From 54725c9f0b30629a961314251574d05360cf5772 Mon Sep 17 00:00:00 2001
From: Simon Morgan <sjm@sjm.io>
Date: Fri, 14 Oct 2016 17:38:31 +0100
Subject: [PATCH] [gotporn] Add new extractor

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/gotporn.py    | 43 ++++++++++++++++++++++++++++++
 2 files changed, 44 insertions(+)
 create mode 100644 youtube_dl/extractor/gotporn.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 08bed8b0c..ca5b8d45b 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -345,6 +345,7 @@ from .googledrive import GoogleDriveIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
 from .goshgay import GoshgayIE
+from .gotporn import GotPornIE
 from .gputechconf import GPUTechConfIE
 from .groupon import GrouponIE
 from .hark import HarkIE
diff --git a/youtube_dl/extractor/gotporn.py b/youtube_dl/extractor/gotporn.py
new file mode 100644
index 000000000..a9e267842
--- /dev/null
+++ b/youtube_dl/extractor/gotporn.py
@@ -0,0 +1,43 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+class GotPornIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?xvideos\.com/video(?P<id>[0-9]+)(?:.*)'
+    _VALID_URL = r'http://www\.gotporn\.com/(?P<display_id>[^/]+)/video-(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.gotporn.com/big-boobs-babe/video-5661549',
+        'md5': '9ad371d58a8ee709d8321a548d6e5d2d',
+        'info_dict': {
+            'id': '5661549',
+            'ext': 'mp4',
+            'title': 'Big Boobs Babe',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+        if not display_id:
+            display_id = video_id
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r'<h1\s+class=[\'"]title-block[\'"]>\s*([^<]+)', webpage, 'title')
+        thumbnail_url = self._html_search_regex(r'<link\s+itemprop=[\'"]thumbnailUrl[\'"]\s+href=[\'"]([^\'"]+)', webpage, 'thumbnail_url')
+        video_url = self._html_search_regex(r'<source.+?src=[\'"]([^\'"]+)[\'"]', webpage, 'video_url')
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'thumbnail': thumbnail_url,
+            'ext': determine_ext(video_url, 'mp4'),
+            'title': title,
+            'age_limit': 18,
+        }