From 7504cc575a851372e39fd2d66f4e837eee24853d Mon Sep 17 00:00:00 2001
From: Jai Grimshaw <jai@jaigrimshaw.com>
Date: Tue, 2 Jun 2015 17:45:38 +1000
Subject: [PATCH] [clickhole] Add extractor

---
 youtube_dl/extractor/__init__.py  |  1 +
 youtube_dl/extractor/clickhole.py | 41 +++++++++++++++++++++++++++++++
 2 files changed, 42 insertions(+)
 create mode 100644 youtube_dl/extractor/clickhole.py

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 67eb96057..2abd039e9 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -72,6 +72,7 @@ from .chirbit import (
 )
 from .cinchcast import CinchcastIE
 from .cinemassacre import CinemassacreIE
+from .clickhole import ClickholeIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
diff --git a/youtube_dl/extractor/clickhole.py b/youtube_dl/extractor/clickhole.py
new file mode 100644
index 000000000..9640b440d
--- /dev/null
+++ b/youtube_dl/extractor/clickhole.py
@@ -0,0 +1,41 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class ClickholeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?clickhole\.com/video/[a-z\-]+(?P<id>[\d]+)'
+    _TEST = {
+        'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
+        'md5': '74229b82e3ffde84b6e11dcadcd3d237',
+        'info_dict': {
+            'id': '2537',
+            'ext': 'mp4',
+            'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
+            'description': 'Click, watch, share',
+            'thumbnail': 're:^https?://.*\.jpg$'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        # Find the embedded iframe
+        embedded_url = self._search_regex(
+            r'<iframe name="embedded".*src="//(.*)&.+">', webpage, 'embedded_url')
+        embed_page = self._download_webpage('http://' + embedded_url, video_id)
+        # Extract the videos from the iframe
+        mp4_video = self._search_regex(
+            r'<source src="(.*\.mp4)" type=.video/mp4. />', embed_page, 'video_url')
+        webm_video = self._search_regex(
+            r'<source src="(.*\.webm)" type=.video/webm. />', embed_page, 'video_url')
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': [{'url': webm_video}, {'url': mp4_video}],
+        }