1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-24 17:34:33 +01:00
youtube-dl/youtube_dl/extractor/sport5.py

93 lines
3.2 KiB
Python
Raw Normal View History

2014-09-27 19:21:46 +02:00
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import ExtractorError
2014-09-27 19:21:46 +02:00
class Sport5IE(InfoExtractor):
_VALID_URL = r'https?://(?:www|vod)?\.sport5\.co\.il/.*\b(?:Vi|docID)=(?P<id>\d+)'
_TESTS = [
{
2014-09-27 19:21:46 +02:00
'url': 'http://vod.sport5.co.il/?Vc=147&Vi=176331&Page=1',
'info_dict': {
'id': 's5-Y59xx1-GUh2',
'ext': 'mp4',
'title': 'ולנסיה-קורדובה 0:3',
'description': 'אלקאסר, גאייה ופגולי סידרו לקבוצה של נונו ניצחון על קורדובה ואת המקום הראשון בליגה',
'duration': 228,
'categories': list,
},
'skip': 'Blocked outside of Israel',
2014-09-27 19:21:46 +02:00
}, {
'url': 'http://www.sport5.co.il/articles.aspx?FolderID=3075&docID=176372&lang=HE',
'info_dict': {
'id': 's5-SiXxx1-hKh2',
'ext': 'mp4',
'title': 'GOALS_CELTIC_270914.mp4',
'description': '',
'duration': 87,
'categories': list,
},
'skip': 'Blocked outside of Israel',
2014-09-27 19:21:46 +02:00
}
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
media_id = mobj.group('id')
2014-09-27 19:21:46 +02:00
webpage = self._download_webpage(url, media_id)
2014-09-27 19:21:46 +02:00
video_id = self._html_search_regex(r'clipId=([\w-]+)', webpage, 'video id')
2014-09-27 19:21:46 +02:00
metadata = self._download_xml(
'http://sport5-metadata-rr-d.nsacdn.com/vod/vod/%s/HDS/metadata.xml' % video_id,
video_id)
2014-09-27 19:21:46 +02:00
error = metadata.find('./Error')
if error is not None:
raise ExtractorError(
'%s returned error: %s - %s' % (
self.IE_NAME,
error.find('./Name').text,
error.find('./Description').text),
expected=True)
2014-09-27 19:21:46 +02:00
title = metadata.find('./Title').text
description = metadata.find('./Description').text
duration = int(metadata.find('./Duration').text)
2014-09-27 19:21:46 +02:00
posters_el = metadata.find('./PosterLinks')
thumbnails = [{
'url': thumbnail.text,
'width': int(thumbnail.get('width')),
'height': int(thumbnail.get('height')),
} for thumbnail in posters_el.findall('./PosterIMG')] if posters_el is not None else []
categories_el = metadata.find('./Categories')
categories = [
cat.get('name') for cat in categories_el.findall('./Category')
] if categories_el is not None else []
2014-09-27 19:21:46 +02:00
formats = [{
'url': fmt.text,
'ext': 'mp4',
'vbr': int(fmt.get('bitrate')),
'width': int(fmt.get('width')),
'height': int(fmt.get('height')),
} for fmt in metadata.findall('./PlaybackLinks/FileURL')]
2014-09-27 19:21:46 +02:00
self._sort_formats(formats)
return {
'id': video_id,
2014-09-27 19:21:46 +02:00
'title': title,
'description': description,
'thumbnails': thumbnails,
2014-09-27 19:21:46 +02:00
'duration': duration,
'categories': categories,
2014-09-27 19:21:46 +02:00
'formats': formats,
2014-11-23 20:41:03 +01:00
}