爬取百度热搜榜

import requests
from bs4 import BeautifulSoup
import pandas as pd
url = ‘http://top.baidu.com/buzz?b=341&c=513&fr=topbuzz_b341_c513‘
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‘}
#伪装爬虫
r=requests.get(url)#请求网站
r.encoding=r.apparent_encoding
html=r.text#获取源代码
soup=BeautifulSoup(x,‘lxml‘)#构造Soup的对象
a=[]
b=[]
for m in soup.find_all(class_="keyword"):
    a.append(m.get_text().strip())  
for n in soup.find_all(class_="list"):
    b.append(n.get_text().strip())
h=pd.DataFrame(data,index=["关键词","热度"])
print("爬取百度热搜榜前十:","\n")
print(data.iloc[0:10])