]> git.bitcoin.ninja Git - youtube-dl/commitdiff
Add support for http://www.extremetube.com
authorrzhxeo <rzhxeot7z81b4700@mailcatch.com>
Mon, 28 Oct 2013 16:35:01 +0000 (17:35 +0100)
committerrzhxeo <rzhxeot7z81b4700@mailcatch.com>
Mon, 28 Oct 2013 16:35:01 +0000 (17:35 +0100)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/extremetube.py [new file with mode: 0644]

index 0d933986f10af717befe791eb4565ab40c5f48b7..5eed1eebd1f354ba42059cc1102a40c9f435ad99 100644 (file)
@@ -39,6 +39,7 @@ from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .escapist import EscapistIE
 from .exfm import ExfmIE
+from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
 from .fktv import (
diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py
new file mode 100644 (file)
index 0000000..981de43
--- /dev/null
@@ -0,0 +1,52 @@
+import os
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse_urlparse,
+    compat_urllib_request,
+    compat_urllib_parse,
+)
+
+class ExtremeTubeIE(InfoExtractor):
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
+    _TEST = {
+        u'url': u'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
+        u'file': u'652431.mp4',
+        u'md5': u'1fb9228f5e3332ec8c057d6ac36f33e0',
+        u'info_dict': {
+            u"title": u"Music Video 14 british euro brit european cumshots swallow",
+            u"uploader": u"unknown",
+            u"age_limit": 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('videoid')
+        url = 'http://www.' + mobj.group('url')
+
+        req = compat_urllib_request.Request(url)
+        req.add_header('Cookie', 'age_verified=1')
+        webpage = self._download_webpage(req, video_id)
+
+        video_title = self._html_search_regex(r'<h1 [^>]*?title="([^"]+)"[^>]*>\1<', webpage, u'title')
+        uploader = self._html_search_regex(r'>Posted by:(?=<)(\s|<[^>]*>)*(.+?)\|', webpage, u'uploader', fatal=False)
+        video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, u'video_url'))
+        path = compat_urllib_parse_urlparse( video_url ).path
+        extension = os.path.splitext( path )[1][1:]
+        format = path.split('/')[5].split('_')[:2]
+        format = "-".join( format )
+
+        age_limit = self._rta_search(webpage)
+
+        return {
+            'id': video_id,
+            'title': video_title,
+            'uploader': uploader,
+            'url': video_url,
+            'ext': extension,
+            'format': format,
+            'format_id': format,
+            'age_limit': age_limit,
+        }