Raphaël G. Git Repositories - youtubedl/blob - 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/(?P<id>[0-9]+)'
  10     _TEST = {
  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': 're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26
  27         webpage = self._download_webpage(url, video_id)
  28
  29         clip = None
  30
  31         clip_store = self._parse_json(
  32             self._search_regex(
  33                 r'data-new-clip-store=(["\'])(?P<json>{.*?"clipId"\s*:\s*%s.*?})\1' % video_id,
  34                 webpage, 'clip store', default='{}', group='json'),
  35             video_id, fatal=False)
  36         if clip_store:
  37             clips = clip_store.get('clips')
  38             if clips and isinstance(clips, list) and isinstance(clips[0], dict):
  39                 clip = clips[0]
  40
  41         def from_clip(field):
  42             if clip:
  43                 clip.get(field)
  44
  45         audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property(
  46             'audio', webpage, 'audio url')
  47         title = from_clip('title') or self._og_search_title(webpage)
  48         description = from_clip('description') or self._og_search_description(webpage)
  49
  50         duration = float_or_none(from_clip('duration') or self._html_search_meta(
  51             'weibo:audio:duration', webpage))
  52
  53         uploader = from_clip('author') or self._og_search_property(
  54             'audio:artist', webpage, 'uploader', fatal=False)
  55         uploader_url = from_clip('author_url') or self._html_search_meta(
  56             'audioboo:channel', webpage, 'uploader url')
  57
  58         return {
  59             'id': video_id,
  60             'url': audio_url,
  61             'title': title,
  62             'description': description,
  63             'duration': duration,
  64             'uploader': uploader,
  65             'uploader_url': uploader_url,
  66         }