1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-27 16:23:00 +08:00
youtube-dl/youtube_dl/extractor/ynet.py
Philipp Hagemeister 8d11b59bbb [ynet] Remove test md5sums
These fluctuate regularly.
2014-10-27 00:06:00 +01:00

50 lines
1.7 KiB
Python

# coding: utf-8
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import compat_urllib_parse
class YnetIE(InfoExtractor):
_VALID_URL = r'http://(?:.+?\.)?ynet\.co\.il/(?:.+?/)?0,7340,(?P<id>L(?:-[0-9]+)+),00\.html'
_TESTS = [
{
'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html',
'info_dict': {
'id': 'L-11659-99244',
'ext': 'flv',
'title': 'איש לא יודע מאיפה באנו',
'thumbnail': 're:^https?://.*\.jpg',
}
}, {
'url': 'http://hot.ynet.co.il/home/0,7340,L-8859-84418,00.html',
'info_dict': {
'id': 'L-8859-84418',
'ext': 'flv',
'title': "צפו: הנשיקה הלוהטת של תורגי' ויוליה פלוטקין",
'thumbnail': 're:^https?://.*\.jpg',
}
}
]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage))
config = json.loads(self._search_regex(r'config=({.+?})$', content, 'video config'))
f4m_url = config['clip']['url']
title = self._og_search_title(webpage)
m = re.search(r'ynet - HOT -- (["\']+)(?P<title>.+?)\1', title)
if m:
title = m.group('title')
return {
'id': video_id,
'title': title,
'formats': self._extract_f4m_formats(f4m_url, video_id),
'thumbnail': self._og_search_thumbnail(webpage),
}