pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-14 22:37:59 +09:00
Code Issues Projects Releases Wiki Activity

[audioboom] Improve robustness and extract uploader (Closes #8812)

Browse Source
This commit is contained in:
Sergey M․ 2016-03-11 19:44:17 +06:00
parent 61f317c24c
commit 883c052378
1 changed files with 34 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
youtube_dl/extractor/audioboom.py
View File

@ -15,25 +15,52 @@ class AudioBoomIE(InfoExtractor):
'ext': 'mp3',
'title': '3/09/2016 Czaban Hour 3',
'description': 'Guest: Nate Davis - NFL free agency, Guest: Stan Gans',
'duration': 2245.72
'duration': 2245.72,
'uploader': 'Steve Czaban',
'uploader_url': 're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._og_search_title(webpage)
clip = None
download_url = self._og_search_property('audio', webpage, 'url')
clip_store = self._parse_json(
self._search_regex(
r'data-new-clip-store=(["\'])(?P<json>{.*?"clipId"\s*:\s*%s.*?})\1' % video_id,
webpage, 'clip store', default='{}', group='json'),
video_id, fatal=False)
if clip_store:
clips = clip_store.get('clips')
if clips and isinstance(clips, list) and isinstance(clips[0], dict):
clip = clips[0]
duration = float_or_none(self._html_search_meta(
'weibo:audio:duration', webpage, fatal=False))
def from_clip(field):
if clip:
clip.get(field)
audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property(
'audio', webpage, 'audio url')
title = from_clip('title') or self._og_search_title(webpage)
description = from_clip('description') or self._og_search_description(webpage)
duration = float_or_none(from_clip('duration') or self._html_search_meta(
'weibo:audio:duration', webpage))
uploader = from_clip('author') or self._og_search_property(
'audio:artist', webpage, 'uploader', fatal=False)
uploader_url = from_clip('author_url') or self._html_search_meta(
'audioboo:channel', webpage, 'uploader url')
return {
'id': video_id,
'url': audio_url,
'title': title,
'url': download_url,
'description': self._og_search_description(webpage),
'description': description,
'duration': duration,
'uploader': uploader,
'uploader_url': uploader_url,
}