Github/stackdump
1
0
Fork 0
mirror of https://github.com/djohnlewis/stackdump synced 2025-04-05 01:03:27 +00:00
Code Issues Projects Releases Wiki Activity

Fixed a bug where extra html/head/body tags were added for every question and answer due to the HTML re-writing process.

Browse Source
This commit is contained in:
Samuel Lai 2012-08-25 16:37:03 +10:00
parent af28d3e403
commit e4b2ee80a0
1 changed files with 2 additions and 2 deletions

4
python/src/stackdump/app.py

@ -719,7 +719,7 @@ def sort_answers(result):
def _rewrite_html(html, app_url_root, sites_by_urls): def _rewrite_html(html, app_url_root, sites_by_urls):
# wrap the given HTML fragment in an element so it looks like a document. # wrap the given HTML fragment in an element so it looks like a document.
html = '<html>%s</html>' % html html = '<div>%s</div>' % html
parser = html5lib.HTMLParser(tree=html5lib.treebuilders.getTreeBuilder('etree')) parser = html5lib.HTMLParser(tree=html5lib.treebuilders.getTreeBuilder('etree'))
html = parser.parse(html) html = parser.parse(html)
@ -755,7 +755,7 @@ def _rewrite_html(html, app_url_root, sites_by_urls):
# with namespaces to conform to XML. # with namespaces to conform to XML.
walker = html5lib.treewalkers.getTreeWalker('etree', implementation=ElementTree) walker = html5lib.treewalkers.getTreeWalker('etree', implementation=ElementTree)
stream = walker(html) stream = walker(html)
serializer = html5lib.serializer.htmlserializer.HTMLSerializer(omit_optional_tags=False, serializer = html5lib.serializer.htmlserializer.HTMLSerializer(omit_optional_tags=True,
quote_attr_values=True, quote_attr_values=True,
minimize_boolean_attributes=False) minimize_boolean_attributes=False)
output_generator = serializer.serialize(stream) output_generator = serializer.serialize(stream)