Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/voicerepublic.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_urllib_request,
   8     compat_urlparse,
   9 )
  10 from ..utils import (
  11     ExtractorError,
  12     determine_ext,
  13     int_or_none,
  14 )
  15
  16
  17 class VoiceRepublicIE(InfoExtractor):
  18     _VALID_URL = r'https?://voicerepublic\.com/(?:talks|embed)/(?P<id>[0-9a-z-]+)'
  19     _TESTS = [{
  20         'url': 'http://voicerepublic.com/talks/watching-the-watchers-building-a-sousveillance-state',
  21         'md5': '0554a24d1657915aa8e8f84e15dc9353',
  22         'info_dict': {
  23             'id': '2296',
  24             'display_id': 'watching-the-watchers-building-a-sousveillance-state',
  25             'ext': 'm4a',
  26             'title': 'Watching the Watchers: Building a Sousveillance State',
  27             'description': 'md5:715ba964958afa2398df615809cfecb1',
  28             'thumbnail': 're:^https?://.*\.(?:png|jpg)$',
  29             'duration': 1800,
  30             'view_count': int,
  31         }
  32     }, {
  33         'url': 'http://voicerepublic.com/embed/watching-the-watchers-building-a-sousveillance-state',
  34         'only_matching': True,
  35     }]
  36
  37     def _real_extract(self, url):
  38         display_id = self._match_id(url)
  39
  40         req = compat_urllib_request.Request(
  41             compat_urlparse.urljoin(url, '/talks/%s' % display_id))
  42         # Older versions of Firefox get redirected to an "upgrade browser" page
  43         req.add_header('User-Agent', 'youtube-dl')
  44         webpage = self._download_webpage(req, display_id)
  45
  46         if '>Queued for processing, please stand by...<' in webpage:
  47             raise ExtractorError(
  48                 'Audio is still queued for processing', expected=True)
  49
  50         config = self._search_regex(
  51             r'(?s)return ({.+?});\s*\n', webpage,
  52             'data', default=None)
  53         data = self._parse_json(config, display_id, fatal=False) if config else None
  54         if data:
  55             title = data['title']
  56             description = data.get('teaser')
  57             talk_id = data.get('talk_id') or display_id
  58             talk = data['talk']
  59             duration = int_or_none(talk.get('duration'))
  60             formats = [{
  61                 'url': compat_urlparse.urljoin(url, talk_url),
  62                 'format_id': format_id,
  63                 'ext': determine_ext(talk_url) or format_id,
  64                 'vcodec': 'none',
  65             } for format_id, talk_url in talk['links'].items()]
  66         else:
  67             title = self._og_search_title(webpage)
  68             description = self._html_search_regex(
  69                 r"(?s)<div class='talk-teaser'[^>]*>(.+?)</div>",
  70                 webpage, 'description', fatal=False)
  71             talk_id = self._search_regex(
  72                 [r"id='jc-(\d+)'", r"data-shareable-id='(\d+)'"],
  73                 webpage, 'talk id', default=None) or display_id
  74             duration = None
  75             player = self._search_regex(
  76                 r"class='vr-player jp-jplayer'([^>]+)>", webpage, 'player')
  77             formats = [{
  78                 'url': compat_urlparse.urljoin(url, talk_url),
  79                 'format_id': format_id,
  80                 'ext': determine_ext(talk_url) or format_id,
  81                 'vcodec': 'none',
  82             } for format_id, talk_url in re.findall(r"data-([^=]+)='([^']+)'", player)]
  83         self._sort_formats(formats)
  84
  85         thumbnail = self._og_search_thumbnail(webpage)
  86         view_count = int_or_none(self._search_regex(
  87             r"class='play-count[^']*'>\s*(\d+) plays",
  88             webpage, 'play count', fatal=False))
  89
  90         return {
  91             'id': talk_id,
  92             'display_id': display_id,
  93             'title': title,
  94             'description': description,
  95             'thumbnail': thumbnail,
  96             'duration': duration,
  97             'view_count': view_count,
  98             'formats': formats,
  99         }