]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/rtp.py
[keek] remove unused import
[yt-dlp.git] / youtube_dl / extractor / rtp.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import json
5
6 from .common import InfoExtractor
7 from ..utils import js_to_json
8
9
10 class RTPIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/p(?P<program_id>[0-9]+)/e(?P<id>[0-9]+)/?'
12 _TEST = {
13 'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas',
14 'info_dict': {
15 'id': '174042',
16 'ext': 'mp3',
17 'title': 'Paixões Cruzadas',
18 'description': 'As paixões musicais de António Cartaxo e António Macedo',
19 'thumbnail': 're:^https?://.*\.jpg',
20 },
21 'params': {
22 'skip_download': True, # RTMP download
23 },
24 }
25
26 def _real_extract(self, url):
27 video_id = self._match_id(url)
28
29 webpage = self._download_webpage(url, video_id)
30 title = self._html_search_meta(
31 'twitter:title', webpage, display_name='title', fatal=True)
32 description = self._html_search_meta('description', webpage)
33 thumbnail = self._og_search_thumbnail(webpage)
34
35 player_config = self._search_regex(
36 r'(?s)RTPPLAY\.player\.newPlayer\(\s*(\{.*?\})\s*\)', webpage, 'player config')
37 config = json.loads(js_to_json(player_config))
38
39 path, ext = config.get('file').rsplit('.', 1)
40 formats = [{
41 'app': config.get('application'),
42 'play_path': '{ext:s}:{path:s}'.format(ext=ext, path=path),
43 'page_url': url,
44 'url': 'rtmp://{streamer:s}/{application:s}'.format(**config),
45 'rtmp_live': config.get('live', False),
46 'ext': ext,
47 'vcodec': config.get('type') == 'audio' and 'none' or None,
48 'player_url': 'http://programas.rtp.pt/play/player.swf?v3',
49 }]
50
51 return {
52 'id': video_id,
53 'title': title,
54 'formats': formats,
55 'description': description,
56 'thumbnail': thumbnail,
57 }