2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..utils import ExtractorError
10 class Sport5IE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www|vod)?\.sport5\.co\.il/.*\b(?:Vi|docID)=(?P<id>\d+)'
14 'url': 'http://vod.sport5.co.il/?Vc=147&Vi=176331&Page=1',
16 'id': 's5-Y59xx1-GUh2',
18 'title': 'ולנסיה-קורדובה 0:3',
19 'description': 'אלקאסר, גאייה ופגולי סידרו לקבוצה של נונו ניצחון על קורדובה ואת המקום הראשון בליגה',
23 'skip': 'Blocked outside of Israel',
25 'url': 'http://www.sport5.co.il/articles.aspx?FolderID=3075&docID=176372&lang=HE',
27 'id': 's5-SiXxx1-hKh2',
29 'title': 'GOALS_CELTIC_270914.mp4',
34 'skip': 'Blocked outside of Israel',
38 def _real_extract(self, url):
39 mobj = re.match(self._VALID_URL, url)
40 media_id = mobj.group('id')
42 webpage = self._download_webpage(url, media_id)
44 video_id = self._html_search_regex('clipId=([\w-]+)', webpage, 'video id')
46 metadata = self._download_xml(
47 'http://sport5-metadata-rr-d.nsacdn.com/vod/vod/%s/HDS/metadata.xml' % video_id,
50 error = metadata.find('./Error')
53 '%s returned error: %s - %s' % (
55 error.find('./Name').text,
56 error.find('./Description').text),
59 title = metadata.find('./Title').text
60 description = metadata.find('./Description').text
61 duration = int(metadata.find('./Duration').text)
63 posters_el = metadata.find('./PosterLinks')
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 []
70 categories_el = metadata.find('./Categories')
72 cat.get('name') for cat in categories_el.findall('./Category')
73 ] if categories_el is not None else []
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)
87 'description': description,
88 'thumbnails': thumbnails,
90 'categories': categories,