yt_dlp/extractor/playfm.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     ExtractorError,
   5     int_or_none,
   6     parse_iso8601,
   7 )
   8
   9
  10 class PlayFMIE(InfoExtractor):
  11     IE_NAME = 'play.fm'
  12     _VALID_URL = r'https?://(?:www\.)?play\.fm/(?P<slug>(?:[^/]+/)+(?P<id>[^/]+))/?(?:$|[?#])'
  13
  14     _TEST = {
  15         'url': 'https://www.play.fm/dan-drastic/sven-tasnadi-leipzig-electronic-music-batofar-paris-fr-2014-07-12',
  16         'md5': 'c505f8307825a245d0c7ad1850001f22',
  17         'info_dict': {
  18             'id': '71276',
  19             'ext': 'mp3',
  20             'title': 'Sven Tasnadi - LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12',
  21             'description': '',
  22             'duration': 5627,
  23             'timestamp': 1406033781,
  24             'upload_date': '20140722',
  25             'uploader': 'Dan Drastic',
  26             'uploader_id': '71170',
  27             'view_count': int,
  28             'comment_count': int,
  29         },
  30     }
  31
  32     def _real_extract(self, url):
  33         mobj = self._match_valid_url(url)
  34         video_id = mobj.group('id')
  35         slug = mobj.group('slug')
  36
  37         recordings = self._download_json(
  38             'http://v2api.play.fm/recordings/slug/%s' % slug, video_id)
  39
  40         error = recordings.get('error')
  41         if isinstance(error, dict):
  42             raise ExtractorError(
  43                 '%s returned error: %s' % (self.IE_NAME, error.get('message')),
  44                 expected=True)
  45
  46         audio_url = recordings['audio']
  47         video_id = compat_str(recordings.get('id') or video_id)
  48         title = recordings['title']
  49         description = recordings.get('description')
  50         duration = int_or_none(recordings.get('recordingDuration'))
  51         timestamp = parse_iso8601(recordings.get('created_at'))
  52         uploader = recordings.get('page', {}).get('title')
  53         uploader_id = compat_str(recordings.get('page', {}).get('id'))
  54         view_count = int_or_none(recordings.get('playCount'))
  55         comment_count = int_or_none(recordings.get('commentCount'))
  56         categories = [tag['name'] for tag in recordings.get('tags', []) if tag.get('name')]
  57
  58         return {
  59             'id': video_id,
  60             'url': audio_url,
  61             'title': title,
  62             'description': description,
  63             'duration': duration,
  64             'timestamp': timestamp,
  65             'uploader': uploader,
  66             'uploader_id': uploader_id,
  67             'view_count': view_count,
  68             'comment_count': comment_count,
  69             'categories': categories,
  70         }