在 Python SGMLParser 中,我无法解析 ' <br/>
' 没有空块,但 ' <br />
'。
我可以运行此代码以成功解析 html,但是如果我将标记从 ' <br />
' 更改为 ' <br/>
' 只是删除空块,则会导致我无法成功解析 html。
除了更换标签外,任何想法解决它?
成功的例子。
# coding=utf-8
from sgmllib import SGMLParser #get SGML
class ListName(SGMLParser):#parser class
def reset(self):
self.is_a = False #get <a></a>
self.name=[] #get text
SGMLParser.reset(self)
def start_a(self,attrs):
self.is_a = True
def end_a(self):
self.is_a = False
def handle_data(self,data):
if self.is_a:
self.name.append(data)
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>
'''
listname=ListName() #init parser
listname.feed(urls) #run parser
print listname.name
listname.close()
结果是:
['1。微妙的','2。火山',“3。鼓风机的女儿”,'4。炮弹','5。订单箱','6。艾米','7。干杯亲爱的','8。冷水','9。我记得','10。爱斯基摩人']
错误的例子:
# coding=utf-8
from sgmllib import SGMLParser #get SGML
class ListName(SGMLParser):#parser class
def reset(self):
self.is_a = False #get <a></a>
self.name=[] #get text
SGMLParser.reset(self)
def start_a(self,attrs):
self.is_a = True
def end_a(self):
self.is_a = False
def handle_data(self,data):
if self.is_a:
self.name.append(data)
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>
'''
listname=ListName() #init parser
listname.feed(urls) #run parser
print listname.name
listname.close()
结果是:
['1。精美的']