获取百度贴吧热议前十及热度

#页面结构

 

#源代码

import requests
from bs4 import BeautifulSoup
import pandas as pd
from pandas import DataFrame
url="https://tophub.today/n/Om4ejxvxEN"
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)
r.encoding=r.apparent_encoding
data=r.text
soup=BeautifulSoup(data,'html.parser')
print(soup.prettify())
a = request.Request(url, headers=headers)            
b = request.urlopen(a).read().decode('utf-8')     
title=re.compile(r'itemid="[0-9]*">(.*?)</a>')    
num=re.compile(r'<td>(.*?)</td>')                
titles=title.findall(b)[0:10]               
nums=num.findall(b)[0:10]                   
m={"今日热议":titles,"热度":nums}
file=pd.DataFrame(m)
print(file)

#输出结果