X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvimeo.py;h=bb08c61509e6d68a8661c3d4876cb258e99fa832;hb=a9c2896e2252839c2e4801189f10acce7ff6413e;hp=a50170ce76923837717dec6df19a558734d46e4e;hpb=0f2999fe2b352795d54e6fcc4027e6a64ce5bc1d;p=youtube-dl diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index a50170ce7..bb08c6150 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -6,10 +6,11 @@ import re import itertools from .common import InfoExtractor +from .subtitles import SubtitlesInfoExtractor from ..utils import ( + compat_HTTPError, compat_urllib_parse, compat_urllib_request, - clean_html, get_element_by_attribute, ExtractorError, @@ -19,7 +20,7 @@ from ..utils import ( ) -class VimeoIE(InfoExtractor): +class VimeoIE(SubtitlesInfoExtractor): """Information extractor for vimeo.com.""" # _VALID_URL matches Vimeo URLs @@ -37,13 +38,14 @@ class VimeoIE(InfoExtractor): _TESTS = [ { 'url': 'http://vimeo.com/56015672#at=0', - 'file': '56015672.mp4', 'md5': '8879b6cc097e987f02484baf890129e5', 'info_dict': { - "upload_date": "20121220", - "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", - "uploader_id": "user7108434", - "uploader": "Filippo Valsorda", + 'id': '56015672', + 'ext': 'mp4', + "upload_date": "20121220", + "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", + "uploader_id": "user7108434", + "uploader": "Filippo Valsorda", "title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", }, }, @@ -84,8 +86,31 @@ class VimeoIE(InfoExtractor): 'videopassword': 'youtube-dl', }, }, + { + 'url': 'http://vimeo.com/76979871', + 'md5': '3363dd6ffebe3784d56f4132317fd446', + 'note': 'Video with subtitles', + 'info_dict': { + 'id': '76979871', + 'ext': 'mp4', + 'title': 'The New Vimeo Player (You Know, For Videos)', + 'description': 'md5:2ec900bf97c3f389378a96aee11260ea', + 'upload_date': '20131015', + 'uploader_id': 'staff', + 'uploader': 'Vimeo Staff', + } + }, ] + @classmethod + def suitable(cls, url): + if VimeoChannelIE.suitable(url): + # Otherwise channel urls like http://vimeo.com/channels/31259 would + # match + return False + else: + return super(VimeoIE, cls).suitable(url) + def _login(self): (username, password) = self._get_login_info() if username is None: @@ -157,7 +182,18 @@ class VimeoIE(InfoExtractor): # Retrieve video webpage to extract further information request = compat_urllib_request.Request(url, None, headers) - webpage = self._download_webpage(request, video_id) + try: + webpage = self._download_webpage(request, video_id) + except ExtractorError as ee: + if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: + errmsg = ee.cause.read() + if b'Because of its privacy settings, this video cannot be played here' in errmsg: + raise ExtractorError( + 'Cannot download embed-only video without embedding ' + 'URL. Please call youtube-dl with the URL of the page ' + 'that embeds this video.', + expected=True) + raise # Now we begin extracting as much information as we can from what we # retrieved. First we extract the information common to all extractors, @@ -206,7 +242,9 @@ class VimeoIE(InfoExtractor): # Extract video thumbnail video_thumbnail = config["video"].get("thumbnail") if video_thumbnail is None: - _, video_thumbnail = sorted((int(width), t_url) for (width, t_url) in config["video"]["thumbs"].items())[-1] + video_thumbs = config["video"].get("thumbs") + if video_thumbs and isinstance(video_thumbs, dict): + _, video_thumbnail = sorted((int(width), t_url) for (width, t_url) in video_thumbs.items())[-1] # Extract video description video_description = None @@ -273,25 +311,37 @@ class VimeoIE(InfoExtractor): if len(formats) == 0: raise ExtractorError('No known codec found') + subtitles = {} + text_tracks = config['request'].get('text_tracks') + if text_tracks: + for tt in text_tracks: + subtitles[tt['lang']] = 'http://vimeo.com' + tt['url'] + + video_subtitles = self.extract_subtitles(video_id, subtitles) + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, subtitles) + return + return { - 'id': video_id, + 'id': video_id, 'uploader': video_uploader, 'uploader_id': video_uploader_id, - 'upload_date': video_upload_date, - 'title': video_title, - 'thumbnail': video_thumbnail, - 'description': video_description, + 'upload_date': video_upload_date, + 'title': video_title, + 'thumbnail': video_thumbnail, + 'description': video_description, 'formats': formats, 'webpage_url': url, 'view_count': view_count, 'like_count': like_count, 'comment_count': comment_count, + 'subtitles': video_subtitles, } class VimeoChannelIE(InfoExtractor): IE_NAME = 'vimeo:channel' - _VALID_URL = r'(?:https?://)?vimeo\.com/channels/(?P[^/]+)' + _VALID_URL = r'(?:https?://)?vimeo\.com/channels/(?P[^/]+)/?(\?.*)?$' _MORE_PAGES_INDICATOR = r']+?title="(.*?)"'