1.打开网站http://top.baidu.com/buzz?b=1&fr=topindex

2.右键找到源代码

3.用工具爬取数据

import requests
from bs4 import BeautifulSoup
import pandas as pd
url="https://tophub.today/"
headers = {'User-Agent:Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
r=requests.get(url)
r.encoding=r.apparent_encoding
x=r.text
soup=BeautifulSoup(x,'lxml')
lst1 = soup.find_all('div', class_='zb-kc-i')
lst2 = soup.find_all('div', class_='f')
print('{:^55}'.format('百度热搜榜'))
print('{:^5}\t{:^40}\t{:^10}'.format('排名', '标题', '热度'))
for i in range(10):
    print('{:^5}\t{:^30}\t{:^10}'.format(i+1, lst1[i].string, lst2[i].string))
    lst.append([i+1,lst1[i].string,lst2[i].string])
print()