[已解决]为什么修改了header还是无法访问B站？

入土

代码如下：

1. import urllib.request
   
2. import chardet
   
3. 
   
4. def main():
   
5.     url = 'https://www.bilibili.com'
   
6. 
   
7.     head = {}
   
8.     head["user-agent"] = "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Mobile Safari/537.36"
   
9.     head['authority'] = 's.search.bilibili.com'
   
10.     head['method'] = 'GET'
    
11.     head['path'] = '/main/suggest?func=suggest&suggest_type=accurate&sub_type=tag&main_ver=v1&highlight=&userid=5146541&bangumi_acc_num=1&special_acc_num=1&topic_acc_num=1&upuser_acc_num=3&tag_num=10&special_num=10&bangumi_num=10&upuser_num=3&term=%E4%B8%BA%E4%BB%80%E4%B9%88B%E7%AB%99%E8%AE%BE%E7%BD%AE1%E4%BA%86headers%E8%BF%98%E6%98%AF%E4%B8%8D%E8%83%BD%E7%88%AC%E5%8F%96&rnd=0.08535939713748864'
    
12. 
    
13.     head['scheme'] = 'https'
    
14.     head['accept'] = 'application/json, text/plain, */*'
    
15.     head['accept-encoding'] = 'gzip, deflate, br'
    
16.     head['accept-language'] = 'zh-CN,zh;q=0.9'
    
17.     head['origin'] = 'https://www.bilibili.com'
    
18.     head['referer'] = 'https://www.bilibili.com/'
    
19.     head['sec-fetch-dest'] = 'empty'
    
20.     head['sec-fetch-mode'] = 'cors'
    
21.     head['sec-fetch-site'] = 'same-site'
    
22.    
    
23.    
    
24.     req = urllib.request.Request(url,headers = head)
    
25.     response = urllib.request.urlopen(url)
    
26.     html = response.read()
    
27.     # 识别网页编码
    
28.     encode = chardet.detect(html)['encoding']
    
29.     if encode == 'GB2312':
    
30.         encode = 'GBK'
    
31. 
    
32.     print("该网页使用的编码是：%s" % encode)
    
33.     print(req.headers)
    
34.         
    
35. if __name__ == "__main__":
    
36.     main()
    

复制代码

最佳答案

月排行榜 / 总排行榜

suchocolate

2020-8-5 22:10:11

response = urllib.request.urlopen(req)

跳转到最佳答案楼层

入土

只添加"user-agent"也无效

suchocolate

response = urllib.request.urlopen(req)

Twilight6

入土 发表于 2020-8-5 22:01
只添加"user-agent"也无效

你 Request 获取时候，还需要通过 urlopen 来打开 Request 的结果

改成这样：

1. import urllib.request
   
2. import chardet
   
3. 
   
4. 
   
5. def main():
   
6.     url = 'https://www.bilibili.com'
   
7. 
   
8.     head = {}
   
9.     head[
   
10.         "user-agent"] = "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Mobile Safari/537.36"
    
11.     head['authority'] = 's.search.bilibili.com'
    
12.     head['method'] = 'GET'
    
13.     head[
    
14.         'path'] = '/main/suggest?func=suggest&suggest_type=accurate&sub_type=tag&main_ver=v1&highlight=&userid=5146541&bangumi_acc_num=1&special_acc_num=1&topic_acc_num=1&upuser_acc_num=3&tag_num=10&special_num=10&bangumi_num=10&upuser_num=3&term=%E4%B8%BA%E4%BB%80%E4%B9%88B%E7%AB%99%E8%AE%BE%E7%BD%AE1%E4%BA%86headers%E8%BF%98%E6%98%AF%E4%B8%8D%E8%83%BD%E7%88%AC%E5%8F%96&rnd=0.08535939713748864'
    
15. 
    
16.     head['scheme'] = 'https'
    
17.     head['accept'] = 'application/json, text/plain, */*'
    
18.     head['accept-encoding'] = 'gzip, deflate, br'
    
19.     head['accept-language'] = 'zh-CN,zh;q=0.9'
    
20.     head['origin'] = 'https://www.bilibili.com'
    
21.     head['referer'] = 'https://www.bilibili.com/'
    
22.     head['sec-fetch-dest'] = 'empty'
    
23.     head['sec-fetch-mode'] = 'cors'
    
24.     head['sec-fetch-site'] = 'same-site'
    
25. 
    
26.     req = urllib.request.Request(url, headers=head)
    
27.     response = urllib.request.urlopen(req)
    
28.     html = response.read()
    
29.     # 识别网页编码
    
30.     encode = chardet.detect(html)['encoding']
    
31.     if encode == 'GB2312':
    
32.         encode = 'GBK'
    
33. 
    
34.     print("该网页使用的编码是：%s" % encode)
    
35.     print(req.headers)
    
36. 
    
37. 
    
38. if __name__ == "__main__":
    
39.     main()

复制代码

入土

Twilight6 发表于 2020-8-5 22:11
改成这样：

谢谢，已解决