Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/sport5.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import ExtractorError
   8
   9
  10 class Sport5IE(InfoExtractor):
  11     _VALID_URL = r'http://(?:www|vod)?\.sport5\.co\.il/.*\b(?:Vi|docID)=(?P<id>\d+)'
  12     _TESTS = [
  13         {
  14             'url': 'http://vod.sport5.co.il/?Vc=147&Vi=176331&Page=1',
  15             'info_dict': {
  16                 'id': 's5-Y59xx1-GUh2',
  17                 'ext': 'mp4',
  18                 'title': 'ולנסיה-קורדובה 0:3',
  19                 'description': 'אלקאסר, גאייה ופגולי סידרו לקבוצה של נונו ניצחון על קורדובה ואת המקום הראשון בליגה',
  20                 'duration': 228,
  21                 'categories': list,
  22             },
  23             'skip': 'Blocked outside of Israel',
  24         }, {
  25             'url': 'http://www.sport5.co.il/articles.aspx?FolderID=3075&docID=176372&lang=HE',
  26             'info_dict': {
  27                 'id': 's5-SiXxx1-hKh2',
  28                 'ext': 'mp4',
  29                 'title': 'GOALS_CELTIC_270914.mp4',
  30                 'description': '',
  31                 'duration': 87,
  32                 'categories': list,
  33             },
  34             'skip': 'Blocked outside of Israel',
  35         }
  36     ]
  37
  38     def _real_extract(self, url):
  39         mobj = re.match(self._VALID_URL, url)
  40         media_id = mobj.group('id')
  41
  42         webpage = self._download_webpage(url, media_id)
  43
  44         video_id = self._html_search_regex('clipId=([\w-]+)', webpage, 'video id')
  45
  46         metadata = self._download_xml(
  47             'http://sport5-metadata-rr-d.nsacdn.com/vod/vod/%s/HDS/metadata.xml' % video_id,
  48             video_id)
  49
  50         error = metadata.find('./Error')
  51         if error is not None:
  52             raise ExtractorError(
  53                 '%s returned error: %s - %s' % (
  54                     self.IE_NAME,
  55                     error.find('./Name').text,
  56                     error.find('./Description').text),
  57                 expected=True)
  58
  59         title = metadata.find('./Title').text
  60         description = metadata.find('./Description').text
  61         duration = int(metadata.find('./Duration').text)
  62
  63         posters_el = metadata.find('./PosterLinks')
  64         thumbnails = [{
  65             'url': thumbnail.text,
  66             'width': int(thumbnail.get('width')),
  67             'height': int(thumbnail.get('height')),
  68         } for thumbnail in posters_el.findall('./PosterIMG')] if posters_el is not None else []
  69
  70         categories_el = metadata.find('./Categories')
  71         categories = [
  72             cat.get('name') for cat in categories_el.findall('./Category')
  73         ] if categories_el is not None else []
  74
  75         formats = [{
  76             'url': fmt.text,
  77             'ext': 'mp4',
  78             'vbr': int(fmt.get('bitrate')),
  79             'width': int(fmt.get('width')),
  80             'height': int(fmt.get('height')),
  81         } for fmt in metadata.findall('./PlaybackLinks/FileURL')]
  82         self._sort_formats(formats)
  83
  84         return {
  85             'id': video_id,
  86             'title': title,
  87             'description': description,
  88             'thumbnails': thumbnails,
  89             'duration': duration,
  90             'categories': categories,
  91             'formats': formats,
  92         }