yt_dlp/extractor/sport5.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..utils import ExtractorError
   7
   8
   9 class Sport5IE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www|vod)?\.sport5\.co\.il/.*\b(?:Vi|docID)=(?P<id>\d+)'
  11     _TESTS = [
  12         {
  13             'url': 'http://vod.sport5.co.il/?Vc=147&Vi=176331&Page=1',
  14             'info_dict': {
  15                 'id': 's5-Y59xx1-GUh2',
  16                 'ext': 'mp4',
  17                 'title': 'ולנסיה-קורדובה 0:3',
  18                 'description': 'אלקאסר, גאייה ופגולי סידרו לקבוצה של נונו ניצחון על קורדובה ואת המקום הראשון בליגה',
  19                 'duration': 228,
  20                 'categories': list,
  21             },
  22             'skip': 'Blocked outside of Israel',
  23         }, {
  24             'url': 'http://www.sport5.co.il/articles.aspx?FolderID=3075&docID=176372&lang=HE',
  25             'info_dict': {
  26                 'id': 's5-SiXxx1-hKh2',
  27                 'ext': 'mp4',
  28                 'title': 'GOALS_CELTIC_270914.mp4',
  29                 'description': '',
  30                 'duration': 87,
  31                 'categories': list,
  32             },
  33             'skip': 'Blocked outside of Israel',
  34         }
  35     ]
  36
  37     def _real_extract(self, url):
  38         mobj = self._match_valid_url(url)
  39         media_id = mobj.group('id')
  40
  41         webpage = self._download_webpage(url, media_id)
  42
  43         video_id = self._html_search_regex(r'clipId=([\w-]+)', webpage, 'video id')
  44
  45         metadata = self._download_xml(
  46             'http://sport5-metadata-rr-d.nsacdn.com/vod/vod/%s/HDS/metadata.xml' % video_id,
  47             video_id)
  48
  49         error = metadata.find('./Error')
  50         if error is not None:
  51             raise ExtractorError(
  52                 '%s returned error: %s - %s' % (
  53                     self.IE_NAME,
  54                     error.find('./Name').text,
  55                     error.find('./Description').text),
  56                 expected=True)
  57
  58         title = metadata.find('./Title').text
  59         description = metadata.find('./Description').text
  60         duration = int(metadata.find('./Duration').text)
  61
  62         posters_el = metadata.find('./PosterLinks')
  63         thumbnails = [{
  64             'url': thumbnail.text,
  65             'width': int(thumbnail.get('width')),
  66             'height': int(thumbnail.get('height')),
  67         } for thumbnail in posters_el.findall('./PosterIMG')] if posters_el is not None else []
  68
  69         categories_el = metadata.find('./Categories')
  70         categories = [
  71             cat.get('name') for cat in categories_el.findall('./Category')
  72         ] if categories_el is not None else []
  73
  74         formats = [{
  75             'url': fmt.text,
  76             'ext': 'mp4',
  77             'vbr': int(fmt.get('bitrate')),
  78             'width': int(fmt.get('width')),
  79             'height': int(fmt.get('height')),
  80         } for fmt in metadata.findall('./PlaybackLinks/FileURL')]
  81         self._sort_formats(formats)
  82
  83         return {
  84             'id': video_id,
  85             'title': title,
  86             'description': description,
  87             'thumbnails': thumbnails,
  88             'duration': duration,
  89             'categories': categories,
  90             'formats': formats,
  91         }