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

修复re没有适配换行问题

Browse Source
This commit is contained in:
g1879 2023-12-15 16:52:53 +08:00
parent 7284b108ef
commit 35c25fa454
4 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
DrissionPage/_functions/tools.py
View File

@ -266,7 +266,7 @@ def raise_error(r):
'No node with given id found', 'Node with given id does not belong to the document', 'No node with given id found', 'Node with given id does not belong to the document',
'No node found for given backend id'): 'No node found for given backend id'):
raise ElementLostError raise ElementLostError
elif error == 'tab closed': elif error == ('tab closed', 'No target with given id found'):
raise PageClosedError raise PageClosedError
elif error == 'timeout': elif error == 'timeout':
raise TimeoutError raise TimeoutError

2
DrissionPage/_pages/chromium_base.py
View File

@ -172,6 +172,8 @@ class ChromiumBase(BasePage):
except: except:
if self._debug: if self._debug:
print('获取文档失败。') print('获取文档失败。')
from traceback import print_exc
print_exc()
print('请把报错信息和重现方法告知作者，感谢。\nhttps://gitee.com/g1879/DrissionPage/issues/new') print('请把报错信息和重现方法告知作者，感谢。\nhttps://gitee.com/g1879/DrissionPage/issues/new')
raise raise
# return False # return False

4
DrissionPage/_pages/chromium_frame.py
View File

@ -4,7 +4,7 @@
@Contact : g1879@qq.com @Contact : g1879@qq.com
""" """
from copy import copy from copy import copy
from re import search, findall from re import search, findall, DOTALL
from time import sleep, perf_counter from time import sleep, perf_counter
from .._elements.chromium_element import ChromiumElement from .._elements.chromium_element import ChromiumElement
@ -304,7 +304,7 @@ class ChromiumFrame(ChromiumBase):
"""返回元素outerHTML文本""" """返回元素outerHTML文本"""
tag = self.tag tag = self.tag
out_html = self._target_page.run_cdp('DOM.getOuterHTML', backendNodeId=self.frame_ele._backend_id)['outerHTML'] out_html = self._target_page.run_cdp('DOM.getOuterHTML', backendNodeId=self.frame_ele._backend_id)['outerHTML']
sign = search(rf'<{tag}.*?>', out_html).group(0) sign = search(rf'<{tag}.*?>', out_html, DOTALL).group(0)
return f'{sign}{self.inner_html}</{tag}>' return f'{sign}{self.inner_html}</{tag}>'
@property @property

4
DrissionPage/_pages/session_page.py
View File

@ -4,7 +4,7 @@
@Contact : g1879@qq.com @Contact : g1879@qq.com
""" """
from pathlib import Path from pathlib import Path
from re import search from re import search, DOTALL
from time import sleep from time import sleep
from urllib.parse import urlparse, quote from urllib.parse import urlparse, quote
@ -379,7 +379,7 @@ def set_charset(response):
# 在headers中获取不到编码，且如果是网页 # 在headers中获取不到编码，且如果是网页
elif content_type.replace(' ', '').startswith('text/html'): elif content_type.replace(' ', '').startswith('text/html'):
re_result = search(b'<meta.*?charset=[ \\\'"]*([^"\\\' />]+).*?>', response.content) re_result = search(b'<meta.*?charset=[ \\\'"]*([^"\\\' />]+).*?>', response.content, DOTALL)
if re_result: if re_result:
charset = re_result.group(1).decode() charset = re_result.group(1).decode()