yt_dlp/extractor/rozhlas.py

   1 from .common import InfoExtractor
   2 from ..utils import extract_attributes, int_or_none, remove_start, traverse_obj
   3
   4
   5 class RozhlasIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?prehravac\.rozhlas\.cz/audio/(?P<id>[0-9]+)'
   7     _TESTS = [{
   8         'url': 'http://prehravac.rozhlas.cz/audio/3421320',
   9         'md5': '504c902dbc9e9a1fd50326eccf02a7e2',
  10         'info_dict': {
  11             'id': '3421320',
  12             'ext': 'mp3',
  13             'title': 'Echo Pavla Klusáka (30.06.2015 21:00)',
  14             'description': 'Osmdesátiny Terryho Rileyho jsou skvělou příležitostí proletět se elektronickými i akustickými díly zakladatatele minimalismu, který je aktivní už přes padesát let'
  15         }
  16     }, {
  17         'url': 'http://prehravac.rozhlas.cz/audio/3421320/embed',
  18         'only_matching': True,
  19     }]
  20
  21     def _real_extract(self, url):
  22         audio_id = self._match_id(url)
  23
  24         webpage = self._download_webpage(
  25             'http://prehravac.rozhlas.cz/audio/%s' % audio_id, audio_id)
  26
  27         title = self._html_search_regex(
  28             r'<h3>(.+?)</h3>\s*<p[^>]*>.*?</p>\s*<div[^>]+id=["\']player-track',
  29             webpage, 'title', default=None) or remove_start(
  30             self._og_search_title(webpage), 'Radio Wave - ')
  31         description = self._html_search_regex(
  32             r'<p[^>]+title=(["\'])(?P<url>(?:(?!\1).)+)\1[^>]*>.*?</p>\s*<div[^>]+id=["\']player-track',
  33             webpage, 'description', fatal=False, group='url')
  34         duration = int_or_none(self._search_regex(
  35             r'data-duration=["\'](\d+)', webpage, 'duration', default=None))
  36
  37         return {
  38             'id': audio_id,
  39             'url': 'http://media.rozhlas.cz/_audio/%s.mp3' % audio_id,
  40             'title': title,
  41             'description': description,
  42             'duration': duration,
  43             'vcodec': 'none',
  44         }
  45
  46
  47 class RozhlasVltavaIE(InfoExtractor):
  48     _VALID_URL = r'https?://(?:\w+\.rozhlas|english\.radio)\.cz/[\w-]+-(?P<id>\d+)'
  49     _TESTS = [{
  50         'url': 'https://wave.rozhlas.cz/papej-masicko-porcujeme-a-bilancujeme-filmy-a-serialy-ktere-letos-zabily-8891337',
  51         'md5': 'ba2fdbc1242fc16771c7695d271ec355',
  52         'info_dict': {
  53             'id': 8891337,
  54             'title': 'md5:21f99739d04ab49d8c189ec711eef4ec',
  55         },
  56         'playlist_count': 1,
  57         'playlist': [{
  58             'md5': 'ba2fdbc1242fc16771c7695d271ec355',
  59             'info_dict': {
  60                 'id': '10520988',
  61                 'ext': 'mp3',
  62                 'title': 'Papej masíčko! Porcujeme a bilancujeme filmy a seriály, které to letos zabily',
  63                 'description': 'md5:1c6d29fb9564e1f17fc1bb83ae7da0bc',
  64                 'duration': 1574,
  65                 'artist': 'Aleš Stuchlý',
  66                 'channel_id': 'radio-wave',
  67             },
  68         }]
  69     }, {
  70         'url': 'https://wave.rozhlas.cz/poslechnete-si-neklid-podcastovy-thriller-o-vine-strachu-a-vztahu-ktery-zasel-8554744',
  71         'info_dict': {
  72             'id': 8554744,
  73             'title': 'Poslechněte si Neklid. Podcastový thriller o vině, strachu a vztahu, který zašel příliš daleko',
  74         },
  75         'playlist_count': 5,
  76         'playlist': [{
  77             'md5': '93d4109cf8f40523699ae9c1d4600bdd',
  78             'info_dict': {
  79                 'id': '9890713',
  80                 'ext': 'mp3',
  81                 'title': 'Neklid #1',
  82                 'description': '1. díl: Neklid: 1. díl',
  83                 'duration': 1025,
  84                 'artist': 'Josef Kokta',
  85                 'channel_id': 'radio-wave',
  86                 'chapter': 'Neklid #1',
  87                 'chapter_number': 1,
  88             },
  89         }, {
  90             'md5': 'e9763235be4a6dcf94bc8a5bac1ca126',
  91             'info_dict': {
  92                 'id': '9890716',
  93                 'ext': 'mp3',
  94                 'title': 'Neklid #2',
  95                 'description': '2. díl: Neklid: 2. díl',
  96                 'duration': 768,
  97                 'artist': 'Josef Kokta',
  98                 'channel_id': 'radio-wave',
  99                 'chapter': 'Neklid #2',
 100                 'chapter_number': 2,
 101             },
 102         }, {
 103             'md5': '00b642ea94b78cc949ac84da09f87895',
 104             'info_dict': {
 105                 'id': '9890722',
 106                 'ext': 'mp3',
 107                 'title': 'Neklid #3',
 108                 'description': '3. díl: Neklid: 3. díl',
 109                 'duration': 607,
 110                 'artist': 'Josef Kokta',
 111                 'channel_id': 'radio-wave',
 112                 'chapter': 'Neklid #3',
 113                 'chapter_number': 3,
 114             },
 115         }, {
 116             'md5': 'faef97b1b49da7df874740f118c19dea',
 117             'info_dict': {
 118                 'id': '9890728',
 119                 'ext': 'mp3',
 120                 'title': 'Neklid #4',
 121                 'description': '4. díl: Neklid: 4. díl',
 122                 'duration': 621,
 123                 'artist': 'Josef Kokta',
 124                 'channel_id': 'radio-wave',
 125                 'chapter': 'Neklid #4',
 126                 'chapter_number': 4,
 127             },
 128         }, {
 129             'md5': '6e729fa39b647325b868d419c76f3efa',
 130             'info_dict': {
 131                 'id': '9890734',
 132                 'ext': 'mp3',
 133                 'title': 'Neklid #5',
 134                 'description': '5. díl: Neklid: 5. díl',
 135                 'duration': 908,
 136                 'artist': 'Josef Kokta',
 137                 'channel_id': 'radio-wave',
 138                 'chapter': 'Neklid #5',
 139                 'chapter_number': 5,
 140             },
 141         }]
 142     }]
 143
 144     def _extract_video(self, entry):
 145         chapter_number = int_or_none(traverse_obj(entry, ('meta', 'ga', 'contentSerialPart')))
 146         return {
 147             'id': entry['meta']['ga']['contentId'],
 148             'title': traverse_obj(entry, ('meta', 'ga', 'contentName')),
 149             'description': entry.get('title'),
 150             'duration': entry.get('duration'),
 151             'artist': traverse_obj(entry, ('meta', 'ga', 'contentAuthor')),
 152             'channel_id': traverse_obj(entry, ('meta', 'ga', 'contentCreator')),
 153             'chapter': traverse_obj(entry, ('meta', 'ga', 'contentNameShort')) if chapter_number else None,
 154             'chapter_number': chapter_number,
 155             'formats': [{
 156                 'url': audio_link['url'],
 157                 'ext': audio_link.get('variant'),
 158                 'format_id': audio_link.get('variant'),
 159                 'abr': audio_link.get('bitrate'),
 160                 'acodec': audio_link.get('variant'),
 161                 'vcodec': 'none',
 162             } for audio_link in entry['audioLinks']],
 163         }
 164
 165     def _real_extract(self, url):
 166         video_id = self._match_id(url)
 167         webpage = self._download_webpage(url, video_id)
 168
 169         # FIXME: Use get_element_text_and_html_by_tag when it accepts less strict html
 170         data = self._parse_json(extract_attributes(self._search_regex(
 171             r'(<div class="mujRozhlasPlayer" data-player=\'[^\']+\'>)',
 172             webpage, 'player'))['data-player'], video_id)['data']
 173
 174         return {
 175             '_type': 'playlist',
 176             'id': data.get('embedId'),
 177             'title': traverse_obj(data, ('series', 'title')),
 178             'entries': map(self._extract_video, data['playlist']),
 179         }