_ Git - youtube-dl/blob - 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     parse_duration,
  12     unified_strdate,
  13 )
  14
  15
  16 class RaiIE(InfoExtractor):
  17     _VALID_URL = r'(?P<url>(?P<host>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)'
  18     _TESTS = [
  19         {
  20             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
  21             'md5': 'c064c0b2d09c278fb293116ef5d0a32d',
  22             'info_dict': {
  23                 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
  24                 'ext': 'mp4',
  25                 'title': 'Report del 07/04/2014',
  26                 'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
  27                 'upload_date': '20140407',
  28                 'duration': 6160,
  29             }
  30         },
  31         {
  32             'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
  33             'md5': '8bb9c151924ce241b74dd52ef29ceafa',
  34             'info_dict': {
  35                 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
  36                 'ext': 'mp4',
  37                 'title': 'TG PRIMO TEMPO',
  38                 'description': '',
  39                 'upload_date': '20140612',
  40                 'duration': 1758,
  41             },
  42             'skip': 'Error 404',
  43         },
  44         {
  45             'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',
  46             'md5': '35cf7c229f22eeef43e48b5cf923bef0',
  47             'info_dict': {
  48                 'id': '7aafdea9-0e5d-49d5-88a6-7e65da67ae13',
  49                 'ext': 'mp4',
  50                 'title': 'State of the Net, Antonella La Carpia: regole virali',
  51                 'description': 'md5:b0ba04a324126903e3da7763272ae63c',
  52                 'upload_date': '20140613',
  53             },
  54             'skip': 'Error 404',
  55         },
  56         {
  57             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
  58             'md5': '35694f062977fe6619943f08ed935730',
  59             'info_dict': {
  60                 'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
  61                 'ext': 'mp4',
  62                 'title': 'Alluvione in Sardegna e dissesto idrogeologico',
  63                 'description': 'Edizione delle ore 20:30 ',
  64             }
  65         },
  66         {
  67             'url': 'http://www.ilcandidato.rai.it/dl/ray/media/Il-Candidato---Primo-episodio-Le-Primarie-28e5525a-b495-45e8-a7c3-bc48ba45d2b6.html',
  68             'md5': '02b64456f7cc09f96ff14e7dd489017e',
  69             'info_dict': {
  70                 'id': '28e5525a-b495-45e8-a7c3-bc48ba45d2b6',
  71                 'ext': 'flv',
  72                 'title': 'Il Candidato - Primo episodio: "Le Primarie"',
  73                 'description': 'Primo appuntamento con "Il candidato" con Filippo Timi, alias Piero Zucca presidente!',
  74                 'uploader': 'RaiTre',
  75             }
  76         },
  77         {
  78             'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
  79             'md5': '037104d2c14132887e5e4cf114569214',
  80             'info_dict': {
  81                 'id': '0c7a664b-d0f4-4b2c-8835-3f82e46f433e',
  82                 'ext': 'flv',
  83                 'title': 'Il pacco',
  84                 'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a',
  85                 'uploader': 'RaiTre',
  86                 'upload_date': '20141221',
  87             },
  88         }
  89     ]
  90
  91     def _extract_relinker_url(self, webpage):
  92         return self._proto_relative_url(self._search_regex(
  93             [r'name="videourl" content="([^"]+)"', r'var\s+videoURL(?:_MP4)?\s*=\s*"([^"]+)"'],
  94             webpage, 'relinker url', default=None))
  95
  96     def _real_extract(self, url):
  97         mobj = re.match(self._VALID_URL, url)
  98         video_id = mobj.group('id')
  99         host = mobj.group('host')
 100
 101         webpage = self._download_webpage(url, video_id)
 102
 103         relinker_url = self._extract_relinker_url(webpage)
 104
 105         if not relinker_url:
 106             iframe_url = self._search_regex(
 107                 [r'<iframe[^>]+src="([^"]*/dl/[^"]+\?iframe\b[^"]*)"',
 108                  r'drawMediaRaiTV\(["\'](.+?)["\']'],
 109                 webpage, 'iframe')
 110             if not iframe_url.startswith('http'):
 111                 iframe_url = compat_urlparse.urljoin(url, iframe_url)
 112             webpage = self._download_webpage(
 113                 iframe_url, video_id)
 114             relinker_url = self._extract_relinker_url(webpage)
 115
 116         relinker = self._download_json(
 117             '%s&output=47' % relinker_url, video_id)
 118
 119         media_url = relinker['video'][0]
 120         ct = relinker.get('ct')
 121         if ct == 'f4m':
 122             formats = self._extract_f4m_formats(
 123                 media_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id)
 124         else:
 125             formats = [{
 126                 'url': media_url,
 127                 'format_id': ct,
 128             }]
 129
 130         json_link = self._html_search_meta(
 131             'jsonlink', webpage, 'JSON link', default=None)
 132         if json_link:
 133             media = self._download_json(
 134                 host + json_link, video_id, 'Downloading video JSON')
 135             title = media.get('name')
 136             description = media.get('desc')
 137             thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
 138             duration = parse_duration(media.get('length'))
 139             uploader = media.get('author')
 140             upload_date = unified_strdate(media.get('date'))
 141         else:
 142             title = (self._search_regex(
 143                 r'var\s+videoTitolo\s*=\s*"(.+?)";',
 144                 webpage, 'title', default=None) or self._og_search_title(webpage)).replace('\\"', '"')
 145             description = self._og_search_description(webpage)
 146             thumbnail = self._og_search_thumbnail(webpage)
 147             duration = None
 148             uploader = self._html_search_meta('Editore', webpage, 'uploader')
 149             upload_date = unified_strdate(self._html_search_meta(
 150                 'item-date', webpage, 'upload date', default=None))
 151
 152         subtitles = self.extract_subtitles(video_id, webpage)
 153
 154         return {
 155             'id': video_id,
 156             'title': title,
 157             'description': description,
 158             'thumbnail': thumbnail,
 159             'uploader': uploader,
 160             'upload_date': upload_date,
 161             'duration': duration,
 162             'formats': formats,
 163             'subtitles': subtitles,
 164         }
 165
 166     def _get_subtitles(self, video_id, webpage):
 167         subtitles = {}
 168         m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
 169         if m:
 170             captions = m.group('captions')
 171             STL_EXT = '.stl'
 172             SRT_EXT = '.srt'
 173             if captions.endswith(STL_EXT):
 174                 captions = captions[:-len(STL_EXT)] + SRT_EXT
 175             subtitles['it'] = [{
 176                 'ext': 'srt',
 177                 'url': 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions),
 178             }]
 179         return subtitles