lxml.html删除节点树和tag对

# encoding: utf-8
import StringIO

from apihelper import info, info_save
from lxml import etree, html
from lxml.html.clean import Cleaner

strhtml = '''\
<html>
   <head>
     <script type="text/javascript" src="evil-site"></script>
     <link rel="alternate" type="text/rss" src="evil-rss">
     <style>
       body {background-image: url(javascript:do_evil)};
       div {color: expression(evil)};
     </style>
   </head>
   <body onload="evil_function()">
     
     <a href="javascript:evil_function()">a link</a>
     <a href="#" onclick="evil_function()">another link</a>
     <p onclick="evil_function()">a paragraph</p>
     <div style="display: none">secret EVIL!</div>
     <object> of EVIL! </object>
     <iframe src="evil-site"></iframe>
     <form action="evil-site">
       Password: <input type="password" name="password">
     </form>
     <blink>annoying EVIL!</blink>
     <a href="evil-site">spam spam SPAM!</a>
     <image src="evil!">
     <div id='nav' class='nav'>this is nav</div>
   </body>
</html>'''

# strhtml = '''<html><head></head>
# <body><div>aaa</div></body>
# </html>'''

etree.DEBUG = 1
print etree.LIBXML_VERSION
utf8_parser=html.HTMLParser(encoding='utf8')
# f = open(xmlFile)
# xml = f.read()
# f.close()
doc=html.fromstring(strhtml, parser=utf8_parser)
# weather = doc.xpath('body/object')
# doc.find('.//body/object').drop_tag()
# doc.find('.//body/object').drop_tree()
doc.find('.//body').drop_tree()
# print '\r\n'.join(doc)
# print info_save(doc)
# print html.tostring(doc)

巴特西

lxml.html删除节点树和tag对

最新文章

热门文章