aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/common.py
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-11-15 12:24:54 +0100
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-11-15 12:24:54 +0100
commitab2d524780736249c8988313db021e83642c24d1 (patch)
tree162e3fb13da0769922631e9c4a9bbce656d784b8 /youtube_dl/extractor/common.py
parent85d61685f15bdc62709c699e849af512db78089f (diff)
Improve the OpenGraph regex
* Do not accept '>' between the property and content attributes. * Recognize the properties if the content attribute is before the property attribute using two regexes (fixes the extraction of the description for SlideshareIE).
Diffstat (limited to 'youtube_dl/extractor/common.py')
-rw-r--r--youtube_dl/extractor/common.py14
1 files changed, 9 insertions, 5 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 9c20d30b4..e02176852 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -315,13 +315,17 @@ class InfoExtractor(object):
# Helper functions for extracting OpenGraph info
@staticmethod
- def _og_regex(prop):
- return r'<meta.+?property=[\'"]og:%s[\'"].+?content=(?:"(.+?)"|\'(.+?)\')' % re.escape(prop)
+ def _og_regexes(prop):
+ esc_prop = re.escape(prop)
+ return [
+ r'<meta[^>]+?property=[\'"]og:%s[\'"][^>]+?content=(?:"(.+?)"|\'(.+?)\')' % esc_prop,
+ r'<meta[^>]+?content=(?:"(.+?)"|\'(.+?)\')[^>]+?property=[\'"]og:%s[\'"]' % esc_prop,
+ ]
def _og_search_property(self, prop, html, name=None, **kargs):
if name is None:
name = 'OpenGraph %s' % prop
- escaped = self._search_regex(self._og_regex(prop), html, name, flags=re.DOTALL, **kargs)
+ escaped = self._search_regex(self._og_regexes(prop), html, name, flags=re.DOTALL, **kargs)
if escaped is None:
return None
return unescapeHTML(escaped)
@@ -336,8 +340,8 @@ class InfoExtractor(object):
return self._og_search_property('title', html, **kargs)
def _og_search_video_url(self, html, name='video url', secure=True, **kargs):
- regexes = [self._og_regex('video')]
- if secure: regexes.insert(0, self._og_regex('video:secure_url'))
+ regexes = self._og_regexes('video')
+ if secure: regexes = self._og_regexes('video:secure_url') + regexes
return self._html_search_regex(regexes, html, name, **kargs)
def _rta_search(self, html):