b5a67373bf02fd3998f32d879e4cb27a9f3d1c8d
[ytdl] / youtube_dl / extractor / rte.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5
6 from ..utils import (
7     float_or_none,
8 )
9
10
11 class RteIE(InfoExtractor):
12     _VALID_URL = r'http?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/(?P<id>[0-9]+)/'
13     _TEST = {
14         'url': 'http://www.rte.ie/player/de/show/10363114/',
15         'info_dict': {
16             'id': '10363114',
17             'ext': 'mp4',
18             'title': 'One News',
19             'thumbnail': 're:^https?://.*\.jpg$',
20             'description': 'The One O\'Clock News followed by Weather.',
21             'duration': 436.844,
22         },
23         'params': {
24             'skip_download': 'f4m fails with --test atm'
25         }
26     }
27     
28     def _real_extract(self, url):
29         video_id = self._match_id(url)
30         webpage = self._download_webpage(url, video_id)
31
32         title = self._og_search_title(webpage)
33         description = self._html_search_meta('description', webpage, 'description')
34         duration = float_or_none(self._html_search_meta(
35             'duration', webpage, 'duration', fatal=False), 1000)
36
37         thumbnail_id = self._search_regex(
38             r'<meta name="thumbnail" content="uri:irus:(.*?)" />', webpage, 'thumbnail')
39         thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg'
40
41         feeds_url = self._html_search_meta("feeds-prefix", webpage, 'feeds url') + video_id
42         json_string = self._download_json(feeds_url, video_id)
43
44         # f4m_url = server + relative_url
45         f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url']
46         f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
47         f4m_formats = [{
48             'format_id': f['format_id'],
49             'url': f['url'],
50             'ext': 'mp4',
51             'width': f['width'],
52             'height': f['height'],
53         } for f in f4m_formats]
54
55         return {
56             'id': video_id,
57             'title': title,
58             'formats': f4m_formats,
59             'description': description,
60             'thumbnail': thumbnail,
61             'duration': duration,
62         }