urllister.py源码分析

<script>function StorePage(){d=document;t=d.selection?(d.selection.type!='None'?d.selection.createRange().text:''):(d.getSelection?d.getSelection():'');void(keyit=window.open('http://www.365key.com/storeit.aspx?t='+escape(d.title)+'&u='+escape(d.location.href)+'&c='+escape(t),'keyit','scrollbars=no,width=475,height=575,left=75,top=20,status=no,resizable=yes'));keyit.focus();}</script>

"""Extract list of URLs in a web page

This program is part of "Dive Into Python", a free Python book for
experienced programmers. Visit http://diveintopython.org/ for the
latest version.
"""

__author__ = "Mark Pilgrim ([email protected])"
__version__ = "$Revision: 1.2 $"
__date__ = "$Date: 2004/05/05 21:57:19 $"
__copyright__ = "Copyright (c) 2001 Mark Pilgrim"
__license__ = "Python"

#声明四个字符串，并赋值

from sgmllib import SGMLParser

#导入SGMLParser类

class URLLister(SGMLParser):

#自定义一个新类URLLister

def reset(self):
SGMLParser.reset(self)

#调用SGMLParser的reset方法，重置类实例
self.urls = []

#初始化self的urls变量为空数组

def start_a(self, attrs):
href = [v for k, v in attrs if k=='href']
if href:
self.urls.extend(href)

#若href不为空，将href添加到urls中

if __name__ == "__main__":
import urllib
usock = urllib.urlopen("http://diveintopython.org/")

#调入urllib这个类，打开http://diveintopython.org/这个网址
parser = URLLister()

#获取类URLLister的实例，并赋给parser
parser.feed(usock.read())

#将usock读取的内容“喂给”parser
parser.close()

#关闭parser
usock.close()

#关闭usock
for url in parser.urls: print url

#打印parser的所有元素