爬取搜狗热搜榜前十

1.导入相应的库

2.打开页面：http://top.sogou.com/（搜狗热搜榜）

3.用F12查找页面代码，找到我们要的数据

4.class="hot-b",class="num"

5.利用代码得出我们想要的数据

#导入库
import requests
import pandas as pd
from bs4 import BeautifulSoup
from pandas import DataFrame
url="http://top.sogou.com/"#搜狗热搜榜
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#统一编码
html = r.text
soup = BeautifulSoup(html,'lxml')#使用工具
title=[]
heat=[]
for m in soup.find_all(class_="hot-b"):
    title.append(m.get_text().strip())  
for n in soup.find_all(class_="num"):
    heat.append(n.get_text().strip())
print(data)
a=pd.DataFrame(data,index=["标题","热度"])
print(a.T)