yt_dlp/extractor/jove.py

   1 from .common import InfoExtractor
   2 from ..utils import ExtractorError, unified_strdate
   3
   4
   5 class JoveIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?jove\.com/video/(?P<id>[0-9]+)'
   7     _CHAPTERS_URL = 'http://www.jove.com/video-chapters?videoid={video_id:}'
   8     _TESTS = [
   9         {
  10             'url': 'http://www.jove.com/video/2744/electrode-positioning-montage-transcranial-direct-current',
  11             'md5': '93723888d82dbd6ba8b3d7d0cd65dd2b',
  12             'info_dict': {
  13                 'id': '2744',
  14                 'ext': 'mp4',
  15                 'title': 'Electrode Positioning and Montage in Transcranial Direct Current Stimulation',
  16                 'description': 'md5:015dd4509649c0908bc27f049e0262c6',
  17                 'thumbnail': r're:^https?://.*\.png$',
  18                 'upload_date': '20110523',
  19             },
  20         },
  21         {
  22             'url': 'http://www.jove.com/video/51796/culturing-caenorhabditis-elegans-axenic-liquid-media-creation',
  23             'md5': '914aeb356f416811d911996434811beb',
  24             'info_dict': {
  25                 'id': '51796',
  26                 'ext': 'mp4',
  27                 'title': 'Culturing Caenorhabditis elegans in Axenic Liquid Media and Creation of Transgenic Worms by Microparticle Bombardment',
  28                 'description': 'md5:35ff029261900583970c4023b70f1dc9',
  29                 'thumbnail': r're:^https?://.*\.png$',
  30                 'upload_date': '20140802',
  31             },
  32         },
  33
  34     ]
  35
  36     def _real_extract(self, url):
  37         mobj = self._match_valid_url(url)
  38         video_id = mobj.group('id')
  39
  40         webpage = self._download_webpage(url, video_id)
  41
  42         chapters_id = self._html_search_regex(
  43             r'/video-chapters\?videoid=([0-9]+)', webpage, 'chapters id')
  44
  45         chapters_xml = self._download_xml(
  46             self._CHAPTERS_URL.format(video_id=chapters_id),
  47             video_id, note='Downloading chapters XML',
  48             errnote='Failed to download chapters XML')
  49
  50         video_url = chapters_xml.attrib.get('video')
  51         if not video_url:
  52             raise ExtractorError('Failed to get the video URL')
  53
  54         title = self._html_search_meta('citation_title', webpage, 'title')
  55         thumbnail = self._og_search_thumbnail(webpage)
  56         description = self._html_search_regex(
  57             r'<div id="section_body_summary"><p class="jove_content">(.+?)</p>',
  58             webpage, 'description', fatal=False)
  59         publish_date = unified_strdate(self._html_search_meta(
  60             'citation_publication_date', webpage, 'publish date', fatal=False))
  61         comment_count = int(self._html_search_regex(
  62             r'<meta name="num_comments" content="(\d+) Comments?"',
  63             webpage, 'comment count', fatal=False))
  64
  65         return {
  66             'id': video_id,
  67             'title': title,
  68             'url': video_url,
  69             'thumbnail': thumbnail,
  70             'description': description,
  71             'upload_date': publish_date,
  72             'comment_count': comment_count,
  73         }