youtube_dl/extractor/libsyn.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import unified_strdate
   8
   9
  10 class LibsynIE(InfoExtractor):
  11     _VALID_URL = r'(?P<mainurl>https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+))'
  12
  13     _TESTS = [{
  14         'url': 'http://html5-player.libsyn.com/embed/episode/id/3377616/',
  15         'md5': '443360ee1b58007bc3dcf09b41d093bb',
  16         'info_dict': {
  17             'id': '3377616',
  18             'ext': 'mp3',
  19             'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  20             'description': 'md5:601cb790edd05908957dae8aaa866465',
  21             'upload_date': '20150220',
  22             'thumbnail': 're:^https?://.*',
  23         },
  24     }, {
  25         'url': 'https://html5-player.libsyn.com/embed/episode/id/3727166/height/75/width/200/theme/standard/direction/no/autoplay/no/autonext/no/thumbnail/no/preload/no/no_addthis/no/',
  26         'md5': '6c5cb21acd622d754d3b1a92b582ce42',
  27         'info_dict': {
  28             'id': '3727166',
  29             'ext': 'mp3',
  30             'title': 'Clients From Hell Podcast - How a Sex Toy Company Kickstarted my Freelance Career',
  31             'upload_date': '20150818',
  32             'thumbnail': 're:^https?://.*',
  33         }
  34     }]
  35
  36     def _real_extract(self, url):
  37         m = re.match(self._VALID_URL, url)
  38         video_id = m.group('id')
  39         url = m.group('mainurl')
  40         webpage = self._download_webpage(url, video_id)
  41
  42         formats = [{
  43             'url': media_url,
  44         } for media_url in set(re.findall(r'var\s+mediaURL(?:Libsyn)?\s*=\s*"([^"]+)"', webpage))]
  45
  46         podcast_title = self._search_regex(
  47             r'<h2>([^<]+)</h2>', webpage, 'podcast title', default=None)
  48         episode_title = self._search_regex(
  49             r'(?:<div class="episode-title">|<h3>)([^<]+)</', webpage, 'episode title')
  50
  51         title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
  52
  53         description = self._html_search_regex(
  54             r'<div id="info_text_body">(.+?)</div>', webpage,
  55             'description', default=None)
  56         thumbnail = self._search_regex(
  57             r'<img[^>]+class="info-show-icon"[^>]+src="([^"]+)"',
  58             webpage, 'thumbnail', fatal=False)
  59         release_date = unified_strdate(self._search_regex(
  60             r'<div class="release_date">Released: ([^<]+)<', webpage, 'release date', fatal=False))
  61
  62         return {
  63             'id': video_id,
  64             'title': title,
  65             'description': description,
  66             'thumbnail': thumbnail,
  67             'upload_date': release_date,
  68             'formats': formats,
  69         }