#小练习 使用SGMLParser获取url链接 分类: HTMLParser 2013-11-12 16:52 471人阅读 评论(0) 收藏

#获取链接
#coding:utf-8
from sgmllib import SGMLParser

class urlparser(SGMLParser):

    def reset(self):
        self.result=[]
        SGMLParser.reset(self)

    def start_a(self,attrs):

        #学习此处使用的列表推导式
        href=[v for k,v in attrs if k=='href']
        if href:
            self.result.extend(href)
 
if __name__ == '__main__':
    urls='''
    <tr>
<td height="207" colspan="2" align="left" valign="top" class="normal">
<p>Damien Rice - 《0》 </p>
<a href="http://galeki.xy568.net/music/Delicate.mp3">1. Delicate</a><br />
<a href="http://galeki.xy568.net/music/Volcano.mp3">2. Volcano</a><br />
<a href="http://galeki.xy568.net/music/The Blower's Daughter.mp3">3. The Blower's Daughter</a><br />
<a href="http://galeki.xy568.net/music/Cannonball.mp3">4. Cannonball </a><br />
<a href="http://galeki.xy568.net/music/Older Chests.mp3">5. Order Chests</a><br />
<a href="http://galeki.xy568.net/music/Amie.mp3">6. Amie</a><br />
<a href="http://galeki.xy568.net/music/Cheers Darlin'.mp3">7. Cheers Darling</a><br />
<a href="http://galeki.xy568.net/music/Cold Water.mp3">8. Cold water</a><br />
<a href="http://galeki.xy568.net/music/I Remember.mp3">9. I remember</a><br />
<a href="http://galeki.xy568.net/music/Eskimo.mp3">10. Eskimo</a></p>
</td>
</tr>
    '''
    upr=urlparser()
    upr.feed(urls)
    for i in upr.result:
        print i
    upr.close()


结果:

http://galeki.xy568.net/music/Delicate.mp3
http://galeki.xy568.net/music/Volcano.mp3
http://galeki.xy568.net/music/The Blower's Daughter.mp3
http://galeki.xy568.net/music/Cannonball.mp3
http://galeki.xy568.net/music/Older Chests.mp3
http://galeki.xy568.net/music/Amie.mp3
http://galeki.xy568.net/music/Cheers Darlin'.mp3
http://galeki.xy568.net/music/Cold Water.mp3
http://galeki.xy568.net/music/I Remember.mp3
http://galeki.xy568.net/music/Eskimo.mp3

版权声明:本文为博主原创文章,未经博主允许不得转载。

原文地址:https://www.cnblogs.com/think1988/p/4628016.html