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

优化修复网页编码逻辑

Browse Source
This commit is contained in:
g1879 2020-09-08 00:04:27 +08:00
parent 224c4642a6
commit 39a96c852e
1 changed files with 8 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
DrissionPage/session_page.py
View File

@ -190,13 +190,6 @@ class SessionPage(object):
if self._response is None: if self._response is None:
self._url_available = False self._url_available = False
else: else:
stream = tuple(x for x in kwargs if x.lower() == 'stream')
if (not stream or not kwargs[stream[0]]) and not self.session.stream:
try:
self._response.html.encoding = self._response.encoding # 修复requests_html丢失编码方式的bug
except:
pass
if self._response.ok: if self._response.ok:
self._url_available = True self._url_available = True
else: else:
@ -227,11 +220,6 @@ class SessionPage(object):
if self._response is None: if self._response is None:
self._url_available = False self._url_available = False
else: else:
try:
self._response.html.encoding = self._response.encoding # 修复requests_html丢失编码方式的bug
except:
pass
if self._response.ok: if self._response.ok:
self._url_available = True self._url_available = True
else: else:
@ -403,25 +391,22 @@ class SessionPage(object):
headers = dict(r.headers) headers = dict(r.headers)
content_type = tuple(x for x in headers if x.lower() == 'content-type') content_type = tuple(x for x in headers if x.lower() == 'content-type')
stream = tuple(x for x in kwargs if x.lower() == 'stream') stream = tuple(x for x in kwargs if x.lower() == 'stream')
not_stream = (not stream or not kwargs[stream[0]]) and not self.session.stream
charset = None charset = None
if not content_type or 'charset' not in headers[content_type[0]].lower(): if not content_type or 'charset' not in headers[content_type[0]].lower():
if (not stream or not kwargs[stream[0]]) and not self.session.stream: if not_stream:
# ======================== re_result = re_SEARCH(r'<meta.*?charset=[ \'"]*([^"\' />]+).*?>',
re_result = None r.iter_content(chunk_size=512).__next__().decode())
for chunk in r.iter_content(chunk_size=512):
re_result = re_SEARCH(r'<meta.*?charset=[ \'"]*([^"\' />]+).*?>', chunk.decode())
break
# ========================
# re_result = re_SEARCH(r'<meta.*?charset=[ \'"]*([^"\' />]+).*?>', r.text)
try: try:
charset = re_result.group(1) charset = re_result.group(1)
except: except:
charset = r.apparent_encoding charset = r.apparent_encoding
else: else:
charset = headers[content_type[0]].split('=')[1] charset = headers[content_type[0]].split('=')[1]
# 避免存在退格符导致乱码或解析出错
if (not stream or not kwargs[stream[0]]) and not self.session.stream: if not_stream: # 加载网页时修复编码
r._content = r.content.replace(b'\x08', b'\\b') r._content = r.content.replace(b'\x08', b'\\b') # 避免存在退格符导致乱码或解析出错
r.html.encoding = r.encoding # 修复requests_html丢失编码方式的bug
if charset: if charset:
r.encoding = charset r.encoding = charset
return r, 'Success' return r, 'Success'