爬取百度热门排行

import requests
from bs4 import BeautifulSoup
import bs4
import pandas as pd
url = 'http://top.baidu.com/buzz?b=341&c=513&fr=topbuzz_b1'
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'}#
r=requests.get(url,timeout=30,headers=headers)
r.encoding=r.apparent_encoding
t=r.text
soup=BeautifulSoup(t,'lxml')
a=[]
b=[]
for i in soup.find_all(class_="list-title"):
    a.append(i.get_text().strip())
for j in soup.find_all('td', class_="last"):
    b.append(j.get_text().strip())
data=[a,b]
c=pd.DataFrame(data,index=["标题","热度"],columns=range(1,51))
print(c.T)

输出结

 

登录网站，管理员工具查看源代码