yt_dlp/extractor/myspace.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     int_or_none,
   7     parse_iso8601,
   8 )
   9
  10
  11 class MySpaceIE(InfoExtractor):
  12     _VALID_URL = r'''(?x)
  13                     https?://
  14                         myspace\.com/[^/]+/
  15                         (?P<mediatype>
  16                             video/[^/]+/(?P<video_id>\d+)|
  17                             music/song/[^/?#&]+-(?P<song_id>\d+)-\d+(?:[/?#&]|$)
  18                         )
  19                     '''
  20
  21     _TESTS = [{
  22         'url': 'https://myspace.com/fiveminutestothestage/video/little-big-town/109594919',
  23         'md5': '9c1483c106f4a695c47d2911feed50a7',
  24         'info_dict': {
  25             'id': '109594919',
  26             'ext': 'mp4',
  27             'title': 'Little Big Town',
  28             'description': 'This country quartet was all smiles while playing a sold out show at the Pacific Amphitheatre in Orange County, California.',
  29             'uploader': 'Five Minutes to the Stage',
  30             'uploader_id': 'fiveminutestothestage',
  31             'timestamp': 1414108751,
  32             'upload_date': '20141023',
  33         },
  34     }, {
  35         # songs
  36         'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681',
  37         'md5': '1d7ee4604a3da226dd69a123f748b262',
  38         'info_dict': {
  39             'id': '93388656',
  40             'ext': 'm4a',
  41             'title': 'Of weakened soul...',
  42             'uploader': 'Killsorrow',
  43             'uploader_id': 'killsorrow',
  44         },
  45     }, {
  46         'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426',
  47         'only_matching': True,
  48     }, {
  49         'url': 'https://myspace.com/thelargemouthbassband/music/song/02-pure-eyes.mp3-94422330-105113388',
  50         'only_matching': True,
  51     }]
  52
  53     def _real_extract(self, url):
  54         mobj = self._match_valid_url(url)
  55         video_id = mobj.group('video_id') or mobj.group('song_id')
  56         is_song = mobj.group('mediatype').startswith('music/song')
  57         webpage = self._download_webpage(url, video_id)
  58         player_url = self._search_regex(
  59             r'videoSwf":"([^"?]*)', webpage, 'player URL', fatal=False)
  60
  61         def formats_from_stream_urls(stream_url, hls_stream_url, http_stream_url, width=None, height=None):
  62             formats = []
  63             vcodec = 'none' if is_song else None
  64             if hls_stream_url:
  65                 formats.append({
  66                     'format_id': 'hls',
  67                     'url': hls_stream_url,
  68                     'protocol': 'm3u8_native',
  69                     'ext': 'm4a' if is_song else 'mp4',
  70                     'vcodec': vcodec,
  71                 })
  72             if stream_url and player_url:
  73                 rtmp_url, play_path = stream_url.split(';', 1)
  74                 formats.append({
  75                     'format_id': 'rtmp',
  76                     'url': rtmp_url,
  77                     'play_path': play_path,
  78                     'player_url': player_url,
  79                     'protocol': 'rtmp',
  80                     'ext': 'flv',
  81                     'width': width,
  82                     'height': height,
  83                     'vcodec': vcodec,
  84                 })
  85             if http_stream_url:
  86                 formats.append({
  87                     'format_id': 'http',
  88                     'url': http_stream_url,
  89                     'width': width,
  90                     'height': height,
  91                     'vcodec': vcodec,
  92                 })
  93             return formats
  94
  95         if is_song:
  96             # songs don't store any useful info in the 'context' variable
  97             song_data = self._search_regex(
  98                 rf'''<button.*data-song-id=(["\']){video_id}\1.*''',
  99                 webpage, 'song_data', default=None, group=0)
 100             if song_data is None:
 101                 # some songs in an album are not playable
 102                 self.report_warning(
 103                     f'{video_id}: No downloadable song on this page')
 104                 return
 105
 106             def search_data(name):
 107                 return self._search_regex(
 108                     rf'''data-{name}=([\'"])(?P<data>.*?)\1''',
 109                     song_data, name, default='', group='data')
 110             formats = formats_from_stream_urls(
 111                 search_data('stream-url'), search_data('hls-stream-url'),
 112                 search_data('http-stream-url'))
 113             if not formats:
 114                 vevo_id = search_data('vevo-id')
 115                 youtube_id = search_data('youtube-id')
 116                 if vevo_id:
 117                     self.to_screen(f'Vevo video detected: {vevo_id}')
 118                     return self.url_result(f'vevo:{vevo_id}', ie='Vevo')
 119                 elif youtube_id:
 120                     self.to_screen(f'Youtube video detected: {youtube_id}')
 121                     return self.url_result(youtube_id, ie='Youtube')
 122                 else:
 123                     raise ExtractorError(
 124                         'Found song but don\'t know how to download it')
 125             return {
 126                 'id': video_id,
 127                 'title': self._og_search_title(webpage),
 128                 'uploader': search_data('artist-name'),
 129                 'uploader_id': search_data('artist-username'),
 130                 'thumbnail': self._og_search_thumbnail(webpage),
 131                 'duration': int_or_none(search_data('duration')),
 132                 'formats': formats,
 133             }
 134         else:
 135             video = self._parse_json(self._search_regex(
 136                 r'context = ({.*?});', webpage, 'context'),
 137                 video_id)['video']
 138             formats = formats_from_stream_urls(
 139                 video.get('streamUrl'), video.get('hlsStreamUrl'),
 140                 video.get('mp4StreamUrl'), int_or_none(video.get('width')),
 141                 int_or_none(video.get('height')))
 142             return {
 143                 'id': video_id,
 144                 'title': video['title'],
 145                 'description': video.get('description'),
 146                 'thumbnail': video.get('imageUrl'),
 147                 'uploader': video.get('artistName'),
 148                 'uploader_id': video.get('artistUsername'),
 149                 'duration': int_or_none(video.get('duration')),
 150                 'timestamp': parse_iso8601(video.get('dateAdded')),
 151                 'formats': formats,
 152             }
 153
 154
 155 class MySpaceAlbumIE(InfoExtractor):
 156     IE_NAME = 'MySpace:album'
 157     _VALID_URL = r'https?://myspace\.com/([^/]+)/music/album/(?P<title>.*-)(?P<id>\d+)'
 158
 159     _TESTS = [{
 160         'url': 'https://myspace.com/starset2/music/album/transmissions-19455773',
 161         'info_dict': {
 162             'title': 'Transmissions',
 163             'id': '19455773',
 164         },
 165         'playlist_count': 14,
 166         'skip': 'this album is only available in some countries',
 167     }, {
 168         'url': 'https://myspace.com/killsorrow/music/album/the-demo-18596029',
 169         'info_dict': {
 170             'title': 'The Demo',
 171             'id': '18596029',
 172         },
 173         'playlist_count': 5,
 174     }]
 175
 176     def _real_extract(self, url):
 177         mobj = self._match_valid_url(url)
 178         playlist_id = mobj.group('id')
 179         display_id = mobj.group('title') + playlist_id
 180         webpage = self._download_webpage(url, display_id)
 181         tracks_paths = re.findall(r'"music:song" content="(.*?)"', webpage)
 182         if not tracks_paths:
 183             raise ExtractorError(
 184                 f'{display_id}: No songs found, try using proxy',
 185                 expected=True)
 186         entries = [
 187             self.url_result(t_path, ie=MySpaceIE.ie_key())
 188             for t_path in tracks_paths]
 189         return {
 190             '_type': 'playlist',
 191             'id': playlist_id,
 192             'display_id': display_id,
 193             'title': self._og_search_title(webpage),
 194             'entries': entries,
 195         }