From 39a8a5236d252b2e4a71bff9a9685e1d1d2743a0 Mon Sep 17 00:00:00 2001
From: g1879 <g1879@qq.com>
Date: Wed, 18 Nov 2020 21:33:08 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BC=98=E5=8C=96=E8=8E=B7=E5=8F=96=E7=BC=96?=
 =?UTF-8?q?=E7=A0=81=E7=9A=84=E9=80=BB=E8=BE=91=EF=BC=9B=E4=BF=AE=E5=A4=8D?=
 =?UTF-8?q?=E4=B8=8B=E8=BD=BD=E4=B8=8D=E8=83=BD=E6=98=BE=E7=A4=BA=E8=BF=9B?=
 =?UTF-8?q?=E5=BA=A6=E7=9A=84=E9=97=AE=E9=A2=98?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 DrissionPage/session_page.py | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/DrissionPage/session_page.py b/DrissionPage/session_page.py
index 79acc91..267a25e 100644
--- a/DrissionPage/session_page.py
+++ b/DrissionPage/session_page.py
@@ -491,11 +491,14 @@ class SessionPage(object):
         else:
             # ----------------获取并设置编码开始-----------------
             # 在headers中获取编码
-            try:
-                charset = r.headers.get('Content-type').split('=')[1]
+            content_type = r.headers.get('content-type')
+            charset = re.search(r'charset[=: ]*(.*)?[;]', content_type)
 
-            # 在headers中获取不到编码
-            except IndexError:
+            if charset:
+                r.encoding = charset.group(1)
+
+            # 在headers中获取不到编码，且如果是网页
+            elif content_type.replace(' ', '').lower().startswith('text/html'):
                 re_result = re_SEARCH(b'<meta.*?charset=[ \\\'"]*([^"\\\' />]+).*?>', r.content)
 
                 if re_result:
@@ -503,7 +506,7 @@ class SessionPage(object):
                 else:
                     charset = r.apparent_encoding
 
-            r.encoding = charset
+                r.encoding = charset
             # ----------------获取并设置编码结束-----------------
 
             return r, 'Success'