yt_dlp/extractor/hearthisat.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     KNOWN_EXTENSIONS,
   4     determine_ext,
   5     str_to_int,
   6 )
   7
   8
   9 class HearThisAtIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?hearthis\.at/(?P<artist>[^/?#]+)/(?P<title>[\w.-]+)'
  11     _PLAYLIST_URL = 'https://hearthis.at/playlist.php'
  12     _TESTS = [{
  13         'url': 'https://hearthis.at/moofi/dr-kreep',
  14         'md5': 'ab6ec33c8fed6556029337c7885eb4e0',
  15         'info_dict': {
  16             'id': '150939',
  17             'display_id': 'moofi - dr-kreep',
  18             'ext': 'wav',
  19             'title': 'Moofi - Dr. Kreep',
  20             'thumbnail': r're:^https?://.*\.jpg$',
  21             'timestamp': 1421564134,
  22             'description': 'md5:1adb0667b01499f9d27e97ddfd53852a',
  23             'upload_date': '20150118',
  24             'view_count': int,
  25             'duration': 70,
  26             'genres': ['Experimental'],
  27         },
  28     }, {
  29         # 'download' link redirects to the original webpage
  30         'url': 'https://hearthis.at/twitchsf/dj-jim-hopkins-totally-bitchin-80s-dance-mix/',
  31         'md5': '5980ceb7c461605d30f1f039df160c6e',
  32         'info_dict': {
  33             'id': '811296',
  34             'display_id': 'twitchsf - dj-jim-hopkins-totally-bitchin-80s-dance-mix',
  35             'ext': 'mp3',
  36             'title': 'TwitchSF - DJ Jim Hopkins -  Totally Bitchin\' 80\'s Dance Mix!',
  37             'description': 'md5:ef26815ca8f483272a87b137ff175be2',
  38             'upload_date': '20160328',
  39             'timestamp': 1459186146,
  40             'thumbnail': r're:^https?://.*\.jpg$',
  41             'view_count': int,
  42             'duration': 4360,
  43             'genres': ['Dance'],
  44         },
  45     }, {
  46         'url': 'https://hearthis.at/tindalos/0001-tindalos-gnrique/eQd/',
  47         'md5': 'cd08e51911f147f6da2d9678905b0bd9',
  48         'info_dict': {
  49             'id': '2685222',
  50             'ext': 'mp3',
  51             'duration': 86,
  52             'view_count': int,
  53             'timestamp': 1545471670,
  54             'display_id': 'tindalos - 0001-tindalos-gnrique',
  55             'thumbnail': r're:^https?://.*\.jpg$',
  56             'genres': ['Other'],
  57             'title': 'Tindalos - Tindalos - générique n°1',
  58             'description': '',
  59             'upload_date': '20181222',
  60         },
  61     }, {
  62         'url': 'https://hearthis.at/sithi2/biochip-c-classics-set-wolle-xdp-tresor.core-special-tresor-globus-berlin-13.07.20011/',
  63         'md5': 'b45ac60f0c8111eef6ddc10ec232e312',
  64         'info_dict': {
  65             'id': '7145959',
  66             'ext': 'mp3',
  67             'description': 'md5:d7ae36a453d78903f6b7ed6eb2fce1f2',
  68             'duration': 8986,
  69             'thumbnail': r're:^https?://.*\.jpg$',
  70             'title': 'md5:62669ce5b1b67f45c6f846033f37d3b9',
  71             'timestamp': 1588699409,
  72             'display_id': 'sithi2 - biochip-c-classics-set-wolle-xdp-tresor.core-special-tresor-globus-berlin-13.07.20011',
  73             'view_count': int,
  74             'upload_date': '20200505',
  75             'genres': ['Other'],
  76         },
  77     }]
  78
  79     def _real_extract(self, url):
  80         m = self._match_valid_url(url)
  81         display_id = '{artist:s} - {title:s}'.format(**m.groupdict())
  82         api_url = url.replace('www.', '').replace('hearthis.at', 'api-v2.hearthis.at')
  83         data_json = self._download_json(api_url, display_id)
  84         track_id = data_json.get('id')
  85         artist_json = data_json.get('user')
  86         title = '{} - {}'.format(artist_json.get('username'), data_json.get('title'))
  87         genre = data_json.get('genre')
  88         description = data_json.get('description')
  89         thumbnail = data_json.get('artwork_url') or data_json.get('thumb')
  90         view_count = str_to_int(data_json.get('playback_count'))
  91         duration = str_to_int(data_json.get('duration'))
  92         timestamp = data_json.get('release_timestamp')
  93
  94         formats = []
  95         mp3_url = data_json.get('stream_url')
  96
  97         if mp3_url:
  98             formats.append({
  99                 'format_id': 'mp3',
 100                 'vcodec': 'none',
 101                 'acodec': 'mp3',
 102                 'url': mp3_url,
 103                 'ext': 'mp3',
 104             })
 105
 106         if data_json.get('download_url'):
 107             download_url = data_json['download_url']
 108             ext = determine_ext(data_json['download_filename'])
 109             if ext in KNOWN_EXTENSIONS:
 110                 formats.append({
 111                     'format_id': ext,
 112                     'vcodec': 'none',
 113                     'ext': ext,
 114                     'url': download_url,
 115                     'acodec': ext,
 116                     'quality': 2,  # Usually better quality
 117                 })
 118
 119         return {
 120             'id': track_id,
 121             'display_id': display_id,
 122             'title': title,
 123             'formats': formats,
 124             'thumbnail': thumbnail,
 125             'description': description,
 126             'duration': duration,
 127             'timestamp': timestamp,
 128             'view_count': view_count,
 129             'genre': genre,
 130         }