X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvimeo.py;h=4b4b472a50da08aeeae9d1f93ff74e1fcc6d56a1;hb=777ac90791e6f105c4c617d22fac404cb316c4f9;hp=ad86d033acc3279f0a821cdb4fd1616ed60c5305;hpb=fcee8ee7842deb1b99a84f078ecfb4abfb266cc1;p=youtube-dl diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index ad86d033a..4b4b472a5 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, @@ -19,12 +20,12 @@ from ..utils import ( ) -class VimeoIE(InfoExtractor): +class VimeoIE(SubtitlesInfoExtractor): """Information extractor for vimeo.com.""" # _VALID_URL matches Vimeo URLs _VALID_URL = r'''(?x) - (?Phttps?://)? + (?P(?:https?:)?//)? (?:(?:www|(?Pplayer))\.)? vimeo(?Ppro)?\.com/ (?:.*?/)? @@ -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", }, }, @@ -84,6 +86,20 @@ 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', + } + }, ] def _login(self): @@ -124,6 +140,19 @@ class VimeoIE(InfoExtractor): 'Verifying the password', 'Wrong password') + def _verify_player_video_password(self, url, video_id): + password = self._downloader.params.get('videopassword', None) + if password is None: + raise ExtractorError('This video is protected by a password, use the --video-password option') + data = compat_urllib_parse.urlencode({'password': password}) + pass_url = url + '/check-password' + password_request = compat_urllib_request.Request(pass_url, data) + password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') + return self._download_json( + password_request, video_id, + 'Verifying the password', + 'Wrong password') + def _real_initialize(self): self._login() @@ -136,9 +165,6 @@ class VimeoIE(InfoExtractor): # Extract ID from URL mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) - video_id = mobj.group('id') if mobj.group('pro') or mobj.group('player'): url = 'http://player.vimeo.com/video/' + video_id @@ -147,7 +173,18 @@ 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, @@ -184,8 +221,7 @@ class VimeoIE(InfoExtractor): cause=e) else: if config.get('view') == 4: - self._verify_video_password(url, video_id, webpage) - return self._real_extract(url) + config = self._verify_player_video_password(url, video_id) # Extract title video_title = config["video"]["title"] @@ -197,7 +233,9 @@ 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 @@ -264,25 +302,37 @@ 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="(.*?)"' @@ -318,7 +368,7 @@ class VimeoChannelIE(InfoExtractor): class VimeoUserIE(VimeoChannelIE): IE_NAME = 'vimeo:user' - _VALID_URL = r'(?:https?://)?vimeo.\com/(?P[^/]+)(?:[#?]|$)' + _VALID_URL = r'(?:https?://)?vimeo\.com/(?P[^/]+)(?:/videos|[#?]|$)' _TITLE_RE = r']+?class="user">([^<>]+?)' @classmethod @@ -335,7 +385,7 @@ class VimeoUserIE(VimeoChannelIE): class VimeoAlbumIE(VimeoChannelIE): IE_NAME = 'vimeo:album' - _VALID_URL = r'(?:https?://)?vimeo.\com/album/(?P\d+)' + _VALID_URL = r'(?:https?://)?vimeo\.com/album/(?P\d+)' _TITLE_RE = r'
\n\s*

(.*?)

' def _page_url(self, base_url, pagenum): @@ -349,7 +399,7 @@ class VimeoAlbumIE(VimeoChannelIE): class VimeoGroupsIE(VimeoAlbumIE): IE_NAME = 'vimeo:group' - _VALID_URL = r'(?:https?://)?vimeo.\com/groups/(?P[^/]+)' + _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P[^/]+)' def _extract_list_title(self, webpage): return self._og_search_title(webpage) @@ -363,7 +413,7 @@ class VimeoGroupsIE(VimeoAlbumIE): class VimeoReviewIE(InfoExtractor): IE_NAME = 'vimeo:review' IE_DESC = 'Review pages on vimeo' - _VALID_URL = r'(?:https?://)?vimeo.\com/[^/]+/review/(?P[^/]+)' + _VALID_URL = r'(?:https?://)?vimeo\.com/[^/]+/review/(?P[^/]+)' _TEST = { 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', 'file': '75524534.mp4',