一个简单的python程序:得到网页中的所有连接

#filename:URLLister.py

from sgmllib import SGMLParser

 

class URLLister(SGMLParser):        #注意这里的处理html的类是继承了SGMLParser类的。。。

        def reset(self):

                SGMLParser.reset(self)

                self.urls = []

 

        def start_a(self,attrs):        #这里的是找的所有的标签。

                href = [v for k,v in attrs if k=='href']                #这里的语法很特别，返回的是一个列表

                if href:

                        self.urls.extend(href)

+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

#这是一个文件读取的类FileRead.py

def readFile(filename):

        data=""

        #f=file("D:\书籍\linux\我的linux备份\新增\xinhua.htm")

        f=file(filename)

        while True:

                line=f.readline()

                if len(line)==0:

                        break

                data+=line

        f.close()

        return data

+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

#test_urllister.py

from URLLister import URLLister                #里面有重要的关于网页的监听

import urllib

from FileRead import readFile       

 

#usock= urllib.urlopen("")                #因为好像禁止读取网络的数据，所以暂时使用静态文件进行测试

 

parser=URLLister()                #这里是使用了一个关于网页文件内容的监听，查找到全部的标签

 

#parser.feed(usock.read())

 

text=readFile(r"D:\书籍\linux\我的linux备份\新增\xinhua.htm")

parser.feed(text)

#usock.close()

parser.close()

for url in parser.urls:

        print url