微博（APP）榜单爬虫及数据可视化

import requests
import json
import re
import time
import csv

headers = {
    'Host': 'api.weibo.cn',
    'Connection': 'keep-alive',
    'User-Agent': 'Weibo/29278 (iPhone; iOS 11.4.1; Scale/2.00)'
}

f = open('1.csv','w+',encoding='utf-8',newline='')
writer = csv.writer(f)
writer.writerow(['user_id','user_location','user_gender','user_follower','text','created_time','reposts_count','comments_count','attitudes_count'])

def get_info(url):
    res = requests.get(url,headers=headers)
    print(url)
    datas = re.findall('"mblog":(.*?),"weibo_position"',res.text,re.S)
    for data in datas:
        json_data = json.loads(data+'}')
        user_id = json_data['user']['name']
        user_location = json_data['user']['location']
        user_gender = json_data['user']['gender']
        user_follower = json_data['user']['followers_count']
        text = json_data['text']
        created_time = json_data['created_at']
        reposts_count = json_data['reposts_count']
        comments_count = json_data['comments_count']
        attitudes_count = json_data['attitudes_count']
        print(user_id,user_location,user_gender,user_follower,text,created_time,reposts_count,comments_count,attitudes_count)
        writer.writerow([user_id,user_location,user_gender,user_follower,text,created_time,reposts_count,comments_count,attitudes_count])
    time.sleep(5)

if __name__ == '__main__':
    urls = ['https://api.weibo.cn/2/cardlist?gsid=_2A252dh7LDeRxGeNM41oV-S_MzDSIHXVTIhUDrDV6PUJbkdANLVTwkWpNSf8_0j6hqTyDS0clYi-pzwDc2Kd8oj_d&wm=3333_2001&i=b9f7194&b=0&from=1088193010&c=iphone&networktype=wifi&v_p=63&skin=default&v_f=1&s=ef8eeeee&lang=zh_CN&sflag=1&ua=iPhone8,1__weibo__8.8.1__iphone__os11.4.1&ft=11&aid=01AuxGxLabPA7Vzz8ZXBUpkeJqWbJ1woycR3lFBdLhoxgQC1I.&moduleID=pagecard&scenes=0&uicode=10000327&luicode=10000010&count=20&extparam=discover&containerid=102803_ctg1_8999_-_ctg1_8999_home&fid=102803_ctg1_8999_-_ctg1_8999_home&lfid=231091&page={}'.format(str(i)) for i in range(1,16)]
    for url in urls:
        get_info(url)

df['location'] = df['user_location'].str.split(' ').str[0]