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

修复获取编码可能出错的bug

Browse Source
This commit is contained in:
g1879 2020-11-15 18:13:23 +08:00
parent 6c35dad79d
commit 798d3e771a
1 changed files with 13 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
DrissionPage/session_page.py
View File

@ -433,26 +433,34 @@ class SessionPage(object):
return None, e
else:
# -------------获取编码开始----------------
headers = dict(r.headers)
content_type = tuple(x for x in headers if x.lower() == 'content-type')
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
# 若headers中没有编码信息，从页面meta标签提取，若失败，用apparent_encoding
if not content_type or 'charset' not in headers[content_type[0]].lower():
# 表示是网页，非下载文件
if not_stream:
re_result = re_SEARCH(r'<meta.*?charset=[ \'"]*([^"\' />]+).*?>',
r.iter_content(chunk_size=512).__next__().decode())
re_result = re_SEARCH(b'<meta.*?charset=[ \\\'"]*([^"\\\' />]+).*?>', r.content)
try:
charset = re_result.group(1)
charset = re_result.group(1).decode()
except:
charset = r.apparent_encoding
# 在headers中获取编码
else:
charset = headers[content_type[0]].split('=')[1]
# -------------获取编码结束----------------
if charset: # 指定网页编码
r.encoding = charset
if not_stream: # 避免存在退格符导致乱码或解析出错
r._content = r.content.replace(b'\x08', b'\\b')
# if not_stream: # 避免存在退格符导致乱码或解析出错
# r._content = r.content.replace(b'\x08', b'\\b')
return r, 'Success'