Raphaël G. Git Repositories - youtubedl/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     ExtractorError,
  10     float_or_none,
  11     parse_duration,
  12     unified_strdate,
  13 )
  14
  15
  16 class NRKIE(InfoExtractor):
  17     _VALID_URL = r'(?:nrk:|https?://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
  18
  19     _TESTS = [
  20         {
  21             'url': 'http://www.nrk.no/video/PS*150533',
  22             'md5': 'bccd850baebefe23b56d708a113229c2',
  23             'info_dict': {
  24                 'id': '150533',
  25                 'ext': 'flv',
  26                 'title': 'Dompap og andre fugler i Piip-Show',
  27                 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
  28                 'duration': 263,
  29             }
  30         },
  31         {
  32             'url': 'http://www.nrk.no/video/PS*154915',
  33             'md5': '0b1493ba1aae7d9579a5ad5531bc395a',
  34             'info_dict': {
  35                 'id': '154915',
  36                 'ext': 'flv',
  37                 'title': 'Slik høres internett ut når du er blind',
  38                 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
  39                 'duration': 20,
  40             }
  41         },
  42     ]
  43
  44     def _real_extract(self, url):
  45         video_id = self._match_id(url)
  46
  47         data = self._download_json(
  48             'http://v8.psapi.nrk.no/mediaelement/%s' % video_id,
  49             video_id, 'Downloading media JSON')
  50
  51         if data['usageRights']['isGeoBlocked']:
  52             raise ExtractorError(
  53                 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
  54                 expected=True)
  55
  56         video_url = data['mediaUrl'] + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81'
  57
  58         duration = parse_duration(data.get('duration'))
  59
  60         images = data.get('images')
  61         if images:
  62             thumbnails = images['webImages']
  63             thumbnails.sort(key=lambda image: image['pixelWidth'])
  64             thumbnail = thumbnails[-1]['imageUrl']
  65         else:
  66             thumbnail = None
  67
  68         return {
  69             'id': video_id,
  70             'url': video_url,
  71             'ext': 'flv',
  72             'title': data['title'],
  73             'description': data['description'],
  74             'duration': duration,
  75             'thumbnail': thumbnail,
  76         }
  77
  78
  79 class NRKPlaylistIE(InfoExtractor):
  80     _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
  81
  82     _TESTS = [{
  83         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
  84         'info_dict': {
  85             'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
  86             'title': 'Gjenopplev den historiske solformørkelsen',
  87             'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
  88         },
  89         'playlist_count': 2,
  90     }, {
  91         'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
  92         'info_dict': {
  93             'id': 'rivertonprisen-til-karin-fossum-1.12266449',
  94             'title': 'Rivertonprisen til Karin Fossum',
  95             'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
  96         },
  97         'playlist_count': 5,
  98     }]
  99
 100     def _real_extract(self, url):
 101         playlist_id = self._match_id(url)
 102
 103         webpage = self._download_webpage(url, playlist_id)
 104
 105         entries = [
 106             self.url_result('nrk:%s' % video_id, 'NRK')
 107             for video_id in re.findall(
 108                 r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
 109                 webpage)
 110         ]
 111
 112         playlist_title = self._og_search_title(webpage)
 113         playlist_description = self._og_search_description(webpage)
 114
 115         return self.playlist_result(
 116             entries, playlist_id, playlist_title, playlist_description)
 117
 118
 119 class NRKTVIE(InfoExtractor):
 120     IE_DESC = 'NRK TV and NRK Radio'
 121     _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+))?'
 122
 123     _TESTS = [
 124         {
 125             'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
 126             'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
 127             'info_dict': {
 128                 'id': 'MUHH48000314',
 129                 'ext': 'flv',
 130                 'title': '20 spørsmål',
 131                 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
 132                 'upload_date': '20140523',
 133                 'duration': 1741.52,
 134             },
 135         },
 136         {
 137             'url': 'https://tv.nrk.no/program/mdfp15000514',
 138             'md5': '383650ece2b25ecec996ad7b5bb2a384',
 139             'info_dict': {
 140                 'id': 'mdfp15000514',
 141                 'ext': 'flv',
 142                 'title': 'Kunnskapskanalen: Grunnlovsjubiléet - Stor ståhei for ingenting',
 143                 'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
 144                 'upload_date': '20140524',
 145                 'duration': 4605.0,
 146             },
 147         },
 148         {
 149             # single playlist video
 150             'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
 151             'md5': 'adbd1dbd813edaf532b0a253780719c2',
 152             'info_dict': {
 153                 'id': 'MSPO40010515-part2',
 154                 'ext': 'flv',
 155                 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
 156                 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 157                 'upload_date': '20150106',
 158             },
 159             'skip': 'Only works from Norway',
 160         },
 161         {
 162             'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
 163             'playlist': [
 164                 {
 165                     'md5': '9480285eff92d64f06e02a5367970a7a',
 166                     'info_dict': {
 167                         'id': 'MSPO40010515-part1',
 168                         'ext': 'flv',
 169                         'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
 170                         'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 171                         'upload_date': '20150106',
 172                     },
 173                 },
 174                 {
 175                     'md5': 'adbd1dbd813edaf532b0a253780719c2',
 176                     'info_dict': {
 177                         'id': 'MSPO40010515-part2',
 178                         'ext': 'flv',
 179                         'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
 180                         'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 181                         'upload_date': '20150106',
 182                     },
 183                 },
 184             ],
 185             'info_dict': {
 186                 'id': 'MSPO40010515',
 187                 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
 188                 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 189                 'upload_date': '20150106',
 190                 'duration': 6947.5199999999995,
 191             },
 192             'skip': 'Only works from Norway',
 193         },
 194         {
 195             'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
 196             'only_matching': True,
 197         }
 198     ]
 199
 200     def _extract_f4m(self, manifest_url, video_id):
 201         return self._extract_f4m_formats(
 202             manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id, f4m_id='hds')
 203
 204     def _real_extract(self, url):
 205         mobj = re.match(self._VALID_URL, url)
 206         video_id = mobj.group('id')
 207         part_id = mobj.group('part_id')
 208         base_url = mobj.group('baseurl')
 209
 210         webpage = self._download_webpage(url, video_id)
 211
 212         title = self._html_search_meta(
 213             'title', webpage, 'title')
 214         description = self._html_search_meta(
 215             'description', webpage, 'description')
 216
 217         thumbnail = self._html_search_regex(
 218             r'data-posterimage="([^"]+)"',
 219             webpage, 'thumbnail', fatal=False)
 220         upload_date = unified_strdate(self._html_search_meta(
 221             'rightsfrom', webpage, 'upload date', fatal=False))
 222         duration = float_or_none(self._html_search_regex(
 223             r'data-duration="([^"]+)"',
 224             webpage, 'duration', fatal=False))
 225
 226         # playlist
 227         parts = re.findall(
 228             r'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage)
 229         if parts:
 230             entries = []
 231             for current_part_id, stream_url, part_title in parts:
 232                 if part_id and current_part_id != part_id:
 233                     continue
 234                 video_part_id = '%s-part%s' % (video_id, current_part_id)
 235                 formats = self._extract_f4m(stream_url, video_part_id)
 236                 entries.append({
 237                     'id': video_part_id,
 238                     'title': part_title,
 239                     'description': description,
 240                     'thumbnail': thumbnail,
 241                     'upload_date': upload_date,
 242                     'formats': formats,
 243                 })
 244             if part_id:
 245                 if entries:
 246                     return entries[0]
 247             else:
 248                 playlist = self.playlist_result(entries, video_id, title, description)
 249                 playlist.update({
 250                     'thumbnail': thumbnail,
 251                     'upload_date': upload_date,
 252                     'duration': duration,
 253                 })
 254                 return playlist
 255
 256         formats = []
 257
 258         f4m_url = re.search(r'data-media="([^"]+)"', webpage)
 259         if f4m_url:
 260             formats.extend(self._extract_f4m(f4m_url.group(1), video_id))
 261
 262         m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage)
 263         if m3u8_url:
 264             formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4', m3u8_id='hls'))
 265         self._sort_formats(formats)
 266
 267         subtitles_url = self._html_search_regex(
 268             r'data-subtitlesurl\s*=\s*(["\'])(?P<url>.+?)\1',
 269             webpage, 'subtitle URL', default=None, group='url')
 270         subtitles = {}
 271         if subtitles_url:
 272             subtitles['no'] = [{
 273                 'ext': 'ttml',
 274                 'url': compat_urlparse.urljoin(base_url, subtitles_url),
 275             }]
 276
 277         return {
 278             'id': video_id,
 279             'title': title,
 280             'description': description,
 281             'thumbnail': thumbnail,
 282             'upload_date': upload_date,
 283             'duration': duration,
 284             'formats': formats,
 285             'subtitles': subtitles,
 286         }