|
楼主 |
发表于 2020-10-12 02:34:18
|
显示全部楼层
谢谢!通过你这个网址我写出来了,中途因为没写cookie被新浪卡了3个小时
- from urllib.request import Request, urlopen
- from fake_useragent import UserAgent
- import requests
- from urllib.parse import urlencode
- import json
- def get_res(url):
- #url = 'https://www.weibo.com/ajax/friendships/friends?page=1&uid=5715470927'
- headers = {
- 'User-Agent':UserAgent().chrome,
- 'Cookie':'SINAGLOBAL=2809735293383.7993.1584504483612; _s_tentry=-; Apache=6590299036100.631.1602408891862; ULV=1602408892284:5:1:1:6590299036100.631.1602408891862:1598306540800; un=18593193392; UOR=,,login.sina.com.cn; login_sid_t=3debbfe8ff2ffe4cb10d7dde5d215edb; cross_origin_proto=SSL; ALF=1633959683; SSOLoginState=1602423684; SCF=Av_D3h0SAn4M4dDvE11TJXoQFM3irgDs2FVu2udrE-s8uhlNeVAf_IkPHz2X_Id6dBjAwv5Fhyav-OWt4DcWdmQ.; SUB=_2A25yh3vVDeRhGeFN6lUU8SbKyDmIHXVR9eodrDV8PUNbmtAKLRHFkW9NQHRX7Hg8sFQ4-U_aiRRwtDREDTH0chCt; SUBP=0033WrSXqPxfM725Ws9jqgMF55529P9D9WWbEK6NwBhzUaJ9YLxuoqUz5JpX5KzhUgL.FoM0eKMfeKnce0-2dJLoIEBLxKnL1h5L1h2LxKBLBonL1-eLxKnLBK-LB.qLxK-L1KeL1Kzt; SUHB=09P9wfR2GiQh3v; wvr=6; XSRF-TOKEN=hoHjMief6hcEGVgqALnncHJf; WBPSESS=Z6ejeHjAsRNOBei-TAIcJwO6JUmrCOPlIXNnyDYgWSpdLL2GYqyBLhZHLnGgWxjTGdgKi0O7E2XWyERbot0iMyppvEqNwFXWAXoIcy43Lf_rLzz8OYiN6nr5DddwMF-9; webim_unReadCount=%7B%22time%22%3A1602436950706%2C%22dm_pub_total%22%3A2%2C%22chat_group_client%22%3A0%2C%22chat_group_notice%22%3A0%2C%22allcountNum%22%3A39%2C%22msgbox%22%3A0%7D'
- }
- response = requests.get(url, headers=headers)
- return response
- def get_users(response,page):
- info = response.content.decode('utf-8','ignore')
- follow_json = json.loads(info)
- print('ok')
- users = follow_json['users']
- return users
- def main():
- content = input('请输入要用户的uid:')
- num = input('请输入要下载的页数:')
- base_url = 'https://www.weibo.com/ajax/friendships/friends?{}'
- with open ('张艺兴微博关注列表试做型初号机.txt', 'w', encoding='utf-8') as f:
- for i in range(int(num)):
- page = i+1
- args = {
- 'page':page,
- 'uid':content
- }
- args = urlencode(args)
- url = base_url.format(args)
- print(url)
- response = get_res(url)
- print('正在打印第%d页'%page)
- users = get_users(response,page)
- f.write('第%d页\n'%page)
- for each in users:
- f.write('Name:'+each['name']+'\n')
- f.write('Uid:'+each['idstr']+'\n')
- f.write('Description:'+each['description']+'\n')
- f.write('--------------------------------------\n\n')
- if __name__ == '__main__':
- main()
复制代码 |
|