_ Git - youtube-dl/blob - youtube_dl/extractor/nrk.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_urlparse
   8 from ..utils import (
   9     determine_ext,
  10     ExtractorError,
  11     float_or_none,
  12     parse_duration,
  13     unified_strdate,
  14 )
  15
  16
  17 class NRKIE(InfoExtractor):
  18     _VALID_URL = r'(?:nrk:|https?://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
  19
  20     _TESTS = [
  21         {
  22             'url': 'http://www.nrk.no/video/PS*150533',
  23             'md5': 'bccd850baebefe23b56d708a113229c2',
  24             'info_dict': {
  25                 'id': '150533',
  26                 'ext': 'flv',
  27                 'title': 'Dompap og andre fugler i Piip-Show',
  28                 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
  29                 'duration': 263,
  30             }
  31         },
  32         {
  33             'url': 'http://www.nrk.no/video/PS*154915',
  34             'md5': '0b1493ba1aae7d9579a5ad5531bc395a',
  35             'info_dict': {
  36                 'id': '154915',
  37                 'ext': 'flv',
  38                 'title': 'Slik høres internett ut når du er blind',
  39                 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
  40                 'duration': 20,
  41             }
  42         },
  43     ]
  44
  45     def _real_extract(self, url):
  46         video_id = self._match_id(url)
  47
  48         data = self._download_json(
  49             'http://v8.psapi.nrk.no/mediaelement/%s' % video_id,
  50             video_id, 'Downloading media JSON')
  51
  52         media_url = data.get('mediaUrl')
  53
  54         if not media_url:
  55             if data['usageRights']['isGeoBlocked']:
  56                 raise ExtractorError(
  57                     'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
  58                     expected=True)
  59
  60         if determine_ext(media_url) == 'f4m':
  61             formats = self._extract_f4m_formats(
  62                 media_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id, f4m_id='hds')
  63         else:
  64             formats = [{
  65                 'url': media_url,
  66                 'ext': 'flv',
  67             }]
  68
  69         duration = parse_duration(data.get('duration'))
  70
  71         images = data.get('images')
  72         if images:
  73             thumbnails = images['webImages']
  74             thumbnails.sort(key=lambda image: image['pixelWidth'])
  75             thumbnail = thumbnails[-1]['imageUrl']
  76         else:
  77             thumbnail = None
  78
  79         return {
  80             'id': video_id,
  81             'title': data['title'],
  82             'description': data['description'],
  83             'duration': duration,
  84             'thumbnail': thumbnail,
  85             'formats': formats,
  86         }
  87
  88
  89 class NRKPlaylistIE(InfoExtractor):
  90     _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
  91
  92     _TESTS = [{
  93         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
  94         'info_dict': {
  95             'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
  96             'title': 'Gjenopplev den historiske solformørkelsen',
  97             'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
  98         },
  99         'playlist_count': 2,
 100     }, {
 101         'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
 102         'info_dict': {
 103             'id': 'rivertonprisen-til-karin-fossum-1.12266449',
 104             'title': 'Rivertonprisen til Karin Fossum',
 105             'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
 106         },
 107         'playlist_count': 5,
 108     }]
 109
 110     def _real_extract(self, url):
 111         playlist_id = self._match_id(url)
 112
 113         webpage = self._download_webpage(url, playlist_id)
 114
 115         entries = [
 116             self.url_result('nrk:%s' % video_id, 'NRK')
 117             for video_id in re.findall(
 118                 r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
 119                 webpage)
 120         ]
 121
 122         playlist_title = self._og_search_title(webpage)
 123         playlist_description = self._og_search_description(webpage)
 124
 125         return self.playlist_result(
 126             entries, playlist_id, playlist_title, playlist_description)
 127
 128
 129 class NRKSkoleIE(InfoExtractor):
 130     IE_DESC = 'NRK Skole'
 131     _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/klippdetalj?.*\btopic=nrk(?::|%3[Aa])klipp(?:/|%2[Ff])(?P<id>\d+)'
 132
 133     _TESTS = [{
 134         'url': 'http://nrk.no/skole/klippdetalj?topic=nrk:klipp/616532',
 135         'md5': '04cd85877cc1913bce73c5d28a47e00f',
 136         'info_dict': {
 137             'id': '6021',
 138             'ext': 'flv',
 139             'title': 'Genetikk og eneggede tvillinger',
 140             'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
 141             'duration': 399,
 142         },
 143     }, {
 144         'url': 'http://www.nrk.no/skole/klippdetalj?topic=nrk%3Aklipp%2F616532#embed',
 145         'only_matching': True,
 146     }]
 147
 148     def _real_extract(self, url):
 149         video_id = self._match_id(url)
 150
 151         webpage = self._download_webpage(url, video_id)
 152
 153         nrk_id = self._search_regex(r'data-nrk-id=["\'](\d+)', webpage, 'nrk id')
 154         return self.url_result('nrk:%s' % nrk_id)
 155
 156
 157 class NRKTVIE(InfoExtractor):
 158     IE_DESC = 'NRK TV and NRK Radio'
 159     _VALID_URL = r'(?P<baseurl>https?://(?:tv|radio)\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
 160
 161     _TESTS = [
 162         {
 163             'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
 164             'info_dict': {
 165                 'id': 'MUHH48000314',
 166                 'ext': 'mp4',
 167                 'title': '20 spørsmål',
 168                 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
 169                 'upload_date': '20140523',
 170                 'duration': 1741.52,
 171             },
 172             'params': {
 173                 # m3u8 download
 174                 'skip_download': True,
 175             },
 176         },
 177         {
 178             'url': 'https://tv.nrk.no/program/mdfp15000514',
 179             'info_dict': {
 180                 'id': 'mdfp15000514',
 181                 'ext': 'mp4',
 182                 'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting',
 183                 'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
 184                 'upload_date': '20140524',
 185                 'duration': 4605.08,
 186             },
 187             'params': {
 188                 # m3u8 download
 189                 'skip_download': True,
 190             },
 191         },
 192         {
 193             # single playlist video
 194             'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
 195             'md5': 'adbd1dbd813edaf532b0a253780719c2',
 196             'info_dict': {
 197                 'id': 'MSPO40010515-part2',
 198                 'ext': 'flv',
 199                 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
 200                 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 201                 'upload_date': '20150106',
 202             },
 203             'skip': 'Only works from Norway',
 204         },
 205         {
 206             'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
 207             'playlist': [
 208                 {
 209                     'md5': '9480285eff92d64f06e02a5367970a7a',
 210                     'info_dict': {
 211                         'id': 'MSPO40010515-part1',
 212                         'ext': 'flv',
 213                         'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
 214                         'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 215                         'upload_date': '20150106',
 216                     },
 217                 },
 218                 {
 219                     'md5': 'adbd1dbd813edaf532b0a253780719c2',
 220                     'info_dict': {
 221                         'id': 'MSPO40010515-part2',
 222                         'ext': 'flv',
 223                         'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
 224                         'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 225                         'upload_date': '20150106',
 226                     },
 227                 },
 228             ],
 229             'info_dict': {
 230                 'id': 'MSPO40010515',
 231                 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
 232                 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 233                 'upload_date': '20150106',
 234                 'duration': 6947.5199999999995,
 235             },
 236             'skip': 'Only works from Norway',
 237         },
 238         {
 239             'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
 240             'only_matching': True,
 241         }
 242     ]
 243
 244     def _extract_f4m(self, manifest_url, video_id):
 245         return self._extract_f4m_formats(
 246             manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id, f4m_id='hds')
 247
 248     def _real_extract(self, url):
 249         mobj = re.match(self._VALID_URL, url)
 250         video_id = mobj.group('id')
 251         part_id = mobj.group('part_id')
 252         base_url = mobj.group('baseurl')
 253
 254         webpage = self._download_webpage(url, video_id)
 255
 256         title = self._html_search_meta(
 257             'title', webpage, 'title')
 258         description = self._html_search_meta(
 259             'description', webpage, 'description')
 260
 261         thumbnail = self._html_search_regex(
 262             r'data-posterimage="([^"]+)"',
 263             webpage, 'thumbnail', fatal=False)
 264         upload_date = unified_strdate(self._html_search_meta(
 265             'rightsfrom', webpage, 'upload date', fatal=False))
 266         duration = float_or_none(self._html_search_regex(
 267             r'data-duration="([^"]+)"',
 268             webpage, 'duration', fatal=False))
 269
 270         # playlist
 271         parts = re.findall(
 272             r'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage)
 273         if parts:
 274             entries = []
 275             for current_part_id, stream_url, part_title in parts:
 276                 if part_id and current_part_id != part_id:
 277                     continue
 278                 video_part_id = '%s-part%s' % (video_id, current_part_id)
 279                 formats = self._extract_f4m(stream_url, video_part_id)
 280                 entries.append({
 281                     'id': video_part_id,
 282                     'title': part_title,
 283                     'description': description,
 284                     'thumbnail': thumbnail,
 285                     'upload_date': upload_date,
 286                     'formats': formats,
 287                 })
 288             if part_id:
 289                 if entries:
 290                     return entries[0]
 291             else:
 292                 playlist = self.playlist_result(entries, video_id, title, description)
 293                 playlist.update({
 294                     'thumbnail': thumbnail,
 295                     'upload_date': upload_date,
 296                     'duration': duration,
 297                 })
 298                 return playlist
 299
 300         formats = []
 301
 302         f4m_url = re.search(r'data-media="([^"]+)"', webpage)
 303         if f4m_url:
 304             formats.extend(self._extract_f4m(f4m_url.group(1), video_id))
 305
 306         m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage)
 307         if m3u8_url:
 308             formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4', m3u8_id='hls'))
 309         self._sort_formats(formats)
 310
 311         subtitles_url = self._html_search_regex(
 312             r'data-subtitlesurl\s*=\s*(["\'])(?P<url>.+?)\1',
 313             webpage, 'subtitle URL', default=None, group='url')
 314         subtitles = {}
 315         if subtitles_url:
 316             subtitles['no'] = [{
 317                 'ext': 'ttml',
 318                 'url': compat_urlparse.urljoin(base_url, subtitles_url),
 319             }]
 320
 321         return {
 322             'id': video_id,
 323             'title': title,
 324             'description': description,
 325             'thumbnail': thumbnail,
 326             'upload_date': upload_date,
 327             'duration': duration,
 328             'formats': formats,
 329             'subtitles': subtitles,
 330         }