1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00

[sport5] Add new extractor

This commit is contained in:
net 2014-09-27 20:21:46 +03:00
parent 11b3ce8509
commit b66745288e
2 changed files with 71 additions and 0 deletions

View file

@ -340,6 +340,7 @@ from .spiegel import SpiegelIE, SpiegelArticleIE
from .spiegeltv import SpiegeltvIE
from .spike import SpikeIE
from .sportdeutschland import SportDeutschlandIE
from .sport5 import Sport5IE
from .stanfordoc import StanfordOpenClassroomIE
from .steam import SteamIE
from .streamcloud import StreamcloudIE

View file

@ -0,0 +1,70 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from youtube_dl.utils import compat_str, compat_urlretrieve
class Sport5IE(InfoExtractor):
_VALID_URL = r'http://.*sport5\.co\.il'
_TESTS = [{
'url': 'http://vod.sport5.co.il/?Vc=147&Vi=176331&Page=1',
'info_dict': {
'id': 's5-Y59xx1-GUh2',
'ext': 'mp4',
'title': 'md5:4a2a5eba7e7dc88fdc446cbca8a41c79',
}
}, {
'url': 'http://www.sport5.co.il/articles.aspx?FolderID=3075&docID=176372&lang=HE',
'info_dict': {
'id': 's5-SiXxx1-hKh2',
'ext': 'mp4',
'title': 'md5:5cb1c6bfc0f16086e59f6683013f8e02',
}
}
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
webpage = self._download_webpage(url, '')
media_id = self._html_search_regex('clipId=(s5-\w+-\w+)', webpage, 'media id')
xml = self._download_xml(
'http://sport5-metadata-rr-d.nsacdn.com/vod/vod/%s/HDS/metadata.xml' % media_id,
media_id, 'Downloading media XML')
title = xml.find('./Title').text
duration = xml.find('./Duration').text
description = xml.find('./Description').text
thumbnail = xml.find('./PosterLinks/PosterIMG').text
player_url = xml.find('./PlaybackLinks/PlayerUrl').text
file_els = xml.findall('./PlaybackLinks/FileURL')
formats = []
for file_el in file_els:
bitrate = file_el.attrib.get('bitrate')
width = int(file_el.attrib.get('width'))
height = int(file_el.attrib.get('height'))
formats.append({
'url': compat_str(file_el.text),
'ext': 'mp4',
'height': height,
'width': width
})
self._sort_formats(formats)
return {
'id': media_id,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
'player_url': player_url,
}