爬虫技巧与正则表达式应用
from bs4 import BeautifulSoup
import requests
urlIndex = []
head = {"User-Agent":"Mozila/5.0(Window NT 6.1; AppleWebKit/537.36 ; Chrome/47.0.2526.106 Safari/537.36 )"}
TimeOut=5
root="http://money.163.com/special/002534M5/review.html"
Page =requests.session().get(root,headers=head,timeout=TimeOut)
Coding= (Page.encoding)
contens= Page.content
soup= BeautifulSoup(contens,from_encoding="gbk")
for result in soup.select("div.colLM li"):
urlIndex.append(result)
for result2 in urlIndex:
title= result2.span.text
wangzhi=(result2.a)["href"]
shijian=(result2.select(".atime"))[0].text
print shijian
文件大小：792.81KB
评论区