_ 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 )
   9 from ..utils import (
  10     parse_duration,
  11     unified_strdate,
  12 )
  13
  14
  15 class RaiIE(InfoExtractor):
  16     _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)'
  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 _extract_relinker_url(self, webpage):
  68         return self._proto_relative_url(self._search_regex(
  69             [r'name="videourl" content="([^"]+)"', r'var\s+videoURL(?:_MP4)?\s*=\s*"([^"]+)"'],
  70             webpage, 'relinker url', default=None))
  71
  72     def _real_extract(self, url):
  73         mobj = re.match(self._VALID_URL, url)
  74         video_id = mobj.group('id')
  75         host = mobj.group('host')
  76
  77         webpage = self._download_webpage(url, video_id)
  78
  79         relinker_url = self._extract_relinker_url(webpage)
  80
  81         if not relinker_url:
  82             iframe_path = self._search_regex(
  83                 r'<iframe[^>]+src="/?(dl/[^"]+\?iframe\b[^"]*)"',
  84                 webpage, 'iframe')
  85             iframe_page = self._download_webpage(
  86                 '%s/%s' % (host, iframe_path), video_id)
  87             relinker_url = self._extract_relinker_url(iframe_page)
  88
  89         relinker = self._download_json(
  90             '%s&output=47' % relinker_url, video_id)
  91
  92         media_url = relinker['video'][0]
  93         ct = relinker.get('ct')
  94         if ct == 'f4m':
  95             formats = self._extract_f4m_formats(
  96                 media_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id)
  97         else:
  98             formats = [{
  99                 'url': media_url,
 100                 'format_id': ct,
 101             }]
 102
 103         json_link = self._html_search_meta(
 104             'jsonlink', webpage, 'JSON link', default=None)
 105         if json_link:
 106             media = self._download_json(
 107                 host + json_link, video_id, 'Downloading video JSON')
 108             title = media.get('name')
 109             description = media.get('desc')
 110             thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
 111             duration = parse_duration(media.get('length'))
 112             uploader = media.get('author')
 113             upload_date = unified_strdate(media.get('date'))
 114         else:
 115             title = self._search_regex(
 116                 r'var\s+videoTitolo\s*=\s*"([^"]+)";',
 117                 webpage, 'title', default=None) or self._og_search_title(webpage)
 118             description = self._og_search_description(webpage)
 119             thumbnail = self._og_search_thumbnail(webpage)
 120             duration = None
 121             uploader = self._html_search_meta('Editore', webpage, 'uploader')
 122             upload_date = unified_strdate(self._html_search_meta(
 123                 'item-date', webpage, 'upload date'))
 124
 125         subtitles = self.extract_subtitles(video_id, webpage)
 126
 127         return {
 128             'id': video_id,
 129             'title': title,
 130             'description': description,
 131             'thumbnail': thumbnail,
 132             'uploader': uploader,
 133             'upload_date': upload_date,
 134             'duration': duration,
 135             'formats': formats,
 136             'subtitles': subtitles,
 137         }
 138
 139     def _get_subtitles(self, video_id, webpage):
 140         subtitles = {}
 141         m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
 142         if m:
 143             captions = m.group('captions')
 144             STL_EXT = '.stl'
 145             SRT_EXT = '.srt'
 146             if captions.endswith(STL_EXT):
 147                 captions = captions[:-len(STL_EXT)] + SRT_EXT
 148             subtitles['it'] = [{
 149                 'ext': 'srt',
 150                 'url': 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions),
 151             }]
 152         return subtitles