youtube_dl/extractor/nerdist.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6 from ..utils import (
   7     determine_ext,
   8     parse_iso8601,
   9     xpath_text,
  10 )
  11
  12
  13 class NerdistIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?nerdist\.com/vepisode/(?P<id>[^/?#]+)'
  15     _TEST = {
  16         'url': 'http://www.nerdist.com/vepisode/exclusive-which-dc-characters-w',
  17         'md5': '3698ed582931b90d9e81e02e26e89f23',
  18         'info_dict': {
  19             'display_id': 'exclusive-which-dc-characters-w',
  20             'id': 'RPHpvJyr',
  21             'ext': 'mp4',
  22             'title': 'Your TEEN TITANS Revealed! Who\'s on the show?',
  23             'thumbnail': 're:^https?://.*/thumbs/.*\.jpg$',
  24             'description': 'Exclusive: Find out which DC Comics superheroes will star in TEEN TITANS Live-Action TV Show on Nerdist News with Jessica Chobot!',
  25             'uploader': 'Eric Diaz',
  26             'upload_date': '20150202',
  27             'timestamp': 1422892808,
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         display_id = self._match_id(url)
  33         webpage = self._download_webpage(url, display_id)
  34
  35         video_id = self._search_regex(
  36             r'''(?x)<script\s+(?:type="text/javascript"\s+)?
  37                 src="https?://content\.nerdist\.com/players/([a-zA-Z0-9_]+)-''',
  38             webpage, 'video ID')
  39         timestamp = parse_iso8601(self._html_search_meta(
  40             'shareaholic:article_published_time', webpage, 'upload date'))
  41         uploader = self._html_search_meta(
  42             'shareaholic:article_author_name', webpage, 'article author')
  43
  44         doc = self._download_xml(
  45             'http://content.nerdist.com/jw6/%s.xml' % video_id, video_id)
  46         video_info = doc.find('.//item')
  47         title = xpath_text(video_info, './title', fatal=True)
  48         description = xpath_text(video_info, './description')
  49         thumbnail = xpath_text(
  50             video_info, './{http://rss.jwpcdn.com/}image', 'thumbnail')
  51
  52         formats = []
  53         for source in video_info.findall('./{http://rss.jwpcdn.com/}source'):
  54             vurl = source.attrib['file']
  55             ext = determine_ext(vurl)
  56             if ext == 'm3u8':
  57                 formats.extend(self._extract_m3u8_formats(
  58                     vurl, video_id, entry_protocol='m3u8_native', ext='mp4',
  59                     preference=0))
  60             elif ext == 'smil':
  61                 formats.extend(self._extract_smil_formats(
  62                     vurl, video_id, fatal=False
  63                 ))
  64             else:
  65                 formats.append({
  66                     'format_id': ext,
  67                     'url': vurl,
  68                 })
  69         self._sort_formats(formats)
  70
  71         return {
  72             'id': video_id,
  73             'display_id': display_id,
  74             'title': title,
  75             'description': description,
  76             'thumbnail': thumbnail,
  77             'timestamp': timestamp,
  78             'formats': formats,
  79             'uploader': uploader,
  80         }