yt_dlp/extractor/myspace.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10     parse_iso8601,
  11 )
  12
  13
  14 class MySpaceIE(InfoExtractor):
  15     _VALID_URL = r'''(?x)
  16                     https?://
  17                         myspace\.com/[^/]+/
  18                         (?P<mediatype>
  19                             video/[^/]+/(?P<video_id>\d+)|
  20                             music/song/[^/?#&]+-(?P<song_id>\d+)-\d+(?:[/?#&]|$)
  21                         )
  22                     '''
  23
  24     _TESTS = [{
  25         'url': 'https://myspace.com/fiveminutestothestage/video/little-big-town/109594919',
  26         'md5': '9c1483c106f4a695c47d2911feed50a7',
  27         'info_dict': {
  28             'id': '109594919',
  29             'ext': 'mp4',
  30             'title': 'Little Big Town',
  31             'description': 'This country quartet was all smiles while playing a sold out show at the Pacific Amphitheatre in Orange County, California.',
  32             'uploader': 'Five Minutes to the Stage',
  33             'uploader_id': 'fiveminutestothestage',
  34             'timestamp': 1414108751,
  35             'upload_date': '20141023',
  36         },
  37     }, {
  38         # songs
  39         'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681',
  40         'md5': '1d7ee4604a3da226dd69a123f748b262',
  41         'info_dict': {
  42             'id': '93388656',
  43             'ext': 'm4a',
  44             'title': 'Of weakened soul...',
  45             'uploader': 'Killsorrow',
  46             'uploader_id': 'killsorrow',
  47         },
  48     }, {
  49         'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426',
  50         'only_matching': True,
  51     }, {
  52         'url': 'https://myspace.com/thelargemouthbassband/music/song/02-pure-eyes.mp3-94422330-105113388',
  53         'only_matching': True,
  54     }]
  55
  56     def _real_extract(self, url):
  57         mobj = re.match(self._VALID_URL, url)
  58         video_id = mobj.group('video_id') or mobj.group('song_id')
  59         is_song = mobj.group('mediatype').startswith('music/song')
  60         webpage = self._download_webpage(url, video_id)
  61         player_url = self._search_regex(
  62             r'videoSwf":"([^"?]*)', webpage, 'player URL', fatal=False)
  63
  64         def formats_from_stream_urls(stream_url, hls_stream_url, http_stream_url, width=None, height=None):
  65             formats = []
  66             vcodec = 'none' if is_song else None
  67             if hls_stream_url:
  68                 formats.append({
  69                     'format_id': 'hls',
  70                     'url': hls_stream_url,
  71                     'protocol': 'm3u8_native',
  72                     'ext': 'm4a' if is_song else 'mp4',
  73                     'vcodec': vcodec,
  74                 })
  75             if stream_url and player_url:
  76                 rtmp_url, play_path = stream_url.split(';', 1)
  77                 formats.append({
  78                     'format_id': 'rtmp',
  79                     'url': rtmp_url,
  80                     'play_path': play_path,
  81                     'player_url': player_url,
  82                     'protocol': 'rtmp',
  83                     'ext': 'flv',
  84                     'width': width,
  85                     'height': height,
  86                     'vcodec': vcodec,
  87                 })
  88             if http_stream_url:
  89                 formats.append({
  90                     'format_id': 'http',
  91                     'url': http_stream_url,
  92                     'width': width,
  93                     'height': height,
  94                     'vcodec': vcodec,
  95                 })
  96             return formats
  97
  98         if is_song:
  99             # songs don't store any useful info in the 'context' variable
 100             song_data = self._search_regex(
 101                 r'''<button.*data-song-id=(["\'])%s\1.*''' % video_id,
 102                 webpage, 'song_data', default=None, group=0)
 103             if song_data is None:
 104                 # some songs in an album are not playable
 105                 self.report_warning(
 106                     '%s: No downloadable song on this page' % video_id)
 107                 return
 108
 109             def search_data(name):
 110                 return self._search_regex(
 111                     r'''data-%s=([\'"])(?P<data>.*?)\1''' % name,
 112                     song_data, name, default='', group='data')
 113             formats = formats_from_stream_urls(
 114                 search_data('stream-url'), search_data('hls-stream-url'),
 115                 search_data('http-stream-url'))
 116             if not formats:
 117                 vevo_id = search_data('vevo-id')
 118                 youtube_id = search_data('youtube-id')
 119                 if vevo_id:
 120                     self.to_screen('Vevo video detected: %s' % vevo_id)
 121                     return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
 122                 elif youtube_id:
 123                     self.to_screen('Youtube video detected: %s' % youtube_id)
 124                     return self.url_result(youtube_id, ie='Youtube')
 125                 else:
 126                     raise ExtractorError(
 127                         'Found song but don\'t know how to download it')
 128             self._sort_formats(formats)
 129             return {
 130                 'id': video_id,
 131                 'title': self._og_search_title(webpage),
 132                 'uploader': search_data('artist-name'),
 133                 'uploader_id': search_data('artist-username'),
 134                 'thumbnail': self._og_search_thumbnail(webpage),
 135                 'duration': int_or_none(search_data('duration')),
 136                 'formats': formats,
 137             }
 138         else:
 139             video = self._parse_json(self._search_regex(
 140                 r'context = ({.*?});', webpage, 'context'),
 141                 video_id)['video']
 142             formats = formats_from_stream_urls(
 143                 video.get('streamUrl'), video.get('hlsStreamUrl'),
 144                 video.get('mp4StreamUrl'), int_or_none(video.get('width')),
 145                 int_or_none(video.get('height')))
 146             self._sort_formats(formats)
 147             return {
 148                 'id': video_id,
 149                 'title': video['title'],
 150                 'description': video.get('description'),
 151                 'thumbnail': video.get('imageUrl'),
 152                 'uploader': video.get('artistName'),
 153                 'uploader_id': video.get('artistUsername'),
 154                 'duration': int_or_none(video.get('duration')),
 155                 'timestamp': parse_iso8601(video.get('dateAdded')),
 156                 'formats': formats,
 157             }
 158
 159
 160 class MySpaceAlbumIE(InfoExtractor):
 161     IE_NAME = 'MySpace:album'
 162     _VALID_URL = r'https?://myspace\.com/([^/]+)/music/album/(?P<title>.*-)(?P<id>\d+)'
 163
 164     _TESTS = [{
 165         'url': 'https://myspace.com/starset2/music/album/transmissions-19455773',
 166         'info_dict': {
 167             'title': 'Transmissions',
 168             'id': '19455773',
 169         },
 170         'playlist_count': 14,
 171         'skip': 'this album is only available in some countries',
 172     }, {
 173         'url': 'https://myspace.com/killsorrow/music/album/the-demo-18596029',
 174         'info_dict': {
 175             'title': 'The Demo',
 176             'id': '18596029',
 177         },
 178         'playlist_count': 5,
 179     }]
 180
 181     def _real_extract(self, url):
 182         mobj = re.match(self._VALID_URL, url)
 183         playlist_id = mobj.group('id')
 184         display_id = mobj.group('title') + playlist_id
 185         webpage = self._download_webpage(url, display_id)
 186         tracks_paths = re.findall(r'"music:song" content="(.*?)"', webpage)
 187         if not tracks_paths:
 188             raise ExtractorError(
 189                 '%s: No songs found, try using proxy' % display_id,
 190                 expected=True)
 191         entries = [
 192             self.url_result(t_path, ie=MySpaceIE.ie_key())
 193             for t_path in tracks_paths]
 194         return {
 195             '_type': 'playlist',
 196             'id': playlist_id,
 197             'display_id': display_id,
 198             'title': self._og_search_title(webpage),
 199             'entries': entries,
 200         }