_ Git - youtube-dl/blob - youtube_dl/extractor/myspace.py

   1 # encoding: 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             'info_dict': {
  21                 'id': '109594919',
  22                 'ext': 'flv',
  23                 'title': 'Little Big Town',
  24                 'description': 'This country quartet was all smiles while playing a sold out show at the Pacific Amphitheatre in Orange County, California.',
  25                 'uploader': 'Five Minutes to the Stage',
  26                 'uploader_id': 'fiveminutestothestage',
  27                 'timestamp': 1414108751,
  28                 'upload_date': '20141023',
  29             },
  30             'params': {
  31                 # rtmp download
  32                 'skip_download': True,
  33             },
  34         },
  35         # songs
  36         {
  37             'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681',
  38             'info_dict': {
  39                 'id': '93388656',
  40                 'ext': 'flv',
  41                 'title': 'Of weakened soul...',
  42                 'uploader': 'Killsorrow',
  43                 'uploader_id': 'killsorrow',
  44             },
  45             'params': {
  46                 # rtmp download
  47                 'skip_download': True,
  48             },
  49         }, {
  50             'add_ie': ['Vevo'],
  51             'url': 'https://myspace.com/threedaysgrace/music/song/animal-i-have-become-28400208-28218041',
  52             'info_dict': {
  53                 'id': 'USZM20600099',
  54                 'ext': 'mp4',
  55                 'title': 'Animal I Have Become',
  56                 'uploader': 'Three Days Grace',
  57                 'timestamp': int,
  58                 'upload_date': '20060502',
  59             },
  60             'skip': 'VEVO is only available in some countries',
  61         }, {
  62             'add_ie': ['Youtube'],
  63             'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426',
  64             'info_dict': {
  65                 'id': 'ypWvQgnJrSU',
  66                 'ext': 'mp4',
  67                 'title': 'Starset - First Light',
  68                 'description': 'md5:2d5db6c9d11d527683bcda818d332414',
  69                 'uploader': 'Yumi K',
  70                 'uploader_id': 'SorenPromotions',
  71                 'upload_date': '20140725',
  72             }
  73         },
  74     ]
  75
  76     def _real_extract(self, url):
  77         mobj = re.match(self._VALID_URL, url)
  78         video_id = mobj.group('id')
  79         webpage = self._download_webpage(url, video_id)
  80         player_url = self._search_regex(
  81             r'playerSwf":"([^"?]*)', webpage, 'player URL')
  82
  83         def rtmp_format_from_stream_url(stream_url, width=None, height=None):
  84             rtmp_url, play_path = stream_url.split(';', 1)
  85             return {
  86                 'format_id': 'rtmp',
  87                 'url': rtmp_url,
  88                 'play_path': play_path,
  89                 'player_url': player_url,
  90                 'protocol': 'rtmp',
  91                 'ext': 'flv',
  92                 'width': width,
  93                 'height': height,
  94             }
  95
  96         if mobj.group('mediatype').startswith('music/song'):
  97             # songs don't store any useful info in the 'context' variable
  98             song_data = self._search_regex(
  99                 r'''<button.*data-song-id=(["\'])%s\1.*''' % video_id,
 100                 webpage, 'song_data', default=None, group=0)
 101             if song_data is None:
 102                 # some songs in an album are not playable
 103                 self.report_warning(
 104                     '%s: No downloadable song on this page' % video_id)
 105                 return
 106
 107             def search_data(name):
 108                 return self._search_regex(
 109                     r'''data-%s=([\'"])(?P<data>.*?)\1''' % name,
 110                     song_data, name, default='', group='data')
 111             stream_url = search_data('stream-url')
 112             if not stream_url:
 113                 vevo_id = search_data('vevo-id')
 114                 youtube_id = search_data('youtube-id')
 115                 if vevo_id:
 116                     self.to_screen('Vevo video detected: %s' % vevo_id)
 117                     return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
 118                 elif youtube_id:
 119                     self.to_screen('Youtube video detected: %s' % youtube_id)
 120                     return self.url_result(youtube_id, ie='Youtube')
 121                 else:
 122                     raise ExtractorError(
 123                         'Found song but don\'t know how to download it')
 124             return {
 125                 'id': video_id,
 126                 'title': self._og_search_title(webpage),
 127                 'uploader': search_data('artist-name'),
 128                 'uploader_id': search_data('artist-username'),
 129                 'thumbnail': self._og_search_thumbnail(webpage),
 130                 'duration': int_or_none(search_data('duration')),
 131                 'formats': [rtmp_format_from_stream_url(stream_url)]
 132             }
 133         else:
 134             video = self._parse_json(self._search_regex(
 135                 r'context = ({.*?});', webpage, 'context'),
 136                 video_id)['video']
 137             formats = []
 138             hls_stream_url = video.get('hlsStreamUrl')
 139             if hls_stream_url:
 140                 formats.append({
 141                     'format_id': 'hls',
 142                     'url': hls_stream_url,
 143                     'protocol': 'm3u8_native',
 144                     'ext': 'mp4',
 145                 })
 146             stream_url = video.get('streamUrl')
 147             if stream_url:
 148                 formats.append(rtmp_format_from_stream_url(
 149                     stream_url,
 150                     int_or_none(video.get('width')),
 151                     int_or_none(video.get('height'))))
 152             self._sort_formats(formats)
 153             return {
 154                 'id': video_id,
 155                 'title': video['title'],
 156                 'description': video.get('description'),
 157                 'thumbnail': video.get('imageUrl'),
 158                 'uploader': video.get('artistName'),
 159                 'uploader_id': video.get('artistUsername'),
 160                 'duration': int_or_none(video.get('duration')),
 161                 'timestamp': parse_iso8601(video.get('dateAdded')),
 162                 'formats': formats,
 163             }
 164
 165
 166 class MySpaceAlbumIE(InfoExtractor):
 167     IE_NAME = 'MySpace:album'
 168     _VALID_URL = r'https?://myspace\.com/([^/]+)/music/album/(?P<title>.*-)(?P<id>\d+)'
 169
 170     _TESTS = [{
 171         'url': 'https://myspace.com/starset2/music/album/transmissions-19455773',
 172         'info_dict': {
 173             'title': 'Transmissions',
 174             'id': '19455773',
 175         },
 176         'playlist_count': 14,
 177         'skip': 'this album is only available in some countries',
 178     }, {
 179         'url': 'https://myspace.com/killsorrow/music/album/the-demo-18596029',
 180         'info_dict': {
 181             'title': 'The Demo',
 182             'id': '18596029',
 183         },
 184         'playlist_count': 5,
 185     }]
 186
 187     def _real_extract(self, url):
 188         mobj = re.match(self._VALID_URL, url)
 189         playlist_id = mobj.group('id')
 190         display_id = mobj.group('title') + playlist_id
 191         webpage = self._download_webpage(url, display_id)
 192         tracks_paths = re.findall(r'"music:song" content="(.*?)"', webpage)
 193         if not tracks_paths:
 194             raise ExtractorError(
 195                 '%s: No songs found, try using proxy' % display_id,
 196                 expected=True)
 197         entries = [
 198             self.url_result(t_path, ie=MySpaceIE.ie_key())
 199             for t_path in tracks_paths]
 200         return {
 201             '_type': 'playlist',
 202             'id': playlist_id,
 203             'display_id': display_id,
 204             'title': self._og_search_title(webpage),
 205             'entries': entries,
 206         }