]> gitweb @ CieloNegro.org - youtube-dl.git/blob - youtube_dl/extractor/audioboom.py
[cbsinteractive] extract formats with `CBSIE`
[youtube-dl.git] / youtube_dl / extractor / audioboom.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import float_or_none
6
7
8 class AudioBoomIE(InfoExtractor):
9     _VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)'
10     _TESTS = [{
11         'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0',
12         'md5': '63a8d73a055c6ed0f1e51921a10a5a76',
13         'info_dict': {
14             'id': '4279833',
15             'ext': 'mp3',
16             'title': '3/09/2016 Czaban Hour 3',
17             'description': 'Guest:   Nate Davis - NFL free agency,   Guest:   Stan Gans',
18             'duration': 2245.72,
19             'uploader': 'Steve Czaban',
20             'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
21         }
22     }, {
23         'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',
24         'only_matching': True,
25     }]
26
27     def _real_extract(self, url):
28         video_id = self._match_id(url)
29
30         webpage = self._download_webpage(url, video_id)
31
32         clip = None
33
34         clip_store = self._parse_json(
35             self._search_regex(
36                 r'data-new-clip-store=(["\'])(?P<json>{.*?"clipId"\s*:\s*%s.*?})\1' % video_id,
37                 webpage, 'clip store', default='{}', group='json'),
38             video_id, fatal=False)
39         if clip_store:
40             clips = clip_store.get('clips')
41             if clips and isinstance(clips, list) and isinstance(clips[0], dict):
42                 clip = clips[0]
43
44         def from_clip(field):
45             if clip:
46                 clip.get(field)
47
48         audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property(
49             'audio', webpage, 'audio url')
50         title = from_clip('title') or self._og_search_title(webpage)
51         description = from_clip('description') or self._og_search_description(webpage)
52
53         duration = float_or_none(from_clip('duration') or self._html_search_meta(
54             'weibo:audio:duration', webpage))
55
56         uploader = from_clip('author') or self._og_search_property(
57             'audio:artist', webpage, 'uploader', fatal=False)
58         uploader_url = from_clip('author_url') or self._html_search_meta(
59             'audioboo:channel', webpage, 'uploader url')
60
61         return {
62             'id': video_id,
63             'url': audio_url,
64             'title': title,
65             'description': description,
66             'duration': duration,
67             'uploader': uploader,
68             'uploader_url': uploader_url,
69         }