yt_dlp/extractor/stitcher.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     clean_html,
   8     ExtractorError,
   9     int_or_none,
  10     str_or_none,
  11     try_get,
  12 )
  13
  14
  15 class StitcherIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?stitcher\.com/(?:podcast|show)/(?:[^/]+/)+e(?:pisode)?/(?:(?P<display_id>[^/#?&]+?)-)?(?P<id>\d+)(?:[/#?&]|$)'
  17     _TESTS = [{
  18         'url': 'http://www.stitcher.com/podcast/the-talking-machines/e/40789481?autoplay=true',
  19         'md5': 'e9635098e0da10b21a0e2b85585530f6',
  20         'info_dict': {
  21             'id': '40789481',
  22             'ext': 'mp3',
  23             'title': 'Machine Learning Mastery and Cancer Clusters',
  24             'description': 'md5:547adb4081864be114ae3831b4c2b42f',
  25             'duration': 1604,
  26             'thumbnail': r're:^https?://.*\.jpg',
  27             'upload_date': '20180126',
  28             'timestamp': 1516989316,
  29         },
  30     }, {
  31         'url': 'http://www.stitcher.com/podcast/panoply/vulture-tv/e/the-rare-hourlong-comedy-plus-40846275?autoplay=true',
  32         'info_dict': {
  33             'id': '40846275',
  34             'display_id': 'the-rare-hourlong-comedy-plus',
  35             'ext': 'mp3',
  36             'title': "The CW's 'Crazy Ex-Girlfriend'",
  37             'description': 'md5:04f1e2f98eb3f5cbb094cea0f9e19b17',
  38             'duration': 2235,
  39             'thumbnail': r're:^https?://.*\.jpg',
  40         },
  41         'params': {
  42             'skip_download': True,
  43         },
  44         'skip': 'Page Not Found',
  45     }, {
  46         # escaped title
  47         'url': 'http://www.stitcher.com/podcast/marketplace-on-stitcher/e/40910226?autoplay=true',
  48         'only_matching': True,
  49     }, {
  50         'url': 'http://www.stitcher.com/podcast/panoply/getting-in/e/episode-2a-how-many-extracurriculars-should-i-have-40876278?autoplay=true',
  51         'only_matching': True,
  52     }, {
  53         'url': 'https://www.stitcher.com/show/threedom/episode/circles-on-a-stick-200212584',
  54         'only_matching': True,
  55     }]
  56
  57     def _real_extract(self, url):
  58         display_id, audio_id = re.match(self._VALID_URL, url).groups()
  59
  60         resp = self._download_json(
  61             'https://api.prod.stitcher.com/episode/' + audio_id,
  62             display_id or audio_id)
  63         episode = try_get(resp, lambda x: x['data']['episodes'][0], dict)
  64         if not episode:
  65             raise ExtractorError(resp['errors'][0]['message'], expected=True)
  66
  67         title = episode['title'].strip()
  68         audio_url = episode['audio_url']
  69
  70         thumbnail = None
  71         show_id = episode.get('show_id')
  72         if show_id and episode.get('classic_id') != -1:
  73             thumbnail = 'https://stitcher-classic.imgix.net/feedimages/%s.jpg' % show_id
  74
  75         return {
  76             'id': audio_id,
  77             'display_id': display_id,
  78             'title': title,
  79             'description': clean_html(episode.get('html_description') or episode.get('description')),
  80             'duration': int_or_none(episode.get('duration')),
  81             'thumbnail': thumbnail,
  82             'url': audio_url,
  83             'vcodec': 'none',
  84             'timestamp': int_or_none(episode.get('date_created')),
  85             'season_number': int_or_none(episode.get('season')),
  86             'season_id': str_or_none(episode.get('season_id')),
  87         }