Raphaël G. Git Repositories - youtubedl/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             'skip': 'Error 404',
  51         },
  52         {
  53             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
  54             'md5': '35694f062977fe6619943f08ed935730',
  55             'info_dict': {
  56                 'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
  57                 'ext': 'mp4',
  58                 'title': 'Alluvione in Sardegna e dissesto idrogeologico',
  59                 'description': 'Edizione delle ore 20:30 ',
  60             }
  61         },
  62     ]
  63
  64     def _real_extract(self, url):
  65         mobj = re.match(self._VALID_URL, url)
  66         video_id = mobj.group('id')
  67
  68         media = self._download_json('%s?json' % mobj.group('url'), video_id, 'Downloading video JSON')
  69
  70         title = media.get('name')
  71         description = media.get('desc')
  72         thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
  73         duration = parse_duration(media.get('length'))
  74         uploader = media.get('author')
  75         upload_date = unified_strdate(media.get('date'))
  76
  77         formats = []
  78
  79         for format_id in ['wmv', 'm3u8', 'mediaUri', 'h264']:
  80             media_url = media.get(format_id)
  81             if not media_url:
  82                 continue
  83             formats.append({
  84                 'url': media_url,
  85                 'format_id': format_id,
  86                 'ext': 'mp4',
  87             })
  88
  89         if self._downloader.params.get('listsubtitles', False):
  90             page = self._download_webpage(url, video_id)
  91             self._list_available_subtitles(video_id, page)
  92             return
  93
  94         subtitles = {}
  95         if self._have_to_download_any_subtitles:
  96             page = self._download_webpage(url, video_id)
  97             subtitles = self.extract_subtitles(video_id, page)
  98
  99         return {
 100             'id': video_id,
 101             'title': title,
 102             'description': description,
 103             'thumbnail': thumbnail,
 104             'uploader': uploader,
 105             'upload_date': upload_date,
 106             'duration': duration,
 107             'formats': formats,
 108             'subtitles': subtitles,
 109         }
 110
 111     def _get_available_subtitles(self, video_id, webpage):
 112         subtitles = {}
 113         m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
 114         if m:
 115             captions = m.group('captions')
 116             STL_EXT = '.stl'
 117             SRT_EXT = '.srt'
 118             if captions.endswith(STL_EXT):
 119                 captions = captions[:-len(STL_EXT)] + SRT_EXT
 120             subtitles['it'] = 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions)
 121         return subtitles