_ Git - youtube-dl/blob - youtube_dl/extractor/jove.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 from datetime import datetime
   6
   7 from .common import InfoExtractor
   8 from ..utils import determine_ext, ExtractorError
   9
  10
  11 class JoveIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?jove\.com/video/(?P<id>[0-9]+)'
  13     _CHAPTERS_URL = 'http://www.jove.com/video-chapters?videoid={video_id:}'
  14     _TEST = {
  15         'url': 'http://www.jove.com/video/2744/electrode-positioning-montage-transcranial-direct-current',
  16         'md5': '93723888d82dbd6ba8b3d7d0cd65dd2b',
  17         'info_dict': {
  18             'id': '2744',
  19             'ext': 'mp4',
  20             'title': 'Electrode Positioning and Montage in Transcranial Direct Current Stimulation',
  21             'description': 'Transcranial direct current stimulation (tDCS) is an established technique to modulate cortical excitability1,2. It has been ...',
  22             'thumbnail': 're:^https?://.*\.png$',
  23             'upload_date': '20110523',
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30
  31         webpage = self._download_webpage(url, video_id)
  32         title = self._html_search_meta('citation_title', webpage, 'title')
  33         thumbnail = self._og_search_thumbnail(webpage)
  34         description = self._html_search_meta(
  35             'description', webpage, 'description', fatal=False)
  36         publish_date = self._html_search_meta(
  37             'citation_publication_date', webpage, 'publish date', fatal=False)
  38         if publish_date:
  39             publish_date = datetime.strptime(publish_date,
  40                                              '%Y/%m/%d').strftime('%Y%m%d')
  41
  42         # Not the same as video_id.
  43         chapters_id = self._html_search_regex(
  44             r'/video-chapters\?videoid=([0-9]+)', webpage, 'chapters id')
  45         chapters_xml = self._download_xml(
  46             self._CHAPTERS_URL.format(video_id=chapters_id),
  47             video_id, note='Downloading chapter XML',
  48             errnote='Failed to download chapter 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         ext = determine_ext(video_url)
  55
  56         return {
  57             'id': video_id,
  58             'title': title,
  59             'url': video_url,
  60             'ext': ext,
  61             'thumbnail': thumbnail,
  62             'description': description,
  63             'upload_date': publish_date,
  64         }