]> git.bitcoin.ninja Git - youtube-dl/commitdiff
[karaoketv] Add new extractor
authornet <net@h-MacBook-Pro-sl-net.local>
Mon, 29 Sep 2014 18:58:42 +0000 (21:58 +0300)
committernet <net@h-MacBook-Pro-sl-net.local>
Mon, 29 Sep 2014 18:58:42 +0000 (21:58 +0300)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/karaoketv.py [new file with mode: 0644]

index 07922156739c7d620640d613911600997a4cf8f2..d12e741a0bd836858d8db31ddf0b32c13bfd9e2d 100644 (file)
@@ -173,6 +173,7 @@ from .jukebox import JukeboxIE
 from .justintv import JustinTVIE
 from .jpopsukitv import JpopsukiIE
 from .kankan import KankanIE
+from .karaoketv import KaraoketvIE
 from .keezmovies import KeezMoviesIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
diff --git a/youtube_dl/extractor/karaoketv.py b/youtube_dl/extractor/karaoketv.py
new file mode 100644 (file)
index 0000000..4d50308
--- /dev/null
@@ -0,0 +1,47 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import json
+import sys
+
+from .common import InfoExtractor
+from ..utils import compat_urllib_parse, ExtractorError
+
+
+class KaraoketvIE(InfoExtractor):
+    _VALID_URL = r'http://karaoketv\.co\.il/\?container=songs&id=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://karaoketv.co.il/?container=songs&id=171568',
+        'info_dict': {
+            'id': '171568',
+            'ext': 'mp4',
+            'title': 'אל העולם שלך - רותם כהן - שרים קריוקי',
+        }
+    }
+
+    def _real_extract(self, url):
+
+        # BUG: SSL23_GET_SERVER_HELLO:unknown protocol 
+        if sys.hexversion < 0x03000000:
+            raise ExtractorError("Only python 3 supported.\n")
+
+        mobj = re.match(self._VALID_URL, url)
+        
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        settings_json = compat_urllib_parse.unquote_plus(self._search_regex(r'config=(.*)', self._og_search_video_url(webpage ,video_id), ''))
+        
+        urls_info_webpage = self._download_webpage(settings_json, 'Downloading settings json')
+
+        urls_info_json = json.loads(urls_info_webpage.replace('\'', '"'))
+
+        url = urls_info_json['playlist'][0]['url']
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'url': url,
+        }
\ No newline at end of file