yt_dlp/extractor/ruv.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     parse_duration,
   5     traverse_obj,
   6     unified_timestamp,
   7 )
   8
   9
  10 class RuvIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?ruv\.is/(?:sarpurinn/[^/]+|node)/(?P<id>[^/]+(?:/\d+)?)'
  12     _TESTS = [{
  13         # m3u8
  14         'url': 'http://ruv.is/sarpurinn/ruv-aukaras/fh-valur/20170516',
  15         'md5': '66347652f4e13e71936817102acc1724',
  16         'info_dict': {
  17             'id': '1144499',
  18             'display_id': 'fh-valur/20170516',
  19             'ext': 'mp4',
  20             'title': 'FH - Valur',
  21             'description': 'Bein útsending frá 3. leik FH og Vals í úrslitum Olísdeildar karla í handbolta.',
  22             'timestamp': 1494963600,
  23             'upload_date': '20170516',
  24         },
  25     }, {
  26         # mp3
  27         'url': 'http://ruv.is/sarpurinn/ras-2/morgunutvarpid/20170619',
  28         'md5': '395ea250c8a13e5fdb39d4670ef85378',
  29         'info_dict': {
  30             'id': '1153630',
  31             'display_id': 'morgunutvarpid/20170619',
  32             'ext': 'mp3',
  33             'title': 'Morgunútvarpið',
  34             'description': 'md5:a4cf1202c0a1645ca096b06525915418',
  35             'timestamp': 1497855000,
  36             'upload_date': '20170619',
  37         },
  38     }, {
  39         'url': 'http://ruv.is/sarpurinn/ruv/frettir/20170614',
  40         'only_matching': True,
  41     }, {
  42         'url': 'http://www.ruv.is/node/1151854',
  43         'only_matching': True,
  44     }, {
  45         'url': 'http://ruv.is/sarpurinn/klippa/secret-soltice-hefst-a-morgun',
  46         'only_matching': True,
  47     }, {
  48         'url': 'http://ruv.is/sarpurinn/ras-1/morgunvaktin/20170619',
  49         'only_matching': True,
  50     }]
  51
  52     def _real_extract(self, url):
  53         display_id = self._match_id(url)
  54
  55         webpage = self._download_webpage(url, display_id)
  56
  57         title = self._og_search_title(webpage)
  58
  59         FIELD_RE = r'video\.%s\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1'
  60
  61         media_url = self._html_search_regex(
  62             FIELD_RE % 'src', webpage, 'video URL', group='url')
  63
  64         video_id = self._search_regex(
  65             r'<link\b[^>]+\bhref=["\']https?://www\.ruv\.is/node/(\d+)',
  66             webpage, 'video id', default=display_id)
  67
  68         ext = determine_ext(media_url)
  69
  70         if ext == 'm3u8':
  71             formats = self._extract_m3u8_formats(
  72                 media_url, video_id, 'mp4', entry_protocol='m3u8_native',
  73                 m3u8_id='hls')
  74         elif ext == 'mp3':
  75             formats = [{
  76                 'format_id': 'mp3',
  77                 'url': media_url,
  78                 'vcodec': 'none',
  79             }]
  80         else:
  81             formats = [{
  82                 'url': media_url,
  83             }]
  84
  85         description = self._og_search_description(webpage, default=None)
  86         thumbnail = self._og_search_thumbnail(
  87             webpage, default=None) or self._search_regex(
  88             FIELD_RE % 'poster', webpage, 'thumbnail', fatal=False)
  89         timestamp = unified_timestamp(self._html_search_meta(
  90             'article:published_time', webpage, 'timestamp', fatal=False))
  91
  92         return {
  93             'id': video_id,
  94             'display_id': display_id,
  95             'title': title,
  96             'description': description,
  97             'thumbnail': thumbnail,
  98             'timestamp': timestamp,
  99             'formats': formats,
 100         }
 101
 102
 103 class RuvSpilaIE(InfoExtractor):
 104     IE_NAME = 'ruv.is:spila'
 105     _VALID_URL = r'https?://(?:www\.)?ruv\.is/(?:(?:sjon|ut)varp|(?:krakka|ung)ruv)/spila/.+/(?P<series_id>[0-9]+)/(?P<id>[a-z0-9]+)'
 106     _TESTS = [{
 107         'url': 'https://www.ruv.is/sjonvarp/spila/ithrottir/30657/9jcnd4',
 108         'info_dict': {
 109             'id': '9jcnd4',
 110             'ext': 'mp4',
 111             'title': '01.02.2022',
 112             'chapters': 'count:4',
 113             'timestamp': 1643743500,
 114             'upload_date': '20220201',
 115             'thumbnail': 'https://d38kdhuogyllre.cloudfront.net/fit-in/1960x/filters:quality(65)/hd_posters/94boog-iti3jg.jpg',
 116             'description': 'Íþróttafréttir.',
 117             'age_limit': 0,
 118         },
 119     }, {
 120         'url': 'https://www.ruv.is/utvarp/spila/i-ljosi-sogunnar/23795/7hqkre',
 121         'info_dict': {
 122             'id': '7hqkre',
 123             'ext': 'mp3',
 124             'thumbnail': 'https://d38kdhuogyllre.cloudfront.net/fit-in/1960x/filters:quality(65)/hd_posters/7hqkre-7uepao.jpg',
 125             'description': 'md5:8d7046549daff35e9a3190dc9901a120',
 126             'chapters': [],
 127             'upload_date': '20220204',
 128             'timestamp': 1643965500,
 129             'title': 'Nellie Bly II',
 130             'age_limit': 0,
 131         },
 132     }, {
 133         'url': 'https://www.ruv.is/ungruv/spila/ungruv/28046/8beuph',
 134         'only_matching': True,
 135     }, {
 136         'url': 'https://www.ruv.is/krakkaruv/spila/krakkafrettir/30712/9jbgb0',
 137         'only_matching': True,
 138     }]
 139
 140     def _real_extract(self, url):
 141         display_id, series_id = self._match_valid_url(url).group('id', 'series_id')
 142         program = self._download_json(
 143             'https://www.ruv.is/gql/', display_id, query={'query': '''{
 144                 Program(id: %s){
 145                     title image description short_description
 146                     episodes(id: {value: "%s"}) {
 147                         rating title duration file image firstrun description
 148                         clips {
 149                             time text
 150                         }
 151                         subtitles {
 152                             name value
 153                         }
 154                     }
 155                 }
 156             }''' % (series_id, display_id)})['data']['Program']  # noqa: UP031
 157         episode = program['episodes'][0]
 158
 159         subs = {}
 160         for trk in episode.get('subtitles'):
 161             if trk.get('name') and trk.get('value'):
 162                 subs.setdefault(trk['name'], []).append({'url': trk['value'], 'ext': 'vtt'})
 163
 164         media_url = episode['file']
 165         if determine_ext(media_url) == 'm3u8':
 166             formats = self._extract_m3u8_formats(media_url, display_id)
 167         else:
 168             formats = [{'url': media_url}]
 169
 170         clips = [
 171             {'start_time': parse_duration(c.get('time')), 'title': c.get('text')}
 172             for c in episode.get('clips') or []]
 173
 174         return {
 175             'id': display_id,
 176             'title': traverse_obj(program, ('episodes', 0, 'title'), 'title'),
 177             'description': traverse_obj(
 178                 program, ('episodes', 0, 'description'), 'description', 'short_description',
 179                 expected_type=lambda x: x or None),
 180             'subtitles': subs,
 181             'thumbnail': episode.get('image', '').replace('$$IMAGESIZE$$', '1960') or None,
 182             'timestamp': unified_timestamp(episode.get('firstrun')),
 183             'formats': formats,
 184             'age_limit': episode.get('rating'),
 185             'chapters': clips,
 186         }