From 358d69a4c43ee6f285bcd299f2ee439ca36e7182 Mon Sep 17 00:00:00 2001
From: ddmgy <dmougey1475@yahoo.com>
Date: Fri, 16 Mar 2018 03:12:18 -0400
Subject: [PATCH] [hentaihaven] Add new extractor

---
 youtube_dl/extractor/extractors.py  |  1 +
 youtube_dl/extractor/hentaihaven.py | 66 +++++++++++++++++++++++++++++
 2 files changed, 67 insertions(+)
 create mode 100644 youtube_dl/extractor/hentaihaven.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 3bde40eb3..50859803c 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -430,6 +430,7 @@ from .hearthisat import HearThisAtIE
 from .heise import HeiseIE
 from .hellporno import HellPornoIE
 from .helsinki import HelsinkiIE
+from .hentaihaven import HentaiHavenIE
 from .hentaistigma import HentaiStigmaIE
 from .hgtv import HGTVComShowIE
 from .hidive import HiDiveIE
diff --git a/youtube_dl/extractor/hentaihaven.py b/youtube_dl/extractor/hentaihaven.py
new file mode 100644
index 000000000..7b6e98b07
--- /dev/null
+++ b/youtube_dl/extractor/hentaihaven.py
@@ -0,0 +1,66 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+class HentaiHavenIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hentaihaven\.org/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://hentaihaven.org/oideyo-shiritsu-yarimari-gakuen-episode-1-hd',
+        'md5': 'd9e1ed0558c0c29267743c463c34e71b',
+        'info_dict': {
+            'id': 'oideyo-shiritsu-yarimari-gakuen-episode-1-hd',
+            'title': 'Oideyo! Shiritsu Yarimari Gakuen – Episode 1',
+            'ext': 'mp4',
+            'age_limit': 18,
+            'formats': [
+                {
+                    'url': 'http://hh.cx/files/34/[HH] Oideyo! Shiritsu Yarimari Gakuen - Episode 1 [DVD] [3FFC5997].mp4',
+                    'ext': 'mp4',
+                    'height': 720,
+                },
+                {
+                    'url': 'http://hh.cx/files/04/[HH] Oideyo! Shiritsu Yarimari Gakuen - Episode 1 [SD].mp4',
+                    'ext': 'mp4',
+                    'height': 480,
+                },
+                {
+                    'url': 'http://hh.cx/files/1a/[HH]direct_PID48840[SD].mp4',
+                    'ext': 'mp4',
+                    'height': 360,
+                },
+            ]
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(
+            r'<h1[^>]+class=(["\'])*entry-title\1*[^>]*>(?P<title>[^<]+)',
+            webpage, 'title', group='title')
+
+        btn_re = re.compile(r'(<a[^>]+class="btn"*[^>]+>)')
+        res_re = re.compile(r'<span[^>]+class=["\']*text-white["\']*[^>]*>([^<]+)')
+        
+        formats = []
+        for (btn, res) in zip(btn_re.findall(webpage), res_re.findall(webpage)):
+            format_info = {}
+            format_info['url'] = self._html_search_regex(
+                r'<a[^>]+href=["\']([^"\']+)["\'][^>]+>',
+                btn, 'href')
+            format_info['ext'] = 'mp4'
+            format_info['height'] = int_or_none(res[:-1])
+            formats.append(format_info)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'age_limit': 18,
+            'formats': formats,
+        }
\ No newline at end of file