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_str,
   8     compat_urlparse,
   9 )
  10 from ..utils import (
  11     ExtractorError,
  12     determine_ext,
  13     int_or_none,
  14     sanitized_Request,
  15 )
  16
  17
  18 class VoiceRepublicIE(InfoExtractor):
  19     _VALID_URL = r'https?://voicerepublic\.com/(?:talks|embed)/(?P<id>[0-9a-z-]+)'
  20     _TESTS = [{
  21         'url': 'http://voicerepublic.com/talks/watching-the-watchers-building-a-sousveillance-state',
  22         'md5': 'b9174d651323f17783000876347116e3',
  23         'info_dict': {
  24             'id': '2296',
  25             'display_id': 'watching-the-watchers-building-a-sousveillance-state',
  26             'ext': 'm4a',
  27             'title': 'Watching the Watchers: Building a Sousveillance State',
  28             'description': 'Secret surveillance programs have metadata too. The people and companies that operate secret surveillance programs can be surveilled.',
  29             'thumbnail': 're:^https?://.*\.(?:png|jpg)$',
  30             'duration': 1800,
  31             'view_count': int,
  32         }
  33     }, {
  34         'url': 'http://voicerepublic.com/embed/watching-the-watchers-building-a-sousveillance-state',
  35         'only_matching': True,
  36     }]
  37
  38     def _real_extract(self, url):
  39         display_id = self._match_id(url)
  40
  41         req = sanitized_Request(
  42             compat_urlparse.urljoin(url, '/talks/%s' % display_id))
  43         # Older versions of Firefox get redirected to an "upgrade browser" page
  44         req.add_header('User-Agent', 'youtube-dl')
  45         webpage = self._download_webpage(req, display_id)
  46
  47         if '>Queued for processing, please stand by...<' in webpage:
  48             raise ExtractorError(
  49                 'Audio is still queued for processing', expected=True)
  50
  51         config = self._search_regex(
  52             r'(?s)return ({.+?});\s*\n', webpage,
  53             'data', default=None)
  54         data = self._parse_json(config, display_id, fatal=False) if config else None
  55         if data:
  56             title = data['title']
  57             description = data.get('teaser')
  58             talk_id = compat_str(data.get('talk_id') or display_id)
  59             talk = data['talk']
  60             duration = int_or_none(talk.get('duration'))
  61             formats = [{
  62                 'url': compat_urlparse.urljoin(url, talk_url),
  63                 'format_id': format_id,
  64                 'ext': determine_ext(talk_url) or format_id,
  65                 'vcodec': 'none',
  66             } for format_id, talk_url in talk['links'].items()]
  67         else:
  68             title = self._og_search_title(webpage)
  69             description = self._html_search_regex(
  70                 r"(?s)<div class='talk-teaser'[^>]*>(.+?)</div>",
  71                 webpage, 'description', fatal=False)
  72             talk_id = self._search_regex(
  73                 [r"id='jc-(\d+)'", r"data-shareable-id='(\d+)'"],
  74                 webpage, 'talk id', default=None) or display_id
  75             duration = None
  76             player = self._search_regex(
  77                 r"class='vr-player jp-jplayer'([^>]+)>", webpage, 'player')
  78             formats = [{
  79                 'url': compat_urlparse.urljoin(url, talk_url),
  80                 'format_id': format_id,
  81                 'ext': determine_ext(talk_url) or format_id,
  82                 'vcodec': 'none',
  83             } for format_id, talk_url in re.findall(r"data-([^=]+)='([^']+)'", player)]
  84         self._sort_formats(formats)
  85
  86         thumbnail = self._og_search_thumbnail(webpage)
  87         view_count = int_or_none(self._search_regex(
  88             r"class='play-count[^']*'>\s*(\d+) plays",
  89             webpage, 'play count', fatal=False))
  90
  91         return {
  92             'id': talk_id,
  93             'display_id': display_id,
  94             'title': title,
  95             'description': description,
  96             'thumbnail': thumbnail,
  97             'duration': duration,
  98             'view_count': view_count,
  99             'formats': formats,
 100         }