Python正则匹配HTML,python获取并正则匹配html中的内容 – 摄影与挖洞

#coding=utf-8

import urllib

import re

def getHtml(url):

page = urllib.urlopen(url)

html = page.read()

return html

def getlink(html):

reg = raw_input('Please input Regular Expression:')

linkre = re.compile(reg)

linklist = re.findall(linkre,html)

return linklist

address = raw_input('Please input url http://')

html = getHtml('http://'+address)

res = getlink(html)

newfile = file('Result.txt','w')

for i in res:

newfile.write(i+'n')

print i

newfile.close()

print 'Find',len(res),'nOutput file : Result.txt'