_ 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 ..utils import (
   8     ExtractorError,
   9     float_or_none,
  10     parse_duration,
  11     unified_strdate,
  12 )
  13
  14
  15 class NRKIE(InfoExtractor):
  16     _VALID_URL = r'http://(?:www\.)?nrk\.no/(?:video|lyd)/[^/]+/(?P<id>[\dA-F]{16})'
  17
  18     _TESTS = [
  19         {
  20             'url': 'http://www.nrk.no/video/dompap_og_andre_fugler_i_piip_show/D0FA54B5C8B6CE59/emne/piipshow/',
  21             'md5': 'a6eac35052f3b242bb6bb7f43aed5886',
  22             'info_dict': {
  23                 'id': '150533',
  24                 'ext': 'flv',
  25                 'title': 'Dompap og andre fugler i Piip-Show',
  26                 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f'
  27             }
  28         },
  29         {
  30             'url': 'http://www.nrk.no/lyd/lyd_av_oppleser_for_blinde/AEFDDD5473BA0198/',
  31             'md5': '3471f2a51718195164e88f46bf427668',
  32             'info_dict': {
  33                 'id': '154915',
  34                 'ext': 'flv',
  35                 'title': 'Slik høres internett ut når du er blind',
  36                 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
  37             }
  38         },
  39     ]
  40
  41     def _real_extract(self, url):
  42         mobj = re.match(self._VALID_URL, url)
  43         video_id = mobj.group('id')
  44
  45         page = self._download_webpage(url, video_id)
  46
  47         video_id = self._html_search_regex(r'<div class="nrk-video" data-nrk-id="(\d+)">', page, 'video id')
  48
  49         data = self._download_json(
  50             'http://v7.psapi.nrk.no/mediaelement/%s' % video_id, video_id, 'Downloading media JSON')
  51
  52         if data['usageRights']['isGeoBlocked']:
  53             raise ExtractorError('NRK har ikke rettig-heter til å vise dette programmet utenfor Norge', expected=True)
  54
  55         video_url = data['mediaUrl'] + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124'
  56
  57         images = data.get('images')
  58         if images:
  59             thumbnails = images['webImages']
  60             thumbnails.sort(key=lambda image: image['pixelWidth'])
  61             thumbnail = thumbnails[-1]['imageUrl']
  62         else:
  63             thumbnail = None
  64
  65         return {
  66             'id': video_id,
  67             'url': video_url,
  68             'ext': 'flv',
  69             'title': data['title'],
  70             'description': data['description'],
  71             'thumbnail': thumbnail,
  72         }
  73
  74
  75 class NRKTVIE(InfoExtractor):
  76     _VALID_URL = r'(?P<baseurl>http://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
  77
  78     _TESTS = [
  79         {
  80             'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
  81             'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
  82             'info_dict': {
  83                 'id': 'MUHH48000314',
  84                 'ext': 'flv',
  85                 'title': '20 spørsmål',
  86                 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
  87                 'upload_date': '20140523',
  88                 'duration': 1741.52,
  89             },
  90         },
  91         {
  92             'url': 'http://tv.nrk.no/program/mdfp15000514',
  93             'md5': '383650ece2b25ecec996ad7b5bb2a384',
  94             'info_dict': {
  95                 'id': 'mdfp15000514',
  96                 'ext': 'flv',
  97                 'title': 'Kunnskapskanalen: Grunnlovsjubiléet - Stor ståhei for ingenting',
  98                 'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
  99                 'upload_date': '20140524',
 100                 'duration': 4605.0,
 101             },
 102         },
 103         {
 104             # single playlist video
 105             'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
 106             'md5': 'adbd1dbd813edaf532b0a253780719c2',
 107             'info_dict': {
 108                 'id': 'MSPO40010515-part2',
 109                 'ext': 'flv',
 110                 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
 111                 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 112                 'upload_date': '20150106',
 113             },
 114             'skip': 'Only works from Norway',
 115         },
 116         {
 117             'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
 118             'playlist': [
 119                 {
 120                     'md5': '9480285eff92d64f06e02a5367970a7a',
 121                     'info_dict': {
 122                         'id': 'MSPO40010515-part1',
 123                         'ext': 'flv',
 124                         'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
 125                         'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 126                         'upload_date': '20150106',
 127                     },
 128                 },
 129                 {
 130                     'md5': 'adbd1dbd813edaf532b0a253780719c2',
 131                     'info_dict': {
 132                         'id': 'MSPO40010515-part2',
 133                         'ext': 'flv',
 134                         'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
 135                         'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 136                         'upload_date': '20150106',
 137                     },
 138                 },
 139             ],
 140             'info_dict': {
 141                 'id': 'MSPO40010515',
 142                 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
 143                 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 144                 'upload_date': '20150106',
 145                 'duration': 6947.5199999999995,
 146             },
 147             'skip': 'Only works from Norway',
 148         }
 149     ]
 150
 151     def _seconds2str(self, s):
 152         return '%02d:%02d:%02d.%03d' % (s / 3600, (s % 3600) / 60, s % 60, (s % 1) * 1000)
 153
 154     def _debug_print(self, txt):
 155         if self._downloader.params.get('verbose', False):
 156             self.to_screen('[debug] %s' % txt)
 157
 158     def _get_subtitles(self, subtitlesurl, video_id, baseurl):
 159         url = "%s%s" % (baseurl, subtitlesurl)
 160         self._debug_print('%s: Subtitle url: %s' % (video_id, url))
 161         captions = self._download_xml(url, video_id, 'Downloading subtitles')
 162         lang = captions.get('lang', 'no')
 163         ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/ns/ttml}'))
 164         srt = ''
 165         for pos, p in enumerate(ps):
 166             begin = parse_duration(p.get('begin'))
 167             duration = parse_duration(p.get('dur'))
 168             starttime = self._seconds2str(begin)
 169             endtime = self._seconds2str(begin + duration)
 170             text = '\n'.join(p.itertext())
 171             srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), starttime, endtime, text)
 172         return {lang: [
 173             {'ext': 'ttml', 'url': url},
 174             {'ext': 'srt', 'data': srt},
 175         ]}
 176
 177     def _extract_f4m(self, manifest_url, video_id):
 178         return self._extract_f4m_formats(manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id)
 179
 180     def _real_extract(self, url):
 181         mobj = re.match(self._VALID_URL, url)
 182         video_id = mobj.group('id')
 183         part_id = mobj.group('part_id')
 184         baseurl = mobj.group('baseurl')
 185
 186         webpage = self._download_webpage(url, video_id)
 187
 188         title = self._html_search_meta(
 189             'title', webpage, 'title')
 190         description = self._html_search_meta(
 191             'description', webpage, 'description')
 192
 193         thumbnail = self._html_search_regex(
 194             r'data-posterimage="([^"]+)"',
 195             webpage, 'thumbnail', fatal=False)
 196         upload_date = unified_strdate(self._html_search_meta(
 197             'rightsfrom', webpage, 'upload date', fatal=False))
 198         duration = float_or_none(self._html_search_regex(
 199             r'data-duration="([^"]+)"',
 200             webpage, 'duration', fatal=False))
 201
 202         # playlist
 203         parts = re.findall(
 204             r'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage)
 205         if parts:
 206             entries = []
 207             for current_part_id, stream_url, part_title in parts:
 208                 if part_id and current_part_id != part_id:
 209                     continue
 210                 video_part_id = '%s-part%s' % (video_id, current_part_id)
 211                 formats = self._extract_f4m(stream_url, video_part_id)
 212                 entries.append({
 213                     'id': video_part_id,
 214                     'title': part_title,
 215                     'description': description,
 216                     'thumbnail': thumbnail,
 217                     'upload_date': upload_date,
 218                     'formats': formats,
 219                 })
 220             if part_id:
 221                 if entries:
 222                     return entries[0]
 223             else:
 224                 playlist = self.playlist_result(entries, video_id, title, description)
 225                 playlist.update({
 226                     'thumbnail': thumbnail,
 227                     'upload_date': upload_date,
 228                     'duration': duration,
 229                 })
 230                 return playlist
 231
 232         formats = []
 233
 234         f4m_url = re.search(r'data-media="([^"]+)"', webpage)
 235         if f4m_url:
 236             formats.extend(self._extract_f4m(f4m_url.group(1), video_id))
 237
 238         m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage)
 239         if m3u8_url:
 240             formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4'))
 241         self._sort_formats(formats)
 242
 243         subtitles_url = self._html_search_regex(
 244             r'data-subtitlesurl[ ]*=[ ]*"([^"]+)"',
 245             webpage, 'subtitle URL', default=None)
 246         subtitles = None
 247         if subtitles_url:
 248             subtitles = self.extract_subtitles(subtitles_url, video_id, baseurl)
 249
 250         return {
 251             'id': video_id,
 252             'title': title,
 253             'description': description,
 254             'thumbnail': thumbnail,
 255             'upload_date': upload_date,
 256             'duration': duration,
 257             'formats': formats,
 258             'subtitles': subtitles,
 259         }