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 (
   6     clean_html,
   7     float_or_none,
   8 )
   9
  10
  11 class AudioBoomIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)'
  13     _TESTS = [{
  14         'url': 'https://audioboom.com/posts/7398103-asim-chaudhry',
  15         'md5': '7b00192e593ff227e6a315486979a42d',
  16         'info_dict': {
  17             'id': '7398103',
  18             'ext': 'mp3',
  19             'title': 'Asim Chaudhry',
  20             'description': 'md5:2f3fef17dacc2595b5362e1d7d3602fc',
  21             'duration': 4000.99,
  22             'uploader': 'Sue Perkins: An hour or so with...',
  23             'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/perkins',
  24         }
  25     }, {
  26         'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',
  27         'only_matching': True,
  28     }]
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32
  33         webpage = self._download_webpage(url, video_id)
  34
  35         clip = None
  36
  37         clip_store = self._parse_json(
  38             self._html_search_regex(
  39                 r'data-new-clip-store=(["\'])(?P<json>{.+?})\1',
  40                 webpage, 'clip store', default='{}', group='json'),
  41             video_id, fatal=False)
  42         if clip_store:
  43             clips = clip_store.get('clips')
  44             if clips and isinstance(clips, list) and isinstance(clips[0], dict):
  45                 clip = clips[0]
  46
  47         def from_clip(field):
  48             if clip:
  49                 return clip.get(field)
  50
  51         audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property(
  52             'audio', webpage, 'audio url')
  53         title = from_clip('title') or self._html_search_meta(
  54             ['og:title', 'og:audio:title', 'audio_title'], webpage)
  55         description = from_clip('description') or clean_html(from_clip('formattedDescription')) or self._og_search_description(webpage)
  56
  57         duration = float_or_none(from_clip('duration') or self._html_search_meta(
  58             'weibo:audio:duration', webpage))
  59
  60         uploader = from_clip('author') or self._html_search_meta(
  61             ['og:audio:artist', 'twitter:audio:artist_name', 'audio_artist'], webpage, 'uploader')
  62         uploader_url = from_clip('author_url') or self._html_search_meta(
  63             'audioboo:channel', webpage, 'uploader url')
  64
  65         return {
  66             'id': video_id,
  67             'url': audio_url,
  68             'title': title,
  69             'description': description,
  70             'duration': duration,
  71             'uploader': uploader,
  72             'uploader_url': uploader_url,
  73         }