ʹÓÃpython»ñÈ¡htmlÒ³ÃæµÄÄÚÈÝ

import urllib
from HTMLParser import HTMLParser
class TitleParser(HTMLParser):
def __init__(self):
self.title = ''
self.divcontent = ''
self.readingtitle = 0
self.readingdiv = 0
HTMLParser.__init__(self)
def handle_starttag(self, tag, attrs):
if tag == 'title':
self.readingtitle = 1
if -1 != tag.find("div"):
self.readingdiv = 1
def handle_data(self, data):
if self.readingtitle:
# Ordinarily, this is slow and a bad practice, but
# we can get away with it because a title is usually
# small and simple.
self.title += data
if self.readingdiv:
self.divcontent += data
def handle_endtag(self, tag):
if tag == 'title':
self.readingtitle = 0
if tag == "div":
self.readingdiv = 0
def gettitle(self):
return self.title
def getdiv(self):
return self.divcontent
def getweb(url):
web = urllib.urlopen('http://blog.chinaunix.net/u3/105068/showart_2223566.html').read()
return web
web = getweb('http://blog.chinaunix.net/u3/105068/showart_2223566.html')
test = TitleParser()
test.feed(web)
file_object = open('abinfile', 'w')
file_object.write(test.title)
file_object.write("\r\n")
file_object.write(test.divcontent)
file_object.close()