yt_dlp/extractor/ruv.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     determine_ext,
   7     parse_duration,
   8     traverse_obj,
   9     unified_timestamp,
  10 )
  11
  12
  13 class RuvIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?ruv\.is/(?:sarpurinn/[^/]+|node)/(?P<id>[^/]+(?:/\d+)?)'
  15     _TESTS = [{
  16         # m3u8
  17         'url': 'http://ruv.is/sarpurinn/ruv-aukaras/fh-valur/20170516',
  18         'md5': '66347652f4e13e71936817102acc1724',
  19         'info_dict': {
  20             'id': '1144499',
  21             'display_id': 'fh-valur/20170516',
  22             'ext': 'mp4',
  23             'title': 'FH - Valur',
  24             'description': 'Bein útsending frá 3. leik FH og Vals í úrslitum Olísdeildar karla í handbolta.',
  25             'timestamp': 1494963600,
  26             'upload_date': '20170516',
  27         },
  28     }, {
  29         # mp3
  30         'url': 'http://ruv.is/sarpurinn/ras-2/morgunutvarpid/20170619',
  31         'md5': '395ea250c8a13e5fdb39d4670ef85378',
  32         'info_dict': {
  33             'id': '1153630',
  34             'display_id': 'morgunutvarpid/20170619',
  35             'ext': 'mp3',
  36             'title': 'Morgunútvarpið',
  37             'description': 'md5:a4cf1202c0a1645ca096b06525915418',
  38             'timestamp': 1497855000,
  39             'upload_date': '20170619',
  40         },
  41     }, {
  42         'url': 'http://ruv.is/sarpurinn/ruv/frettir/20170614',
  43         'only_matching': True,
  44     }, {
  45         'url': 'http://www.ruv.is/node/1151854',
  46         'only_matching': True,
  47     }, {
  48         'url': 'http://ruv.is/sarpurinn/klippa/secret-soltice-hefst-a-morgun',
  49         'only_matching': True,
  50     }, {
  51         'url': 'http://ruv.is/sarpurinn/ras-1/morgunvaktin/20170619',
  52         'only_matching': True,
  53     }]
  54
  55     def _real_extract(self, url):
  56         display_id = self._match_id(url)
  57
  58         webpage = self._download_webpage(url, display_id)
  59
  60         title = self._og_search_title(webpage)
  61
  62         FIELD_RE = r'video\.%s\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1'
  63
  64         media_url = self._html_search_regex(
  65             FIELD_RE % 'src', webpage, 'video URL', group='url')
  66
  67         video_id = self._search_regex(
  68             r'<link\b[^>]+\bhref=["\']https?://www\.ruv\.is/node/(\d+)',
  69             webpage, 'video id', default=display_id)
  70
  71         ext = determine_ext(media_url)
  72
  73         if ext == 'm3u8':
  74             formats = self._extract_m3u8_formats(
  75                 media_url, video_id, 'mp4', entry_protocol='m3u8_native',
  76                 m3u8_id='hls')
  77         elif ext == 'mp3':
  78             formats = [{
  79                 'format_id': 'mp3',
  80                 'url': media_url,
  81                 'vcodec': 'none',
  82             }]
  83         else:
  84             formats = [{
  85                 'url': media_url,
  86             }]
  87
  88         description = self._og_search_description(webpage, default=None)
  89         thumbnail = self._og_search_thumbnail(
  90             webpage, default=None) or self._search_regex(
  91             FIELD_RE % 'poster', webpage, 'thumbnail', fatal=False)
  92         timestamp = unified_timestamp(self._html_search_meta(
  93             'article:published_time', webpage, 'timestamp', fatal=False))
  94
  95         return {
  96             'id': video_id,
  97             'display_id': display_id,
  98             'title': title,
  99             'description': description,
 100             'thumbnail': thumbnail,
 101             'timestamp': timestamp,
 102             'formats': formats,
 103         }
 104
 105
 106 class RuvSpilaIE(InfoExtractor):
 107     IE_NAME = 'ruv.is:spila'
 108     _VALID_URL = r'https?://(?:www\.)?ruv\.is/(?:(?:sjon|ut)varp|(?:krakka|ung)ruv)/spila/.+/(?P<series_id>[0-9]+)/(?P<id>[a-z0-9]+)'
 109     _TESTS = [{
 110         'url': 'https://www.ruv.is/sjonvarp/spila/ithrottir/30657/9jcnd4',
 111         'info_dict': {
 112             'id': '9jcnd4',
 113             'ext': 'mp4',
 114             'title': '01.02.2022',
 115             'chapters': 'count:4',
 116             'timestamp': 1643743500,
 117             'upload_date': '20220201',
 118             'thumbnail': 'https://d38kdhuogyllre.cloudfront.net/fit-in/1960x/filters:quality(65)/hd_posters/94boog-iti3jg.jpg',
 119             'description': 'Íþróttafréttir.',
 120             'age_limit': 0,
 121         },
 122     }, {
 123         'url': 'https://www.ruv.is/utvarp/spila/i-ljosi-sogunnar/23795/7hqkre',
 124         'info_dict': {
 125             'id': '7hqkre',
 126             'ext': 'mp3',
 127             'thumbnail': 'https://d38kdhuogyllre.cloudfront.net/fit-in/1960x/filters:quality(65)/hd_posters/7hqkre-7uepao.jpg',
 128             'description': 'md5:8d7046549daff35e9a3190dc9901a120',
 129             'chapters': [],
 130             'upload_date': '20220204',
 131             'timestamp': 1643965500,
 132             'title': 'Nellie Bly II',
 133             'age_limit': 0,
 134         },
 135     }, {
 136         'url': 'https://www.ruv.is/ungruv/spila/ungruv/28046/8beuph',
 137         'only_matching': True
 138     }, {
 139         'url': 'https://www.ruv.is/krakkaruv/spila/krakkafrettir/30712/9jbgb0',
 140         'only_matching': True
 141     }]
 142
 143     def _real_extract(self, url):
 144         display_id, series_id = self._match_valid_url(url).group('id', 'series_id')
 145         program = self._download_json(
 146             'https://www.ruv.is/gql/', display_id, query={'query': '''{
 147                 Program(id: %s){
 148                     title image description short_description
 149                     episodes(id: {value: "%s"}) {
 150                         rating title duration file image firstrun description
 151                         clips {
 152                             time text
 153                         }
 154                         subtitles {
 155                             name value
 156                         }
 157                     }
 158                 }
 159             }''' % (series_id, display_id)})['data']['Program']
 160         episode = program['episodes'][0]
 161
 162         subs = {}
 163         for trk in episode.get('subtitles'):
 164             if trk.get('name') and trk.get('value'):
 165                 subs.setdefault(trk['name'], []).append({'url': trk['value'], 'ext': 'vtt'})
 166
 167         media_url = episode['file']
 168         if determine_ext(media_url) == 'm3u8':
 169             formats = self._extract_m3u8_formats(media_url, display_id)
 170         else:
 171             formats = [{'url': media_url}]
 172
 173         clips = [
 174             {'start_time': parse_duration(c.get('time')), 'title': c.get('text')}
 175             for c in episode.get('clips') or []]
 176
 177         return {
 178             'id': display_id,
 179             'title': traverse_obj(program, ('episodes', 0, 'title'), 'title'),
 180             'description': traverse_obj(
 181                 program, ('episodes', 0, 'description'), 'description', 'short_description',
 182                 expected_type=lambda x: x or None),
 183             'subtitles': subs,
 184             'thumbnail': episode.get('image', '').replace('$$IMAGESIZE$$', '1960') or None,
 185             'timestamp': unified_timestamp(episode.get('firstrun')),
 186             'formats': formats,
 187             'age_limit': episode.get('rating'),
 188             'chapters': clips
 189         }