Skip to content
Browse files

Merge pull request #4 from ercpe/master

Ignore HTML5 start tags 'footer' and 'nav' too
  • Loading branch information...
2 parents b515473 + d26ff98 commit d48c4ab3c707f9987f904970a8fda37bf4ca67ef @chrisspen committed Mar 17, 2013
Showing with 1 addition and 1 deletion.
  1. +1 −1 webarticle2text.py
View
2 webarticle2text.py
@@ -92,7 +92,7 @@ def __init__(self):
def handle_starttag(self, tag, attrs):
ignore0 = self._ignore
tag = tag.lower()
- if tag in ('script','style','option','ul','li','legend','object','noscript','label'): # 'h1','h2','h3','h4','h5','h6',
+ if tag in ('script','style','option','ul','li','legend','object','noscript','label', 'footer', 'nav', 'aside'): # 'h1','h2','h3','h4','h5','h6',
self._ignore = True
attrd = dict(attrs)
self._lasttag = tag.lower()

0 comments on commit d48c4ab

Please sign in to comment.
Something went wrong with that request. Please try again.