直接上爬虫代码

如果你对python感兴趣，我这有个学习Python基地，里面有很多学习资料，感兴趣的+Q群：688244617

import requests
import re


tmpt_url = 'https://weibo.com/p/1005051678105910/follow?page=%d#Pl_Official_HisRelation__59'
def get_data(tmpt_url):
    urllist = [tmpt_url%i for i in range(1,6)]
    user_id = [] #粉丝ID
    user_name = [] #粉丝名称
    user_follow = [] #粉丝的关注
    user_fans = [] #粉丝的粉丝量
    user_address = [] #粉丝的地址

    headers = {'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
    'Accept-Encoding':'gzip, deflate, br',
    'Accept-Language':'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
    'Connection':'keep-alive',
    'Cookie':'请在自己的浏览器中查看，因涉及个人隐私不公开',
    'Host':'weibo.com',
    'Upgrade-Insecure-Requests':'1',
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:65.0) Gecko/20100101 Firefox/65.0'}

    for url in urllist:
        html = requests.get(url,headers=headers).text
        user_id.extend(re.findall(r'<a class=\"S_txt1\" target=\"_blank\"  usercard=\"id=(d+)&refer_flag=d+_\" href=\"\/S+?refer_flag=d+_\" >S+<\/a>',html))
        user_name.extend(re.findall(r'<a class=\"S_txt1\" target=\"_blank\"  usercard=\"id=d+&refer_flag=d+_\" href=\"\/S+?refer_flag=d+_\" >(S+)<\/a>',html))
        user_follow.extend(re.findall(r'关注 <em class=\"count\"><a target=\"_blank\" href=\"\/d+\/follow\" >(d+)<\/a>',html))
        user_fans.extend(re.findall(r'粉丝<em class=\"count\"><a target=\"_blank\" href=\"\/d+\/fans?current=fans\" >(d+)<\/a>',html))
        user_address.extend(re.findall(r'<em class=\"tit S_txt2\">地址<\/em><span>(S+s?S+?)<\/span>\r\n\t\t\t\t\t<\/div>',html))
    print('user_id',user_id)
    print('user_name',user_name)
    print('user_follow',user_follow)
    print('user_fans',user_fans)
    print('user_address',user_address)

这个url是孙俪的微博账号
下面是她粉丝列表前5页爬到的信息，包括：粉丝ID，粉丝名称，粉丝的关注，粉丝的粉丝量，粉丝的地址