[已解决]为什么修改了header还是无法访问B站？

入土

代码如下：

import urllib.request
import chardet

def main():
    url = 'https://www.bilibili.com'

    head = {}
    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"
    head['authority'] = 's.search.bilibili.com'
    head['method'] = 'GET'
    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'

    head['scheme'] = 'https'
    head['accept'] = 'application/json, text/plain, */*'
    head['accept-encoding'] = 'gzip, deflate, br'
    head['accept-language'] = 'zh-CN,zh;q=0.9'
    head['origin'] = 'https://www.bilibili.com'
    head['referer'] = 'https://www.bilibili.com/'
    head['sec-fetch-dest'] = 'empty'
    head['sec-fetch-mode'] = 'cors'
    head['sec-fetch-site'] = 'same-site'
    
    
    req = urllib.request.Request(url,headers = head)
    response = urllib.request.urlopen(url)
    html = response.read()
    # 识别网页编码
    encode = chardet.detect(html)['encoding']
    if encode == 'GB2312':
        encode = 'GBK'
 
    print("该网页使用的编码是：%s" % encode)
    print(req.headers)
        
if __name__ == "__main__":
    main()

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：

import urllib.request
import chardet


def main():
    url = 'https://www.bilibili.com'

    head = {}
    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"
    head['authority'] = 's.search.bilibili.com'
    head['method'] = 'GET'
    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'

    head['scheme'] = 'https'
    head['accept'] = 'application/json, text/plain, */*'
    head['accept-encoding'] = 'gzip, deflate, br'
    head['accept-language'] = 'zh-CN,zh;q=0.9'
    head['origin'] = 'https://www.bilibili.com'
    head['referer'] = 'https://www.bilibili.com/'
    head['sec-fetch-dest'] = 'empty'
    head['sec-fetch-mode'] = 'cors'
    head['sec-fetch-site'] = 'same-site'

    req = urllib.request.Request(url, headers=head)
    response = urllib.request.urlopen(req)
    html = response.read()
    # 识别网页编码
    encode = chardet.detect(html)['encoding']
    if encode == 'GB2312':
        encode = 'GBK'

    print("该网页使用的编码是：%s" % encode)
    print(req.headers)


if __name__ == "__main__":
    main()

入土

Twilight6 发表于 2020-8-5 22:11
改成这样：

谢谢，已解决