0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

fix html cleanup of empty string

Browse source
This commit is contained in:
j 2013-12-01 12:35:38 +00:00
parent 6f68729b6f
commit 37cd92dfba
1 changed files with 2 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
ox/html.py
View file

@ -395,6 +395,8 @@ def sanitize_fragment(html):
import html5lib import html5lib
return html5lib.parseFragment(html).toxml().decode('utf-8') return html5lib.parseFragment(html).toxml().decode('utf-8')
''' '''
if not html:
return u''
import lxml.html import lxml.html
body = lxml.html.document_fromstring(html).find('body') body = lxml.html.document_fromstring(html).find('body')
html = lxml.html.tostring(body, encoding='utf-8')[6:-7].decode('utf-8') html = lxml.html.tostring(body, encoding='utf-8')[6:-7].decode('utf-8')