]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rtp.py
533ee27cbefcb1bb19bc2bedf06163a0c64d74e2
[youtubedl] / youtube_dl / extractor / rtp.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7
8
9 class RTPIE(InfoExtractor):
10 _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/p(?P<program_id>[0-9]+)/(?P<id>[^/?#]+)/?'
11 _TESTS = [{
12 'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas',
13 'md5': 'e736ce0c665e459ddb818546220b4ef8',
14 'info_dict': {
15 'id': 'e174042',
16 'ext': 'mp3',
17 'title': 'Paixões Cruzadas',
18 'description': 'As paixões musicais de António Cartaxo e António Macedo',
19 'thumbnail': r're:^https?://.*\.jpg',
20 },
21 'params': {
22 # rtmp download
23 'skip_download': True,
24 },
25 }, {
26 'url': 'http://www.rtp.pt/play/p831/a-quimica-das-coisas',
27 'only_matching': True,
28 }]
29
30 def _real_extract(self, url):
31 video_id = self._match_id(url)
32
33 webpage = self._download_webpage(url, video_id)
34 title = self._html_search_meta(
35 'twitter:title', webpage, display_name='title', fatal=True)
36 description = self._html_search_meta('description', webpage)
37 thumbnail = self._og_search_thumbnail(webpage)
38
39 player_config = self._search_regex(
40 r'(?s)RTPPLAY\.player\.newPlayer\(\s*(\{.*?\})\s*\)', webpage, 'player config')
41 config = self._parse_json(player_config, video_id)
42
43 path, ext = config.get('file').rsplit('.', 1)
44 formats = [{
45 'format_id': 'rtmp',
46 'ext': ext,
47 'vcodec': config.get('type') == 'audio' and 'none' or None,
48 'preference': -2,
49 'url': 'rtmp://{streamer:s}/{application:s}'.format(**config),
50 'app': config.get('application'),
51 'play_path': '{ext:s}:{path:s}'.format(ext=ext, path=path),
52 'page_url': url,
53 'rtmp_live': config.get('live', False),
54 'player_url': 'http://programas.rtp.pt/play/player.swf?v3',
55 'rtmp_real_time': True,
56 }]
57
58 # Construct regular HTTP download URLs
59 replacements = {
60 'audio': {
61 'format_id': 'mp3',
62 'pattern': r'^nas2\.share/wavrss/',
63 'repl': 'http://rsspod.rtp.pt/podcasts/',
64 'vcodec': 'none',
65 },
66 'video': {
67 'format_id': 'mp4_h264',
68 'pattern': r'^nas2\.share/h264/',
69 'repl': 'http://rsspod.rtp.pt/videocasts/',
70 'vcodec': 'h264',
71 },
72 }
73 r = replacements[config['type']]
74 if re.match(r['pattern'], config['file']) is not None:
75 formats.append({
76 'format_id': r['format_id'],
77 'url': re.sub(r['pattern'], r['repl'], config['file']),
78 'vcodec': r['vcodec'],
79 })
80
81 self._sort_formats(formats)
82
83 return {
84 'id': video_id,
85 'title': title,
86 'formats': formats,
87 'description': description,
88 'thumbnail': thumbnail,
89 }