python 解析html标签中的属性

来源：互联网发布：数据库模型图是什么编辑：程序博客网时间：2024/05/24 02:26

#!/usr/bin/pythonfrom lxml import etreefrom io import StringIO, BytesIOfrom HTMLParser import HTMLParserfrom 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]

0 0