diff options
author | Sergey M․ <dstftw@gmail.com> | 2014-09-28 03:26:47 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2014-09-28 03:26:47 +0700 |
commit | a0a90b3ba14ef09735624214f04bfaaa91efe8a2 (patch) | |
tree | f12c7c0e5a33386f6275331fe1e19807744b2ddc /youtube_dl/extractor | |
parent | ee0d90707a38537355bab8527edd9a42d6514aa9 (diff) | |
parent | c6641823238ac70091520fe9b4b02ec3d41cb1a9 (diff) |
Merge branch 'lenaten-ynet'
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/ynet.py | 54 |
2 files changed, 55 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5a14540a3..079221567 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -451,6 +451,7 @@ from .yahoo import ( YahooNewsIE, YahooSearchIE, ) +from .ynet import YnetIE from .youjizz import YouJizzIE from .youku import YoukuIE from .youporn import YouPornIE diff --git a/youtube_dl/extractor/ynet.py b/youtube_dl/extractor/ynet.py new file mode 100644 index 000000000..66d53962a --- /dev/null +++ b/youtube_dl/extractor/ynet.py @@ -0,0 +1,54 @@ +# 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', + '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', + } + } + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + 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), + }
\ No newline at end of file |