python网页列表爬虫

 

#-*- encoding: utf-8 -*-

 

import htmllib,urllib,formatter,string

 

class GetLinks(htmllib.HTMLParser,str):

    def __init__(self,str): 

        self.str=str

        self.links = {}

        f = formatter.NullFormatter()

        htmllib.HTMLParser.__init__(self, f)

 

    def anchor_bgn(self, href, name, type):

        self.save_bgn()

        self.link = href

 

    def anchor_end(self): 

        text = string.strip(self.save_end()) 

        if text.find(self.str)!=-1 :

            if self.link and text:

                self.links[text] = self.link

 

def findall(str1,strfront,i,strlat):

    fp = urllib.urlopen(strfront+str(i)+strlat)

    data = fp.read()

    fp.close()

    linkdemo = GetLinks(str1) 

    linkdemo.feed(data) 

    linkdemo.close()

 

    for href, link in linkdemo.links.items(): 

        print href, "=>", link

 

i=1

strfront='http://readthedocs.org/docs/learn-python-the-hard-way-zh_cn-translation/en/latest/ex'

strlat='.html'

search='ex'

while i<20 :

    findall(search,strfront,i,strlat)

    i=i+1