Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/libsyn.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     clean_html,
   9     get_element_by_class,
  10     parse_duration,
  11     strip_or_none,
  12     unified_strdate,
  13 )
  14
  15
  16 class LibsynIE(InfoExtractor):
  17     _VALID_URL = r'(?P<mainurl>https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+))'
  18
  19     _TESTS = [{
  20         'url': 'http://html5-player.libsyn.com/embed/episode/id/6385796/',
  21         'md5': '2a55e75496c790cdeb058e7e6c087746',
  22         'info_dict': {
  23             'id': '6385796',
  24             'ext': 'mp3',
  25             'title': "Champion Minded - Developing a Growth Mindset",
  26             # description fetched using another request:
  27             # http://html5-player.libsyn.com/embed/getitemdetails?item_id=6385796
  28             # 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
  29             'upload_date': '20180320',
  30             'thumbnail': 're:^https?://.*',
  31         },
  32     }, {
  33         '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/',
  34         'md5': '6c5cb21acd622d754d3b1a92b582ce42',
  35         'info_dict': {
  36             'id': '3727166',
  37             'ext': 'mp3',
  38             'title': 'Clients From Hell Podcast - How a Sex Toy Company Kickstarted my Freelance Career',
  39             'upload_date': '20150818',
  40             'thumbnail': 're:^https?://.*',
  41         }
  42     }]
  43
  44     def _real_extract(self, url):
  45         url, video_id = re.match(self._VALID_URL, url).groups()
  46         webpage = self._download_webpage(url, video_id)
  47
  48         data = self._parse_json(self._search_regex(
  49             r'var\s+playlistItem\s*=\s*({.+?});',
  50             webpage, 'JSON data block'), video_id)
  51
  52         episode_title = data.get('item_title') or get_element_by_class('episode-title', webpage)
  53         if not episode_title:
  54             self._search_regex(
  55                 [r'data-title="([^"]+)"', r'<title>(.+?)</title>'],
  56                 webpage, 'episode title')
  57         episode_title = episode_title.strip()
  58
  59         podcast_title = strip_or_none(clean_html(self._search_regex(
  60             r'<h3>([^<]+)</h3>', webpage, 'podcast title',
  61             default=None) or get_element_by_class('podcast-title', webpage)))
  62
  63         title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
  64
  65         formats = []
  66         for k, format_id in (('media_url_libsyn', 'libsyn'), ('media_url', 'main'), ('download_link', 'download')):
  67             f_url = data.get(k)
  68             if not f_url:
  69                 continue
  70             formats.append({
  71                 'url': f_url,
  72                 'format_id': format_id,
  73             })
  74
  75         description = self._html_search_regex(
  76             r'<p\s+id="info_text_body">(.+?)</p>', webpage,
  77             'description', default=None)
  78         if description:
  79             # Strip non-breaking and normal spaces
  80             description = description.replace('\u00A0', ' ').strip()
  81         release_date = unified_strdate(self._search_regex(
  82             r'<div class="release_date">Released: ([^<]+)<',
  83             webpage, 'release date', default=None) or data.get('release_date'))
  84
  85         return {
  86             'id': video_id,
  87             'title': title,
  88             'description': description,
  89             'thumbnail': data.get('thumbnail_url'),
  90             'upload_date': release_date,
  91             'duration': parse_duration(data.get('duration')),
  92             'formats': formats,
  93         }