youtube_dl/extractor/playfm.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     ExtractorError,
  10     int_or_none,
  11     parse_iso8601,
  12 )
  13
  14
  15 class PlayFMIE(InfoExtractor):
  16     IE_NAME = 'play.fm'
  17     _VALID_URL = r'https?://(?:www\.)?play\.fm/(?P<slug>(?:[^/]+/)+(?P<id>[^/]+))/?(?:$|[?#])'
  18
  19     _TEST = {
  20         'url': 'https://www.play.fm/dan-drastic/sven-tasnadi-leipzig-electronic-music-batofar-paris-fr-2014-07-12',
  21         'md5': 'c505f8307825a245d0c7ad1850001f22',
  22         'info_dict': {
  23             'id': '71276',
  24             'ext': 'mp3',
  25             'title': 'Sven Tasnadi - LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12',
  26             'description': '',
  27             'duration': 5627,
  28             'timestamp': 1406033781,
  29             'upload_date': '20140722',
  30             'uploader': 'Dan Drastic',
  31             'uploader_id': '71170',
  32             'view_count': int,
  33             'comment_count': int,
  34         },
  35     }
  36
  37     def _real_extract(self, url):
  38         mobj = re.match(self._VALID_URL, url)
  39         video_id = mobj.group('id')
  40         slug = mobj.group('slug')
  41
  42         recordings = self._download_json(
  43             'http://v2api.play.fm/recordings/slug/%s' % slug, video_id)
  44
  45         error = recordings.get('error')
  46         if isinstance(error, dict):
  47             raise ExtractorError(
  48                 '%s returned error: %s' % (self.IE_NAME, error.get('message')),
  49                 expected=True)
  50
  51         audio_url = recordings['audio']
  52         video_id = compat_str(recordings.get('id') or video_id)
  53         title = recordings['title']
  54         description = recordings.get('description')
  55         duration = int_or_none(recordings.get('recordingDuration'))
  56         timestamp = parse_iso8601(recordings.get('created_at'))
  57         uploader = recordings.get('page', {}).get('title')
  58         uploader_id = compat_str(recordings.get('page', {}).get('id'))
  59         view_count = int_or_none(recordings.get('playCount'))
  60         comment_count = int_or_none(recordings.get('commentCount'))
  61         categories = [tag['name'] for tag in recordings.get('tags', []) if tag.get('name')]
  62
  63         return {
  64             'id': video_id,
  65             'url': audio_url,
  66             'title': title,
  67             'description': description,
  68             'duration': duration,
  69             'timestamp': timestamp,
  70             'uploader': uploader,
  71             'uploader_id': uploader_id,
  72             'view_count': view_count,
  73             'comment_count': comment_count,
  74             'categories': categories,
  75         }