Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/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'https?://myspace\.com/([^/]+)/(?P<mediatype>video/[^/]+/|music/song/.*?)(?P<id>\d+)'
  16
  17     _TESTS = [
  18         {
  19             'url': 'https://myspace.com/fiveminutestothestage/video/little-big-town/109594919',
  20             'md5': '9c1483c106f4a695c47d2911feed50a7',
  21             'info_dict': {
  22                 'id': '109594919',
  23                 'ext': 'mp4',
  24                 'title': 'Little Big Town',
  25                 'description': 'This country quartet was all smiles while playing a sold out show at the Pacific Amphitheatre in Orange County, California.',
  26                 'uploader': 'Five Minutes to the Stage',
  27                 'uploader_id': 'fiveminutestothestage',
  28                 'timestamp': 1414108751,
  29                 'upload_date': '20141023',
  30             },
  31         },
  32         # songs
  33         {
  34             'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681',
  35             'md5': '1d7ee4604a3da226dd69a123f748b262',
  36             'info_dict': {
  37                 'id': '93388656',
  38                 'ext': 'm4a',
  39                 'title': 'Of weakened soul...',
  40                 'uploader': 'Killsorrow',
  41                 'uploader_id': 'killsorrow',
  42             },
  43         }, {
  44             'add_ie': ['Youtube'],
  45             'url': 'https://myspace.com/threedaysgrace/music/song/animal-i-have-become-28400208-28218041',
  46             'info_dict': {
  47                 'id': 'xqds0B_meys',
  48                 'ext': 'webm',
  49                 'title': 'Three Days Grace - Animal I Have Become',
  50                 'description': 'md5:8bd86b3693e72a077cf863a8530c54bb',
  51                 'uploader': 'ThreeDaysGraceVEVO',
  52                 'uploader_id': 'ThreeDaysGraceVEVO',
  53                 'upload_date': '20091002',
  54             },
  55         }, {
  56             'add_ie': ['Youtube'],
  57             'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426',
  58             'info_dict': {
  59                 'id': 'ypWvQgnJrSU',
  60                 'ext': 'mp4',
  61                 'title': 'Starset - First Light',
  62                 'description': 'md5:2d5db6c9d11d527683bcda818d332414',
  63                 'uploader': 'Yumi K',
  64                 'uploader_id': 'SorenPromotions',
  65                 'upload_date': '20140725',
  66             }
  67         },
  68     ]
  69
  70     def _real_extract(self, url):
  71         mobj = re.match(self._VALID_URL, url)
  72         video_id = mobj.group('id')
  73         is_song = mobj.group('mediatype').startswith('music/song')
  74         webpage = self._download_webpage(url, video_id)
  75         player_url = self._search_regex(
  76             r'videoSwf":"([^"?]*)', webpage, 'player URL', fatal=False)
  77
  78         def formats_from_stream_urls(stream_url, hls_stream_url, http_stream_url, width=None, height=None):
  79             formats = []
  80             vcodec = 'none' if is_song else None
  81             if hls_stream_url:
  82                 formats.append({
  83                     'format_id': 'hls',
  84                     'url': hls_stream_url,
  85                     'protocol': 'm3u8_native',
  86                     'ext': 'm4a' if is_song else 'mp4',
  87                     'vcodec': vcodec,
  88                 })
  89             if stream_url and player_url:
  90                 rtmp_url, play_path = stream_url.split(';', 1)
  91                 formats.append({
  92                     'format_id': 'rtmp',
  93                     'url': rtmp_url,
  94                     'play_path': play_path,
  95                     'player_url': player_url,
  96                     'protocol': 'rtmp',
  97                     'ext': 'flv',
  98                     'width': width,
  99                     'height': height,
 100                     'vcodec': vcodec,
 101                 })
 102             if http_stream_url:
 103                 formats.append({
 104                     'format_id': 'http',
 105                     'url': http_stream_url,
 106                     'width': width,
 107                     'height': height,
 108                     'vcodec': vcodec,
 109                 })
 110             return formats
 111
 112         if is_song:
 113             # songs don't store any useful info in the 'context' variable
 114             song_data = self._search_regex(
 115                 r'''<button.*data-song-id=(["\'])%s\1.*''' % video_id,
 116                 webpage, 'song_data', default=None, group=0)
 117             if song_data is None:
 118                 # some songs in an album are not playable
 119                 self.report_warning(
 120                     '%s: No downloadable song on this page' % video_id)
 121                 return
 122
 123             def search_data(name):
 124                 return self._search_regex(
 125                     r'''data-%s=([\'"])(?P<data>.*?)\1''' % name,
 126                     song_data, name, default='', group='data')
 127             formats = formats_from_stream_urls(
 128                 search_data('stream-url'), search_data('hls-stream-url'),
 129                 search_data('http-stream-url'))
 130             if not formats:
 131                 vevo_id = search_data('vevo-id')
 132                 youtube_id = search_data('youtube-id')
 133                 if vevo_id:
 134                     self.to_screen('Vevo video detected: %s' % vevo_id)
 135                     return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
 136                 elif youtube_id:
 137                     self.to_screen('Youtube video detected: %s' % youtube_id)
 138                     return self.url_result(youtube_id, ie='Youtube')
 139                 else:
 140                     raise ExtractorError(
 141                         'Found song but don\'t know how to download it')
 142             self._sort_formats(formats)
 143             return {
 144                 'id': video_id,
 145                 'title': self._og_search_title(webpage),
 146                 'uploader': search_data('artist-name'),
 147                 'uploader_id': search_data('artist-username'),
 148                 'thumbnail': self._og_search_thumbnail(webpage),
 149                 'duration': int_or_none(search_data('duration')),
 150                 'formats': formats,
 151             }
 152         else:
 153             video = self._parse_json(self._search_regex(
 154                 r'context = ({.*?});', webpage, 'context'),
 155                 video_id)['video']
 156             formats = formats_from_stream_urls(
 157                 video.get('streamUrl'), video.get('hlsStreamUrl'),
 158                 video.get('mp4StreamUrl'), int_or_none(video.get('width')),
 159                 int_or_none(video.get('height')))
 160             self._sort_formats(formats)
 161             return {
 162                 'id': video_id,
 163                 'title': video['title'],
 164                 'description': video.get('description'),
 165                 'thumbnail': video.get('imageUrl'),
 166                 'uploader': video.get('artistName'),
 167                 'uploader_id': video.get('artistUsername'),
 168                 'duration': int_or_none(video.get('duration')),
 169                 'timestamp': parse_iso8601(video.get('dateAdded')),
 170                 'formats': formats,
 171             }
 172
 173
 174 class MySpaceAlbumIE(InfoExtractor):
 175     IE_NAME = 'MySpace:album'
 176     _VALID_URL = r'https?://myspace\.com/([^/]+)/music/album/(?P<title>.*-)(?P<id>\d+)'
 177
 178     _TESTS = [{
 179         'url': 'https://myspace.com/starset2/music/album/transmissions-19455773',
 180         'info_dict': {
 181             'title': 'Transmissions',
 182             'id': '19455773',
 183         },
 184         'playlist_count': 14,
 185         'skip': 'this album is only available in some countries',
 186     }, {
 187         'url': 'https://myspace.com/killsorrow/music/album/the-demo-18596029',
 188         'info_dict': {
 189             'title': 'The Demo',
 190             'id': '18596029',
 191         },
 192         'playlist_count': 5,
 193     }]
 194
 195     def _real_extract(self, url):
 196         mobj = re.match(self._VALID_URL, url)
 197         playlist_id = mobj.group('id')
 198         display_id = mobj.group('title') + playlist_id
 199         webpage = self._download_webpage(url, display_id)
 200         tracks_paths = re.findall(r'"music:song" content="(.*?)"', webpage)
 201         if not tracks_paths:
 202             raise ExtractorError(
 203                 '%s: No songs found, try using proxy' % display_id,
 204                 expected=True)
 205         entries = [
 206             self.url_result(t_path, ie=MySpaceIE.ie_key())
 207             for t_path in tracks_paths]
 208         return {
 209             '_type': 'playlist',
 210             'id': playlist_id,
 211             'display_id': display_id,
 212             'title': self._og_search_title(webpage),
 213             'entries': entries,
 214         }