Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/jove.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     unified_strdate
   9 )
  10
  11
  12 class JoveIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?jove\.com/video/(?P<id>[0-9]+)'
  14     _CHAPTERS_URL = 'http://www.jove.com/video-chapters?videoid={video_id:}'
  15     _TESTS = [
  16         {
  17             'url': 'http://www.jove.com/video/2744/electrode-positioning-montage-transcranial-direct-current',
  18             'md5': '93723888d82dbd6ba8b3d7d0cd65dd2b',
  19             'info_dict': {
  20                 'id': '2744',
  21                 'ext': 'mp4',
  22                 'title': 'Electrode Positioning and Montage in Transcranial Direct Current Stimulation',
  23                 'description': 'md5:015dd4509649c0908bc27f049e0262c6',
  24                 'thumbnail': r're:^https?://.*\.png$',
  25                 'upload_date': '20110523',
  26             }
  27         },
  28         {
  29             'url': 'http://www.jove.com/video/51796/culturing-caenorhabditis-elegans-axenic-liquid-media-creation',
  30             'md5': '914aeb356f416811d911996434811beb',
  31             'info_dict': {
  32                 'id': '51796',
  33                 'ext': 'mp4',
  34                 'title': 'Culturing Caenorhabditis elegans in Axenic Liquid Media and Creation of Transgenic Worms by Microparticle Bombardment',
  35                 'description': 'md5:35ff029261900583970c4023b70f1dc9',
  36                 'thumbnail': r're:^https?://.*\.png$',
  37                 'upload_date': '20140802',
  38             }
  39         },
  40
  41     ]
  42
  43     def _real_extract(self, url):
  44         mobj = re.match(self._VALID_URL, url)
  45         video_id = mobj.group('id')
  46
  47         webpage = self._download_webpage(url, video_id)
  48
  49         chapters_id = self._html_search_regex(
  50             r'/video-chapters\?videoid=([0-9]+)', webpage, 'chapters id')
  51
  52         chapters_xml = self._download_xml(
  53             self._CHAPTERS_URL.format(video_id=chapters_id),
  54             video_id, note='Downloading chapters XML',
  55             errnote='Failed to download chapters XML')
  56
  57         video_url = chapters_xml.attrib.get('video')
  58         if not video_url:
  59             raise ExtractorError('Failed to get the video URL')
  60
  61         title = self._html_search_meta('citation_title', webpage, 'title')
  62         thumbnail = self._og_search_thumbnail(webpage)
  63         description = self._html_search_regex(
  64             r'<div id="section_body_summary"><p class="jove_content">(.+?)</p>',
  65             webpage, 'description', fatal=False)
  66         publish_date = unified_strdate(self._html_search_meta(
  67             'citation_publication_date', webpage, 'publish date', fatal=False))
  68         comment_count = int(self._html_search_regex(
  69             r'<meta name="num_comments" content="(\d+) Comments?"',
  70             webpage, 'comment count', fatal=False))
  71
  72         return {
  73             'id': video_id,
  74             'title': title,
  75             'url': video_url,
  76             'thumbnail': thumbnail,
  77             'description': description,
  78             'upload_date': publish_date,
  79             'comment_count': comment_count,
  80         }