youtube_dl/extractor/srgssr.py

   1 # coding: 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     parse_iso8601,
  10     qualities,
  11 )
  12
  13
  14 class SRGSSRIE(InfoExtractor):
  15     _VALID_URL = r'(?:https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|srgssr):(?P<bu>srf|rts|rsi|rtr|swi):(?:[^:]+:)?(?P<type>video|audio):(?P<id>[0-9a-f\-]{36}|\d+)'
  16
  17     _ERRORS = {
  18         'AGERATING12': 'To protect children under the age of 12, this video is only available between 8 p.m. and 6 a.m.',
  19         'AGERATING18': 'To protect children under the age of 18, this video is only available between 11 p.m. and 5 a.m.',
  20         # 'ENDDATE': 'For legal reasons, this video was only available for a specified period of time.',
  21         'GEOBLOCK': 'For legal reasons, this video is only available in Switzerland.',
  22         'LEGAL': 'The video cannot be transmitted for legal reasons.',
  23         'STARTDATE': 'This video is not yet available. Please try again later.',
  24     }
  25
  26     def get_media_data(self, bu, media_type, media_id):
  27         media_data = self._download_json(
  28             'http://il.srgssr.ch/integrationlayer/1.0/ue/%s/%s/play/%s.json' % (bu, media_type, media_id),
  29             media_id)[media_type.capitalize()]
  30
  31         if media_data.get('block') and media_data['block'] in self._ERRORS:
  32             raise ExtractorError('%s said: %s' % (
  33                 self.IE_NAME, self._ERRORS[media_data['block']]), expected=True)
  34
  35         return media_data
  36
  37     def _real_extract(self, url):
  38         bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
  39
  40         if bu == 'rts':
  41             return self.url_result('rts:%s' % media_id, 'RTS')
  42
  43         media_data = self.get_media_data(bu, media_type, media_id)
  44
  45         metadata = media_data['AssetMetadatas']['AssetMetadata'][0]
  46         title = metadata['title']
  47         description = metadata.get('description')
  48         created_date = media_data.get('createdDate') or metadata.get('createdDate')
  49         timestamp = parse_iso8601(created_date)
  50
  51         thumbnails = [{
  52             'id': image.get('id'),
  53             'url': image['url'],
  54         } for image in media_data.get('Image', {}).get('ImageRepresentations', {}).get('ImageRepresentation', [])]
  55
  56         preference = qualities(['LQ', 'MQ', 'SD', 'HQ', 'HD'])
  57         formats = []
  58         for source in media_data.get('Playlists', {}).get('Playlist', []) + media_data.get('Downloads', {}).get('Download', []):
  59             protocol = source.get('@protocol')
  60             for asset in source['url']:
  61                 asset_url = asset['text']
  62                 quality = asset['@quality']
  63                 format_id = '%s-%s' % (protocol, quality)
  64                 if protocol == 'HTTP-HDS':
  65                     formats.extend(self._extract_f4m_formats(
  66                         asset_url + '?hdcore=3.4.0', media_id,
  67                         f4m_id=format_id, fatal=False))
  68                 elif protocol == 'HTTP-HLS':
  69                     formats.extend(self._extract_m3u8_formats(
  70                         asset_url, media_id, 'mp4', 'm3u8_native',
  71                         m3u8_id=format_id, fatal=False))
  72                 else:
  73                     ext = None
  74                     if protocol == 'RTMP':
  75                         ext = self._search_regex(r'([a-z0-9]+):[^/]+', asset_url, 'ext')
  76                     formats.append({
  77                         'format_id': format_id,
  78                         'url': asset_url,
  79                         'preference': preference(quality),
  80                         'ext': ext,
  81                     })
  82         self._sort_formats(formats)
  83
  84         return {
  85             'id': media_id,
  86             'title': title,
  87             'description': description,
  88             'timestamp': timestamp,
  89             'thumbnails': thumbnails,
  90             'formats': formats,
  91         }
  92
  93
  94 class SRGSSRPlayIE(InfoExtractor):
  95     IE_DESC = 'srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites'
  96     _VALID_URL = r'https?://(?:(?:www|play)\.)?(?P<bu>srf|rts|rsi|rtr|swissinfo)\.ch/play/(?:tv|radio)/[^/]+/(?P<type>video|audio)/[^?]+\?id=(?P<id>[0-9a-f\-]{36}|\d+)'
  97
  98     _TESTS = [{
  99         'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
 100         'md5': '4cd93523723beff51bb4bee974ee238d',
 101         'info_dict': {
 102             'id': '28e1a57d-5b76-4399-8ab3-9097f071e6c5',
 103             'ext': 'm4v',
 104             'upload_date': '20130701',
 105             'title': 'Snowden beantragt Asyl in Russland',
 106             'timestamp': 1372713995,
 107         }
 108     }, {
 109         # No Speichern (Save) button
 110         'url': 'http://www.srf.ch/play/tv/top-gear/video/jaguar-xk120-shadow-und-tornado-dampflokomotive?id=677f5829-e473-4823-ac83-a1087fe97faa',
 111         'md5': '0a274ce38fda48c53c01890651985bc6',
 112         'info_dict': {
 113             'id': '677f5829-e473-4823-ac83-a1087fe97faa',
 114             'ext': 'flv',
 115             'upload_date': '20130710',
 116             'title': 'Jaguar XK120, Shadow und Tornado-Dampflokomotive',
 117             'description': 'md5:88604432b60d5a38787f152dec89cd56',
 118             'timestamp': 1373493600,
 119         },
 120     }, {
 121         'url': 'http://www.rtr.ch/play/radio/actualitad/audio/saira-tujetsch-tuttina-cuntinuar-cun-sedrun-muster-turissem?id=63cb0778-27f8-49af-9284-8c7a8c6d15fc',
 122         'info_dict': {
 123             'id': '63cb0778-27f8-49af-9284-8c7a8c6d15fc',
 124             'ext': 'mp3',
 125             'upload_date': '20151013',
 126             'title': 'Saira: Tujetsch - tuttina cuntinuar cun Sedrun Mustér Turissem',
 127             'timestamp': 1444750398,
 128         },
 129         'params': {
 130             # rtmp download
 131             'skip_download': True,
 132         },
 133     }, {
 134         'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260',
 135         'md5': '67a2a9ae4e8e62a68d0e9820cc9782df',
 136         'info_dict': {
 137             'id': '6348260',
 138             'display_id': '6348260',
 139             'ext': 'mp4',
 140             'duration': 1796,
 141             'title': 'Le 19h30',
 142             'description': '',
 143             'uploader': '19h30',
 144             'upload_date': '20141201',
 145             'timestamp': 1417458600,
 146             'thumbnail': 're:^https?://.*\.image',
 147             'view_count': int,
 148         },
 149         'params': {
 150             # m3u8 download
 151             'skip_download': True,
 152         }
 153     }]
 154
 155     def _real_extract(self, url):
 156         bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
 157         # other info can be extracted from url + '&layout=json'
 158         return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR')