yt_dlp/extractor/hearthisat.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     KNOWN_EXTENSIONS,
   5     str_to_int,
   6 )
   7
   8
   9 class HearThisAtIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?hearthis\.at/(?P<artist>[^/]+)/(?P<title>[A-Za-z0-9\-]+)/?$'
  11     _PLAYLIST_URL = 'https://hearthis.at/playlist.php'
  12     _TESTS = [{
  13         'url': 'https://hearthis.at/moofi/dr-kreep',
  14         'md5': 'ab6ec33c8fed6556029337c7885eb4e0',
  15         'info_dict': {
  16             'id': '150939',
  17             'ext': 'wav',
  18             'title': 'Moofi - Dr. Kreep',
  19             'thumbnail': r're:^https?://.*\.jpg$',
  20             'timestamp': 1421564134,
  21             'description': 'md5:1adb0667b01499f9d27e97ddfd53852a',
  22             'upload_date': '20150118',
  23             'view_count': int,
  24             'duration': 71,
  25             'genre': 'Experimental',
  26         }
  27     }, {
  28         # 'download' link redirects to the original webpage
  29         'url': 'https://hearthis.at/twitchsf/dj-jim-hopkins-totally-bitchin-80s-dance-mix/',
  30         'md5': '5980ceb7c461605d30f1f039df160c6e',
  31         'info_dict': {
  32             'id': '811296',
  33             'ext': 'mp3',
  34             'title': 'TwitchSF - DJ Jim Hopkins -  Totally Bitchin\' 80\'s Dance Mix!',
  35             'description': 'md5:ef26815ca8f483272a87b137ff175be2',
  36             'upload_date': '20160328',
  37             'timestamp': 1459186146,
  38             'thumbnail': r're:^https?://.*\.jpg$',
  39             'view_count': int,
  40             'duration': 4360,
  41             'genre': 'Dance',
  42         },
  43     }]
  44
  45     def _real_extract(self, url):
  46         m = self._match_valid_url(url)
  47         display_id = '{artist:s} - {title:s}'.format(**m.groupdict())
  48         api_url = url.replace('www.', '').replace('hearthis.at', 'api-v2.hearthis.at')
  49         data_json = self._download_json(api_url, display_id)
  50         track_id = data_json.get('id')
  51         artist_json = data_json.get('user')
  52         title = '{} - {}'.format(artist_json.get('username'), data_json.get('title'))
  53         genre = data_json.get('genre')
  54         description = data_json.get('description')
  55         thumbnail = data_json.get('artwork_url') or data_json.get('thumb')
  56         view_count = str_to_int(data_json.get('playback_count'))
  57         duration = str_to_int(data_json.get('duration'))
  58         timestamp = data_json.get('release_timestamp')
  59
  60         formats = []
  61         mp3_url = data_json.get('stream_url')
  62
  63         if mp3_url:
  64             formats.append({
  65                 'format_id': 'mp3',
  66                 'vcodec': 'none',
  67                 'acodec': 'mp3',
  68                 'url': mp3_url,
  69                 'ext': 'mp3',
  70             })
  71
  72         if data_json.get('download_url'):
  73             download_url = data_json['download_url']
  74             ext = determine_ext(data_json['download_filename'])
  75             if ext in KNOWN_EXTENSIONS:
  76                 formats.append({
  77                     'format_id': ext,
  78                     'vcodec': 'none',
  79                     'ext': ext,
  80                     'url': download_url,
  81                     'acodec': ext,
  82                     'quality': 2,  # Usually better quality
  83                 })
  84
  85         return {
  86             'id': track_id,
  87             'display_id': display_id,
  88             'title': title,
  89             'formats': formats,
  90             'thumbnail': thumbnail,
  91             'description': description,
  92             'duration': duration,
  93             'timestamp': timestamp,
  94             'view_count': view_count,
  95             'genre': genre,
  96         }