From b9a836515fad5df57a86412b2cd41c49869ec0d6 Mon Sep 17 00:00:00 2001 From: Filippo Valsorda Date: Tue, 29 Oct 2013 16:44:35 -0400 Subject: Update the Vimeo test vector md5 confirmed that this is indeed the first 10241 (we went off by one with byte range 0-10240) of the full, playing mp4, so they probably reencoded or something --- youtube_dl/extractor/vimeo.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'youtube_dl/extractor/vimeo.py') diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index b4dbcd2ee..c7d864a2b 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -27,7 +27,7 @@ class VimeoIE(InfoExtractor): { u'url': u'http://vimeo.com/56015672#at=0', u'file': u'56015672.mp4', - u'md5': u'ae7a1d8b183758a0506b0622f37dfa14', + u'md5': u'8879b6cc097e987f02484baf890129e5', u'info_dict': { u"upload_date": u"20121220", u"description": u"This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", -- cgit v1.2.3 From 9103bbc5cd11957de2e906e4401dcf4df9511d28 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Sun, 3 Nov 2013 12:11:13 +0100 Subject: 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. --- youtube_dl/extractor/vimeo.py | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'youtube_dl/extractor/vimeo.py') diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index c7d864a2b..62273fd33 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -20,7 +20,7 @@ class VimeoIE(InfoExtractor): """Information extractor for vimeo.com.""" # _VALID_URL matches Vimeo URLs - _VALID_URL = r'(?Phttps?://)?(?:(?:www|player)\.)?vimeo(?Ppro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)/?(?:[?].*)?(?:#.*)?$' + _VALID_URL = r'(?Phttps?://)?(?:(?:www|(?Pplayer))\.)?vimeo(?Ppro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?Pplay_redirect_hls\?clip_id=)?(?:videos?/)?(?P[0-9]+)/?(?:[?].*)?(?:#.*)?$' _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): -- cgit v1.2.3 From a56f9de156c7cca29dfa45de1dadc66e10a265f2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Sun, 3 Nov 2013 14:03:17 +0100 Subject: Style fixes for extractors: remove spaces around (,),{ and } --- youtube_dl/extractor/vimeo.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'youtube_dl/extractor/vimeo.py') diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 62273fd33..d465bf20b 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -203,7 +203,7 @@ class VimeoIE(InfoExtractor): # Vimeo specific: extract video codec and quality information # First consider quality, then codecs, then take everything codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')] - files = { 'hd': [], 'sd': [], 'other': []} + files = {'hd': [], 'sd': [], 'other': []} config_files = config["video"].get("files") or config["request"].get("files") for codec_name, codec_extension in codecs: for quality in config_files.get(codec_name, []): -- cgit v1.2.3