]>
Commit | Line | Data |
---|---|---|
70d1924f | 1 | import re |
55992530 | 2 | import json |
70d1924f JMF |
3 | |
4 | from .common import InfoExtractor | |
e0da32df | 5 | from ..compat import ( |
5c9ced95 | 6 | compat_str, |
9bccdc70 | 7 | compat_HTTPError, |
e0da32df | 8 | ) |
1cc79574 | 9 | from ..utils import ( |
70d1924f | 10 | ExtractorError, |
7d3d06a1 | 11 | int_or_none, |
9165d6ba | 12 | parse_iso8601, |
4dfbf869 | 13 | parse_qs, |
70d1924f JMF |
14 | ) |
15 | ||
88bd97e3 | 16 | |
9618c448 | 17 | class VevoBaseIE(InfoExtractor): |
9d0c08a0 | 18 | def _extract_json(self, webpage, video_id): |
9618c448 S |
19 | return self._parse_json( |
20 | self._search_regex( | |
21 | r'window\.__INITIAL_STORE__\s*=\s*({.+?});\s*</script>', | |
22 | webpage, 'initial store'), | |
9d0c08a0 | 23 | video_id) |
9618c448 S |
24 | |
25 | ||
26 | class VevoIE(VevoBaseIE): | |
2975fe1a | 27 | ''' |
0577177e | 28 | Accepts urls from vevo.com or in the format 'vevo:{id}' |
3266f0c6 | 29 | (currently used by MTVIE and MySpaceIE) |
2975fe1a | 30 | ''' |
f25571ff | 31 | _VALID_URL = r'''(?x) |
92519402 | 32 | (?:https?://(?:www\.)?vevo\.com/watch/(?!playlist|genre)(?:[^/]+/(?:[^/]+/)?)?| |
f25571ff | 33 | https?://cache\.vevo\.com/m/html/embed\.html\?video=| |
ebce53b3 | 34 | https?://videoplayer\.vevo\.com/embed/embedded\?videoId=| |
d1e41164 | 35 | https?://embed\.vevo\.com/.*?[?&]isrc=| |
f25571ff PH |
36 | vevo:) |
37 | (?P<id>[^&?#]+)''' | |
fd5e6f7e | 38 | |
dd2d55f1 | 39 | _TESTS = [] |
2975fe1a | 40 | _VERSIONS = { |
9165d6ba | 41 | 0: 'youtube', # only in AuthenticateVideo videoVersions |
2975fe1a | 42 | 1: 'level3', |
43 | 2: 'akamai', | |
44 | 3: 'level3', | |
45 | 4: 'amazon', | |
46 | } | |
47 | ||
682f8c43 | 48 | def _initialize_api(self, video_id): |
9165d6ba | 49 | webpage = self._download_webpage( |
b07ea5ea | 50 | 'https://accounts.vevo.com/token', None, |
9165d6ba | 51 | note='Retrieving oauth token', |
b07ea5ea S |
52 | errnote='Unable to retrieve oauth token', |
53 | data=json.dumps({ | |
54 | 'client_id': 'SPupX1tvqFEopQ1YS6SS', | |
55 | 'grant_type': 'urn:vevo:params:oauth:grant-type:anonymous', | |
56 | }).encode('utf-8'), | |
57 | headers={ | |
58 | 'Content-Type': 'application/json', | |
59 | }) | |
9165d6ba | 60 | |
621a2800 | 61 | if re.search(r'(?i)THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION', webpage): |
bc7e77a0 S |
62 | self.raise_geo_restricted( |
63 | '%s said: This page is currently unavailable in your region' % self.IE_NAME) | |
9165d6ba | 64 | |
65 | auth_info = self._parse_json(webpage, video_id) | |
55992530 | 66 | self._api_url_template = self.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info['legacy_token'] |
9165d6ba | 67 | |
516ea41a | 68 | def _call_api(self, path, *args, **kwargs): |
9bccdc70 RA |
69 | try: |
70 | data = self._download_json(self._api_url_template % path, *args, **kwargs) | |
71 | except ExtractorError as e: | |
72 | if isinstance(e.cause, compat_HTTPError): | |
73 | errors = self._parse_json(e.cause.read().decode(), None)['errors'] | |
74 | error_message = ', '.join([error['message'] for error in errors]) | |
75 | raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True) | |
76 | raise | |
77 | return data | |
9165d6ba | 78 | |
72321ead | 79 | def _real_extract(self, url): |
4b942883 | 80 | video_id = self._match_id(url) |
72321ead | 81 | |
9bccdc70 | 82 | self._initialize_api(video_id) |
682f8c43 | 83 | |
9bccdc70 RA |
84 | video_info = self._call_api( |
85 | 'video/%s' % video_id, video_id, 'Downloading api video info', | |
86 | 'Failed to download video info') | |
2975fe1a | 87 | |
9bccdc70 RA |
88 | video_versions = self._call_api( |
89 | 'video/%s/streams' % video_id, video_id, | |
90 | 'Downloading video versions info', | |
91 | 'Failed to download video versions info', | |
92 | fatal=False) | |
ff51983e | 93 | |
9bccdc70 | 94 | # Some videos are only available via webpage (e.g. |
067aa17e | 95 | # https://github.com/ytdl-org/youtube-dl/issues/9366) |
9bccdc70 RA |
96 | if not video_versions: |
97 | webpage = self._download_webpage(url, video_id) | |
9d0c08a0 YCH |
98 | json_data = self._extract_json(webpage, video_id) |
99 | if 'streams' in json_data.get('default', {}): | |
100 | video_versions = json_data['default']['streams'][video_id][0] | |
101 | else: | |
102 | video_versions = [ | |
103 | value | |
104 | for key, value in json_data['apollo']['data'].items() | |
105 | if key.startswith('%s.streams' % video_id)] | |
9618c448 | 106 | |
9bccdc70 RA |
107 | uploader = None |
108 | artist = None | |
109 | featured_artist = None | |
110 | artists = video_info.get('artists') | |
111 | for curr_artist in artists: | |
112 | if curr_artist.get('role') == 'Featured': | |
113 | featured_artist = curr_artist['name'] | |
114 | else: | |
115 | artist = uploader = curr_artist['name'] | |
9165d6ba | 116 | |
9bccdc70 RA |
117 | formats = [] |
118 | for video_version in video_versions: | |
9d0c08a0 | 119 | version = self._VERSIONS.get(video_version.get('version'), 'generic') |
9bccdc70 RA |
120 | version_url = video_version.get('url') |
121 | if not version_url: | |
122 | continue | |
9165d6ba | 123 | |
9bccdc70 RA |
124 | if '.ism' in version_url: |
125 | continue | |
126 | elif '.mpd' in version_url: | |
127 | formats.extend(self._extract_mpd_formats( | |
128 | version_url, video_id, mpd_id='dash-%s' % version, | |
129 | note='Downloading %s MPD information' % version, | |
130 | errnote='Failed to download %s MPD information' % version, | |
131 | fatal=False)) | |
132 | elif '.m3u8' in version_url: | |
133 | formats.extend(self._extract_m3u8_formats( | |
134 | version_url, video_id, 'mp4', 'm3u8_native', | |
135 | m3u8_id='hls-%s' % version, | |
136 | note='Downloading %s m3u8 information' % version, | |
137 | errnote='Failed to download %s m3u8 information' % version, | |
138 | fatal=False)) | |
139 | else: | |
140 | m = re.search(r'''(?xi) | |
141 | _(?P<width>[0-9]+)x(?P<height>[0-9]+) | |
142 | _(?P<vcodec>[a-z0-9]+) | |
143 | _(?P<vbr>[0-9]+) | |
144 | _(?P<acodec>[a-z0-9]+) | |
145 | _(?P<abr>[0-9]+) | |
146 | \.(?P<ext>[a-z0-9]+)''', version_url) | |
147 | if not m: | |
9165d6ba | 148 | continue |
9165d6ba | 149 | |
9bccdc70 RA |
150 | formats.append({ |
151 | 'url': version_url, | |
152 | 'format_id': 'http-%s-%s' % (version, video_version['quality']), | |
153 | 'vcodec': m.group('vcodec'), | |
154 | 'acodec': m.group('acodec'), | |
155 | 'vbr': int(m.group('vbr')), | |
156 | 'abr': int(m.group('abr')), | |
157 | 'ext': m.group('ext'), | |
158 | 'width': int(m.group('width')), | |
159 | 'height': int(m.group('height')), | |
160 | }) | |
2975fe1a | 161 | self._sort_formats(formats) |
27579b9e | 162 | |
881dbc86 | 163 | track = video_info['title'] |
9508738f S |
164 | if featured_artist: |
165 | artist = '%s ft. %s' % (artist, featured_artist) | |
166 | title = '%s - %s' % (artist, track) if artist else track | |
5c9ced95 S |
167 | |
168 | genres = video_info.get('genres') | |
169 | genre = ( | |
3089bc74 S |
170 | genres[0] if genres and isinstance(genres, list) |
171 | and isinstance(genres[0], compat_str) else None) | |
9165d6ba | 172 | |
6cadf8c8 PH |
173 | is_explicit = video_info.get('isExplicit') |
174 | if is_explicit is True: | |
175 | age_limit = 18 | |
176 | elif is_explicit is False: | |
177 | age_limit = 0 | |
178 | else: | |
179 | age_limit = None | |
180 | ||
45d7bc2f | 181 | return { |
88bd97e3 | 182 | 'id': video_id, |
ff51983e | 183 | 'title': title, |
88bd97e3 | 184 | 'formats': formats, |
9165d6ba | 185 | 'thumbnail': video_info.get('imageUrl') or video_info.get('thumbnailUrl'), |
9bccdc70 | 186 | 'timestamp': parse_iso8601(video_info.get('releaseDate')), |
9165d6ba | 187 | 'uploader': uploader, |
9bccdc70 RA |
188 | 'duration': int_or_none(video_info.get('duration')), |
189 | 'view_count': int_or_none(video_info.get('views', {}).get('total')), | |
6cadf8c8 | 190 | 'age_limit': age_limit, |
881dbc86 S |
191 | 'track': track, |
192 | 'artist': uploader, | |
193 | 'genre': genre, | |
88bd97e3 | 194 | } |
e0da32df S |
195 | |
196 | ||
9618c448 | 197 | class VevoPlaylistIE(VevoBaseIE): |
92519402 | 198 | _VALID_URL = r'https?://(?:www\.)?vevo\.com/watch/(?P<kind>playlist|genre)/(?P<id>[^/?#&]+)' |
e0da32df S |
199 | |
200 | _TESTS = [{ | |
e2bd301c S |
201 | 'url': 'http://www.vevo.com/watch/genre/rock', |
202 | 'info_dict': { | |
203 | 'id': 'rock', | |
204 | 'title': 'Rock', | |
205 | }, | |
206 | 'playlist_count': 20, | |
e0da32df S |
207 | }, { |
208 | 'url': 'http://www.vevo.com/watch/genre/rock?index=0', | |
209 | 'only_matching': True, | |
210 | }] | |
211 | ||
212 | def _real_extract(self, url): | |
5ad28e7f | 213 | mobj = self._match_valid_url(url) |
e2bd301c S |
214 | playlist_id = mobj.group('id') |
215 | playlist_kind = mobj.group('kind') | |
e0da32df S |
216 | |
217 | webpage = self._download_webpage(url, playlist_id) | |
218 | ||
4dfbf869 | 219 | qs = parse_qs(url) |
e0da32df S |
220 | index = qs.get('index', [None])[0] |
221 | ||
222 | if index: | |
223 | video_id = self._search_regex( | |
224 | r'<meta[^>]+content=(["\'])vevo://video/(?P<id>.+?)\1[^>]*>', | |
225 | webpage, 'video id', default=None, group='id') | |
226 | if video_id: | |
227 | return self.url_result('vevo:%s' % video_id, VevoIE.ie_key()) | |
228 | ||
9d0c08a0 | 229 | playlists = self._extract_json(webpage, playlist_id)['default']['%ss' % playlist_kind] |
e0da32df | 230 | |
e2bd301c S |
231 | playlist = (list(playlists.values())[0] |
232 | if playlist_kind == 'playlist' else playlists[playlist_id]) | |
e0da32df S |
233 | |
234 | entries = [ | |
235 | self.url_result('vevo:%s' % src, VevoIE.ie_key()) | |
236 | for src in playlist['isrcs']] | |
237 | ||
238 | return self.playlist_result( | |
78a3ff33 | 239 | entries, playlist.get('playlistId') or playlist_id, |
e0da32df | 240 | playlist.get('name'), playlist.get('description')) |