]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/konserthusetplay.py
[iprima] Relax _VALID_URL (closes #18515)
[youtube-dl] / youtube_dl / extractor / konserthusetplay.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import (
6     determine_ext,
7     float_or_none,
8     int_or_none,
9     url_or_none,
10 )
11
12
13 class KonserthusetPlayIE(InfoExtractor):
14     _VALID_URL = r'https?://(?:www\.)?(?:konserthusetplay|rspoplay)\.se/\?.*\bm=(?P<id>[^&]+)'
15     _TESTS = [{
16         'url': 'http://www.konserthusetplay.se/?m=CKDDnlCY-dhWAAqiMERd-A',
17         'md5': 'e3fd47bf44e864bd23c08e487abe1967',
18         'info_dict': {
19             'id': 'CKDDnlCY-dhWAAqiMERd-A',
20             'ext': 'mp4',
21             'title': 'Orkesterns instrument: Valthornen',
22             'description': 'md5:f10e1f0030202020396a4d712d2fa827',
23             'thumbnail': 're:^https?://.*$',
24             'duration': 398.76,
25         },
26     }, {
27         'url': 'http://rspoplay.se/?m=elWuEH34SMKvaO4wO_cHBw',
28         'only_matching': True,
29     }]
30
31     def _real_extract(self, url):
32         video_id = self._match_id(url)
33
34         webpage = self._download_webpage(url, video_id)
35
36         e = self._search_regex(
37             r'https?://csp\.picsearch\.com/rest\?.*\be=(.+?)[&"\']', webpage, 'e')
38
39         rest = self._download_json(
40             'http://csp.picsearch.com/rest?e=%s&containerId=mediaplayer&i=object' % e,
41             video_id, transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1])
42
43         media = rest['media']
44         player_config = media['playerconfig']
45         playlist = player_config['playlist']
46
47         source = next(f for f in playlist if f.get('bitrates') or f.get('provider'))
48
49         FORMAT_ID_REGEX = r'_([^_]+)_h264m\.mp4'
50
51         formats = []
52
53         m3u8_url = source.get('url')
54         if m3u8_url and determine_ext(m3u8_url) == 'm3u8':
55             formats.extend(self._extract_m3u8_formats(
56                 m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
57                 m3u8_id='hls', fatal=False))
58
59         fallback_url = source.get('fallbackUrl')
60         fallback_format_id = None
61         if fallback_url:
62             fallback_format_id = self._search_regex(
63                 FORMAT_ID_REGEX, fallback_url, 'format id', default=None)
64
65         connection_url = (player_config.get('rtmp', {}).get(
66             'netConnectionUrl') or player_config.get(
67             'plugins', {}).get('bwcheck', {}).get('netConnectionUrl'))
68         if connection_url:
69             for f in source['bitrates']:
70                 video_url = f.get('url')
71                 if not video_url:
72                     continue
73                 format_id = self._search_regex(
74                     FORMAT_ID_REGEX, video_url, 'format id', default=None)
75                 f_common = {
76                     'vbr': int_or_none(f.get('bitrate')),
77                     'width': int_or_none(f.get('width')),
78                     'height': int_or_none(f.get('height')),
79                 }
80                 f = f_common.copy()
81                 f.update({
82                     'url': connection_url,
83                     'play_path': video_url,
84                     'format_id': 'rtmp-%s' % format_id if format_id else 'rtmp',
85                     'ext': 'flv',
86                 })
87                 formats.append(f)
88                 if format_id and format_id == fallback_format_id:
89                     f = f_common.copy()
90                     f.update({
91                         'url': fallback_url,
92                         'format_id': 'http-%s' % format_id if format_id else 'http',
93                     })
94                     formats.append(f)
95
96         if not formats and fallback_url:
97             formats.append({
98                 'url': fallback_url,
99             })
100
101         self._sort_formats(formats)
102
103         title = player_config.get('title') or media['title']
104         description = player_config.get('mediaInfo', {}).get('description')
105         thumbnail = media.get('image')
106         duration = float_or_none(media.get('duration'), 1000)
107
108         subtitles = {}
109         captions = source.get('captionsAvailableLanguages')
110         if isinstance(captions, dict):
111             for lang, subtitle_url in captions.items():
112                 subtitle_url = url_or_none(subtitle_url)
113                 if lang != 'none' and subtitle_url:
114                     subtitles.setdefault(lang, []).append({'url': subtitle_url})
115
116         return {
117             'id': video_id,
118             'title': title,
119             'description': description,
120             'thumbnail': thumbnail,
121             'duration': duration,
122             'formats': formats,
123             'subtitles': subtitles,
124         }