From f38de77f6ec5548c94c6183d0240381c31320711 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 17 Jul 2013 10:38:23 +0200 Subject: [PATCH] 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. --- youtube_dl/extractor/common.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index ec988fc90..da50abfc1 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -14,6 +14,7 @@ clean_html, compiled_regex_type, ExtractorError, + unescapeHTML, ) class InfoExtractor(object): @@ -270,7 +271,8 @@ def _og_regex(prop): 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)