]> gitweb @ CieloNegro.org - youtube-dl.git/blob - youtube_dl/extractor/rai.py
[ign] Fix extraction of video in articles
[youtube-dl.git] / 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             'skip': 'Error 404',
40         },
41         {
42             'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',
43             'md5': '35cf7c229f22eeef43e48b5cf923bef0',
44             'info_dict': {
45                 'id': '7aafdea9-0e5d-49d5-88a6-7e65da67ae13',
46                 'ext': 'mp4',
47                 'title': 'State of the Net, Antonella La Carpia: regole virali',
48                 'description': 'md5:b0ba04a324126903e3da7763272ae63c',
49                 'upload_date': '20140613',
50             },
51             'skip': 'Error 404',
52         },
53         {
54             'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
55             'md5': '35694f062977fe6619943f08ed935730',
56             'info_dict': {
57                 'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
58                 'ext': 'mp4',
59                 'title': 'Alluvione in Sardegna e dissesto idrogeologico',
60                 'description': 'Edizione delle ore 20:30 ',
61             }
62         },
63     ]
64
65     def _real_extract(self, url):
66         mobj = re.match(self._VALID_URL, url)
67         video_id = mobj.group('id')
68
69         media = self._download_json('%s?json' % mobj.group('url'), video_id, 'Downloading video JSON')
70
71         title = media.get('name')
72         description = media.get('desc')
73         thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
74         duration = parse_duration(media.get('length'))
75         uploader = media.get('author')
76         upload_date = unified_strdate(media.get('date'))
77
78         formats = []
79
80         for format_id in ['wmv', 'm3u8', 'mediaUri', 'h264']:
81             media_url = media.get(format_id)
82             if not media_url:
83                 continue
84             formats.append({
85                 'url': media_url,
86                 'format_id': format_id,
87                 'ext': 'mp4',
88             })
89
90         if self._downloader.params.get('listsubtitles', False):
91             page = self._download_webpage(url, video_id)
92             self._list_available_subtitles(video_id, page)
93             return
94
95         subtitles = {}
96         if self._have_to_download_any_subtitles:
97             page = self._download_webpage(url, video_id)
98             subtitles = self.extract_subtitles(video_id, page)
99
100         return {
101             'id': video_id,
102             'title': title,
103             'description': description,
104             'thumbnail': thumbnail,
105             'uploader': uploader,
106             'upload_date': upload_date,
107             'duration': duration,
108             'formats': formats,
109             'subtitles': subtitles,
110         }
111
112     def _get_available_subtitles(self, video_id, webpage):
113         subtitles = {}
114         m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
115         if m:
116             captions = m.group('captions')
117             STL_EXT = '.stl'
118             SRT_EXT = '.srt'
119             if captions.endswith(STL_EXT):
120                 captions = captions[:-len(STL_EXT)] + SRT_EXT
121             subtitles['it'] = 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions)
122         return subtitles