blackteay/DrissionPage
1
0
Fork 0
mirror of https://gitee.com/g1879/DrissionPage.git synced 2024-12-10 04:00:23 +08:00
Code Issues Projects Releases Wiki Activity

4.1.0.0b13Frame对象改为单例；parent()增加timeout参数；sr内找元素元素加上timeout参数；修复两个问题

Browse Source
This commit is contained in:
g1879 2024-07-26 19:07:30 +08:00
parent 0812f5233f
commit 955c72d61c
11 changed files with 102 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
DrissionPage/__init__.py
View File

@ -14,4 +14,4 @@ from ._pages.chromium_page import ChromiumPage
from ._pages.mix_page import MixPage
from ._pages.mix_page import MixPage as WebPage
__version__ = '4.1.0.0b12'
__version__ = '4.1.0.0b13'

5
DrissionPage/_base/base.py
View File

@ -136,10 +136,11 @@ class DrissionElement(BaseElement):
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):
def parent(self, level_or_loc=1, index=1, timeout=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
"""
if isinstance(level_or_loc, int):
@ -154,7 +155,7 @@ class DrissionElement(BaseElement):
else:
raise TypeError('level_or_loc参数只能是tuple、int或str。')
return self._ele(loc, timeout=0, relative=True, raise_err=False, method='parent()')
return self._ele(loc, timeout=timeout, relative=True, raise_err=False, method='parent()')
def child(self, locator='', index=1, timeout=None, ele_only=True):
"""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

8
DrissionPage/_base/base.pyi
View File

@ -13,9 +13,10 @@ from DownloadKit import DownloadKit
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.mix_page import MixPage
from .._pages.session_page import SessionPage
class BaseParser(object):
@ -82,6 +83,8 @@ class BaseElement(BaseParser):
def nexts(self): ...
def get_frame(self, loc_or_ind, timeout=None) -> ChromiumFrame: ...
class DrissionElement(BaseElement):
@ -103,7 +106,8 @@ class DrissionElement(BaseElement):
def parent(self,
level_or_loc: Union[tuple, str, int] = 1,
index: int = 1) -> Union[DrissionElement, None]: ...
index: int = 1,
timeout: float = None) -> Union[DrissionElement, None]: ...
def child(self,
locator: Union[Tuple[str, str], str, int] = '',

72
DrissionPage/_elements/chromium_element.py
View File

@ -232,13 +232,14 @@ class ChromiumElement(DrissionElement):
if (is_checked and uncheck) or (not is_checked and not uncheck):
self.click()
def parent(self, level_or_loc=1, index=1):
def parent(self, level_or_loc=1, index=1, timeout=0):
"""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
"""
return super().parent(level_or_loc, index)
return super().parent(level_or_loc, index, timeout=timeout)
def child(self, locator='', index=1, timeout=None, ele_only=True):
"""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
@ -1041,10 +1042,11 @@ class ShadowRoot(BaseElement):
Thread(target=run_js, args=(self, script, as_expr,
self.owner.timeouts.script if timeout is None else timeout, args)).start()
def parent(self, level_or_loc=1, index=1):
def parent(self, level_or_loc=1, index=1, timeout=0):
"""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
"""
if isinstance(level_or_loc, int):
@ -1061,12 +1063,13 @@ class ShadowRoot(BaseElement):
else:
raise TypeError('level_or_loc参数只能是tuple、int或str。')
return self.parent_ele._ele(loc, timeout=0, relative=True, raise_err=False, method='parent()')
return self.parent_ele._ele(loc, timeout=timeout, relative=True, raise_err=False, method='parent()')
def child(self, locator='', index=1):
def child(self, locator='', index=1, timeout=None):
"""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
"""
if not locator:
@ -1078,14 +1081,16 @@ class ShadowRoot(BaseElement):
loc = loc[1].lstrip('./')
loc = f'xpath:./{loc}'
ele = self._ele(loc, index=index, relative=True)
ele = self._ele(loc, index=index, relative=True, timeout=timeout)
return ele if ele else NoneElement(self.owner, 'child()', {'locator': locator, 'index': index})
return ele if ele else NoneElement(self.owner, 'child()',
{'locator': locator, 'index': index, 'timeout': timeout})
def next(self, locator='', index=1):
def next(self, locator='', index=1, timeout=None):
"""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
"""
loc = get_loc(locator, True)
@ -1094,15 +1099,17 @@ class ShadowRoot(BaseElement):
loc = loc[1].lstrip('./')
xpath = f'xpath:./{loc}'
ele = self.parent_ele._ele(xpath, index=index, relative=True)
ele = self.parent_ele._ele(xpath, index=index, relative=True, timeout=timeout)
return ele if ele else NoneElement(self.owner, 'next()', {'locator': locator, 'index': index})
return ele if ele else NoneElement(self.owner, 'next()',
{'locator': locator, 'index': index, 'timeout': timeout})
def before(self, locator='', index=1):
def before(self, locator='', index=1, timeout=None):
"""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
"""
loc = get_loc(locator, True)
@ -1111,23 +1118,27 @@ class ShadowRoot(BaseElement):
loc = loc[1].lstrip('./')
xpath = f'xpath:./preceding::{loc}'
ele = self.parent_ele._ele(xpath, index=index, relative=True)
ele = self.parent_ele._ele(xpath, index=index, relative=True, timeout=timeout)
return ele if ele else NoneElement(self.owner, 'before()', {'locator': locator, 'index': index})
return ele if ele else NoneElement(self.owner, 'before()',
{'locator': locator, 'index': index, 'timeout': timeout})
def after(self, locator='', index=1):
def after(self, locator='', index=1, timeout=None):
"""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
"""
nodes = self.afters(locator=locator)
return nodes[index - 1] if nodes else NoneElement(self.owner, 'after()', {'locator': locator, 'index': index})
nodes = self.afters(locator=locator, timeout=timeout)
return nodes[index - 1] if nodes else NoneElement(self.owner, 'after()',
{'locator': locator, 'index': index, 'timeout': timeout})
def children(self, locator=''):
def children(self, locator='', timeout=None):
"""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
"""
if not locator:
@ -1139,11 +1150,12 @@ class ShadowRoot(BaseElement):
loc = loc[1].lstrip('./')
loc = f'xpath:./{loc}'
return self._ele(loc, index=None, relative=True)
return self._ele(loc, index=None, relative=True, timeout=timeout)
def nexts(self, locator=''):
def nexts(self, locator='', timeout=None):
"""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
"""
loc = get_loc(locator, True)
@ -1152,12 +1164,13 @@ class ShadowRoot(BaseElement):
loc = loc[1].lstrip('./')
xpath = f'xpath:./{loc}'
return self.parent_ele._ele(xpath, index=None, relative=True)
return self.parent_ele._ele(xpath, index=None, relative=True, timeout=timeout)
def befores(self, locator=''):
def befores(self, locator='', timeout=None):
"""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
"""
loc = get_loc(locator, True)
@ -1166,18 +1179,19 @@ class ShadowRoot(BaseElement):
loc = loc[1].lstrip('./')
xpath = f'xpath:./preceding::{loc}'
return self.parent_ele._ele(xpath, index=None, relative=True)
return self.parent_ele._ele(xpath, index=None, relative=True, timeout=timeout)
def afters(self, locator=''):
def afters(self, locator='', timeout=None):
"""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
"""
eles1 = self.nexts(locator)
loc = get_loc(locator, True)[1].lstrip('./')
xpath = f'xpath:./following::{loc}'
return eles1 + self.parent_ele._ele(xpath, index=None, relative=True)
return eles1 + self.parent_ele._ele(xpath, index=None, relative=True, timeout=timeout)
def ele(self, locator, index=1, timeout=None):
"""返回当前元素下级符合条件的一个元素
@ -1251,7 +1265,10 @@ class ShadowRoot(BaseElement):
css = []
for i in eles:
c = i.css_path
if c.startswith('html:nth-child(1)>body:nth-child(1)>shadow_root:nth-child(1)'):
if c in ('html:nth-child(1)', 'html:nth-child(1)>body:nth-child(1)',
'html:nth-child(1)>body:nth-child(1)>shadow_root:nth-child(1)'):
continue
elif c.startswith('html:nth-child(1)>body:nth-child(1)>shadow_root:nth-child(1)'):
c = c[61:]
css.append(c)
if index is not None:
@ -1265,7 +1282,8 @@ class ShadowRoot(BaseElement):
else:
node_ids = [self.owner._run_cdp('DOM.querySelector', nodeId=self._node_id, selector=i)['nodeId']
for i in css]
if 0 in node_ids:
node_ids = [i for i in node_ids if i]
if not node_ids:
return None
r = make_chromium_eles(self.owner, _ids=node_ids, index=index, is_obj_id=False)
return None if r is False else r
@ -1476,6 +1494,8 @@ def make_chromium_eles(page, _ids, index=1, is_obj_id=True, ele_only=False):
else: # 获取全部
nodes = ChromiumElementsList(page=page)
for obj_id in _ids:
# if obj_id == 0:
# continue
tmp = get_node_func(page, obj_id, ele_only)
if tmp is False:
return False

21
DrissionPage/_elements/chromium_element.pyi
View File

@ -101,7 +101,8 @@ class ChromiumElement(DrissionElement):
def parent(self,
level_or_loc: Union[tuple, str, int] = 1,
index: int = 1) -> ChromiumElement: ...
index: int = 1,
timeout: float = 0) -> ChromiumElement: ...
def child(self,
locator: Union[Tuple[str, str], str, int] = '',
@ -309,31 +310,31 @@ class ShadowRoot(BaseElement):
def run_async_js(self, script: str, *args, as_expr: bool = False, timeout: float = None) -> None: ...
def parent(self, level_or_loc: Union[str, int] = 1, index: int = 1) -> ChromiumElement: ...
def parent(self, level_or_loc: Union[str, int] = 1, index: int = 1, timeout: float = 0) -> ChromiumElement: ...
def child(self,
locator: Union[Tuple[str, str], str] = '',
index: int = 1) -> ChromiumElement: ...
index: int = 1, timeout:float=None) -> ChromiumElement: ...
def next(self,
locator: Union[Tuple[str, str], str] = '',
index: int = 1) -> ChromiumElement: ...
index: int = 1, timeout:float=None) -> ChromiumElement: ...
def before(self,
locator: Union[Tuple[str, str], str] = '',
index: int = 1) -> ChromiumElement: ...
index: int = 1, timeout:float=None) -> ChromiumElement: ...
def after(self,
locator: Union[Tuple[str, str], str] = '',
index: int = 1) -> ChromiumElement: ...
index: int = 1, timeout:float=None) -> ChromiumElement: ...
def children(self, locator: Union[Tuple[str, str], str] = '') -> List[ChromiumElement]: ...
def children(self, locator: Union[Tuple[str, str], str] = '', timeout:float=None) -> List[ChromiumElement]: ...
def nexts(self, locator: Union[Tuple[str, str], str] = '') -> List[ChromiumElement]: ...
def nexts(self, locator: Union[Tuple[str, str], str] = '', timeout:float=None) -> List[ChromiumElement]: ...
def befores(self, locator: Union[Tuple[str, str], str] = '') -> List[ChromiumElement]: ...
def befores(self, locator: Union[Tuple[str, str], str] = '', timeout:float=None) -> List[ChromiumElement]: ...
def afters(self, locator: Union[Tuple[str, str], str] = '') -> List[ChromiumElement]: ...
def afters(self, locator: Union[Tuple[str, str], str] = '', timeout:float=None) -> List[ChromiumElement]: ...
def ele(self,
locator: Union[Tuple[str, str], str],

1
DrissionPage/_functions/elements.py
View File

@ -170,6 +170,7 @@ class SessionFilter(SessionFilterOne):
"""
self._list = _text_all(self._list, SessionElementsList(page=self._list._page),
text=text, fuzzy=fuzzy, contain=contain)
return self
def _get_attr(self, name, value, method, equal=True):
"""返回通过某个方法可获得某个值的元素

2
DrissionPage/_functions/tools.py
View File

@ -226,6 +226,8 @@ def raise_error(result, ignore=None, user=False):
r = StorageError()
elif error == 'Sanitizing cookie failed':
r = CookieFormatError(f'cookie格式不正确：{result["args"]}')
elif error == 'Invalid header name':
r = ValueError(f'header名不正确。\n参数：{result["args"]["headers"]}')
elif error == 'Given expression does not evaluate to a function':
r = JavaScriptError(f'传入的js无法解析成函数：\n{result["args"]["functionDeclaration"]}')
elif error.endswith("' wasn't found"):

8
DrissionPage/_functions/web.py
View File

@ -372,11 +372,15 @@ def format_headers(txt):
"""
if isinstance(txt, (dict, CaseInsensitiveDict)):
for k, v in txt.items():
txt[k] = str(v)
if k in (':method', ':scheme', ':authority', ':path'):
txt.pop(k)
else:
txt[k] = str(v)
return txt
headers = {}
for header in txt.split('\n'):
if header:
name, value = header.split(': ', maxsplit=1)
headers[name] = value
if name not in (':method', ':scheme', ':authority', ':path'):
headers[name] = value
return headers

24
DrissionPage/_pages/chromium_frame.py
View File

@ -10,6 +10,7 @@ from re import search, findall, DOTALL
from time import sleep, perf_counter
from .._elements.chromium_element import ChromiumElement
from .._functions.settings import Settings
from .._pages.chromium_base import ChromiumBase
from .._units.listener import FrameListener
from .._units.rect import FrameRect
@ -21,6 +22,24 @@ from ..errors import ContextLostError, ElementLostError, PageDisconnectedError,
class ChromiumFrame(ChromiumBase):
_Frames = {}
def __new__(cls, owner, ele, info=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
"""
node = info['node'] if info else owner._run_cdp('DOM.describeNode', backendNodeId=ele._backend_id)['node']
if Settings.singleton_tab_obj and node['frameId'] in cls._Frames:
r = cls._Frames[node['frameId']]
while not hasattr(r, '_frame_id'):
sleep(.1)
return r
r = object.__new__(cls)
cls._Frames[node['frameId']] = r
return r
def __init__(self, owner, ele, info=None):
"""
:param owner: frame所在的页面对象
@ -33,7 +52,7 @@ class ChromiumFrame(ChromiumBase):
self._frame_ele = ele
self._reloading = False
node = info['node'] if not info else owner._run_cdp('DOM.describeNode', backendNodeId=ele._backend_id)['node']
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
@ -385,10 +404,11 @@ class ChromiumFrame(ChromiumBase):
else:
return self.doc_ele._run_js(script, *args, as_expr=as_expr, timeout=timeout)
def parent(self, level_or_loc=1, index=1):
def parent(self, level_or_loc=1, index=1, timeout=0):
"""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
"""
return self.frame_ele.parent(level_or_loc, index)

4
DrissionPage/_pages/chromium_frame.pyi
View File

@ -21,6 +21,7 @@ from .._units.waiter import FrameWaiter
class ChromiumFrame(ChromiumBase):
_Frames: dict = ...
def __init__(self,
owner: Union[ChromiumTab, ChromiumFrame],
@ -156,7 +157,8 @@ class ChromiumFrame(ChromiumBase):
def parent(self,
level_or_loc: Union[Tuple[str, str], str, int] = 1,
index: int = 1) -> ChromiumElement: ...
index: int = 1,
timeout: float = 0) -> ChromiumElement: ...
def prev(self,
locator: Union[Tuple[str, str], str, int] = '',

1
DrissionPage/_units/setter.py
View File

@ -770,6 +770,7 @@ class WindowSetter(object):
return self._owner._run_cdp('Browser.getWindowForTarget')
except:
sleep(.1)
raise RuntimeError('获取窗口信息失败。')
def _perform(self, bounds):
"""执行改变窗口大小操作