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