_ Git - youtube-dl/blob - youtube_dl/extractor/rai.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_urlparse
   5 from ..utils import (
   6     determine_ext,
   7     ExtractorError,
   8     find_xpath_attr,
   9     fix_xml_ampersands,
  10     int_or_none,
  11     parse_duration,
  12     unified_strdate,
  13     update_url_query,
  14     xpath_text,
  15 )
  16
  17
  18 class RaiTVIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/(?:[^/]+/)+media/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
  20     _TESTS = [
  21         {
  22             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
  23             'md5': '8970abf8caf8aef4696e7b1f2adfc696',
  24             'info_dict': {
  25                 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
  26                 'ext': 'mp4',
  27                 'title': 'Report del 07/04/2014',
  28                 'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
  29                 'upload_date': '20140407',
  30                 'duration': 6160,
  31                 'thumbnail': 're:^https?://.*\.jpg$',
  32             }
  33         },
  34         {
  35             # no m3u8 stream
  36             'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
  37             # HDS download, MD5 is unstable
  38             'info_dict': {
  39                 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
  40                 'ext': 'flv',
  41                 'title': 'TG PRIMO TEMPO',
  42                 'upload_date': '20140612',
  43                 'duration': 1758,
  44                 'thumbnail': 're:^https?://.*\.jpg$',
  45             },
  46             'skip': 'Geo-restricted to Italy',
  47         },
  48         {
  49             'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',
  50             'md5': '35cf7c229f22eeef43e48b5cf923bef0',
  51             'info_dict': {
  52                 'id': '7aafdea9-0e5d-49d5-88a6-7e65da67ae13',
  53                 'ext': 'mp4',
  54                 'title': 'State of the Net, Antonella La Carpia: regole virali',
  55                 'description': 'md5:b0ba04a324126903e3da7763272ae63c',
  56                 'upload_date': '20140613',
  57             },
  58             'skip': 'Error 404',
  59         },
  60         {
  61             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
  62             'info_dict': {
  63                 'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
  64                 'ext': 'mp4',
  65                 'title': 'Alluvione in Sardegna e dissesto idrogeologico',
  66                 'description': 'Edizione delle ore 20:30 ',
  67             },
  68             'skip': 'invalid urls',
  69         },
  70         {
  71             'url': 'http://www.ilcandidato.rai.it/dl/ray/media/Il-Candidato---Primo-episodio-Le-Primarie-28e5525a-b495-45e8-a7c3-bc48ba45d2b6.html',
  72             'md5': 'e57493e1cb8bc7c564663f363b171847',
  73             'info_dict': {
  74                 'id': '28e5525a-b495-45e8-a7c3-bc48ba45d2b6',
  75                 'ext': 'mp4',
  76                 'title': 'Il Candidato - Primo episodio: "Le Primarie"',
  77                 'description': 'md5:364b604f7db50594678f483353164fb8',
  78                 'upload_date': '20140923',
  79                 'duration': 386,
  80                 'thumbnail': 're:^https?://.*\.jpg$',
  81             }
  82         },
  83     ]
  84
  85     def _real_extract(self, url):
  86         video_id = self._match_id(url)
  87
  88         media = self._download_json(
  89             'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % video_id,
  90             video_id, 'Downloading video JSON')
  91
  92         thumbnails = []
  93         for image_type in ('image', 'image_medium', 'image_300'):
  94             thumbnail_url = media.get(image_type)
  95             if thumbnail_url:
  96                 thumbnails.append({
  97                     'url': compat_urlparse.urljoin(url, thumbnail_url),
  98                 })
  99
 100         formats = []
 101         media_type = media['type']
 102         if 'Audio' in media_type:
 103             formats.append({
 104                 'format_id': media.get('formatoAudio'),
 105                 'url': media['audioUrl'],
 106                 'ext': media.get('formatoAudio'),
 107             })
 108         elif 'Video' in media_type:
 109             for platform in ('mon', 'flash', 'native'):
 110                 headers = {}
 111                 # TODO: rename --cn-verification-proxy
 112                 cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
 113                 if cn_verification_proxy:
 114                     headers['Ytdl-request-proxy'] = cn_verification_proxy
 115
 116                 relinker = self._download_xml(
 117                     media['mediaUri'], video_id,
 118                     note='Downloading XML metadata for platform %s' % platform,
 119                     transform_source=fix_xml_ampersands,
 120                     query={'output': 45, 'pl': platform}, headers=headers)
 121
 122                 media_url = find_xpath_attr(relinker, './url', 'type', 'content').text
 123                 if media_url == 'http://download.rai.it/video_no_available.mp4':
 124                     self.raise_geo_restricted()
 125
 126                 ext = determine_ext(media_url)
 127                 if (platform == 'mon' and ext != 'm3u8') or (platform == 'flash' and ext != 'f4m'):
 128                     continue
 129
 130                 if ext == 'm3u8':
 131                     formats.extend(self._extract_m3u8_formats(
 132                         media_url, video_id, 'mp4', 'm3u8_native',
 133                         m3u8_id='hls', fatal=False))
 134                 elif ext == 'f4m':
 135                     manifest_url = update_url_query(
 136                         media_url, {'hdcore': '3.7.0', 'plugin': 'aasp-3.7.0.39.44'})
 137                     formats.extend(self._extract_f4m_formats(
 138                         manifest_url, video_id, f4m_id='hds', fatal=False))
 139                 else:
 140                     bitrate = int_or_none(xpath_text(relinker, 'bitrate'))
 141                     formats.append({
 142                         'url': media_url,
 143                         'tbr': bitrate if bitrate > 0 else None,
 144                         'format_id': 'http-%d' % bitrate if bitrate > 0 else 'http',
 145                     })
 146
 147             self._sort_formats(formats)
 148         else:
 149             raise ExtractorError('not a media file')
 150
 151         subtitles = {}
 152         captions = media.get('subtitlesUrl')
 153         if captions:
 154             STL_EXT = '.stl'
 155             SRT_EXT = '.srt'
 156             if captions.endswith(STL_EXT):
 157                 captions = captions[:-len(STL_EXT)] + SRT_EXT
 158             subtitles['it'] = [{
 159                 'ext': 'srt',
 160                 'url': captions,
 161             }]
 162
 163         return {
 164             'id': video_id,
 165             'title': media['name'],
 166             'description': media.get('desc'),
 167             'thumbnails': thumbnails,
 168             'uploader': media.get('author'),
 169             'upload_date': unified_strdate(media.get('date')),
 170             'duration': parse_duration(media.get('length')),
 171             'formats': formats,
 172             'subtitles': subtitles,
 173         }
 174
 175
 176 class RaiIE(InfoExtractor):
 177     _VALID_URL = r'https?://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
 178     _TESTS = [
 179         {
 180             'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
 181             'md5': '2dd727e61114e1ee9c47f0da6914e178',
 182             'info_dict': {
 183                 'id': '59d69d28-6bb6-409d-a4b5-ed44096560af',
 184                 'ext': 'mp4',
 185                 'title': 'Il pacco',
 186                 'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a',
 187                 'upload_date': '20141221',
 188             },
 189         }
 190     ]
 191
 192     @classmethod
 193     def suitable(cls, url):
 194         return False if RaiTVIE.suitable(url) else super(RaiIE, cls).suitable(url)
 195
 196     def _real_extract(self, url):
 197         video_id = self._match_id(url)
 198         webpage = self._download_webpage(url, video_id)
 199
 200         iframe_url = self._search_regex(
 201             [r'<iframe[^>]+src="([^"]*/dl/[^"]+\?iframe\b[^"]*)"',
 202              r'drawMediaRaiTV\(["\'](.+?)["\']'],
 203             webpage, 'iframe')
 204         if not iframe_url.startswith('http'):
 205             iframe_url = compat_urlparse.urljoin(url, iframe_url)
 206         return self.url_result(iframe_url)