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