python 获取一个网页里的a 标签

#!/usr/bin/python

# -*- coding: utf-8 -*-

#encoding=utf-8

#Filename:urllib2-header.py

import re

import urllib2

import sys

url= "http://www.jb51.net"

send_headers = {

 'Host':'www.jb51.net',

 'User-Agent':'Mozilla/5.0 (Windows NT 6.2; rv:16.0) Gecko/20100101 Firefox/16.0',

 'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',

 'Connection':'keep-alive'

}

req = urllib2.Request(url,headers=send_headers)

r = urllib2.urlopen(req)

html = r.read().replace(" ","")

urls=re.findall(r"<a.*?href=.*?<\/a>",html,re.I)

for i in urls:

  print i

巴特西

python 获取一个网页里的a 标签

最新文章

热门文章