_ Git - youtube-dl/blob - youtube_dl/extractor/libsyn.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     parse_duration,
  10     unified_strdate,
  11 )
  12
  13
  14 class LibsynIE(InfoExtractor):
  15     _VALID_URL = r'(?P<mainurl>https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+))'
  16
  17     _TESTS = [{
  18         'url': 'http://html5-player.libsyn.com/embed/episode/id/6385796/',
  19         'md5': '2a55e75496c790cdeb058e7e6c087746',
  20         'info_dict': {
  21             'id': '6385796',
  22             'ext': 'mp3',
  23             'title': "Champion Minded - Developing a Growth Mindset",
  24             'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
  25             'upload_date': '20180320',
  26             'thumbnail': 're:^https?://.*',
  27         },
  28     }, {
  29         '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/',
  30         'md5': '6c5cb21acd622d754d3b1a92b582ce42',
  31         'info_dict': {
  32             'id': '3727166',
  33             'ext': 'mp3',
  34             'title': 'Clients From Hell Podcast - How a Sex Toy Company Kickstarted my Freelance Career',
  35             'upload_date': '20150818',
  36             'thumbnail': 're:^https?://.*',
  37         }
  38     }]
  39
  40     def _real_extract(self, url):
  41         m = re.match(self._VALID_URL, url)
  42         video_id = m.group('id')
  43         url = m.group('mainurl')
  44         webpage = self._download_webpage(url, video_id)
  45
  46         podcast_title = self._search_regex(
  47             r'<h3>([^<]+)</h3>', webpage, 'podcast title', default=None)
  48         if podcast_title:
  49             podcast_title = podcast_title.strip()
  50         episode_title = self._search_regex(
  51             r'(?:<div class="episode-title">|<h4>)([^<]+)</', webpage, 'episode title')
  52         if episode_title:
  53             episode_title = episode_title.strip()
  54
  55         title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
  56
  57         description = self._html_search_regex(
  58             r'<p\s+id="info_text_body">(.+?)</p>', webpage,
  59             'description', default=None)
  60         if description:
  61             # Strip non-breaking and normal spaces
  62             description = description.replace('\u00A0', ' ').strip()
  63         release_date = unified_strdate(self._search_regex(
  64             r'<div class="release_date">Released: ([^<]+)<', webpage, 'release date', fatal=False))
  65
  66         data_json = self._search_regex(r'var\s+playlistItem\s*=\s*(\{.*?\});\n', webpage, 'JSON data block')
  67         data = json.loads(data_json)
  68
  69         formats = [{
  70             'url': data['media_url'],
  71             'format_id': 'main',
  72         }, {
  73             'url': data['media_url_libsyn'],
  74             'format_id': 'libsyn',
  75         }]
  76         thumbnail = data.get('thumbnail_url')
  77         duration = parse_duration(data.get('duration'))
  78
  79         return {
  80             'id': video_id,
  81             'title': title,
  82             'description': description,
  83             'thumbnail': thumbnail,
  84             'upload_date': release_date,
  85             'duration': duration,
  86             'formats': formats,
  87         }