python模块之HTMLParser抓页面上的所有URL链接

# -*- coding: utf-8 -*-
#python 27
#xiaodeng
#python模块之HTMLParser抓页面上的所有URL链接


import urllib
#MyParser类写法一
‘‘‘
from HTMLParser import HTMLParser
class MyParser(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
       
    def handle_starttag(self, tag, attrs):
        if tag == ‘a‘:
            for name,value in attrs:
                if name == ‘href‘ and value.startswith(‘http‘):
                    print value

‘‘‘

#MyParser类写法二
import HTMLParser
class MyParser(HTMLParser.HTMLParser):
       
    def handle_starttag(self, tag, attrs):
　　　　　#这里重新定义了处理开始标签的函数
        if tag == ‘a‘:#判断标签<a>的属性
            for name,value in attrs:
                if name == ‘href‘ and value.startswith(‘http‘):#以什么字符串开头
                    print value
                    
if __name__ == ‘__main__‘:
    url=‘http://www.cnblogs.com/‘
    content=urllib.urlopen(url).read()
    my=MyParser()
    my.feed(content)
    my.close()
    
‘‘‘ 
http://www.cnblogs.com/Jaryleely/p/careertwo.html
http://www.cnblogs.com/Jaryleely/
http://www.cnblogs.com/Jaryleely/
http://www.cnblogs.com/Jaryleely/p/careertwo.html#commentform
http://www.cnblogs.com/Jaryleely/p/careertwo.html
http://www.cnblogs.com/AndroidJotting/p/4983688.html
http://www.cnblogs.com/AndroidJotting/
http://www.cnblogs.com/AndroidJotting/
http://www.cnblogs.com/AndroidJotting/p/4983688.html#commentform
http://www.cnblogs.com/AndroidJotting/p/4983688.html
http://www.cnblogs.com/fuly550871915/p/4983682.html
http://www.cnblogs.com/fuly550871915/
http://www.cnblogs.com/fuly550871915/
http://www.cnblogs.com/fuly550871915/p/4983682.html#commentform
http://www.cnblogs.com/fuly550871915/p/4983682.html
http://www.cnblogs.com/Ray-liang/p/4983592.html
http://www.cnblogs.com/Ray-liang/
http://www.cnblogs.com/Ray-liang/
http://www.cnblogs.com/Ray-liang/p/4983592.html#commentform
http://www.cnblogs.com/Ray-liang/p/4983592.html
.......
‘‘‘