yt_dlp/extractor/spreaker.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import itertools
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     float_or_none,
  10     int_or_none,
  11     str_or_none,
  12     try_get,
  13     unified_timestamp,
  14     url_or_none,
  15 )
  16
  17
  18 def _extract_episode(data, episode_id=None):
  19     title = data['title']
  20     download_url = data['download_url']
  21
  22     series = try_get(data, lambda x: x['show']['title'], compat_str)
  23     uploader = try_get(data, lambda x: x['author']['fullname'], compat_str)
  24
  25     thumbnails = []
  26     for image in ('image_original', 'image_medium', 'image'):
  27         image_url = url_or_none(data.get('%s_url' % image))
  28         if image_url:
  29             thumbnails.append({'url': image_url})
  30
  31     def stats(key):
  32         return int_or_none(try_get(
  33             data,
  34             (lambda x: x['%ss_count' % key],
  35              lambda x: x['stats']['%ss' % key])))
  36
  37     def duration(key):
  38         return float_or_none(data.get(key), scale=1000)
  39
  40     return {
  41         'id': compat_str(episode_id or data['episode_id']),
  42         'url': download_url,
  43         'display_id': data.get('permalink'),
  44         'title': title,
  45         'description': data.get('description'),
  46         'timestamp': unified_timestamp(data.get('published_at')),
  47         'uploader': uploader,
  48         'uploader_id': str_or_none(data.get('author_id')),
  49         'creator': uploader,
  50         'duration': duration('duration') or duration('length'),
  51         'view_count': stats('play'),
  52         'like_count': stats('like'),
  53         'comment_count': stats('message'),
  54         'format': 'MPEG Layer 3',
  55         'format_id': 'mp3',
  56         'container': 'mp3',
  57         'ext': 'mp3',
  58         'thumbnails': thumbnails,
  59         'series': series,
  60         'extractor_key': SpreakerIE.ie_key(),
  61     }
  62
  63
  64 class SpreakerIE(InfoExtractor):
  65     _VALID_URL = r'''(?x)
  66                     https?://
  67                         api\.spreaker\.com/
  68                         (?:
  69                             (?:download/)?episode|
  70                             v2/episodes
  71                         )/
  72                         (?P<id>\d+)
  73                     '''
  74     _TESTS = [{
  75         'url': 'https://api.spreaker.com/episode/12534508',
  76         'info_dict': {
  77             'id': '12534508',
  78             'display_id': 'swm-ep15-how-to-market-your-music-part-2',
  79             'ext': 'mp3',
  80             'title': 'EP:15 | Music Marketing (Likes) - Part 2',
  81             'description': 'md5:0588c43e27be46423e183076fa071177',
  82             'timestamp': 1502250336,
  83             'upload_date': '20170809',
  84             'uploader': 'SWM',
  85             'uploader_id': '9780658',
  86             'duration': 1063.42,
  87             'view_count': int,
  88             'like_count': int,
  89             'comment_count': int,
  90             'series': 'Success With Music (SWM)',
  91         },
  92     }, {
  93         'url': 'https://api.spreaker.com/download/episode/12534508/swm_ep15_how_to_market_your_music_part_2.mp3',
  94         'only_matching': True,
  95     }, {
  96         'url': 'https://api.spreaker.com/v2/episodes/12534508?export=episode_segments',
  97         'only_matching': True,
  98     }]
  99
 100     def _real_extract(self, url):
 101         episode_id = self._match_id(url)
 102         data = self._download_json(
 103             'https://api.spreaker.com/v2/episodes/%s' % episode_id,
 104             episode_id)['response']['episode']
 105         return _extract_episode(data, episode_id)
 106
 107
 108 class SpreakerPageIE(InfoExtractor):
 109     _VALID_URL = r'https?://(?:www\.)?spreaker\.com/user/[^/]+/(?P<id>[^/?#&]+)'
 110     _TESTS = [{
 111         'url': 'https://www.spreaker.com/user/9780658/swm-ep15-how-to-market-your-music-part-2',
 112         'only_matching': True,
 113     }]
 114
 115     def _real_extract(self, url):
 116         display_id = self._match_id(url)
 117         webpage = self._download_webpage(url, display_id)
 118         episode_id = self._search_regex(
 119             (r'data-episode_id=["\'](?P<id>\d+)',
 120              r'episode_id\s*:\s*(?P<id>\d+)'), webpage, 'episode id')
 121         return self.url_result(
 122             'https://api.spreaker.com/episode/%s' % episode_id,
 123             ie=SpreakerIE.ie_key(), video_id=episode_id)
 124
 125
 126 class SpreakerShowIE(InfoExtractor):
 127     _VALID_URL = r'https?://api\.spreaker\.com/show/(?P<id>\d+)'
 128     _TESTS = [{
 129         'url': 'https://api.spreaker.com/show/4652058',
 130         'info_dict': {
 131             'id': '4652058',
 132         },
 133         'playlist_mincount': 118,
 134     }]
 135
 136     def _entries(self, show_id):
 137         for page_num in itertools.count(1):
 138             episodes = self._download_json(
 139                 'https://api.spreaker.com/show/%s/episodes' % show_id,
 140                 show_id, note='Downloading JSON page %d' % page_num, query={
 141                     'page': page_num,
 142                     'max_per_page': 100,
 143                 })
 144             pager = try_get(episodes, lambda x: x['response']['pager'], dict)
 145             if not pager:
 146                 break
 147             results = pager.get('results')
 148             if not results or not isinstance(results, list):
 149                 break
 150             for result in results:
 151                 if not isinstance(result, dict):
 152                     continue
 153                 yield _extract_episode(result)
 154             if page_num == pager.get('last_page'):
 155                 break
 156
 157     def _real_extract(self, url):
 158         show_id = self._match_id(url)
 159         return self.playlist_result(self._entries(show_id), playlist_id=show_id)
 160
 161
 162 class SpreakerShowPageIE(InfoExtractor):
 163     _VALID_URL = r'https?://(?:www\.)?spreaker\.com/show/(?P<id>[^/?#&]+)'
 164     _TESTS = [{
 165         'url': 'https://www.spreaker.com/show/success-with-music',
 166         'only_matching': True,
 167     }]
 168
 169     def _real_extract(self, url):
 170         display_id = self._match_id(url)
 171         webpage = self._download_webpage(url, display_id)
 172         show_id = self._search_regex(
 173             r'show_id\s*:\s*(?P<id>\d+)', webpage, 'show id')
 174         return self.url_result(
 175             'https://api.spreaker.com/show/%s' % show_id,
 176             ie=SpreakerShowIE.ie_key(), video_id=show_id)