]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/freesound.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
14 class FreesoundIE(InfoExtractor
):
15 _VALID_URL
= r
'https?://(?:www\.)?freesound\.org/people/[^/]+/sounds/(?P<id>[^/]+)'
17 'url': 'http://www.freesound.org/people/miklovan/sounds/194503/',
18 'md5': '12280ceb42c81f19a515c745eae07650',
22 'title': 'gulls in the city.wav',
23 'description': 'the sounds of seagulls in the city',
25 'uploader': 'miklovan',
26 'upload_date': '20130715',
31 def _real_extract(self
, url
):
32 audio_id
= self
._match
_id
(url
)
34 webpage
= self
._download
_webpage
(url
, audio_id
)
36 audio_url
= self
._og
_search
_property
('audio', webpage
, 'song url')
37 title
= self
._og
_search
_property
('audio:title', webpage
, 'song title')
39 description
= self
._html
_search
_regex
(
40 r
'(?s)id=["\']sound_description
["\'][^>]*>(.+?)</div>',
41 webpage, 'description', fatal=False)
43 duration = float_or_none(
44 get_element_by_class('duration', webpage), scale=1000)
46 upload_date = unified_strdate(get_element_by_id('sound_date', webpage))
47 uploader = self._og_search_property(
48 'audio:artist', webpage, 'uploader', fatal=False)
50 channels = self._html_search_regex(
51 r'Channels</dt><dd>(.+?)</dd>', webpage,
52 'channels info', fatal=False)
54 tags_str = get_element_by_class('tags', webpage)
55 tags = re.findall(r'<a[^>]+>([^<]+)', tags_str) if tags_str else None
57 audio_urls = [audio_url]
60 if LQ_FORMAT in audio_url:
61 audio_urls.append(audio_url.replace(LQ_FORMAT, '-hq.mp3'))
65 'format_note': channels,
67 } for quality, format_url in enumerate(audio_urls)]
68 self._sort_formats(formats)
73 'description': description,
76 'upload_date': upload_date,