youtube_dl/extractor/rai.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_urllib_parse,
   8     compat_urlparse,
   9 )
  10 from ..utils import (
  11     ExtractorError,
  12     determine_ext,
  13     parse_duration,
  14     unified_strdate,
  15     int_or_none,
  16     xpath_text,
  17 )
  18
  19
  20 class RaiTVIE(InfoExtractor):
  21     _VALID_URL = r'http://(?:.+?\.)?(?: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'
  22     _TESTS = [
  23         {
  24             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
  25             'md5': '96382709b61dd64a6b88e0f791e6df4c',
  26             'info_dict': {
  27                 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
  28                 'ext': 'flv',
  29                 'title': 'Report del 07/04/2014',
  30                 'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
  31                 'upload_date': '20140407',
  32                 'duration': 6160,
  33             }
  34         },
  35         {
  36             'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
  37             'md5': 'd9751b78eac9710d62c2447b224dea39',
  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             },
  45         },
  46         {
  47             'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',
  48             'md5': '35cf7c229f22eeef43e48b5cf923bef0',
  49             'info_dict': {
  50                 'id': '7aafdea9-0e5d-49d5-88a6-7e65da67ae13',
  51                 'ext': 'mp4',
  52                 'title': 'State of the Net, Antonella La Carpia: regole virali',
  53                 'description': 'md5:b0ba04a324126903e3da7763272ae63c',
  54                 'upload_date': '20140613',
  55             },
  56             'skip': 'Error 404',
  57         },
  58         {
  59             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
  60             'info_dict': {
  61                 'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
  62                 'ext': 'mp4',
  63                 'title': 'Alluvione in Sardegna e dissesto idrogeologico',
  64                 'description': 'Edizione delle ore 20:30 ',
  65             },
  66             'skip': 'invalid urls',
  67         },
  68         {
  69             'url': 'http://www.ilcandidato.rai.it/dl/ray/media/Il-Candidato---Primo-episodio-Le-Primarie-28e5525a-b495-45e8-a7c3-bc48ba45d2b6.html',
  70             'md5': '496ab63e420574447f70d02578333437',
  71             'info_dict': {
  72                 'id': '28e5525a-b495-45e8-a7c3-bc48ba45d2b6',
  73                 'ext': 'flv',
  74                 'title': 'Il Candidato - Primo episodio: "Le Primarie"',
  75                 'description': 'md5:364b604f7db50594678f483353164fb8',
  76                 'upload_date': '20140923',
  77                 'duration': 386,
  78             }
  79         },
  80     ]
  81
  82     def _real_extract(self, url):
  83         video_id = self._match_id(url)
  84         media = self._download_json(
  85             'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % video_id,
  86             video_id, 'Downloading video JSON')
  87
  88         thumbnails = []
  89         for image_type in ('image', 'image_medium', 'image_300'):
  90             thumbnail_url = media.get(image_type)
  91             if thumbnail_url:
  92                 thumbnails.append({
  93                     'url': thumbnail_url,
  94                 })
  95
  96         subtitles = []
  97         formats = []
  98         media_type = media['type']
  99         if 'Audio' in media_type:
 100             formats.append({
 101                 'format_id': media.get('formatoAudio'),
 102                 'url': media['audioUrl'],
 103                 'ext': media.get('formatoAudio'),
 104             })
 105         elif 'Video' in media_type:
 106             def fix_xml(xml):
 107                 return xml.replace(' tag elementi', '').replace('>/', '</')
 108
 109             relinker = self._download_xml(
 110                 media['mediaUri'] + '&output=43', video_id, transform_source=fix_xml)
 111
 112             has_subtitle = False
 113
 114             for element in relinker.findall('element'):
 115                 media_url = xpath_text(element, 'url')
 116                 ext = determine_ext(media_url)
 117                 content_type = xpath_text(element, 'content-type')
 118                 if ext == 'm3u8':
 119                     m3u8_formats = self._extract_m3u8_formats(
 120                         media_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls',
 121                         fatal=None)
 122                     if m3u8_formats:
 123                         formats.extend(m3u8_formats)
 124                 elif ext == 'f4m':
 125                     f4m_formats = self._extract_f4m_formats(
 126                         media_url + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44',
 127                         video_id, f4m_id='hds', fatal=None)
 128                     if f4m_formats:
 129                         formats.extend(f4m_formats)
 130                 elif ext == 'stl':
 131                     has_subtitle = True
 132                 elif content_type.startswith('video/'):
 133                     bitrate = int_or_none(xpath_text(element, 'bitrate'))
 134                     formats.append({
 135                         'url': media_url,
 136                         'tbr': bitrate if bitrate > 0 else None,
 137                         'format_id': 'http-%d' % bitrate if bitrate > 0 else 'http',
 138                     })
 139                 elif content_type.startswith('image/'):
 140                     thumbnails.append({
 141                         'url': media_url,
 142                     })
 143
 144             self._sort_formats(formats)
 145
 146             if has_subtitle:
 147                 webpage = self._download_webpage(url, video_id)
 148                 subtitles = self._get_subtitles(video_id, webpage)
 149         else:
 150             raise ExtractorError('not a media file')
 151
 152         return {
 153             'id': video_id,
 154             'title': media['name'],
 155             'description': media.get('desc'),
 156             'thumbnails': thumbnails,
 157             'uploader': media.get('author'),
 158             'upload_date': unified_strdate(media.get('date')),
 159             'duration': parse_duration(media.get('length')),
 160             'formats': formats,
 161             'subtitles': subtitles,
 162         }
 163
 164     def _get_subtitles(self, video_id, webpage):
 165         subtitles = {}
 166         m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
 167         if m:
 168             captions = m.group('captions')
 169             STL_EXT = '.stl'
 170             SRT_EXT = '.srt'
 171             if captions.endswith(STL_EXT):
 172                 captions = captions[:-len(STL_EXT)] + SRT_EXT
 173             subtitles['it'] = [{
 174                 'ext': 'srt',
 175                 'url': 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions),
 176             }]
 177         return subtitles
 178
 179
 180 class RaiIE(InfoExtractor):
 181     _VALID_URL = r'http://(?:.+?\.)?(?: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'
 182     _TESTS = [
 183         {
 184             'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
 185             'md5': 'e0e7a8a131e249d1aa0ebf270d1d8db7',
 186             'info_dict': {
 187                 'id': '59d69d28-6bb6-409d-a4b5-ed44096560af',
 188                 'ext': 'flv',
 189                 'title': 'Il pacco',
 190                 'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a',
 191                 'upload_date': '20141221',
 192             },
 193         }
 194     ]
 195
 196     @classmethod
 197     def suitable(cls, url):
 198         return False if RaiTVIE.suitable(url) else super(RaiIE, cls).suitable(url)
 199
 200     def _real_extract(self, url):
 201         video_id = self._match_id(url)
 202         webpage = self._download_webpage(url, video_id)
 203
 204         iframe_url = self._search_regex(
 205             [r'<iframe[^>]+src="([^"]*/dl/[^"]+\?iframe\b[^"]*)"',
 206              r'drawMediaRaiTV\(["\'](.+?)["\']'],
 207             webpage, 'iframe')
 208         if not iframe_url.startswith('http'):
 209             iframe_url = compat_urlparse.urljoin(url, iframe_url)
 210         return self.url_result(iframe_url)