_ Git - youtube-dl/blob - youtube_dl/extractor/libsyn.py

   1 # encoding: utf-8
   2 from .common import InfoExtractor
   3 from ..utils import (
   4     unified_strdate,
   5 )
   6
   7 class LibsynIE(InfoExtractor):
   8     _VALID_URL = r'(?:https?:)?//html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+)(?:/.*)?'
   9     _TESTS = [{
  10         'url': "http://html5-player.libsyn.com/embed/episode/id/3377616/",
  11         'info_dict': {
  12             'id': "3377616",
  13             'ext': "mp3",
  14             'title': "Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  15             'description': "<p>Bassem Youssef joins executive producer Steve Bodow and senior producer Sara Taksler for a conversation about how&nbsp;<em style=\"font-family: Tahoma, Geneva, sans-serif; font-size: 12.8000001907349px;\">The Daily Show</em>&nbsp;inspired Bassem to create&nbsp;<em style=\"font-family: Tahoma, Geneva, sans-serif; font-size: 12.8000001907349px;\">Al-Bernameg</em>, his massively popular (and now banned) Egyptian news satire program. Sara discusses her soon-to-be-released documentary,&nbsp;<em style=\"font-family: Tahoma, Geneva, sans-serif; font-size: 12.8000001907349px;\">Tickling Giants</em>, which chronicles how Bassem and his staff risked their safety every day to tell jokes.</p>",
  16         },
  17     }]
  18
  19     def _real_extract(self, url):
  20         if url.startswith('//'):
  21             url = 'https:' + url
  22         display_id = self._match_id(url)
  23         webpage = self._download_webpage(url, display_id)
  24
  25         podcast_title         = self._search_regex(r'<h2>(.*?)</h2>', webpage, 'show title')
  26         podcast_episode_title = self._search_regex(r'<h3>(.*?)</h3>', webpage, 'episode title')
  27         podcast_date          = unified_strdate(self._search_regex(r'<div class="release_date">Released: (.*?)</div>', webpage, 'release date'))
  28         podcast_description   = self._search_regex(r'<div id="info_text_body">(.*?)</div>', webpage, 'description')
  29
  30         url0 = self._search_regex(r'var mediaURLLibsyn = "(?P<url0>https?://.*)";', webpage, 'first media URL')
  31         url1 = self._search_regex(r'var mediaURL = "(?P<url1>https?://.*)";', webpage, 'second media URL')
  32
  33         if url0 != url1:
  34             formats = [{
  35                 'url': url0
  36             }, {
  37                 'url': url1
  38             }]
  39         else:
  40             formats = [{
  41                 'url': url0
  42             }]
  43
  44         return {
  45             'id': display_id,
  46             'title': podcast_episode_title,
  47             'description': podcast_description,
  48             'upload_date': podcast_date,
  49             'formats': formats,
  50         }