Add the 'webpage_url' field to info_dict

The url for the video page, it must allow to reproduce the result.
It's automatically set by YoutubeDL if it's missing.
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-11-03 12:11:13 +01:00
parent b6c45014ae
commit 9103bbc5cd
5 changed files with 24 additions and 11 deletions

View file

@ -20,7 +20,7 @@ class VimeoIE(InfoExtractor):
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
_VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$'
_VALID_URL = r'(?P<proto>https?://)?(?:(?:www|(?P<player>player))\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?(?:#.*)?$'
_NETRC_MACHINE = 'vimeo'
IE_NAME = u'vimeo'
_TESTS = [
@ -128,11 +128,9 @@ class VimeoIE(InfoExtractor):
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('id')
if not mobj.group('proto'):
url = 'https://' + url
elif mobj.group('pro'):
if mobj.group('pro') or mobj.group('player'):
url = 'http://player.vimeo.com/video/' + video_id
elif mobj.group('direct_link'):
else:
url = 'https://vimeo.com/' + video_id
# Retrieve video webpage to extract further information
@ -234,7 +232,7 @@ class VimeoIE(InfoExtractor):
if len(formats) == 0:
raise ExtractorError(u'No known codec found')
return [{
return {
'id': video_id,
'uploader': video_uploader,
'uploader_id': video_uploader_id,
@ -243,7 +241,8 @@ class VimeoIE(InfoExtractor):
'thumbnail': video_thumbnail,
'description': video_description,
'formats': formats,
}]
'webpage_url': url,
}
class VimeoChannelIE(InfoExtractor):