yt_dlp/extractor/libsyn.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     clean_html,
   8     get_element_by_class,
   9     parse_duration,
  10     strip_or_none,
  11     unified_strdate,
  12 )
  13
  14
  15 class LibsynIE(InfoExtractor):
  16     _VALID_URL = r'(?P<mainurl>https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+))'
  17
  18     _TESTS = [{
  19         'url': 'http://html5-player.libsyn.com/embed/episode/id/6385796/',
  20         'md5': '2a55e75496c790cdeb058e7e6c087746',
  21         'info_dict': {
  22             'id': '6385796',
  23             'ext': 'mp3',
  24             'title': "Champion Minded - Developing a Growth Mindset",
  25             # description fetched using another request:
  26             # http://html5-player.libsyn.com/embed/getitemdetails?item_id=6385796
  27             # 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
  28             'upload_date': '20180320',
  29             'thumbnail': 're:^https?://.*',
  30         },
  31     }, {
  32         '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/',
  33         'md5': '6c5cb21acd622d754d3b1a92b582ce42',
  34         'info_dict': {
  35             'id': '3727166',
  36             'ext': 'mp3',
  37             'title': 'Clients From Hell Podcast - How a Sex Toy Company Kickstarted my Freelance Career',
  38             'upload_date': '20150818',
  39             'thumbnail': 're:^https?://.*',
  40         }
  41     }]
  42
  43     def _real_extract(self, url):
  44         url, video_id = self._match_valid_url(url).groups()
  45         webpage = self._download_webpage(url, video_id)
  46
  47         data = self._parse_json(self._search_regex(
  48             r'var\s+playlistItem\s*=\s*({.+?});',
  49             webpage, 'JSON data block'), video_id)
  50
  51         episode_title = data.get('item_title') or get_element_by_class('episode-title', webpage)
  52         if not episode_title:
  53             self._search_regex(
  54                 [r'data-title="([^"]+)"', r'<title>(.+?)</title>'],
  55                 webpage, 'episode title')
  56         episode_title = episode_title.strip()
  57
  58         podcast_title = strip_or_none(clean_html(self._search_regex(
  59             r'<h3>([^<]+)</h3>', webpage, 'podcast title',
  60             default=None) or get_element_by_class('podcast-title', webpage)))
  61
  62         title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
  63
  64         formats = []
  65         for k, format_id in (('media_url_libsyn', 'libsyn'), ('media_url', 'main'), ('download_link', 'download')):
  66             f_url = data.get(k)
  67             if not f_url:
  68                 continue
  69             formats.append({
  70                 'url': f_url,
  71                 'format_id': format_id,
  72             })
  73
  74         description = self._html_search_regex(
  75             r'<p\s+id="info_text_body">(.+?)</p>', webpage,
  76             'description', default=None)
  77         if description:
  78             # Strip non-breaking and normal spaces
  79             description = description.replace('\u00A0', ' ').strip()
  80         release_date = unified_strdate(self._search_regex(
  81             r'<div class="release_date">Released: ([^<]+)<',
  82             webpage, 'release date', default=None) or data.get('release_date'))
  83
  84         return {
  85             'id': video_id,
  86             'title': title,
  87             'description': description,
  88             'thumbnail': data.get('thumbnail_url'),
  89             'upload_date': release_date,
  90             'duration': parse_duration(data.get('duration')),
  91             'formats': formats,
  92         }