youtube-dl/youtube_dl/extractor/ynet.py

54 lines
1.8 KiB
Python
Raw Normal View History

2014-09-27 17:11:22 +00:00
# coding: utf-8
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import compat_urllib_parse
2014-09-27 17:11:22 +00:00
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',
'md5': '002b44ee2f33d50363a1c153bed524cf',
'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',
'md5': '6455046ae1b48cf7e2b7cae285e53a16',
'info_dict': {
'id': 'L-8859-84418',
'ext': 'flv',
'title': "צפו: הנשיקה הלוהטת של תורגי' ויוליה פלוטקין",
'thumbnail': 're:^https?://.*\.jpg',
}
2014-09-27 17:11:22 +00:00
}
]
2014-09-27 17:11:22 +00:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
2014-09-27 17:11:22 +00:00
webpage = self._download_webpage(url, video_id)
2014-09-27 17:11:22 +00:00
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')
2014-09-27 17:11:22 +00:00
return {
'id': video_id,
2014-09-27 17:11:22 +00:00
'title': title,
'formats': self._extract_f4m_formats(f4m_url, video_id),
2014-09-27 17:11:22 +00:00
'thumbnail': self._og_search_thumbnail(webpage),
}