Python 爬取微博热搜页面

import requests
import random
import re
import urllib3
#警告忽略
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
class Wb():
    def __init__(self):
        #利用session保持回话
        self.session=requests.Session()
        #清理headers字典，不然update好像不会起作用
        self.session.headers.clear()

        self.header={
            "Host": "weibo.com",
            "Connection": "keep-alive",
            "Upgrade-Insecure-Requests": "1",
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) "
                          "AppleWebKit/537.36 (KHTML, like Gecko) "
                          "Chrome/86.0.4240.198 Safari/537.36",
            "Accept": "text/html,application/xhtml+xml,application/xml;"
                      "q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,"
                      "application/signed-exchange;v=b3;q=0.9",
            "Sec-Fetch-Site": "cross-site",
            "Sec-Fetch-Mode": "navigate",
            "Sec-Fetch-Dest": "document",
            "Accept-Encoding": "gzip, deflate, br",
            "Accept-Language": "zh-CN,zh;q=0.9",
        }
        #设置代理如果需要fiddler抓包分析代码提交的参数使用下面代理如果不使用选择下面的代码self.fiddler_proxies=None
        self.fiddler_proxies = {'http': 'http://127.0.0.1:8888', 'https': 'http://127.0.0.1:8888'}
        # self.fiddler_proxies=None


    def get_top_summary(self):
        #更新添加header   headers.update只会覆盖相同键值的值不会覆盖全部
        self.session.headers.update(self.header)
        #verify=False 不检查证书
        response=self.session.get(url="https://weibo.com/",proxies=self.fiddler_proxies,verify=False)
        print(response.url)
        response.encoding='gbk'
        data1={
            "cb":"gen_callback",
            "fp":'{"os":"1","browser":"Chrome86,0,4240,198",'
                 '"fonts":"undefined","screenInfo":"1920*1080*24",'
                 '"plugins":"Portable Document Format::internal-pdf-viewer::'
                 'Chromium PDF Plugin|::mhjfbmdgcfjbbpaeojofohoefgiehjai::'
                 'Chromium PDF Viewer|::internal-nacl-plugin::Native Client"}'
        }
        header1={
            "Host": "passport.weibo.com",
            "Cache-Control": "max-age=0",
            "If-Modified-Since": "0",
            "Content-Type": "application/x-www-form-urlencoded",
            "Accept": "*/*",
            "Origin": "https://passport.weibo.com",
            "Sec-Fetch-Site": "same-origin",
            "Sec-Fetch-Mode": "cors",
            "Sec-Fetch-Dest": "empty",
            "Referer": response.url,
        }
        self.session.headers.update(header1)
        response1=self.session.post(url="https://passport.weibo.com/visitor/genvisitor"
                                    ,data=data1,proxies=self.fiddler_proxies,verify=False)
        #利用正则表达式解析tid参数的值
        t=re.search('{"tid":"(.*)","new_tid"',response1.text).groups()[0]
        data2={
            "a":"incarnate",
            "t":t.replace("\\",""),
            "w": "2",
            "c": "095",
            "gc":"",
            "cb":"cross_domain",
            "from":"weibo",
            "_rand":random.random()
        }
        header2={
            "Sec-Fetch-Mode": "no-cors",
            "Sec-Fetch-Dest": "script",
            "Cookie":"tid="+t.replace("\\","")+"__095"
        }
        self.session.headers.update(header2)
        response2 = self.session.get(url="https://passport.weibo.com/visitor/visitor",
                                     params=data2,proxies=self.fiddler_proxies,verify=False)
        #从返回值中获取cookie字典
        cookie = requests.utils.dict_from_cookiejar(response2.cookies)


        header3={
            "Cookie":"SUB="+cookie["SUB"]+";"+"SUBP="+cookie["SUBP"],
            "Host": "s.weibo.com",
            "Upgrade-Insecure-Requests": "1"

        }
        self.session.headers.update(header3)
        response3=self.session.get(url="https://s.weibo.com/top/summary",
                                   proxies=self.fiddler_proxies,verify=False)
        # print(response3.text)


if __name__ == '__main__':
    wb=Wb()
    wb.get_top_summary()