yt_dlp/extractor/libsyn.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_html,
   4     get_element_by_class,
   5     parse_duration,
   6     strip_or_none,
   7     unified_strdate,
   8 )
   9
  10
  11 class LibsynIE(InfoExtractor):
  12     _VALID_URL = r'(?P<mainurl>https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+))'
  13
  14     _TESTS = [{
  15         'url': 'http://html5-player.libsyn.com/embed/episode/id/6385796/',
  16         'md5': '2a55e75496c790cdeb058e7e6c087746',
  17         'info_dict': {
  18             'id': '6385796',
  19             'ext': 'mp3',
  20             'title': "Champion Minded - Developing a Growth Mindset",
  21             # description fetched using another request:
  22             # http://html5-player.libsyn.com/embed/getitemdetails?item_id=6385796
  23             # 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
  24             'upload_date': '20180320',
  25             'thumbnail': 're:^https?://.*',
  26         },
  27     }, {
  28         'url': 'https://html5-player.libsyn.com/embed/episode/id/3727166/height/75/width/200/theme/standard/direction/no/autoplay/no/autonext/no/thumbnail/no/preload/no/no_addthis/no/',
  29         'md5': '6c5cb21acd622d754d3b1a92b582ce42',
  30         'info_dict': {
  31             'id': '3727166',
  32             'ext': 'mp3',
  33             'title': 'Clients From Hell Podcast - How a Sex Toy Company Kickstarted my Freelance Career',
  34             'upload_date': '20150818',
  35             'thumbnail': 're:^https?://.*',
  36         }
  37     }]
  38
  39     def _real_extract(self, url):
  40         url, video_id = self._match_valid_url(url).groups()
  41         webpage = self._download_webpage(url, video_id)
  42
  43         data = self._parse_json(self._search_regex(
  44             r'var\s+playlistItem\s*=\s*({.+?});',
  45             webpage, 'JSON data block'), video_id)
  46
  47         episode_title = data.get('item_title') or get_element_by_class('episode-title', webpage)
  48         if not episode_title:
  49             self._search_regex(
  50                 [r'data-title="([^"]+)"', r'<title>(.+?)</title>'],
  51                 webpage, 'episode title')
  52         episode_title = episode_title.strip()
  53
  54         podcast_title = strip_or_none(clean_html(self._search_regex(
  55             r'<h3>([^<]+)</h3>', webpage, 'podcast title',
  56             default=None) or get_element_by_class('podcast-title', webpage)))
  57
  58         title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
  59
  60         formats = []
  61         for k, format_id in (('media_url_libsyn', 'libsyn'), ('media_url', 'main'), ('download_link', 'download')):
  62             f_url = data.get(k)
  63             if not f_url:
  64                 continue
  65             formats.append({
  66                 'url': f_url,
  67                 'format_id': format_id,
  68             })
  69
  70         description = self._html_search_regex(
  71             r'<p\s+id="info_text_body">(.+?)</p>', webpage,
  72             'description', default=None)
  73         if description:
  74             # Strip non-breaking and normal spaces
  75             description = description.replace('\u00A0', ' ').strip()
  76         release_date = unified_strdate(self._search_regex(
  77             r'<div class="release_date">Released: ([^<]+)<',
  78             webpage, 'release date', default=None) or data.get('release_date'))
  79
  80         return {
  81             'id': video_id,
  82             'title': title,
  83             'description': description,
  84             'thumbnail': data.get('thumbnail_url'),
  85             'upload_date': release_date,
  86             'duration': parse_duration(data.get('duration')),
  87             'formats': formats,
  88         }