]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/rte.py
Merge remote-tracking branch 'Dineshs91/f4m-2.0'
[yt-dlp.git] / 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/in/show/(?P<id>[0-9]+)/'
13 _TEST = {
14 'url': 'http://www.rte.ie/player/in/show/10336191/',
15 'info_dict': {
16 'id': '10336191',
17 'ext': 'mp4',
18 'title': 'Nine News',
19 'thumbnail': 're:^https?://.*\.jpg$',
20 'description': 'The One O\'Clock News followed by Weather.',
21 'duration': 1622.963,
22 }
23 }
24
25 def _real_extract(self, url):
26 video_id = self._match_id(url)
27
28 webpage = self._download_webpage(url, video_id)
29 title = self._og_search_title(webpage)
30
31 description = self._search_regex(r'<meta name="description" content="(.*?)" />', webpage, 'description')
32 duration = float_or_none(self._html_search_meta('duration', webpage, 'duration'), 1000)
33
34 thumbnail_id = self._search_regex(r'<meta name="thumbnail" content="uri:irus:(.*?)" />', webpage, 'thumbnail')
35 thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg'
36
37 feeds_url = self._html_search_meta("feeds-prefix", webpage, 'feeds url') + video_id
38 json_string = self._download_json(feeds_url, video_id)
39
40 # f4m_url = server + relative_url
41 f4m_url = json_string['shows'][0]['media:group'][0]['rte:server'] + json_string['shows'][0]['media:group'][0]['url']
42 f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
43 f4m_formats = [{
44 'format_id': f['format_id'],
45 'url': f['url'],
46 'ext': 'mp4',
47 'width': f['width'],
48 'height': f['height'],
49 } for f in f4m_formats ]
50
51 return {
52 'id': video_id,
53 'title': title,
54 'formats': f4m_formats,
55 'description': description,
56 'thumbnail': thumbnail,
57 'duration': duration,
58 }