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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .subtitles import SubtitlesInfoExtractor
   6 from ..utils import (
   7     parse_duration,
   8     unified_strdate,
   9     compat_urllib_parse,
  10 )
  11
  12
  13 class RaiIE(SubtitlesInfoExtractor):
  14     _VALID_URL = r'(?P<url>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)'
  15     _TESTS = [
  16         {
  17             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
  18             'md5': 'c064c0b2d09c278fb293116ef5d0a32d',
  19             'info_dict': {
  20                 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
  21                 'ext': 'mp4',
  22                 'title': 'Report del 07/04/2014',
  23                 'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
  24                 'upload_date': '20140407',
  25                 'duration': 6160,
  26             }
  27         },
  28         {
  29             'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
  30             'md5': '8bb9c151924ce241b74dd52ef29ceafa',
  31             'info_dict': {
  32                 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
  33                 'ext': 'mp4',
  34                 'title': 'TG PRIMO TEMPO',
  35                 'description': '',
  36                 'upload_date': '20140612',
  37                 'duration': 1758,
  38             }
  39         },
  40         {
  41             'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',
  42             'md5': '35cf7c229f22eeef43e48b5cf923bef0',
  43             'info_dict': {
  44                 'id': '7aafdea9-0e5d-49d5-88a6-7e65da67ae13',
  45                 'ext': 'mp4',
  46                 'title': 'State of the Net, Antonella La Carpia: regole virali',
  47                 'description': 'md5:b0ba04a324126903e3da7763272ae63c',
  48                 'upload_date': '20140613',
  49             }
  50         },
  51         {
  52             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
  53             'md5': '35694f062977fe6619943f08ed935730',
  54             'info_dict': {
  55                 'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
  56                 'ext': 'mp4',
  57                 'title': 'Alluvione in Sardegna e dissesto idrogeologico',
  58                 'description': 'Edizione delle ore 20:30 ',
  59             }
  60         },
  61     ]
  62
  63     def _real_extract(self, url):
  64         mobj = re.match(self._VALID_URL, url)
  65         video_id = mobj.group('id')
  66
  67         media = self._download_json('%s?json' % mobj.group('url'), video_id, 'Downloading video JSON')
  68
  69         title = media.get('name')
  70         description = media.get('desc')
  71         thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
  72         duration = parse_duration(media.get('length'))
  73         uploader = media.get('author')
  74         upload_date = unified_strdate(media.get('date'))
  75
  76         formats = []
  77
  78         for format_id in ['wmv', 'm3u8', 'mediaUri', 'h264']:
  79             media_url = media.get(format_id)
  80             if not media_url:
  81                 continue
  82             formats.append({
  83                 'url': media_url,
  84                 'format_id': format_id,
  85                 'ext': 'mp4',
  86             })
  87
  88         if self._downloader.params.get('listsubtitles', False):
  89             page = self._download_webpage(url, video_id)
  90             self._list_available_subtitles(video_id, page)
  91             return
  92
  93         subtitles = {}
  94         if self._have_to_download_any_subtitles:
  95             page = self._download_webpage(url, video_id)
  96             subtitles = self.extract_subtitles(video_id, page)
  97
  98         return {
  99             'id': video_id,
 100             'title': title,
 101             'description': description,
 102             'thumbnail': thumbnail,
 103             'uploader': uploader,
 104             'upload_date': upload_date,
 105             'duration': duration,
 106             'formats': formats,
 107             'subtitles': subtitles,
 108         }
 109
 110     def _get_available_subtitles(self, video_id, webpage):
 111         subtitles = {}
 112         m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
 113         if m:
 114             captions = m.group('captions')
 115             STL_EXT = '.stl'
 116             SRT_EXT = '.srt'
 117             if captions.endswith(STL_EXT):
 118                 captions = captions[:-len(STL_EXT)] + SRT_EXT
 119             subtitles['it'] = 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions)
 120         return subtitles