Raphaël G. Git Repositories - youtubedl/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 )
   9 from ..utils import (
  10     parse_duration,
  11     unified_strdate,
  12 )
  13
  14
  15 class RaiIE(InfoExtractor):
  16     _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)'
  17     _TESTS = [
  18         {
  19             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
  20             'md5': 'c064c0b2d09c278fb293116ef5d0a32d',
  21             'info_dict': {
  22                 'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
  23                 'ext': 'mp4',
  24                 'title': 'Report del 07/04/2014',
  25                 'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
  26                 'upload_date': '20140407',
  27                 'duration': 6160,
  28             }
  29         },
  30         {
  31             'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
  32             'md5': '8bb9c151924ce241b74dd52ef29ceafa',
  33             'info_dict': {
  34                 'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
  35                 'ext': 'mp4',
  36                 'title': 'TG PRIMO TEMPO',
  37                 'description': '',
  38                 'upload_date': '20140612',
  39                 'duration': 1758,
  40             },
  41             'skip': 'Error 404',
  42         },
  43         {
  44             'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',
  45             'md5': '35cf7c229f22eeef43e48b5cf923bef0',
  46             'info_dict': {
  47                 'id': '7aafdea9-0e5d-49d5-88a6-7e65da67ae13',
  48                 'ext': 'mp4',
  49                 'title': 'State of the Net, Antonella La Carpia: regole virali',
  50                 'description': 'md5:b0ba04a324126903e3da7763272ae63c',
  51                 'upload_date': '20140613',
  52             },
  53             'skip': 'Error 404',
  54         },
  55         {
  56             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
  57             'md5': '35694f062977fe6619943f08ed935730',
  58             'info_dict': {
  59                 'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
  60                 'ext': 'mp4',
  61                 'title': 'Alluvione in Sardegna e dissesto idrogeologico',
  62                 'description': 'Edizione delle ore 20:30 ',
  63             }
  64         },
  65     ]
  66
  67     def _real_extract(self, url):
  68         mobj = re.match(self._VALID_URL, url)
  69         video_id = mobj.group('id')
  70
  71         media = self._download_json('%s?json' % mobj.group('url'), video_id, 'Downloading video JSON')
  72
  73         title = media.get('name')
  74         description = media.get('desc')
  75         thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
  76         duration = parse_duration(media.get('length'))
  77         uploader = media.get('author')
  78         upload_date = unified_strdate(media.get('date'))
  79
  80         formats = []
  81
  82         for format_id in ['wmv', 'm3u8', 'mediaUri', 'h264']:
  83             media_url = media.get(format_id)
  84             if not media_url:
  85                 continue
  86             formats.append({
  87                 'url': media_url,
  88                 'format_id': format_id,
  89                 'ext': 'mp4',
  90             })
  91
  92         subtitles = self.extract_subtitles(video_id, url)
  93
  94         return {
  95             'id': video_id,
  96             'title': title,
  97             'description': description,
  98             'thumbnail': thumbnail,
  99             'uploader': uploader,
 100             'upload_date': upload_date,
 101             'duration': duration,
 102             'formats': formats,
 103             'subtitles': subtitles,
 104         }
 105
 106     def _get_subtitles(self, video_id, url):
 107         webpage = self._download_webpage(url, video_id)
 108         subtitles = {}
 109         m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
 110         if m:
 111             captions = m.group('captions')
 112             STL_EXT = '.stl'
 113             SRT_EXT = '.srt'
 114             if captions.endswith(STL_EXT):
 115                 captions = captions[:-len(STL_EXT)] + SRT_EXT
 116             subtitles['it'] = [{
 117                 'ext': 'srt',
 118                 'url': 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions),
 119             }]
 120         return subtitles