python 解析html标签中的属性

最新推荐文章于 2023-06-14 19:29:49 发布

lavins

最新推荐文章于 2023-06-14 19:29:49 发布

阅读量5.4k

点赞数

分类专栏： python 文章标签： python htmlparse

本文链接：https://blog.csdn.net/herohenu/article/details/50722470

版权

python 专栏收录该内容

1 篇文章 0 订阅

订阅专栏

#!/usr/bin/python
from lxml import etree
from io import StringIO, BytesIO
from HTMLParser import HTMLParser
from lxml import html 
if __name__ == '__main__':
            # print(type(data))
         data ={u'seatbid': [{u'bid': [{u'nurl': u'http://baidu.com', u'cid': u'986191', u'crid': u'4581591', u'price': 0.1317348624101392, u'adid': u'56cb0b8b70f8f8100805eeda', u'adomain': [u'mobvista.com'], u'adm': u'<a href="http://52.0.105.35/0.jpg" width ="320" height ="50" /> <html> <body><script type=\'text/javascript\'>  var ifr = document.createElement(\'iframe\'); ifr.style.display = \'none\'; ifr.src = \'http://beijing.com?a=1&appname=test\'; document.body.appendChild(ifr); </script> </body></html></a> ', u'id': u'222'}]}], u'id': u'bid1-7'}
         admstr = data['seatbid'][0]['bid'][0]['adm']
         tree = html.fromstring(admstr)
         # print [e.text_content() for e in tree.xpath("//a")]  // result  is ok 
         parser = etree.HTMLParser()
         tree   = etree.parse(StringIO(admstr), parser)      


         ahref = [a.attrib['href'] for a in tree.xpath("//a")]
         imghref=[img.attrib['src'] for img in tree.xpath("//img")]
         print     "ahref is :",ahref[0]
         print "imghref is :",imghref[0]