aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/tube8.py
diff options
context:
space:
mode:
authorFilippo Valsorda <filippo.valsorda@gmail.com>2013-10-28 01:38:28 -0400
committerFilippo Valsorda <filippo.valsorda@gmail.com>2013-10-28 01:38:28 -0400
commiteb6a2277a2ab1cb48b4705dbb4bfe95cb03ee8e4 (patch)
treea67ce29ad6b14e3aa3f8ed3a5957344746af31dd /youtube_dl/extractor/tube8.py
parentf8778fb0fa80d7af7c84f0201c7683465350008c (diff)
parent71865091abbb0166edeffff14da019542260557f (diff)
Merge pull request #1659 by @rzhxeo
Add support for http://www.tube8.com
Diffstat (limited to 'youtube_dl/extractor/tube8.py')
-rw-r--r--youtube_dl/extractor/tube8.py63
1 files changed, 63 insertions, 0 deletions
diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py
new file mode 100644
index 000000000..ebc8c1f4f
--- /dev/null
+++ b/youtube_dl/extractor/tube8.py
@@ -0,0 +1,63 @@
+import os
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_parse_urlparse,
+ compat_urllib_request,
+ compat_urllib_parse,
+ unescapeHTML,
+)
+from ..aes import (
+ aes_decrypt_text
+)
+
+class Tube8IE(InfoExtractor):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>tube8\.com/[^/]+/[^/]+/(?P<videoid>[0-9]+)/?)'
+ _TEST = {
+ u'url': u'http://www.tube8.com/teen/kasia-music-video/229795/',
+ u'file': u'229795.mp4',
+ u'md5': u'e9e0b0c86734e5e3766e653509475db0',
+ u'info_dict': {
+ u"description": u"hot teen Kasia grinding",
+ u"uploader": u"unknown",
+ u"title": u"Kasia music video",
+ }
+ }
+
+ 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'videotitle ="([^"]+)', webpage, u'title')
+ video_description = self._html_search_regex(r'>Description:</strong>(.+?)<', webpage, u'description', fatal=False)
+ video_uploader = self._html_search_regex(r'>Submitted by:</strong>(?:\s|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False)
+ thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False)
+ if thumbnail:
+ thumbnail = thumbnail.replace('\\/', '/')
+
+ video_url = self._html_search_regex(r'"video_url":"([^"]+)', webpage, u'video_url')
+ if webpage.find('"encrypted":true')!=-1:
+ password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password')
+ video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
+ path = compat_urllib_parse_urlparse( video_url ).path
+ extension = os.path.splitext( path )[1][1:]
+ format = path.split('/')[4].split('_')[:2]
+ format = "-".join( format )
+
+ return {
+ 'id': video_id,
+ 'uploader': video_uploader,
+ 'title': video_title,
+ 'thumbnail': thumbnail,
+ 'description': video_description,
+ 'url': video_url,
+ 'ext': extension,
+ 'format': format,
+ 'format_id': format,
+ }