From 1d45a23b745cdbb361dd5cef8f848f7ebcfa8f5a Mon Sep 17 00:00:00 2001
From: rzhxeo <rzhxeot7z81b4700@mailcatch.com>
Date: Sat, 26 Oct 2013 23:27:30 +0200
Subject: [PATCH 1/3] Add support for http://www.tube8.com
---
youtube_dl/extractor/__init__.py | 1 +
youtube_dl/extractor/tube8.py | 63 ++++++++++++++++++++++++++++++++
2 files changed, 64 insertions(+)
create mode 100644 youtube_dl/extractor/tube8.py
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index db69af361..84fc2e4fa 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -121,6 +121,7 @@ from .tf1 import TF1IE
from .thisav import ThisAVIE
from .traileraddict import TrailerAddictIE
from .trilulilu import TriluliluIE
+from .tube8 import Tube8IE
from .tudou import TudouIE
from .tumblr import TumblrIE
from .tutv import TutvIE
diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py
new file mode 100644
index 000000000..b7e7d984d
--- /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>(?:\w|<[^>]*>)*(.+?)<', 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,
+ }
From 8cb57d9b91cce72b522d89b5e3e469c433956a07 Mon Sep 17 00:00:00 2001
From: rzhxeo <rzhxeo@users.noreply.github.com>
Date: Sun, 27 Oct 2013 00:21:27 +0200
Subject: [PATCH 2/3] [Tube8IE] Escape dot in regex
---
youtube_dl/extractor/tube8.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py
index b7e7d984d..ef8d21642 100644
--- a/youtube_dl/extractor/tube8.py
+++ b/youtube_dl/extractor/tube8.py
@@ -13,7 +13,7 @@ from ..aes import (
)
class Tube8IE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>tube8.com/[^/]+/[^/]+/(?P<videoid>[0-9]+)/?)'
+ _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',
From 71865091abbb0166edeffff14da019542260557f Mon Sep 17 00:00:00 2001
From: rzhxeo <rzhxeo@users.noreply.github.com>
Date: Sun, 27 Oct 2013 01:08:03 +0200
Subject: [PATCH 3/3] [Tube8IE] Fix regex for uploader extraction
---
youtube_dl/extractor/tube8.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py
index ef8d21642..ebc8c1f4f 100644
--- a/youtube_dl/extractor/tube8.py
+++ b/youtube_dl/extractor/tube8.py
@@ -36,7 +36,7 @@ class Tube8IE(InfoExtractor):
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>(?:\w|<[^>]*>)*(.+?)<', webpage, u'uploader', 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('\\/', '/')