self.browser._get_tab(id_or_num=id_or_num, title=title, url=url,
tab_type=tab_type, mix=False, as_id=as_id)
def get_tabs(self, title=None, url=None, tab_type='page', as_id=False):
return self.browser._get_tabs(title=title, url=url, tab_type=tab_type, mix=False, as_id=as_id)
def new_tab(self, url=None, new_window=False, background=False, new_context=False):
return self.browser._new_tab(False, url=url, new_window=new_window,
background=background, new_context=new_context)
def activate_tab(self, id_ind_tab):
self.browser.activate_tab(id_ind_tab)
def close(self):
self.browser._close_tab(self)
def close_tabs(self, tabs_or_ids, others=False):
self.browser.close_tabs(tabs_or_ids=tabs_or_ids, others=others)
def quit(self, timeout=5, force=True, del_data=False):
self.browser.quit(timeout, force, del_data=del_data)
def _on_disconnect(self):
ChromiumPage._PAGES.pop(self._browser.id, None)
@@ -0,0 +1,224 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from pathlib import Path
from typing import Union, Tuple, List, Optional
from .._base.chromium import Chromium
from .._configs.chromium_options import ChromiumOptions
from .._pages.chromium_base import ChromiumBase
from .._pages.chromium_tab import ChromiumTab
from .._units.rect import TabRect
from .._units.setter import ChromiumPageSetter
from .._units.waiter import ChromiumPageWaiter
class ChromiumPage(ChromiumBase):
"""用于管理浏览器和一个标签页的类"""
_PAGES: dict = ...
tab: ChromiumPage = ...
_browser: Chromium = ...
_rect: Optional[TabRect] = ...
_is_exist: bool = ...
def __new__(cls,
addr_or_opts: Union[str, int, ChromiumOptions] = None,
tab_id: str = None):
"""
:param addr_or_opts: 浏览器地址:端口、ws地址、ChromiumOptions对象或端口数字(int)
:param tab_id: 要控制的标签页id,不指定默认为激活的
"""
...
def __init__(self,
addr_or_opts: Union[str, int, ChromiumOptions] = None,
tab_id: str = None):
"""
:param addr_or_opts: 浏览器地址:端口、ws地址、ChromiumOptions对象或端口数字(int)
:param tab_id: 要控制的标签页id,不指定默认为激活的
"""
...
@property
def set(self) -> ChromiumPageSetter:
"""返回用于设置的对象"""
...
@property
def wait(self) -> ChromiumPageWaiter:
"""返回用于等待的对象"""
...
@property
def browser(self) -> Chromium:
"""返回浏览器对象"""
...
@property
def tabs_count(self) -> int:
"""返回标签页数量"""
...
@property
def tab_ids(self) -> List[str]:
"""返回所有标签页id组成的列表"""
...
@property
def latest_tab(self) -> Union[ChromiumTab, ChromiumPage, str]:
"""返回最新的标签页,最新标签页指最后创建或最后被激活的
当Settings.singleton_tab_obj==True时返回Tab对象,否则返回tab id"""
...
@property
def process_id(self) -> Optional[int]:
"""返回浏览器进程id"""
...
@property
def browser_version(self) -> str:
"""返回所控制的浏览器版本号"""
...
@property
def address(self) -> str:
"""返回浏览器地址ip:port"""
...
def save(self,
path: Union[str, Path] = None,
name: str = None,
as_pdf: bool = False,
landscape: bool = ...,
displayHeaderFooter: bool = ...,
printBackground: bool = ...,
scale: float = ...,
paperWidth: float = ...,
paperHeight: float = ...,
marginTop: float = ...,
marginBottom: float = ...,
marginLeft: float = ...,
marginRight: float = ...,
pageRanges: str = ...,
headerTemplate: str = ...,
footerTemplate: str = ...,
preferCSSPageSize: bool = ...,
generateTaggedPDF: bool = ...,
generateDocumentOutline: bool = ...) -> Union[bytes, str]:
"""把当前页面保存为文件,如果path和name参数都为None,只返回文本
:param path: 保存路径,为None且name不为None时保存在当前路径
:param name: 文件名,为None且path不为None时用title属性值
:param as_pdf: 为Ture保存为pdf,否则为mhtml且忽略kwargs参数
:param landscape: 纸张方向,as_pdf为True时才生效
:param displayHeaderFooter: 是否显示页头页脚,as_pdf为True时才生效
:param printBackground: 是否打印背景图片,as_pdf为True时才生效
:param scale: 缩放比例,as_pdf为True时才生效
:param paperWidth: 页面宽度(英寸),as_pdf为True时才生效
:param paperHeight: 页面高度(英寸),as_pdf为True时才生效
:param marginTop: 上边距(英寸),as_pdf为True时才生效
:param marginBottom: 下边距(英寸),as_pdf为True时才生效
:param marginLeft: 左边距(英寸),as_pdf为True时才生效
:param marginRight: 右边距(英寸),as_pdf为True时才生效
:param pageRanges: 页面范围,格式'1-5, 8, 11-13',as_pdf为True时才生效
:param headerTemplate: 页头HTML模板,as_pdf为True时才生效
模板可包含以下class:
- date:日期
- title:文档标题
- url:文档url
- pageNumber:当前页码
- totalPages:总页数
示例:<span class=title></span>
:param footerTemplate: 页脚HTML模板,格式与页头的一样,as_pdf为True时才生效
:param preferCSSPageSize: 是否使用css定义的页面大小,as_pdf为True时才生效
:param generateTaggedPDF: 是否生成带标签的(可访问的)PDF。默认为嵌入器选择,as_pdf为True时才生效
:param generateDocumentOutline: 是否将文档大纲嵌入到PDF中。,as_pdf为True时才生效
:return: as_pdf为True时返回bytes,否则返回文件文本
"""
...
def get_tab(self,
id_or_num: Union[str, ChromiumTab, int] = None,
title: str = None,
url: str = None,
tab_type: Union[str, list, tuple] = 'page',
as_id: bool = False) -> Union[ChromiumTab, str, None]:
"""获取一个标签页对象,id_or_num不为None时,后面几个参数无效
:param id_or_num: 要获取的标签页id或序号,序号从1开始,可传入负数获取倒数第几个,不是视觉排列顺序,而是激活顺序
:param title: 要匹配title的文本,模糊匹配,为None则匹配所有
:param url: 要匹配url的文本,模糊匹配,为None则匹配所有
:param tab_type: tab类型,可用列表输入多个,如 'page', 'iframe' 等,为None则匹配所有
:param as_id: 是否返回标签页id而不是标签页对象
:return: ChromiumTab对象
"""
...
def get_tabs(self,
title: str = None,
url: str = None,
tab_type: Union[str, list, tuple] = 'page',
as_id: bool = False) -> Union[List[ChromiumTab], List[str]]:
"""查找符合条件的tab,返回它们组成的列表
:param title: 要匹配title的文本,模糊匹配,为None则匹配所有
:param url: 要匹配url的文本,模糊匹配,为None则匹配所有
:param tab_type: tab类型,可用列表输入多个,如 'page', 'iframe' 等,为None则匹配所有
:param as_id: 是否返回标签页id而不是标签页对象
:return: ChromiumTab对象组成的列表
"""
...
def new_tab(self,
url: str = None,
new_window: bool = False,
background: bool = False,
new_context: bool = False) -> ChromiumTab:
"""新建一个标签页
:param url: 新标签页跳转到的网址
:param new_window: 是否在新窗口打开标签页
:param background: 是否不激活新标签页,如new_window为True则无效
:param new_context: 是否创建新的上下文
:return: 新标签页对象
"""
...
def activate_tab(self,
id_ind_tab: Union[int, str, ChromiumTab]) -> None:
"""使标签页变为活动状态
:param id_ind_tab: 标签页id(str)、Tab对象或标签页序号(int),序号从1开始
:return: None
"""
...
def close(self) -> None:
"""关闭Page管理的标签页"""
...
def close_tabs(self,
tabs_or_ids: Union[str, ChromiumTab, List[Union[str, ChromiumTab]],
Tuple[Union[str, ChromiumTab]]],
others: bool = False) -> None:
"""关闭传入的标签页,可传入多个
:param tabs_or_ids: 要关闭的标签页对象或id,可传入列表或元组
:param others: 是否关闭指定标签页之外的
:return: None
"""
...
def quit(self,
timeout: float = 5,
force: bool = True,
del_data: bool = False) -> None:
"""关闭浏览器
:param timeout: 等待浏览器关闭超时时间(秒)
:param force: 关闭超时是否强制终止进程
:param del_data: 是否删除用户文件夹
:return: None
"""
...
def _on_disconnect(self) -> None:
"""浏览器退出时执行"""
...
@@ -0,0 +1,76 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from copy import copy
from time import sleep
from .._functions.settings import Settings
from .._functions.web import save_page
from .._pages.chromium_base import ChromiumBase
from .._units.setter import TabSetter
from .._units.waiter import TabWaiter
class ChromiumTab(ChromiumBase):
_TABS = {}
def __new__(cls, browser, tab_id):
if Settings.singleton_tab_obj and tab_id in cls._TABS:
r = cls._TABS[tab_id]
while not hasattr(r, '_frame_id'):
sleep(.05)
return r
r = object.__new__(cls)
cls._TABS[tab_id] = r
return r
def __init__(self, browser, tab_id):
if Settings.singleton_tab_obj and hasattr(self, '_created'):
return
self._created = True
super().__init__(browser, tab_id)
self._tab = self
self._type = 'ChromiumTab'
def __repr__(self):
return f'<ChromiumTab browser_id={self.browser.id} tab_id={self.tab_id}>'
def _d_set_runtime_settings(self):
self._timeouts = copy(self.browser.timeouts)
self.retry_times = self.browser.retry_times
self.retry_interval = self.browser.retry_interval
self._load_mode = self.browser._load_mode
self._download_path = self.browser.download_path
self._auto_handle_alert = self.browser._auto_handle_alert
self._none_ele_return_value = self.browser._none_ele_return_value
self._none_ele_value = self.browser._none_ele_value
def close(self, others=False):
if others:
self.browser.close_tabs(self.tab_id, others=True)
else:
self.browser._close_tab(self)
@property
def set(self):
if self._set is None:
self._set = TabSetter(self)
return self._set
@property
def wait(self):
if self._wait is None:
self._wait = TabWaiter(self)
return self._wait
def save(self, path=None, name=None, as_pdf=False, **kwargs):
return save_page(self, path, name, as_pdf, kwargs)
def _on_disconnect(self):
if not self._disconnect_flag:
ChromiumTab._TABS.pop(self.tab_id, None)
@@ -0,0 +1,110 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from pathlib import Path
from typing import Union, Optional
from .chromium_base import ChromiumBase
from .._base.chromium import Chromium
from .._units.rect import TabRect
from .._units.setter import TabSetter
from .._units.waiter import TabWaiter
class ChromiumTab(ChromiumBase):
"""实现浏览器标签页的类"""
_TABS: dict = ...
_tab: ChromiumTab = ...
_rect: Optional[TabRect] = ...
def __new__(cls, browser: Chromium, tab_id: str):
"""
:param browser: Browser对象
:param tab_id: 标签页id
"""
...
def __init__(self, browser: Chromium, tab_id: str):
"""
:param browser: Browser对象
:param tab_id: 标签页id
"""
...
def _d_set_runtime_settings(self) -> None:
"""重写设置浏览器运行参数方法"""
...
def close(self, others: bool = False) -> None:
"""关闭标签页
:param others: 是否关闭其它,保留自己
:return: None
"""
...
@property
def set(self) -> TabSetter:
"""返回用于设置的对象"""
...
@property
def wait(self) -> TabWaiter:
"""返回用于等待的对象"""
...
def save(self,
path: Union[str, Path] = None,
name: str = None,
as_pdf: bool = False,
landscape: bool = False,
displayHeaderFooter: bool = False,
printBackground: bool = False,
scale: float = 1,
paperWidth: float = 8.5,
paperHeight: float = 11,
marginTop: float = 11,
marginBottom: float = 1,
marginLeft: float = 1,
marginRight: float = 1,
pageRanges: str = '',
headerTemplate: str = '',
footerTemplate: str = '',
preferCSSPageSize: bool = False,
generateTaggedPDF: bool = ...,
generateDocumentOutline: bool = ...) -> Union[bytes, str]:
"""把当前页面保存为文件,如果path和name参数都为None,只返回文本
:param path: 保存路径,为None且name不为None时保存在当前路径
:param name: 文件名,为None且path不为None时用title属性值
:param as_pdf: 为Ture保存为pdf,否则为mhtml且忽略kwargs参数
:param landscape: 纸张方向,as_pdf为True时才生效
:param displayHeaderFooter: 是否显示页头页脚,as_pdf为True时才生效
:param printBackground: 是否打印背景图片,as_pdf为True时才生效
:param scale: 缩放比例,as_pdf为True时才生效
:param paperWidth: 页面宽度(英寸),as_pdf为True时才生效
:param paperHeight: 页面高度(英寸),as_pdf为True时才生效
:param marginTop: 上边距(英寸),as_pdf为True时才生效
:param marginBottom: 下边距(英寸),as_pdf为True时才生效
:param marginLeft: 左边距(英寸),as_pdf为True时才生效
:param marginRight: 右边距(英寸),as_pdf为True时才生效
:param pageRanges: 页面范围,格式'1-5, 8, 11-13',as_pdf为True时才生效
:param headerTemplate: 页头HTML模板,as_pdf为True时才生效
模板可包含以下class:
- date:日期
- title:文档标题
- url:文档url
- pageNumber:当前页码
- totalPages:总页数
示例:<span class=title></span>
:param footerTemplate: 页脚HTML模板,格式与页头的一样,as_pdf为True时才生效
:param preferCSSPageSize: 是否使用css定义的页面大小,as_pdf为True时才生效
:param generateTaggedPDF: 是否生成带标签的(可访问的)PDF。默认为嵌入器选择,as_pdf为True时才生效
:param generateDocumentOutline: 是否将文档大纲嵌入到PDF中。,as_pdf为True时才生效
:return: as_pdf为True时返回bytes,否则返回文件文本
"""
...
def _on_disconnect(self): ...
@@ -0,0 +1,199 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from .chromium_tab import ChromiumTab
from .._base.base import BasePage
from .._configs.session_options import SessionOptions
from .._functions.cookies import set_session_cookies, set_tab_cookies
from .._functions.settings import Settings as _S
from .._pages.session_page import SessionPage
from .._units.setter import MixTabSetter
class MixTab(SessionPage, ChromiumTab, BasePage):
def __init__(self, browser, tab_id):
if _S.singleton_tab_obj and hasattr(self, '_created'):
return
self._d_mode = True
self._session_options = None
self._headers = None
self._response = None
self._session = None
self._encoding = None
self._timeout = 10
super(SessionPage, self).__init__(browser=browser, tab_id=tab_id)
self._type = 'MixTab'
def __call__(self, locator, index=1, timeout=None):
return super(SessionPage, self).__call__(locator, index=index, timeout=timeout) if self._d_mode \
else super().__call__(locator, index=index)
def __repr__(self):
return f'<MixTab browser_id={self.browser.id} tab_id={self.tab_id}>'
@property
def set(self):
if self._set is None:
self._set = MixTabSetter(self)
return self._set
@property
def url(self):
return self._browser_url if self._d_mode else self._session_url
@property
def _browser_url(self):
return super(SessionPage, self).url if self._driver else None
@property
def title(self):
return super(SessionPage, self).title if self._d_mode else super().title
@property
def raw_data(self):
return super(SessionPage, self).html if self._d_mode else super().raw_data
@property
def html(self):
return super(SessionPage, self).html if self._d_mode else super().html
@property
def json(self):
return super(SessionPage, self).json if self._d_mode else super().json
@property
def response(self):
return self._response
@property
def mode(self):
return 'd' if self._d_mode else 's'
@property
def user_agent(self):
return super(SessionPage, self).user_agent if self._d_mode else super().user_agent
@property
def _session_url(self):
return self._response.url if self._response else None
@property
def timeout(self):
return self.timeouts.base if self._d_mode else self._timeout
def get(self, url, show_errmsg=False, retry=None, interval=None, timeout=None, **kwargs):
if self._d_mode:
if kwargs:
raise ValueError(_S._lang.join(_S._lang.S_MODE_ONLY, ARGS=", ".join(kwargs.keys())))
return super(SessionPage, self).get(url, show_errmsg, retry, interval, timeout)
if timeout is None:
timeout = self.timeouts.page_load
return super().get(url, show_errmsg, retry, interval, timeout, **kwargs)
def post(self, url, show_errmsg=False, retry=None, interval=None, timeout=None, **kwargs):
if self.mode == 'd':
self.cookies_to_session()
if timeout is None:
kwargs['timeout'] = self.timeouts.page_load
if self._session is None:
self._create_session()
super().post(url, show_errmsg, retry, interval, **kwargs)
return self.response
def ele(self, locator, index=1, timeout=None):
return (super(SessionPage, self).ele(locator, index=index, timeout=timeout)
if self._d_mode else super().ele(locator, index=index))
def eles(self, locator, timeout=None):
return super(SessionPage, self).eles(locator, timeout=timeout) if self._d_mode else super().eles(locator)
def s_ele(self, locator=None, index=1, timeout=None):
return (super(SessionPage, self).s_ele(locator, index=index, timeout=timeout)
if self._d_mode else super().s_ele(locator, index=index, timeout=timeout))
def s_eles(self, locator, timeout=None):
return (super(SessionPage, self).s_eles(locator, timeout=timeout)
if self._d_mode else super().s_eles(locator, timeout=timeout))
def change_mode(self, mode=None, go=True, copy_cookies=True):
if mode:
mode = mode.lower()
if mode is not None and ((mode == 'd' and self._d_mode) or (mode == 's' and not self._d_mode)):
return
self._d_mode = not self._d_mode
# s模式转d模式
if self._d_mode:
if self._driver is None or not self._driver.is_running:
self._driver_init(self.tab_id)
self._get_document()
self._url = super(SessionPage, self).url
if self._session_url:
if copy_cookies:
self.cookies_to_browser()
if go:
self.get(self._session_url)
return
# d模式转s模式
if self._session is None:
self._set_session_options(
self.browser._session_options or SessionOptions(read_file=self.browser._session_options is None))
self._create_session()
self._url = self._session_url
if self._driver:
if copy_cookies:
self.cookies_to_session()
if go:
url = super(SessionPage, self).url
if url.startswith('http'):
self.get(url)
def cookies_to_session(self, copy_user_agent=True):
if not self._session:
return
if copy_user_agent:
user_agent = self._run_cdp('Runtime.evaluate', expression='navigator.userAgent;')['result']['value']
self._headers.update({"User-Agent": user_agent})
set_session_cookies(self.session, super(SessionPage, self).cookies())
def cookies_to_browser(self):
if self._driver is None or not self._driver.is_running:
return
set_tab_cookies(self, super().cookies())
def cookies(self, all_domains=False, all_info=False):
return super(SessionPage, self).cookies(all_domains, all_info) if self._d_mode \
else super().cookies(all_domains, all_info)
def close(self, others=False, session=False):
if others:
self.browser.close_tabs(self.tab_id, others=True)
else:
self.browser._close_tab(self)
if session and self._session:
self._session.close()
if self._response is not None:
self._response.close()
def _find_elements(self, locator, timeout, index=1, relative=False, raise_err=None):
return super(SessionPage, self)._find_elements(locator, timeout=timeout, index=index, relative=relative) \
if self._d_mode else super()._find_elements(locator, index=index, timeout=timeout)
def _set_session_options(self, session_or_options=None):
if session_or_options is None:
session_or_options = self.browser._session_options or SessionOptions(
read_file=self.browser._session_options is None)
super()._set_session_options(session_or_options)
@@ -0,0 +1,298 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from http.cookiejar import CookieJar
from typing import Union, Tuple, Any, Optional, Literal
from requests import Session, Response
from .chromium_frame import ChromiumFrame
from .chromium_tab import ChromiumTab
from .session_page import SessionPage
from .._base.chromium import Chromium
from .._elements.chromium_element import ChromiumElement
from .._elements.session_element import SessionElement
from .._functions.cookies import CookiesList
from .._functions.elements import SessionElementsList, ChromiumElementsList
from .._units.setter import MixTabSetter
from .._units.waiter import MixTabWaiter
class MixTab(SessionPage, ChromiumTab):
_tab: MixTab = ...
_d_mode: bool = ...
_set: MixTabSetter = ...
def __init__(self, browser: Chromium, tab_id: str):
"""
:param browser: Chromium对象
:param tab_id: 标签页id
"""
...
def __call__(self,
locator: Union[Tuple[str, str], str, ChromiumElement, SessionElement],
index: int = 1,
timeout: float = None) -> Union[ChromiumElement, SessionElement]:
"""在内部查找元素
例:ele = page('@id=ele_id')
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param timeout: 超时时间(秒)
:return: 子元素对象
"""
...
@property
def set(self) -> MixTabSetter:
"""返回用于设置的对象"""
...
@property
def wait(self) -> MixTabWaiter:
"""返回用于等待的对象"""
...
@property
def url(self) -> Union[str, None]:
"""返回浏览器当前url"""
...
@property
def _browser_url(self) -> Union[str, None]:
"""返回浏览器当前url"""
...
@property
def title(self) -> str:
"""返回当前页面title"""
...
@property
def raw_data(self) -> Union[str, bytes]:
"""返回页码原始数据数据"""
...
@property
def html(self) -> str:
"""返回页面html文本"""
...
@property
def json(self) -> dict:
"""当返回内容是json格式时,返回对应的字典"""
...
@property
def response(self) -> Response:
"""返回 s 模式获取到的 Response 对象,切换到 s 模式"""
...
@property
def mode(self) -> Literal['s', 'd']:
"""返回当前模式,'s'或'd' """
...
@property
def user_agent(self) -> str:
"""返回user agent"""
...
@property
def session(self) -> Session:
"""返回Session对象,如未初始化则按配置信息创建"""
...
@property
def _session_url(self) -> str:
"""返回 session 保存的url"""
...
@property
def timeout(self) -> float:
"""返回通用timeout设置"""
...
def get(self,
url: str,
show_errmsg: bool = False,
retry: Optional[int] = None,
interval: Optional[float] = None,
timeout: Optional[float] = None,
params: Optional[dict] = None,
data: Any = None,
json: Any = None,
headers: Optional[dict] = None,
cookies: Union[CookieJar, dict] = None,
files: Optional[Any] = None,
auth: Optional[Any] = None,
allow_redirects: bool = True,
proxies: Optional[dict] = None,
hooks: Optional[Any] = None,
stream: bool = None,
verify: Union[bool, str] = None,
cert: [str, Tuple[str, str]] = None) -> Union[bool, None]:
"""跳转到一个url
:param url: 目标url
:param show_errmsg: 是否显示和抛出异常
:param retry: 重试次数,为None时使用页面对象retry_times属性值
:param interval: 重试间隔(秒),为None时使用页面对象retry_interval属性值
:param timeout: 连接超时时间
:param params: url中的参数
:param data: 携带的数据
:param json: 要发送的 JSON 数据,会自动设置 Content-Type 为 application/json
:param headers: 请求头
:param cookies: cookies信息
:param files: 要上传的文件,可以是一个字典,其中键是文件名,值是文件对象或文件路径
:param auth: 身份认证信息
:param allow_redirects: 是否允许重定向
:param proxies: 代理信息
:param hooks: 回调方法
:param stream: 是否使用流式传输
:param verify: 是否验证 SSL 证书
:param cert: SSL客户端证书文件的路径(.pem格式),或('cert', 'key')元组
:return: s模式时返回url是否可用,d模式时返回获取到的Response对象
"""
...
def post(self,
url: str,
show_errmsg: bool = False,
retry: Optional[int] = None,
interval: Optional[float] = None,
timeout: Optional[float] = None,
params: Optional[dict] = None,
data: Any = None,
json: Any = None,
headers: Optional[dict] = None,
cookies: Union[CookieJar, dict] = None,
files: Optional[Any] = None,
auth: Optional[Any] = None,
allow_redirects: bool = True,
proxies: Optional[dict] = None,
hooks: Optional[Any] = None,
stream: bool = None,
verify: Union[bool, str] = None,
cert: [str, Tuple[str, str]] = None) -> Response:
"""用post方式跳转到url
:param url: 目标url
:param show_errmsg: 是否显示和抛出异常
:param retry: 重试次数,为None时使用页面对象retry_times属性值
:param interval: 重试间隔(秒),为None时使用页面对象retry_interval属性值
:param timeout: 连接超时时间
:param params: url中的参数
:param data: 携带的数据
:param json: 要发送的 JSON 数据,会自动设置 Content-Type 为 application/json
:param headers: 请求头
:param cookies: cookies信息
:param files: 要上传的文件,可以是一个字典,其中键是文件名,值是文件对象或文件路径
:param auth: 身份认证信息
:param allow_redirects: 是否允许重定向
:param proxies: 代理信息
:param hooks: 回调方法
:param stream: 是否使用流式传输
:param verify: 是否验证 SSL 证书
:param cert: SSL客户端证书文件的路径(.pem格式),或('cert', 'key')元组
:return: 获取到的Response对象
"""
...
def ele(self,
locator: Union[Tuple[str, str], str, ChromiumElement, SessionElement],
index: int = 1,
timeout: float = None) -> Union[ChromiumElement, SessionElement]:
"""返回第一个符合条件的元素、属性或节点文本
:param locator: 元素的定位信息,可以是元素对象,loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param timeout: 查找元素超时时间(秒),默认与页面等待时间一致
:return: 元素对象或属性、文本节点文本
"""
...
def eles(self,
locator: Union[Tuple[str, str], str],
timeout: float = None) -> Union[ChromiumElementsList, SessionElementsList]:
"""返回页面中所有符合条件的元素、属性或节点文本
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param timeout: 查找元素超时时间(秒),默认与页面等待时间一致
:return: 元素对象或属性、文本组成的列表
"""
...
def s_ele(self,
locator: Union[Tuple[str, str], str] = None,
index: int = 1,
timeout: float = None) -> SessionElement:
"""查找第一个符合条件的元素以SessionElement形式返回,d模式处理复杂页面时效率很高
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param timeout: 查找元素超时时间(秒),默认与页面等待时间一致
:return: SessionElement对象或属性、文本
"""
...
def s_eles(self, locator: Union[Tuple[str, str], str], timeout: float = None) -> SessionElementsList:
"""查找所有符合条件的元素以SessionElement形式返回,d模式处理复杂页面时效率很高
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param timeout: 查找元素超时时间(秒),默认与页面等待时间一致
:return: SessionElement对象或属性、文本组成的列表
"""
...
def change_mode(self, mode: str = None, go: bool = True, copy_cookies: bool = True) -> None:
"""切换模式,接收's'或'd',除此以外的字符串会切换为 d 模式
如copy_cookies为True,切换时会把当前模式的cookies复制到目标模式
切换后,如果go是True,调用相应的get函数使访问的页面同步
:param mode: 模式字符串
:param go: 是否跳转到原模式的url
:param copy_cookies: 是否复制cookies到目标模式
:return: None
"""
...
def cookies_to_session(self, copy_user_agent: bool = True) -> None:
"""把浏览器的cookies复制到session对象
:param copy_user_agent: 是否复制ua信息
:return: None
"""
...
def cookies_to_browser(self) -> None:
"""把session对象的cookies复制到浏览器"""
...
def cookies(self, all_domains: bool = False, all_info: bool = False) -> CookiesList:
"""返回cookies
:param all_domains: 是否返回所有域的cookies
:param all_info: 是否返回所有信息,False则只返回name、value、domain
:return: cookies信息
"""
...
def close(self, others: bool = False) -> None:
"""关闭标签页
:param others: 是否关闭其它,保留自己
:return: None
"""
...
def _find_elements(self,
locator: Union[Tuple[str, str], str, ChromiumElement, SessionElement, ChromiumFrame],
timeout: float,
index: Optional[int] = 1,
relative: bool = False,
raise_err: bool = None) \
-> Union[ChromiumElement, SessionElement, ChromiumFrame, SessionElementsList, ChromiumElementsList]:
"""返回页面中符合条件的元素、属性或节点文本,默认返回第一个
:param locator: 元素的定位信息,可以是元素对象,loc元组,或查询字符串
:param timeout: 查找元素超时时间(秒),d模式专用
:param index: 第几个结果,从1开始,可传入负数获取倒数第几个,为None返回所有
:param relative: MixTab用的表示是否相对定位的参数
:param raise_err: 找不到元素是是否抛出异常,为None时根据全局设置
:return: 元素对象或属性、文本节点文本
"""
...
@@ -0,0 +1,296 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from pathlib import Path
from re import search, DOTALL
from time import sleep
from urllib.parse import urlparse
from requests import Response
from requests.structures import CaseInsensitiveDict
from tldextract import TLDExtract
from .._base.base import BasePage
from .._elements.session_element import SessionElement, make_session_ele
from .._functions.cookies import cookie_to_dict, CookiesList
from .._functions.settings import Settings as _S
from .._functions.web import format_headers
from .._units.setter import SessionPageSetter
class SessionPage(BasePage):
def __init__(self, session_or_options=None, timeout=None):
super().__init__()
self._response = None
self._set = None
self._encoding = None
self._type = 'SessionPage'
self._page = self
self._set_session_options(session_or_options)
self._s_set_runtime_settings()
if timeout is not None: # 即将废弃
self._timeout = timeout
if not self._session:
self._create_session()
def __repr__(self):
return f'<SessionPage url={self.url}>'
def _s_set_runtime_settings(self):
self._timeout = self._session_options.timeout
self._download_path = str(Path(self._session_options.download_path or '.').absolute())
self.retry_times = self._session_options.retry_times
self.retry_interval = self._session_options.retry_interval
def __call__(self, locator, index=1, timeout=None):
return self.ele(locator, index=index)
# -----------------共有属性和方法-------------------
@property
def title(self):
ele = self._ele('xpath://title', raise_err=False)
return ele.text if ele else None
@property
def url(self):
return self._url
@property
def _session_url(self):
return self._url
@property
def raw_data(self):
return self.response.content if self.response else b''
@property
def html(self):
return self.response.text if self.response else ''
@property
def json(self):
try:
return self.response.json()
except Exception:
return None
@property
def user_agent(self):
return self._headers.get('user-agent', '')
@property
def session(self):
return self._session
@property
def response(self):
return self._response
@property
def encoding(self):
return self._encoding
@property
def set(self):
if self._set is None:
self._set = SessionPageSetter(self)
return self._set
@property
def timeout(self):
return self._timeout
def get(self, url, show_errmsg=False, retry=None, interval=None, timeout=None, **kwargs):
"""用get方式跳转到url,可输入文件路径
:param url: 目标url,可指定本地文件路径
:param show_errmsg: 是否显示和抛出异常
:param retry: 重试次数,为None时使用页面对象retry_times属性值
:param interval: 重试间隔(秒),为None时使用页面对象retry_interval属性值
:param timeout: 连接超时时间(秒),为None时使用页面对象timeout属性值
:param kwargs: 连接参数
:return: url是否可用
"""
retry, interval, is_file = self._before_connect(url.replace('file:///', '', 1), retry, interval)
if is_file:
with open(self._url, 'rb') as f:
r = Response()
r._content = f.read()
r.status_code = 200
r.url = self._url
self._response = r
return True
return self._s_connect(self._url, 'get', show_errmsg, retry, interval, **kwargs)
def post(self, url, show_errmsg=False, retry=None, interval=None, **kwargs):
"""用post方式跳转到url
:param url: 目标url
:param show_errmsg: 是否显示和抛出异常
:param retry: 重试次数,为None时使用页面对象retry_times属性值
:param interval: 重试间隔(秒),为None时使用页面对象timeout属性值
:param kwargs: 连接参数
:return: url是否可用
"""
return self._s_connect(url, 'post', show_errmsg, retry, interval, **kwargs)
def ele(self, locator, index=1, timeout=None):
return self._ele(locator, index=index, method='ele()')
def eles(self, locator, timeout=None):
return self._ele(locator, index=None)
def s_ele(self, locator=None, index=1):
return make_session_ele(self) if locator is None else self._ele(locator, index=index, method='s_ele()')
def s_eles(self, locator):
return self._ele(locator, index=None)
def _find_elements(self, locator, timeout, index=1, relative=True, raise_err=None):
return locator if isinstance(locator, SessionElement) else make_session_ele(self, locator, index=index)
def cookies(self, all_domains=False, all_info=False):
if all_domains:
cookies = self.session.cookies
else:
if self.url:
ex_url = TLDExtract(
suffix_list_urls=["https://publicsuffix.org/list/public_suffix_list.dat",
f"file:///{_S.suffixes_list}"]).extract_str(self._session_url)
domain = f'{ex_url.domain}.{ex_url.suffix}' if ex_url.suffix else ex_url.domain
cookies = tuple(c for c in self.session.cookies if domain in c.domain or c.domain == '')
else:
cookies = tuple(c for c in self.session.cookies)
if all_info:
r = CookiesList()
for c in cookies:
r.append(cookie_to_dict(c))
else:
r = CookiesList()
for c in cookies:
c = cookie_to_dict(c)
r.append({'name': c['name'], 'value': c['value'], 'domain': c['domain']})
return r
def close(self):
self._session.close()
if self._response is not None:
self._response.close()
def _s_connect(self, url, mode, show_errmsg=False, retry=None, interval=None, **kwargs):
retry, interval, is_file = self._before_connect(url, retry, interval)
self._response = self._make_response(self._url, mode, retry, interval, show_errmsg, **kwargs)
if self._response is None:
self._url_available = False
else:
if self._response.ok:
self._url_available = True
else:
if show_errmsg:
raise ConnectionError(_S._lang.join(_S._lang.STATUS_CODE_, self._response.status_code))
self._url_available = False
return self._url_available
def _make_response(self, url, mode='get', retry=None, interval=None, show_errmsg=False, **kwargs):
kwargs = CaseInsensitiveDict(kwargs)
if 'headers' in kwargs:
kwargs['headers'] = CaseInsensitiveDict(format_headers(kwargs['headers']))
else:
kwargs['headers'] = CaseInsensitiveDict()
# 设置referer和host值
parsed_url = urlparse(url)
hostname = parsed_url.netloc
scheme = parsed_url.scheme
if not check_headers(kwargs['headers'], self._headers, 'Referer'):
kwargs['headers']['Referer'] = self.url if self.url else f'{scheme}://{hostname}'
elif not kwargs['headers']['Referer']:
kwargs['headers'].pop('Referer')
if not check_headers(kwargs['headers'], self._headers, 'Host'):
kwargs['headers']['Host'] = hostname
elif not kwargs['headers']['Host']:
kwargs['headers'].pop('Host')
if not check_headers(kwargs, self._headers, 'timeout'):
kwargs['timeout'] = self.timeout
h = CaseInsensitiveDict(self._headers)
for k, v in kwargs['headers'].items():
h[k] = v
kwargs['headers'] = h
r = err = None
retry = retry if retry is not None else self.retry_times
interval = interval if interval is not None else self.retry_interval
for i in range(retry + 1):
try:
if mode == 'get':
r = self.session.get(url, **kwargs)
elif mode == 'post':
r = self.session.post(url, **kwargs)
if r and r.content:
if self._encoding:
r.encoding = self._encoding
return r
return set_charset(r)
except Exception as e:
err = e
# if r and r.status_code in (403, 404):
# break
if i < retry:
sleep(interval)
if show_errmsg:
print(f'{_S._lang.RETRY} {url}')
if show_errmsg:
if err:
raise err
elif r is not None:
raise (ConnectionError(_S._lang.join(_S._lang.STATUS_CODE_, r.status_code)) if r.content
else ConnectionError(_S._lang.join(_S._lang.CONTENT_IS_EMPTY)))
else:
raise ConnectionError(_S._lang.join(_S._lang.CONNECT_ERR))
else:
if r is not None:
return r if r.content else None
else:
return None
def check_headers(kwargs, headers, arg):
return arg in kwargs or arg in headers
def set_charset(response):
# 在headers中获取编码
content_type = response.headers.get('content-type', '').lower()
if not content_type.endswith(';'):
content_type += ';'
charset = search(r'charset[=: ]*(.*)?;?', content_type)
if charset:
response.encoding = charset.group(1)
# 在headers中获取不到编码,且如果是网页
elif content_type.replace(' ', '').startswith('text/html'):
re_result = search(b'<meta.*?charset=[ \\\'"]*([^"\\\' />]+).*?>', response.content, DOTALL)
if re_result:
charset = re_result.group(1).decode()
else:
charset = response.apparent_encoding
response.encoding = charset
return response
@@ -0,0 +1,322 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from pathlib import Path
from typing import Any, Union, Tuple, Optional
from requests import Session, Response
from requests.structures import CaseInsensitiveDict
from .._base.base import BasePage
from .._configs.session_options import SessionOptions
from .._elements.session_element import SessionElement
from .._functions.cookies import CookiesList
from .._functions.elements import SessionElementsList
from .._units.setter import SessionPageSetter
class SessionPage(BasePage):
"""SessionPage封装了页面操作的常用功能,使用requests来获取、解析网页"""
_session_options: Optional[SessionOptions] = ...
_url: str = ...
_response: Optional[Response] = ...
_url_available: bool = ...
_timeout: float = ...
retry_times: int = ...
retry_interval: float = ...
_set: Optional[SessionPageSetter] = ...
_encoding: Optional[str] = ...
_page: SessionPage = ...
def __init__(self, session_or_options: Union[Session, SessionOptions] = None):
"""
:param session_or_options: Session对象或SessionOptions对象
"""
...
def _s_set_runtime_settings(self) -> None:
"""设置运行时用到的属性"""
...
def __call__(self,
locator: Union[Tuple[str, str], str, SessionElement],
index: int = 1,
timeout: float = None) -> SessionElement:
"""在内部查找元素
例:ele2 = ele1('@id=ele_id')
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param timeout: 不起实际作用,用于和ChromiumElement对应,便于无差别调用
:return: SessionElement对象或属性文本
"""
...
@property
def title(self) -> str:
"""返回网页title"""
...
@property
def url(self) -> str:
"""返回当前访问url"""
...
@property
def _session_url(self) -> str:
"""返回当前访问url"""
...
@property
def raw_data(self) -> Union[str, bytes]:
"""返回页面原始数据"""
...
@property
def html(self) -> str:
"""返回页面的html文本"""
...
@property
def json(self) -> Union[dict, None]:
"""当返回内容是json格式时,返回对应的字典,非json格式时返回None"""
...
@property
def user_agent(self) -> str:
"""返回user agent"""
...
@property
def session(self) -> Session:
"""返回Session对象"""
...
@property
def response(self) -> Response:
"""返回访问url得到的Response对象"""
...
@property
def encoding(self) -> str:
"""返回设置的编码,s模式专用"""
...
@property
def set(self) -> SessionPageSetter:
"""返回用于设置的对象"""
...
@property
def timeout(self) -> float:
"""返回超时设置"""
...
def get(self,
url: Union[Path, str],
show_errmsg: bool | None = False,
retry: int | None = None,
interval: float | None = None,
timeout: float | None = None,
params: dict | None = ...,
data: Any = ...,
json: Any = ...,
headers: Union[dict, str, None] = ...,
cookies: Any | None = ...,
files: Any | None = ...,
auth: Any | None = ...,
allow_redirects: bool = ...,
proxies: dict | None = ...,
hooks: Any | None = ...,
stream: Any | None = ...,
verify: Any | None = ...,
cert: Any | None = ...) -> bool:
"""用get方式跳转到url
:param url: 目标url
:param show_errmsg: 是否显示和抛出异常
:param retry: 重试次数,为None时使用页面对象retry_times属性值
:param interval: 重试间隔(秒),为None时使用页面对象retry_interval属性值
:param timeout: 连接超时时间
:param params: url中的参数
:param data: 携带的数据
:param json: 要发送的 JSON 数据,会自动设置 Content-Type 为 application/json
:param headers: 请求头
:param cookies: cookies信息
:param files: 要上传的文件,可以是一个字典,其中键是文件名,值是文件对象或文件路径
:param auth: 身份认证信息
:param allow_redirects: 是否允许重定向
:param proxies: 代理信息
:param hooks: 回调方法
:param stream: 是否使用流式传输
:param verify: 是否验证 SSL 证书
:param cert: SSL客户端证书文件的路径(.pem格式),或('cert', 'key')元组
:return: s模式时返回url是否可用,d模式时返回获取到的Response对象
"""
...
def post(self,
url: str,
show_errmsg: bool = False,
retry: int | None = None,
interval: float | None = None,
timeout: float | None = ...,
params: dict | None = ...,
data: Any = ...,
json: Any = ...,
headers: Union[dict, str, None] = ...,
cookies: Any | None = ...,
files: Any | None = ...,
auth: Any | None = ...,
allow_redirects: bool = ...,
proxies: dict | None = ...,
hooks: Any | None = ...,
stream: Any | None = ...,
verify: Any | None = ...,
cert: Any | None = ...) -> bool:
"""用post方式跳转到url
:param url: 目标url
:param show_errmsg: 是否显示和抛出异常
:param retry: 重试次数,为None时使用页面对象retry_times属性值
:param interval: 重试间隔(秒),为None时使用页面对象retry_interval属性值
:param timeout: 连接超时时间
:param params: url中的参数
:param data: 携带的数据
:param json: 要发送的 JSON 数据,会自动设置 Content-Type 为 application/json
:param headers: 请求头
:param cookies: cookies信息
:param files: 要上传的文件,可以是一个字典,其中键是文件名,值是文件对象或文件路径
:param auth: 身份认证信息
:param allow_redirects: 是否允许重定向
:param proxies: 代理信息
:param hooks: 回调方法
:param stream: 是否使用流式传输
:param verify: 是否验证 SSL 证书
:param cert: SSL客户端证书文件的路径(.pem格式),或('cert', 'key')元组
:return: s模式时返回url是否可用,d模式时返回获取到的Response对象
"""
...
def ele(self,
locator: Union[Tuple[str, str], str, SessionElement],
index: int = 1,
timeout: float = None) -> SessionElement:
"""返回页面中符合条件的一个元素、属性或节点文本
:param locator: 元素的定位信息,可以是元素对象,loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param timeout: 不起实际作用,用于和ChromiumElement对应,便于无差别调用
:return: SessionElement对象或属性、文本
"""
...
def eles(self,
locator: Union[Tuple[str, str], str],
timeout: float = None) -> SessionElementsList:
"""返回页面中所有符合条件的元素、属性或节点文本
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param timeout: 不起实际作用,用于和ChromiumElement对应,便于无差别调用
:return: SessionElement对象或属性、文本组成的列表
"""
...
def s_ele(self,
locator: Union[Tuple[str, str], str, SessionElement] = None,
index: int = 1) -> SessionElement:
"""返回页面中符合条件的一个元素、属性或节点文本
:param locator: 元素的定位信息,可以是元素对象,loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:return: SessionElement对象或属性、文本
"""
...
def s_eles(self, locator: Union[Tuple[str, str], str]) -> SessionElementsList:
"""返回页面中符合条件的所有元素、属性或节点文本
:param locator: 元素的定位信息,可以是元素对象,loc元组,或查询字符串
:return: SessionElement对象或属性、文本
"""
...
def _find_elements(self,
locator: Union[Tuple[str, str], str, SessionElement],
timeout: float,
index: Optional[int] = 1,
relative: bool = True,
raise_err: bool = None) -> Union[SessionElement, SessionElementsList]:
"""返回页面中符合条件的元素、属性或节点文本,默认返回第一个
:param locator: 元素的定位信息,可以是元素对象,loc元组,或查询字符串
:param timeout: 不起实际作用,用于和父类对应
:param index: 第几个结果,从1开始,可传入负数获取倒数第几个,为None返回所有
:param raise_err: 找不到元素是是否抛出异常,为None时根据全局设置
:return: SessionElement对象
"""
...
def cookies(self,
all_domains: bool = False,
all_info: bool = False) -> CookiesList:
"""返回cookies
:param all_domains: 是否返回所有域的cookies
:param all_info: 是否返回所有信息,False则只返回name、value、domain
:return: cookies组成的列表
"""
...
def close(self) -> None:
"""关闭Session对象"""
...
def _s_connect(self,
url: str,
mode: str,
show_errmsg: bool = False,
retry: int = None,
interval: float = None,
**kwargs) -> bool:
"""执行get或post连接
:param url: 目标url
:param mode: 'get' 或 'post'
:param show_errmsg: 是否显示和抛出异常
:param retry: 重试次数
:param interval: 重试间隔(秒)
:param kwargs: 连接参数
:return: url是否可用
"""
...
def _make_response(self,
url: str,
mode: str = 'get',
retry: int = None,
interval: float = None,
show_errmsg: bool = False,
**kwargs) -> Response:
"""生成Response对象
:param url: 目标url
:param mode: 'get' 或 'post'
:param show_errmsg: 是否显示和抛出异常
:param kwargs: 其它参数
:return: Response对象
"""
...
def check_headers(kwargs: Union[dict, CaseInsensitiveDict],
headers: Union[dict, CaseInsensitiveDict],
arg: str) -> bool:
"""检查kwargs或headers中是否有arg所示属性
:param kwargs: 要检查的参数dict
:param headers: 要检查的headers
:param arg: 属性名称
:return: 检查结果
"""
...
def set_charset(response: Response) -> Response:
"""设置Response对象的编码
:param response: Response对象
:return: Response对象
"""
...
@@ -0,0 +1,260 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from .chromium_page import ChromiumPage
from .session_page import SessionPage
from .._base.base import BasePage
from .._configs.chromium_options import ChromiumOptions
from .._configs.session_options import SessionOptions
from .._functions.cookies import set_session_cookies, set_tab_cookies
from .._functions.settings import Settings as _S
from .._units.setter import WebPageSetter
class WebPage(SessionPage, ChromiumPage, BasePage):
def __new__(cls, mode='d', timeout=None, chromium_options=None, session_or_options=None):
# 即将废弃timeout
return super().__new__(cls, chromium_options)
def __init__(self, mode='d', timeout=None, chromium_options=None, session_or_options=None):
# 即将废弃timeout
if hasattr(self, '_created'):
return
mode = mode.lower()
if mode not in ('s', 'd'):
raise ValueError(_S._lang.join(_S._lang.INCORRECT_VAL_, 'mode', ALLOW_VAL='"s", "d"', CURR_VAL=mode))
self._d_mode = mode == 'd'
self._has_driver = True
self._has_session = True
super().__init__(session_or_options=session_or_options)
if not chromium_options:
chromium_options = ChromiumOptions(read_file=chromium_options)
chromium_options.set_timeouts(base=self._timeout).set_paths(download_path=self.download_path)
super(SessionPage, self).__init__(addr_or_opts=chromium_options, timeout=timeout) # 即将废弃timeout
self._type = 'WebPage'
self.change_mode(mode, go=False, copy_cookies=False)
def __call__(self, locator, index=1, timeout=None):
if self._d_mode:
return super(SessionPage, self).__call__(locator, index=index, timeout=timeout)
return super().__call__(locator, index=index)
def __repr__(self):
return f'<WebPage browser_id={self.browser.id} tab_id={self.tab_id}>'
@property
def latest_tab(self):
return self.browser._get_tab(id_or_num=self.tab_ids[0], mix=True, as_id=not _S.singleton_tab_obj)
@property
def set(self):
if self._set is None:
self._set = WebPageSetter(self)
return self._set
@property
def url(self):
return self._browser_url if self._d_mode else self._session_url
@property
def _browser_url(self):
return super(SessionPage, self).url if self._driver else None
@property
def title(self):
return super(SessionPage, self).title if self._d_mode else super().title
@property
def raw_data(self):
if self._d_mode:
return super(SessionPage, self).html if self._has_driver else ''
return super().raw_data
@property
def html(self):
if self._d_mode:
return super(SessionPage, self).html if self._has_driver else ''
return super().html
@property
def json(self):
return super(SessionPage, self).json if self._d_mode else super().json
@property
def response(self):
return self._response
@property
def mode(self):
return 'd' if self._d_mode else 's'
@property
def user_agent(self):
return super(SessionPage, self).user_agent if self._d_mode else super().user_agent
@property
def session(self):
if self._session is None:
self._create_session()
return self._session
@property
def _session_url(self):
return self._response.url if self._response else None
@property
def timeout(self):
return self.timeouts.base if self._d_mode else self._timeout
@property
def download_path(self):
return self.browser.download_path
def get(self, url, show_errmsg=False, retry=None, interval=None, timeout=None, **kwargs):
if self._d_mode:
return super(SessionPage, self).get(url, show_errmsg, retry, interval, timeout)
if timeout is None:
timeout = self.timeouts.page_load if self._has_driver else self.timeout
return super().get(url, show_errmsg, retry, interval, timeout, **kwargs)
def post(self, url, show_errmsg=False, retry=None, interval=None, **kwargs):
if self.mode == 'd':
self.cookies_to_session()
super().post(url, show_errmsg, retry, interval, **kwargs)
return self.response
def ele(self, locator, index=1, timeout=None):
return (super(SessionPage, self).ele(locator, index=index, timeout=timeout)
if self._d_mode else super().ele(locator, index=index))
def eles(self, locator, timeout=None):
return super(SessionPage, self).eles(locator, timeout=timeout) if self._d_mode else super().eles(locator)
def s_ele(self, locator=None, index=1, timeout=None):
return (super(SessionPage, self).s_ele(locator, index=index, timeout=timeout)
if self._d_mode else super().s_ele(locator, index=index, timeout=timeout))
def s_eles(self, locator, timeout=None):
return (super(SessionPage, self).s_eles(locator, timeout=timeout)
if self._d_mode else super().s_eles(locator, timeout=timeout))
def change_mode(self, mode=None, go=True, copy_cookies=True):
if mode:
mode = mode.lower()
if mode is not None and ((mode == 'd' and self._d_mode) or (mode == 's' and not self._d_mode)):
return
self._d_mode = not self._d_mode
# s模式转d模式
if self._d_mode:
if self._driver is None or not self._driver.is_running:
self._driver_init(self.tab_id)
self._get_document()
self._url = None if not self._has_driver else super(SessionPage, self).url
self._has_driver = True
if self._session_url:
if copy_cookies:
self.cookies_to_browser()
if go:
self.get(self._session_url)
return
# d模式转s模式
self._has_session = True
self._url = self._session_url
if self._has_driver and self._driver.is_running:
if copy_cookies:
self.cookies_to_session()
if go and not self.get(super(SessionPage, self).url):
raise ConnectionError(_S._lang.join(_S._lang.S_MODE_GET_FAILED))
def cookies_to_session(self, copy_user_agent=True):
if not self._has_session:
return
if copy_user_agent:
user_agent = self._run_cdp('Runtime.evaluate', expression='navigator.userAgent;')['result']['value']
self._headers.update({"User-Agent": user_agent})
set_session_cookies(self.session, super(SessionPage, self).cookies())
def cookies_to_browser(self):
if not self._has_driver:
return
set_tab_cookies(self, super().cookies())
def cookies(self, all_domains=False, all_info=False):
return super(SessionPage, self).cookies(all_domains, all_info) if self._d_mode \
else super().cookies(all_domains, all_info)
def get_tab(self, id_or_num=None, title=None, url=None, tab_type='page', as_id=False):
return self.browser._get_tab(id_or_num=id_or_num, title=title, url=url,
tab_type=tab_type, mix=True, as_id=as_id)
def get_tabs(self, title=None, url=None, tab_type='page', as_id=False):
return self.browser._get_tabs(title=title, url=url, tab_type=tab_type, mix=True, as_id=as_id)
def new_tab(self, url=None, new_window=False, background=False, new_context=False):
return self.browser._new_tab(url=url, new_window=new_window, background=background, new_context=new_context)
def close_driver(self):
if self._has_driver:
self.change_mode('s')
try:
self.driver.run('Browser.close')
except Exception:
pass
self._driver.stop()
self._driver = None
self._has_driver = None
def close_session(self):
if self._has_session:
self.change_mode('d')
self._session.close()
if self._response is not None:
self._response.close()
self._session = None
self._response = None
self._has_session = None
def close(self):
if self._has_driver:
self.browser._close_tab(self)
if self._session:
self._session.close()
if self._response is not None:
self._response.close()
def _find_elements(self, locator, timeout, index=1, relative=False, raise_err=None):
if self._d_mode:
return super(SessionPage, self)._find_elements(locator, timeout=timeout, index=index, relative=relative)
return super()._find_elements(locator, index=index, timeout=timeout)
def quit(self, timeout=5, force=True, del_data=False):
if self._has_session:
self._session.close()
self._session = None
self._response = None
self._has_session = None
if self._has_driver:
super(SessionPage, self).quit(timeout, force, del_data=del_data)
self._driver = None
self._has_driver = None
def _set_session_options(self, session_or_options=None):
if session_or_options is None:
session_or_options = self.browser._session_options or SessionOptions(
read_file=self.browser._session_options is None)
super()._set_session_options(session_or_options)
@@ -0,0 +1,380 @@
# -*- coding:utf-8 -*-
"""
@Author : g1879
@Contact : g1879@qq.com
@Website : https://DrissionPage.cn
@Copyright: (c) 2020 by g1879, Inc. All Rights Reserved.
"""
from http.cookiejar import CookieJar
from typing import Union, Tuple, List, Any, Optional, Literal
from requests import Session, Response
from .chromium_frame import ChromiumFrame
from .chromium_page import ChromiumPage
from .mix_tab import MixTab
from .session_page import SessionPage
from .._base.base import BasePage
from .._configs.chromium_options import ChromiumOptions
from .._configs.session_options import SessionOptions
from .._elements.chromium_element import ChromiumElement
from .._elements.session_element import SessionElement
from .._functions.cookies import CookiesList
from .._functions.elements import SessionElementsList, ChromiumElementsList
from .._units.setter import WebPageSetter
from .._units.waiter import WebPageWaiter
class WebPage(SessionPage, ChromiumPage, BasePage):
"""整合浏览器和request的页面类"""
_d_mode: bool = ...
_set: WebPageSetter = ...
_has_driver: Optional[bool] = ...
_has_session: Optional[bool] = ...
_session_options: Union[SessionOptions, None] = ...
_chromium_options: Union[ChromiumOptions, None] = ...
def __init__(self,
mode: str = 'd',
chromium_options: Union[ChromiumOptions, bool] = None,
session_or_options: Union[Session, SessionOptions, bool] = None) -> None:
"""初始化函数
:param mode: 'd' 或 's',即driver模式和session模式
:param chromium_options: ChromiumOptions对象,传入None时从默认ini文件读取,传入False时不读取ini文件,使用默认配置
:param session_or_options: Session对象或SessionOptions对象,传入None时从默认ini文件读取,传入False时不读取ini文件,使用默认配置
"""
...
def __call__(self,
locator: Union[Tuple[str, str], str, ChromiumElement, SessionElement],
index: int = 1,
timeout: float = None) -> Union[ChromiumElement, SessionElement]:
"""在内部查找元素
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param timeout: 超时时间(秒)
:return: 子元素对象
"""
...
@property
def latest_tab(self) -> Union[MixTab, WebPage, str]:
"""返回最新的标签页,最新标签页指最后创建或最后被激活的
当Settings.singleton_tab_obj==True时返回Tab对象,否则返回tab id"""
...
@property
def set(self) -> WebPageSetter:
"""返回用于设置的对象"""
...
@property
def wait(self) -> WebPageWaiter:
"""返回用于等待的对象"""
...
@property
def url(self) -> Union[str, None]:
"""返回浏览器当前url"""
...
@property
def _browser_url(self) -> Union[str, None]:
"""返回浏览器当前url"""
...
@property
def title(self) -> str:
"""返回当前页面title"""
...
@property
def raw_data(self) -> Union[str, bytes]:
"""返回页码原始数据数据"""
...
@property
def html(self) -> str:
"""返回页面html文本"""
...
@property
def json(self) -> dict:
"""当返回内容是json格式时,返回对应的字典"""
...
@property
def response(self) -> Response:
"""返回 s 模式获取到的 Response 对象,切换到 s 模式"""
...
@property
def mode(self) -> Literal['s', 'd']:
"""返回当前模式,'s'或'd' """
...
@property
def user_agent(self) -> str:
"""返回user agent"""
...
@property
def session(self) -> Session:
"""返回Session对象,如未初始化则按配置信息创建"""
...
@property
def _session_url(self) -> str:
"""返回 session 保存的url"""
...
@property
def timeout(self) -> float:
"""返回通用timeout设置"""
...
def get(self,
url: str,
show_errmsg: bool = False,
retry: Optional[int] = None,
interval: Optional[float] = None,
timeout: Optional[float] = None,
params: Optional[dict] = None,
data: Any = None,
json: Any = None,
headers: Optional[dict] = None,
cookies: Union[CookieJar, dict] = None,
files: Optional[Any] = None,
auth: Optional[Any] = None,
allow_redirects: bool = True,
proxies: Optional[dict] = None,
hooks: Optional[Any] = None,
stream: bool = None,
verify: Union[bool, str] = None,
cert: [str, Tuple[str, str]] = None) -> Union[bool, None]:
"""跳转到一个url
:param url: 目标url
:param show_errmsg: 是否显示和抛出异常
:param retry: 重试次数,为None时使用页面对象retry_times属性值
:param interval: 重试间隔(秒),为None时使用页面对象retry_interval属性值
:param timeout: 连接超时时间
:param params: url中的参数
:param data: 携带的数据
:param json: 要发送的 JSON 数据,会自动设置 Content-Type 为 application/json
:param headers: 请求头
:param cookies: cookies信息
:param files: 要上传的文件,可以是一个字典,其中键是文件名,值是文件对象或文件路径
:param auth: 身份认证信息
:param allow_redirects: 是否允许重定向
:param proxies: 代理信息
:param hooks: 回调方法
:param stream: 是否使用流式传输
:param verify: 是否验证 SSL 证书
:param cert: SSL客户端证书文件的路径(.pem格式),或('cert', 'key')元组
:return: s模式时返回url是否可用,d模式时返回获取到的Response对象
"""
...
def post(self,
url: str,
show_errmsg: bool = False,
retry: Optional[int] = None,
interval: Optional[float] = None,
timeout: Optional[float] = None,
params: Optional[dict] = None,
data: Any = None,
json: Any = None,
headers: Optional[dict] = None,
cookies: Union[CookieJar, dict] = None,
files: Optional[Any] = None,
auth: Optional[Any] = None,
allow_redirects: bool = True,
proxies: Optional[dict] = None,
hooks: Optional[Any] = None,
stream: bool = None,
verify: Union[bool, str] = None,
cert: [str, Tuple[str, str]] = None) -> Response:
"""用post方式跳转到url
:param url: 目标url
:param show_errmsg: 是否显示和抛出异常
:param retry: 重试次数,为None时使用页面对象retry_times属性值
:param interval: 重试间隔(秒),为None时使用页面对象retry_interval属性值
:param timeout: 连接超时时间
:param params: url中的参数
:param data: 携带的数据
:param json: 要发送的 JSON 数据,会自动设置 Content-Type 为 application/json
:param headers: 请求头
:param cookies: cookies信息
:param files: 要上传的文件,可以是一个字典,其中键是文件名,值是文件对象或文件路径
:param auth: 身份认证信息
:param allow_redirects: 是否允许重定向
:param proxies: 代理信息
:param hooks: 回调方法
:param stream: 是否使用流式传输
:param verify: 是否验证 SSL 证书
:param cert: SSL客户端证书文件的路径(.pem格式),或('cert', 'key')元组
:return: 获取到的Response对象
"""
...
def ele(self,
locator: Union[Tuple[str, str], str, ChromiumElement, SessionElement],
index: int = 1,
timeout: float = None) -> Union[ChromiumElement, SessionElement]:
"""返回第一个符合条件的元素、属性或节点文本
:param locator: 元素的定位信息,可以是元素对象,loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param timeout: 查找元素超时时间(秒),默认与页面等待时间一致
:return: 元素对象或属性、文本节点文本
"""
...
def eles(self,
locator: Union[Tuple[str, str], str],
timeout: float = None) -> Union[ChromiumElementsList, SessionElementsList]:
"""返回页面中所有符合条件的元素、属性或节点文本
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param timeout: 查找元素超时时间(秒),默认与页面等待时间一致
:return: 元素对象或属性、文本组成的列表
"""
...
def s_ele(self,
locator: Union[Tuple[str, str], str] = None,
index: int = 1,
timeout: float = None) -> SessionElement:
"""查找第一个符合条件的元素以SessionElement形式返回,d模式处理复杂页面时效率很高
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param index: 获取第几个,从1开始,可传入负数获取倒数第几个
:param timeout: 查找元素超时时间(秒),默认与页面等待时间一致
:return: SessionElement对象或属性、文本
"""
...
def s_eles(self, locator: Union[Tuple[str, str], str], timeout: float = None) -> SessionElementsList:
"""查找所有符合条件的元素以SessionElement形式返回,d模式处理复杂页面时效率很高
:param locator: 元素的定位信息,可以是loc元组,或查询字符串
:param timeout: 查找元素超时时间(秒),默认与页面等待时间一致
:return: SessionElement对象或属性、文本组成的列表
"""
...
def change_mode(self,
mode: str = None,
go: bool = True,
copy_cookies: bool = True) -> None:
"""切换模式,接收's'或'd',除此以外的字符串会切换为 d 模式
如copy_cookies为True,切换时会把当前模式的cookies复制到目标模式
切换后,如果go是True,调用相应的get函数使访问的页面同步
:param mode: 模式字符串
:param go: 是否跳转到原模式的url
:param copy_cookies: 是否复制cookies到目标模式
:return: None
"""
...
def cookies_to_session(self, copy_user_agent: bool = True) -> None:
"""把driver对象的cookies复制到session对象
:param copy_user_agent: 是否复制ua信息
:return: None
"""
...
def cookies_to_browser(self) -> None:
"""把session对象的cookies复制到浏览器"""
...
def cookies(self,
all_domains: bool = False,
all_info: bool = False) -> CookiesList:
"""返回cookies
:param all_domains: 是否返回所有域的cookies
:param all_info: 是否返回所有信息,False则只返回name、value、domain
:return: cookies信息
"""
...
def get_tab(self,
id_or_num: Union[str, MixTab, int] = None,
title: str = None,
url: str = None,
tab_type: Union[str, list, tuple] = 'page',
as_id: bool = False) -> Union[MixTab, str, None]:
"""获取一个标签页对象,id_or_num不为None时,后面几个参数无效
:param id_or_num: 要获取的标签页id或序号,序号从1开始,可传入负数获取倒数第几个,不是视觉排列顺序,而是激活顺序
:param title: 要匹配title的文本,模糊匹配,为None则匹配所有
:param url: 要匹配url的文本,模糊匹配,为None则匹配所有
:param tab_type: tab类型,可用列表输入多个,如 'page', 'iframe' 等,为None则匹配所有
:param as_id: 是否返回标签页id而不是标签页对象
:return: MixTab对象
"""
...
def get_tabs(self,
title: str = None,
url: str = None,
tab_type: Union[str, list, tuple] = 'page',
as_id: bool = False) -> Union[List[MixTab], List[str]]:
"""查找符合条件的tab,返回它们组成的列表
:param title: 要匹配title的文本,模糊匹配,为None则匹配所有
:param url: 要匹配url的文本,模糊匹配,为None则匹配所有
:param tab_type: tab类型,可用列表输入多个,如 'page', 'iframe' 等,为None则匹配所有
:param as_id: 是否返回标签页id而不是标签页对象
:return: ChromiumTab对象组成的列表
"""
...
def new_tab(self,
url: str = None,
new_window: bool = False,
background: bool = False,
new_context: bool = False) -> MixTab:
"""新建一个标签页
:param url: 新标签页跳转到的网址
:param new_window: 是否在新窗口打开标签页
:param background: 是否不激活新标签页,如new_window为True则无效
:param new_context: 是否创建新的上下文
:return: 新标签页对象
"""
...
def close_driver(self) -> None:
"""关闭driver及浏览器"""
...
def close_session(self) -> None:
"""关闭session"""
...
def close(self) -> None:
"""关闭标签页和Session"""
...
def _find_elements(self,
locator: Union[Tuple[str, str], str, ChromiumElement, SessionElement, ChromiumFrame],
timeout: float,
index: Optional[int] = 1,
relative: bool = False,
raise_err: bool = None) -> Union[
ChromiumElement, SessionElement, ChromiumFrame, SessionElementsList, ChromiumElementsList]:
"""返回页面中符合条件的元素、属性或节点文本,默认返回第一个
:param locator: 元素的定位信息,可以是元素对象,loc元组,或查询字符串
:param timeout: 查找元素超时时间(秒),d模式专用
:param index: 第几个结果,从1开始,可传入负数获取倒数第几个,为None返回所有
:param relative: MixTab用的表示是否相对定位的参数
:param raise_err: 找不到元素是是否抛出异常,为None时根据全局设置
:return: 元素对象或属性、文本节点文本
"""
...
def quit(self,
timeout: float = 5,
force: bool = True,
del_data: bool = False) -> None:
"""关闭浏览器和Session
:param timeout: 等待浏览器关闭超时时间(秒)
:param force: 关闭超时是否强制终止进程
:param del_data: 是否删除用户文件夹
:return: None
"""
...
Loaded 100 of 7311 files, more files were not shown because too many files have changed in this diff. Show more