爬虫入门之知乎关注人物信息

爬取知乎作者关注的人物信息

# -*- coding: utf-8 -*-
import requests
import json
import pandas as pd

headers={"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36",
         "authority": "www.zhihu.com",
         "cookie": '_xsrf=B9FRuYo2HC3LXmk9t8SMsRVtG0L0n9kZ; _zap=1f9bc2a0-73fe-4c17-9946-7f817fe27051; d_c0="AKCYoIi42RCPTi0cGHuNcQ1edLvrjSbjsik=|1582268904"; _ga=GA1.2.878415566.1583044370; _gid=GA1.2.1285811604.1583851980; l_n_c=1; r_cap_id="YTIzNTYwZTRjMDlmNDQyOWJlZWU5MTYxZTg1NTI0ZjM=|1583851991|1e35d8bc335cc7a2ffe443ec0edc69991a3bae52"; cap_id="MjE2NzM3OTM4MWZmNDJhMDgzY2JlNWQ5NzUwMjRhZGI=|1583851991|a5b8bd2bb38b61e221e9507c11b5b7a2c2672a73"; l_cap_id="YjdlNjMxMWQxNzM3NGEyZDliZThkOTk3ZGY5MzU3OTg=|1583851991|ed4a81f7bbb36e32e4f6f317669da2019c3362a5"; n_c=1; client_id="bzNwMi1qaEptRGRRTUx0VjhJSFpoQ2p6eU54OA==|1583852003|d4290bf396c67adb4dcacc2419faea0b04d68f29"; capsion_ticket="2|1:0|10:1583852003|14:capsion_ticket|44:ZmNiNWE2NzhkMDAyNGUxZWIxNzE2MWRiYWZhYWNiNWI=|ed6dc8a5cfd8a97199e9ae9ba68e2826adfa9d720317f778c61ee85c4074c67b"; z_c0="2|1:0|10:1583852045|4:z_c0|92:Mi4xdFRoUENRQUFBQUFBb0ppZ2lMalpFQ1lBQUFCZ0FsVk5EZmhVWHdDTVNoTzZGSUp3ckU1cDhJZVo5a2dWbFB4QVNB|63433eeff506c77e86f72a6768a49350af81744b2f2c072f1b945ccf974238a7"; q_c1=a8f798fb8b3840a18d4266cadd424978|1583852070000|1583852070000; tshl=fashion; tst=r; Hm_lvt_98beee57fd2ef70ccdd5ca52b9740c49=1583672325,1583851980,1583851982,1583854945; KLBRSID=2177cbf908056c6654e972f5ddc96dc2|1583992911|1583991949; Hm_lpvt_98beee57fd2ef70ccdd5ca52b9740c49=1583992913'}

params={"include": "data[*].answer_count,articles_count,gender,follower_count,is_followed,is_following,badge[?(type=best_answerer)].topics",
        "offset": 20,
        "limit": 20}

url="https://www.zhihu.com/api/v4/members/jian-guo-yun-34/followees?include=data%5B%2A%5D.answer_count%2Carticles_count%2Cgender%2Cfollower_count%2Cis_followed%2Cis_following%2Cbadge%5B%3F%28type%3Dbest_answerer%29%5D.topics&limit=20&offset=20"

response=requests.get(url,headers=headers,params=params)
data=response.json()["data"]

df=pd.DataFrame.from_dict(data)
df.to_excel('user.xlsx')