]>
Commit | Line | Data |
---|---|---|
45d7bc2f JMF |
1 | from __future__ import unicode_literals |
2 | ||
70d1924f | 3 | import re |
55992530 | 4 | import json |
70d1924f JMF |
5 | |
6 | from .common import InfoExtractor | |
e0da32df | 7 | from ..compat import ( |
5c9ced95 | 8 | compat_str, |
e0da32df | 9 | compat_urlparse, |
9bccdc70 | 10 | compat_HTTPError, |
e0da32df | 11 | ) |
1cc79574 | 12 | from ..utils import ( |
70d1924f | 13 | ExtractorError, |
7d3d06a1 | 14 | int_or_none, |
9165d6ba | 15 | parse_iso8601, |
70d1924f JMF |
16 | ) |
17 | ||
88bd97e3 | 18 | |
9618c448 | 19 | class VevoBaseIE(InfoExtractor): |
9d0c08a0 | 20 | def _extract_json(self, webpage, video_id): |
9618c448 S |
21 | return self._parse_json( |
22 | self._search_regex( | |
23 | r'window\.__INITIAL_STORE__\s*=\s*({.+?});\s*</script>', | |
24 | webpage, 'initial store'), | |
9d0c08a0 | 25 | video_id) |
9618c448 S |
26 | |
27 | ||
28 | class VevoIE(VevoBaseIE): | |
2975fe1a | 29 | ''' |
0577177e | 30 | Accepts urls from vevo.com or in the format 'vevo:{id}' |
3266f0c6 | 31 | (currently used by MTVIE and MySpaceIE) |
2975fe1a | 32 | ''' |
f25571ff | 33 | _VALID_URL = r'''(?x) |
92519402 | 34 | (?:https?://(?:www\.)?vevo\.com/watch/(?!playlist|genre)(?:[^/]+/(?:[^/]+/)?)?| |
f25571ff | 35 | https?://cache\.vevo\.com/m/html/embed\.html\?video=| |
ebce53b3 | 36 | https?://videoplayer\.vevo\.com/embed/embedded\?videoId=| |
d1e41164 | 37 | https?://embed\.vevo\.com/.*?[?&]isrc=| |
f25571ff PH |
38 | vevo:) |
39 | (?P<id>[^&?#]+)''' | |
fd5e6f7e | 40 | |
dd2d55f1 | 41 | _TESTS = [] |
2975fe1a | 42 | _VERSIONS = { |
9165d6ba | 43 | 0: 'youtube', # only in AuthenticateVideo videoVersions |
2975fe1a | 44 | 1: 'level3', |
45 | 2: 'akamai', | |
46 | 3: 'level3', | |
47 | 4: 'amazon', | |
48 | } | |
49 | ||
682f8c43 | 50 | def _initialize_api(self, video_id): |
9165d6ba | 51 | webpage = self._download_webpage( |
b07ea5ea | 52 | 'https://accounts.vevo.com/token', None, |
9165d6ba | 53 | note='Retrieving oauth token', |
b07ea5ea S |
54 | errnote='Unable to retrieve oauth token', |
55 | data=json.dumps({ | |
56 | 'client_id': 'SPupX1tvqFEopQ1YS6SS', | |
57 | 'grant_type': 'urn:vevo:params:oauth:grant-type:anonymous', | |
58 | }).encode('utf-8'), | |
59 | headers={ | |
60 | 'Content-Type': 'application/json', | |
61 | }) | |
9165d6ba | 62 | |
621a2800 | 63 | if re.search(r'(?i)THIS PAGE IS CURRENTLY UNAVAILABLE IN YOUR REGION', webpage): |
bc7e77a0 S |
64 | self.raise_geo_restricted( |
65 | '%s said: This page is currently unavailable in your region' % self.IE_NAME) | |
9165d6ba | 66 | |
67 | auth_info = self._parse_json(webpage, video_id) | |
55992530 | 68 | self._api_url_template = self.http_scheme() + '//apiv2.vevo.com/%s?token=' + auth_info['legacy_token'] |
9165d6ba | 69 | |
516ea41a | 70 | def _call_api(self, path, *args, **kwargs): |
9bccdc70 RA |
71 | try: |
72 | data = self._download_json(self._api_url_template % path, *args, **kwargs) | |
73 | except ExtractorError as e: | |
74 | if isinstance(e.cause, compat_HTTPError): | |
75 | errors = self._parse_json(e.cause.read().decode(), None)['errors'] | |
76 | error_message = ', '.join([error['message'] for error in errors]) | |
77 | raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True) | |
78 | raise | |
79 | return data | |
9165d6ba | 80 | |
72321ead | 81 | def _real_extract(self, url): |
4b942883 | 82 | video_id = self._match_id(url) |
72321ead | 83 | |
9bccdc70 | 84 | self._initialize_api(video_id) |
682f8c43 | 85 | |
9bccdc70 RA |
86 | video_info = self._call_api( |
87 | 'video/%s' % video_id, video_id, 'Downloading api video info', | |
88 | 'Failed to download video info') | |
2975fe1a | 89 | |
9bccdc70 RA |
90 | video_versions = self._call_api( |
91 | 'video/%s/streams' % video_id, video_id, | |
92 | 'Downloading video versions info', | |
93 | 'Failed to download video versions info', | |
94 | fatal=False) | |
ff51983e | 95 | |
9bccdc70 | 96 | # Some videos are only available via webpage (e.g. |
067aa17e | 97 | # https://github.com/ytdl-org/youtube-dl/issues/9366) |
9bccdc70 RA |
98 | if not video_versions: |
99 | webpage = self._download_webpage(url, video_id) | |
9d0c08a0 YCH |
100 | json_data = self._extract_json(webpage, video_id) |
101 | if 'streams' in json_data.get('default', {}): | |
102 | video_versions = json_data['default']['streams'][video_id][0] | |
103 | else: | |
104 | video_versions = [ | |
105 | value | |
106 | for key, value in json_data['apollo']['data'].items() | |
107 | if key.startswith('%s.streams' % video_id)] | |
9618c448 | 108 | |
9bccdc70 RA |
109 | uploader = None |
110 | artist = None | |
111 | featured_artist = None | |
112 | artists = video_info.get('artists') | |
113 | for curr_artist in artists: | |
114 | if curr_artist.get('role') == 'Featured': | |
115 | featured_artist = curr_artist['name'] | |
116 | else: | |
117 | artist = uploader = curr_artist['name'] | |
9165d6ba | 118 | |
9bccdc70 RA |
119 | formats = [] |
120 | for video_version in video_versions: | |
9d0c08a0 | 121 | version = self._VERSIONS.get(video_version.get('version'), 'generic') |
9bccdc70 RA |
122 | version_url = video_version.get('url') |
123 | if not version_url: | |
124 | continue | |
9165d6ba | 125 | |
9bccdc70 RA |
126 | if '.ism' in version_url: |
127 | continue | |
128 | elif '.mpd' in version_url: | |
129 | formats.extend(self._extract_mpd_formats( | |
130 | version_url, video_id, mpd_id='dash-%s' % version, | |
131 | note='Downloading %s MPD information' % version, | |
132 | errnote='Failed to download %s MPD information' % version, | |
133 | fatal=False)) | |
134 | elif '.m3u8' in version_url: | |
135 | formats.extend(self._extract_m3u8_formats( | |
136 | version_url, video_id, 'mp4', 'm3u8_native', | |
137 | m3u8_id='hls-%s' % version, | |
138 | note='Downloading %s m3u8 information' % version, | |
139 | errnote='Failed to download %s m3u8 information' % version, | |
140 | fatal=False)) | |
141 | else: | |
142 | m = re.search(r'''(?xi) | |
143 | _(?P<width>[0-9]+)x(?P<height>[0-9]+) | |
144 | _(?P<vcodec>[a-z0-9]+) | |
145 | _(?P<vbr>[0-9]+) | |
146 | _(?P<acodec>[a-z0-9]+) | |
147 | _(?P<abr>[0-9]+) | |
148 | \.(?P<ext>[a-z0-9]+)''', version_url) | |
149 | if not m: | |
9165d6ba | 150 | continue |
9165d6ba | 151 | |
9bccdc70 RA |
152 | formats.append({ |
153 | 'url': version_url, | |
154 | 'format_id': 'http-%s-%s' % (version, video_version['quality']), | |
155 | 'vcodec': m.group('vcodec'), | |
156 | 'acodec': m.group('acodec'), | |
157 | 'vbr': int(m.group('vbr')), | |
158 | 'abr': int(m.group('abr')), | |
159 | 'ext': m.group('ext'), | |
160 | 'width': int(m.group('width')), | |
161 | 'height': int(m.group('height')), | |
162 | }) | |
2975fe1a | 163 | self._sort_formats(formats) |
27579b9e | 164 | |
881dbc86 | 165 | track = video_info['title'] |
9508738f S |
166 | if featured_artist: |
167 | artist = '%s ft. %s' % (artist, featured_artist) | |
168 | title = '%s - %s' % (artist, track) if artist else track | |
5c9ced95 S |
169 | |
170 | genres = video_info.get('genres') | |
171 | genre = ( | |
3089bc74 S |
172 | genres[0] if genres and isinstance(genres, list) |
173 | and isinstance(genres[0], compat_str) else None) | |
9165d6ba | 174 | |
6cadf8c8 PH |
175 | is_explicit = video_info.get('isExplicit') |
176 | if is_explicit is True: | |
177 | age_limit = 18 | |
178 | elif is_explicit is False: | |
179 | age_limit = 0 | |
180 | else: | |
181 | age_limit = None | |
182 | ||
45d7bc2f | 183 | return { |
88bd97e3 | 184 | 'id': video_id, |
ff51983e | 185 | 'title': title, |
88bd97e3 | 186 | 'formats': formats, |
9165d6ba | 187 | 'thumbnail': video_info.get('imageUrl') or video_info.get('thumbnailUrl'), |
9bccdc70 | 188 | 'timestamp': parse_iso8601(video_info.get('releaseDate')), |
9165d6ba | 189 | 'uploader': uploader, |
9bccdc70 RA |
190 | 'duration': int_or_none(video_info.get('duration')), |
191 | 'view_count': int_or_none(video_info.get('views', {}).get('total')), | |
6cadf8c8 | 192 | 'age_limit': age_limit, |
881dbc86 S |
193 | 'track': track, |
194 | 'artist': uploader, | |
195 | 'genre': genre, | |
88bd97e3 | 196 | } |
e0da32df S |
197 | |
198 | ||
9618c448 | 199 | class VevoPlaylistIE(VevoBaseIE): |
92519402 | 200 | _VALID_URL = r'https?://(?:www\.)?vevo\.com/watch/(?P<kind>playlist|genre)/(?P<id>[^/?#&]+)' |
e0da32df S |
201 | |
202 | _TESTS = [{ | |
e2bd301c S |
203 | 'url': 'http://www.vevo.com/watch/genre/rock', |
204 | 'info_dict': { | |
205 | 'id': 'rock', | |
206 | 'title': 'Rock', | |
207 | }, | |
208 | 'playlist_count': 20, | |
e0da32df S |
209 | }, { |
210 | 'url': 'http://www.vevo.com/watch/genre/rock?index=0', | |
211 | 'only_matching': True, | |
212 | }] | |
213 | ||
214 | def _real_extract(self, url): | |
5ad28e7f | 215 | mobj = self._match_valid_url(url) |
e2bd301c S |
216 | playlist_id = mobj.group('id') |
217 | playlist_kind = mobj.group('kind') | |
e0da32df S |
218 | |
219 | webpage = self._download_webpage(url, playlist_id) | |
220 | ||
221 | qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) | |
222 | index = qs.get('index', [None])[0] | |
223 | ||
224 | if index: | |
225 | video_id = self._search_regex( | |
226 | r'<meta[^>]+content=(["\'])vevo://video/(?P<id>.+?)\1[^>]*>', | |
227 | webpage, 'video id', default=None, group='id') | |
228 | if video_id: | |
229 | return self.url_result('vevo:%s' % video_id, VevoIE.ie_key()) | |
230 | ||
9d0c08a0 | 231 | playlists = self._extract_json(webpage, playlist_id)['default']['%ss' % playlist_kind] |
e0da32df | 232 | |
e2bd301c S |
233 | playlist = (list(playlists.values())[0] |
234 | if playlist_kind == 'playlist' else playlists[playlist_id]) | |
e0da32df S |
235 | |
236 | entries = [ | |
237 | self.url_result('vevo:%s' % src, VevoIE.ie_key()) | |
238 | for src in playlist['isrcs']] | |
239 | ||
240 | return self.playlist_result( | |
78a3ff33 | 241 | entries, playlist.get('playlistId') or playlist_id, |
e0da32df | 242 | playlist.get('name'), playlist.get('description')) |