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_str
   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'http://(?:www\.)?nrk\.no/(?:video|lyd)/[^/]+/(?P<id>[\dA-F]{16})'
  18
  19     _TESTS = [
  20         {
  21             'url': 'http://www.nrk.no/video/dompap_og_andre_fugler_i_piip_show/D0FA54B5C8B6CE59/emne/piipshow/',
  22             'md5': 'a6eac35052f3b242bb6bb7f43aed5886',
  23             'info_dict': {
  24                 'id': '150533',
  25                 'ext': 'flv',
  26                 'title': 'Dompap og andre fugler i Piip-Show',
  27                 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f'
  28             }
  29         },
  30         {
  31             'url': 'http://www.nrk.no/lyd/lyd_av_oppleser_for_blinde/AEFDDD5473BA0198/',
  32             'md5': '3471f2a51718195164e88f46bf427668',
  33             'info_dict': {
  34                 'id': '154915',
  35                 'ext': 'flv',
  36                 'title': 'Slik høres internett ut når du er blind',
  37                 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
  38             }
  39         },
  40     ]
  41
  42     def _real_extract(self, url):
  43         mobj = re.match(self._VALID_URL, url)
  44         video_id = mobj.group('id')
  45
  46         page = self._download_webpage(url, video_id)
  47
  48         video_id = self._html_search_regex(r'<div class="nrk-video" data-nrk-id="(\d+)">', page, 'video id')
  49
  50         data = self._download_json(
  51             'http://v7.psapi.nrk.no/mediaelement/%s' % video_id, video_id, 'Downloading media JSON')
  52
  53         if data['usageRights']['isGeoBlocked']:
  54             raise ExtractorError('NRK har ikke rettig-heter til å vise dette programmet utenfor Norge', expected=True)
  55
  56         video_url = data['mediaUrl'] + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124'
  57
  58         images = data.get('images')
  59         if images:
  60             thumbnails = images['webImages']
  61             thumbnails.sort(key=lambda image: image['pixelWidth'])
  62             thumbnail = thumbnails[-1]['imageUrl']
  63         else:
  64             thumbnail = None
  65
  66         return {
  67             'id': video_id,
  68             'url': video_url,
  69             'ext': 'flv',
  70             'title': data['title'],
  71             'description': data['description'],
  72             'thumbnail': thumbnail,
  73         }
  74
  75
  76 class NRKTVIE(InfoExtractor):
  77     _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+))?'
  78
  79     _TESTS = [
  80         {
  81             'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
  82             'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
  83             'info_dict': {
  84                 'id': 'MUHH48000314',
  85                 'ext': 'flv',
  86                 'title': '20 spørsmål',
  87                 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
  88                 'upload_date': '20140523',
  89                 'duration': 1741.52,
  90             },
  91         },
  92         {
  93             'url': 'http://tv.nrk.no/program/mdfp15000514',
  94             'md5': '383650ece2b25ecec996ad7b5bb2a384',
  95             'info_dict': {
  96                 'id': 'mdfp15000514',
  97                 'ext': 'flv',
  98                 'title': 'Kunnskapskanalen: Grunnlovsjubiléet - Stor ståhei for ingenting',
  99                 'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
 100                 'upload_date': '20140524',
 101                 'duration': 4605.0,
 102             },
 103         },
 104         {
 105             # single playlist video
 106             'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
 107             'md5': 'adbd1dbd813edaf532b0a253780719c2',
 108             'info_dict': {
 109                 'id': 'MSPO40010515-part2',
 110                 'ext': 'flv',
 111                 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
 112                 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 113                 'upload_date': '20150106',
 114             },
 115             'skip': 'Only works from Norway',
 116         },
 117         {
 118             'url': 'http://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
 119             'playlist': [
 120                 {
 121                     'md5': '9480285eff92d64f06e02a5367970a7a',
 122                     'info_dict': {
 123                         'id': 'MSPO40010515-part1',
 124                         'ext': 'flv',
 125                         'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
 126                         'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 127                         'upload_date': '20150106',
 128                     },
 129                 },
 130                 {
 131                     'md5': 'adbd1dbd813edaf532b0a253780719c2',
 132                     'info_dict': {
 133                         'id': 'MSPO40010515-part2',
 134                         'ext': 'flv',
 135                         'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
 136                         'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 137                         'upload_date': '20150106',
 138                     },
 139                 },
 140             ],
 141             'info_dict': {
 142                 'id': 'MSPO40010515',
 143                 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
 144                 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 145                 'upload_date': '20150106',
 146                 'duration': 6947.5199999999995,
 147             },
 148             'skip': 'Only works from Norway',
 149         }
 150     ]
 151
 152     def _seconds2str(self, s):
 153         return '%02d:%02d:%02d.%03d' % (s / 3600, (s % 3600) / 60, s % 60, (s % 1) * 1000)
 154
 155     def _debug_print(self, txt):
 156         if self._downloader.params.get('verbose', False):
 157             self.to_screen('[debug] %s' % txt)
 158
 159     def _get_subtitles(self, subtitlesurl, video_id, baseurl):
 160         url = "%s%s" % (baseurl, subtitlesurl)
 161         self._debug_print('%s: Subtitle url: %s' % (video_id, url))
 162         captions = self._download_xml(
 163             url, video_id, 'Downloading subtitles',
 164             transform_source=lambda s: s.replace(r'<br />', '\r\n'))
 165         lang = captions.get('lang', 'no')
 166         ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/ns/ttml}'))
 167         srt = ''
 168         for pos, p in enumerate(ps):
 169             begin = parse_duration(p.get('begin'))
 170             duration = parse_duration(p.get('dur'))
 171             starttime = self._seconds2str(begin)
 172             endtime = self._seconds2str(begin + duration)
 173             srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (compat_str(pos), starttime, endtime, p.text)
 174         return {lang: [
 175             {'ext': 'ttml', 'url': url},
 176             {'ext': 'srt', 'data': srt},
 177         ]}
 178
 179     def _extract_f4m(self, manifest_url, video_id):
 180         return self._extract_f4m_formats(manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id)
 181
 182     def _real_extract(self, url):
 183         mobj = re.match(self._VALID_URL, url)
 184         video_id = mobj.group('id')
 185         part_id = mobj.group('part_id')
 186         baseurl = mobj.group('baseurl')
 187
 188         webpage = self._download_webpage(url, video_id)
 189
 190         title = self._html_search_meta(
 191             'title', webpage, 'title')
 192         description = self._html_search_meta(
 193             'description', webpage, 'description')
 194
 195         thumbnail = self._html_search_regex(
 196             r'data-posterimage="([^"]+)"',
 197             webpage, 'thumbnail', fatal=False)
 198         upload_date = unified_strdate(self._html_search_meta(
 199             'rightsfrom', webpage, 'upload date', fatal=False))
 200         duration = float_or_none(self._html_search_regex(
 201             r'data-duration="([^"]+)"',
 202             webpage, 'duration', fatal=False))
 203
 204         # playlist
 205         parts = re.findall(
 206             r'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage)
 207         if parts:
 208             entries = []
 209             for current_part_id, stream_url, part_title in parts:
 210                 if part_id and current_part_id != part_id:
 211                     continue
 212                 video_part_id = '%s-part%s' % (video_id, current_part_id)
 213                 formats = self._extract_f4m(stream_url, video_part_id)
 214                 entries.append({
 215                     'id': video_part_id,
 216                     'title': part_title,
 217                     'description': description,
 218                     'thumbnail': thumbnail,
 219                     'upload_date': upload_date,
 220                     'formats': formats,
 221                 })
 222             if part_id:
 223                 if entries:
 224                     return entries[0]
 225             else:
 226                 playlist = self.playlist_result(entries, video_id, title, description)
 227                 playlist.update({
 228                     'thumbnail': thumbnail,
 229                     'upload_date': upload_date,
 230                     'duration': duration,
 231                 })
 232                 return playlist
 233
 234         formats = []
 235
 236         f4m_url = re.search(r'data-media="([^"]+)"', webpage)
 237         if f4m_url:
 238             formats.extend(self._extract_f4m(f4m_url.group(1), video_id))
 239
 240         m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage)
 241         if m3u8_url:
 242             formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4'))
 243         self._sort_formats(formats)
 244
 245         subtitles_url = self._html_search_regex(
 246             r'data-subtitlesurl[ ]*=[ ]*"([^"]+)"',
 247             webpage, 'subtitle URL', default=None)
 248         subtitles = None
 249         if subtitles_url:
 250             subtitles = self.extract_subtitles(subtitles_url, video_id, baseurl)
 251
 252         return {
 253             'id': video_id,
 254             'title': title,
 255             'description': description,
 256             'thumbnail': thumbnail,
 257             'upload_date': upload_date,
 258             'duration': duration,
 259             'formats': formats,
 260             'subtitles': subtitles,
 261         }