From f6199a619d98fb6684655bab7c9a2da8b910f450 Mon Sep 17 00:00:00 2001
From: Simon Morgan <sjm@sjm.io>
Date: Fri, 7 Oct 2016 16:17:57 +0100
Subject: [PATCH] [yuvutu] Add new extractor

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/yuvutu.py     | 46 ++++++++++++++++++++++++++++++
 2 files changed, 47 insertions(+)
 create mode 100644 youtube_dl/extractor/yuvutu.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index feee06004..6ae0f5a4c 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -1162,6 +1162,7 @@ from .youtube import (
     YoutubeUserIE,
     YoutubeWatchLaterIE,
 )
+from .yuvutu import YuvutuIE
 from .zapiks import ZapiksIE
 from .zdf import ZDFIE, ZDFChannelIE
 from .zingmp3 import ZingMp3IE
diff --git a/youtube_dl/extractor/yuvutu.py b/youtube_dl/extractor/yuvutu.py
new file mode 100644
index 000000000..ebf0846fb
--- /dev/null
+++ b/youtube_dl/extractor/yuvutu.py
@@ -0,0 +1,46 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+
+class YuvutuIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?yuvutu.com/video/(?P<id>[0-9]+)(?:.*)'
+    _TEST = {
+        'url': 'http://www.yuvutu.com/video/330/',
+        'md5': 'af4a0d2eabec6b6bd43cd6b68543fa9c',
+        'info_dict': {
+            'id': '330',
+            'title': 'carnal bliss',
+            'ext': 'flv',
+            'age_limit': 18,
+        }
+    }
+
+    _title_regex = r"class=[\"']video-title-content[\"']>.+?>(.+?)<"
+    _thumbnail_regex = r"itemprop=[\"']thumbnailURL[\"']\s+content=[\"'](.+?)[\"']"
+    _embed_regex = r"[\"'](\/embed_video\.php.+?)[\"']"
+    _video_regex = r"file:\s*[\"']([^\s]+)[\"']"
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(self._title_regex, webpage, 'title')
+
+        embed_url = self._html_search_regex(self._embed_regex, webpage,
+                                            'embed')
+        embed_webpage = self._download_webpage(
+            "http://www.yuvutu.com/" + embed_url, video_id)
+        video_url = self._html_search_regex(self._video_regex, embed_webpage,
+                                            'video_url')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': determine_ext(video_url, 'mp4'),
+            'title': title,
+            'age_limit': 18,
+        }