#!/usr/bin/env python
import HTMLParser
import sys,urllib
class myparser(HTMLParser.HTMLParser):
def __init__(self):
HTMLParser.HTMLParser.__init__(self)
self.recording=0
self.data=[]
def handle_starttag(self,tag,attributes):
if tag=='span':
self.recording=1
if self.recording==1:
for name,value in attributes:
if name=='class' and value == 'row_proxy_ip':
print name
self.recoding==2
def handle_endtag(self,tag):
if tag=='span' and self.recording:
self.recording=0
def handle_data(self,data):
if self.recording==2:
self.data.append(data)
html=myparser()
file1=(urllib.urlopen("http://www.proxcn.com/proxy-server-list").read())
html.feed(file1)
print html.data
html.close()