yt_dlp/extractor/jove.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     unified_strdate
   5 )
   6
   7
   8 class JoveIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?jove\.com/video/(?P<id>[0-9]+)'
  10     _CHAPTERS_URL = 'http://www.jove.com/video-chapters?videoid={video_id:}'
  11     _TESTS = [
  12         {
  13             'url': 'http://www.jove.com/video/2744/electrode-positioning-montage-transcranial-direct-current',
  14             'md5': '93723888d82dbd6ba8b3d7d0cd65dd2b',
  15             'info_dict': {
  16                 'id': '2744',
  17                 'ext': 'mp4',
  18                 'title': 'Electrode Positioning and Montage in Transcranial Direct Current Stimulation',
  19                 'description': 'md5:015dd4509649c0908bc27f049e0262c6',
  20                 'thumbnail': r're:^https?://.*\.png$',
  21                 'upload_date': '20110523',
  22             }
  23         },
  24         {
  25             'url': 'http://www.jove.com/video/51796/culturing-caenorhabditis-elegans-axenic-liquid-media-creation',
  26             'md5': '914aeb356f416811d911996434811beb',
  27             'info_dict': {
  28                 'id': '51796',
  29                 'ext': 'mp4',
  30                 'title': 'Culturing Caenorhabditis elegans in Axenic Liquid Media and Creation of Transgenic Worms by Microparticle Bombardment',
  31                 'description': 'md5:35ff029261900583970c4023b70f1dc9',
  32                 'thumbnail': r're:^https?://.*\.png$',
  33                 'upload_date': '20140802',
  34             }
  35         },
  36
  37     ]
  38
  39     def _real_extract(self, url):
  40         mobj = self._match_valid_url(url)
  41         video_id = mobj.group('id')
  42
  43         webpage = self._download_webpage(url, video_id)
  44
  45         chapters_id = self._html_search_regex(
  46             r'/video-chapters\?videoid=([0-9]+)', webpage, 'chapters id')
  47
  48         chapters_xml = self._download_xml(
  49             self._CHAPTERS_URL.format(video_id=chapters_id),
  50             video_id, note='Downloading chapters XML',
  51             errnote='Failed to download chapters XML')
  52
  53         video_url = chapters_xml.attrib.get('video')
  54         if not video_url:
  55             raise ExtractorError('Failed to get the video URL')
  56
  57         title = self._html_search_meta('citation_title', webpage, 'title')
  58         thumbnail = self._og_search_thumbnail(webpage)
  59         description = self._html_search_regex(
  60             r'<div id="section_body_summary"><p class="jove_content">(.+?)</p>',
  61             webpage, 'description', fatal=False)
  62         publish_date = unified_strdate(self._html_search_meta(
  63             'citation_publication_date', webpage, 'publish date', fatal=False))
  64         comment_count = int(self._html_search_regex(
  65             r'<meta name="num_comments" content="(\d+) Comments?"',
  66             webpage, 'comment count', fatal=False))
  67
  68         return {
  69             'id': video_id,
  70             'title': title,
  71             'url': video_url,
  72             'thumbnail': thumbnail,
  73             'description': description,
  74             'upload_date': publish_date,
  75             'comment_count': comment_count,
  76         }