爬取每日热点中微博热度榜

import requests
from bs4 import BeautifulSoup



def get(url,list,num): #定义一个获取信息函数
    headers = {‘user-agent‘:‘Mo+zilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11‘} #伪装爬虫 不然无法爬取网页信息
    r = requests.get(url,timeout = 30,headers=headers)  #发送请求 时间为30s
    
    soup = BeautifulSoup(r.text,"html.parser")
   
    list1 = soup.find_all(‘span‘,class_=‘t‘)  #寻找标签为span的数据
    list2 = soup.find_all(‘span‘,class_=‘e‘)
    
    print("{:^10}\t{:^30}\t{:^10}\t".format(‘排名‘,‘标题‘,‘热度‘))
    
    for i in range(num):
        print("{:^10}\t{:^30}\t{:^10}\t".format(i+1,list1[i].string,list2[i].string))  #遍历前十个数据打印出来
        list.append([i+1,list1[i].string,list2[i].string]) #将数据添加进列表中

def create_file(file_path,msg): #定义一个创建文件夹,将爬取的资源用txt格式打开
    f=open(file_path,"a")
    f.write(str(msg)) #将列表数据变为字符串，直接用列表报错
    f.close 

def main():
    list = []
    url = "https://tophub.today/"
    get(url,list,10)
    
    create_file("D:\python\weibolist.txt",list)

    
main()