aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2013-07-17 10:38:23 +0200
committerPhilipp Hagemeister <phihag@phihag.de>2013-07-17 10:38:23 +0200
commitf38de77f6ec5548c94c6183d0240381c31320711 (patch)
tree83691db34533f8a02c29f009e3a351f2d3e203d1
parent58e7d46d1b1d8a145c82795fa8fb75a232455274 (diff)
downloadyoutube-dl-f38de77f6ec5548c94c6183d0240381c31320711.zip
youtube-dl-f38de77f6ec5548c94c6183d0240381c31320711.tar.gz
youtube-dl-f38de77f6ec5548c94c6183d0240381c31320711.tar.bz2
Use unescapeHTML for OpenGraph properties
These are attribute values, so we don't need the more complex and whitespace-destroying cleanHTML - we just need to unescape quotes, that's it.
-rw-r--r--youtube_dl/extractor/common.py4
1 files changed, 3 insertions, 1 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index ec988fc..da50abf 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -14,6 +14,7 @@ from ..utils import (
clean_html,
compiled_regex_type,
ExtractorError,
+ unescapeHTML,
)
class InfoExtractor(object):
@@ -270,7 +271,8 @@ class InfoExtractor(object):
def _og_search_property(self, prop, html, name=None, **kargs):
if name is None:
name = 'OpenGraph %s' % prop
- return self._html_search_regex(self._og_regex(prop), html, name, flags=re.DOTALL, **kargs)
+ escaped = self._search_regex(self._og_regex(prop), html, name, flags=re.DOTALL, **kargs)
+ return unescapeHTML(escaped)
def _og_search_thumbnail(self, html, **kargs):
return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs)