Merge pull request vansl#5 from xudong07/master

全局的headers被意外修改后不可再用于获取页面
zuoyouzuo · Feb 6, 2018 · f525be2 · f525be2
2 parents 8965fa9 + a634800
commit f525be2
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 3 deletions.
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1,4 @@
+.vscode/settings.json
+.vscode/tasks.json
+.vscode/launch.json
+.vscode/extensions.json
diff --git a/spider.py b/spider.py
@@ -144,7 +144,9 @@ def main(amount,firstIndex):
 class Download(threading.Thread):  
     def __init__(self, urlMannager):  
         threading.Thread.__init__(self)  
-        self.urlMannager=urlMannager 
+        self.urlMannager=urlMannager
+        self.pic_headers = headers
+        self.pic_headers['Host'] = 'wx3.sinaimg.cn'
 
     def download_Img(self,url):
         isGif=re.match(r'(.*\.sinaimg\.cn\/)(\w+)(\/.+\.gif)',url)
@@ -157,8 +159,8 @@ def download_Img(self,url):
         if not os.path.exists('img'):
             os.mkdir('img')
         with open ('img/'+str(len(os.listdir('./img')))+extensionName, 'wb') as f:
-            headers['Host']='wx3.sinaimg.cn'
-            f.write(requests.get(url,headers=headers).content)
+            # headers['Host']='wx3.sinaimg.cn'
+            f.write(requests.get(url,headers=self.pic_headers).content)
             f.close()
         L.release()