yt_dlp/extractor/playfm.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     ExtractorError,
   9     int_or_none,
  10     parse_iso8601,
  11 )
  12
  13
  14 class PlayFMIE(InfoExtractor):
  15     IE_NAME = 'play.fm'
  16     _VALID_URL = r'https?://(?:www\.)?play\.fm/(?P<slug>(?:[^/]+/)+(?P<id>[^/]+))/?(?:$|[?#])'
  17
  18     _TEST = {
  19         'url': 'https://www.play.fm/dan-drastic/sven-tasnadi-leipzig-electronic-music-batofar-paris-fr-2014-07-12',
  20         'md5': 'c505f8307825a245d0c7ad1850001f22',
  21         'info_dict': {
  22             'id': '71276',
  23             'ext': 'mp3',
  24             'title': 'Sven Tasnadi - LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12',
  25             'description': '',
  26             'duration': 5627,
  27             'timestamp': 1406033781,
  28             'upload_date': '20140722',
  29             'uploader': 'Dan Drastic',
  30             'uploader_id': '71170',
  31             'view_count': int,
  32             'comment_count': int,
  33         },
  34     }
  35
  36     def _real_extract(self, url):
  37         mobj = self._match_valid_url(url)
  38         video_id = mobj.group('id')
  39         slug = mobj.group('slug')
  40
  41         recordings = self._download_json(
  42             'http://v2api.play.fm/recordings/slug/%s' % slug, video_id)
  43
  44         error = recordings.get('error')
  45         if isinstance(error, dict):
  46             raise ExtractorError(
  47                 '%s returned error: %s' % (self.IE_NAME, error.get('message')),
  48                 expected=True)
  49
  50         audio_url = recordings['audio']
  51         video_id = compat_str(recordings.get('id') or video_id)
  52         title = recordings['title']
  53         description = recordings.get('description')
  54         duration = int_or_none(recordings.get('recordingDuration'))
  55         timestamp = parse_iso8601(recordings.get('created_at'))
  56         uploader = recordings.get('page', {}).get('title')
  57         uploader_id = compat_str(recordings.get('page', {}).get('id'))
  58         view_count = int_or_none(recordings.get('playCount'))
  59         comment_count = int_or_none(recordings.get('commentCount'))
  60         categories = [tag['name'] for tag in recordings.get('tags', []) if tag.get('name')]
  61
  62         return {
  63             'id': video_id,
  64             'url': audio_url,
  65             'title': title,
  66             'description': description,
  67             'duration': duration,
  68             'timestamp': timestamp,
  69             'uploader': uploader,
  70             'uploader_id': uploader_id,
  71             'view_count': view_count,
  72             'comment_count': comment_count,
  73             'categories': categories,
  74         }