mirror of
https://gitee.com/g1879/DrissionPage.git
synced 2024-12-10 04:00:23 +08:00
当response的header没有charset时,尝试从meta获取
This commit is contained in:
parent
a31ed1d354
commit
1c823470bd
@ -5,6 +5,7 @@
|
|||||||
@File : session_page.py
|
@File : session_page.py
|
||||||
"""
|
"""
|
||||||
import os
|
import os
|
||||||
|
import re
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
from random import random
|
from random import random
|
||||||
from time import time
|
from time import time
|
||||||
@ -216,10 +217,11 @@ class SessionPage(object):
|
|||||||
return_value = False
|
return_value = False
|
||||||
else:
|
else:
|
||||||
headers = dict(r.headers)
|
headers = dict(r.headers)
|
||||||
if 'Content-Type' not in headers:
|
if 'Content-Type' not in headers or 'charset' not in headers['Content-Type']:
|
||||||
charset = 'utf-8'
|
re_result = re.search(r'<meta.*?charset=([^"\']+)', r.text)
|
||||||
else:
|
try:
|
||||||
if 'charset' not in headers['Content-Type']:
|
charset = re_result.group(1)
|
||||||
|
except:
|
||||||
charset = 'utf-8'
|
charset = 'utf-8'
|
||||||
else:
|
else:
|
||||||
charset = headers['Content-Type'].split('=')[1]
|
charset = headers['Content-Type'].split('=')[1]
|
||||||
|
Loading…
x
Reference in New Issue
Block a user