From b0434adccc77aa6dfe330fd8702f4dc34ecd0642 Mon Sep 17 00:00:00 2001
From: Sam <sguan@umich.edu>
Date: Sat, 14 Apr 2018 03:10:00 -0400
Subject: [PATCH] scientology.py Add new extractor

---
 youtube_dl/extractor/extractors.py  |  1 +
 youtube_dl/extractor/scientology.py | 42 +++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+)
 create mode 100644 youtube_dl/extractor/scientology.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index c9f60114d..6bb3c5a7d 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -941,6 +941,7 @@ from .safari import (
 from .sapo import SapoIE
 from .savefrom import SaveFromIE
 from .sbs import SBSIE
+from .scientology import ScientologyIE
 from .screencast import ScreencastIE
 from .screencastomatic import ScreencastOMaticIE
 from .scrippsnetworks import ScrippsNetworksWatchIE
diff --git a/youtube_dl/extractor/scientology.py b/youtube_dl/extractor/scientology.py
new file mode 100644
index 000000000..adbe43c15
--- /dev/null
+++ b/youtube_dl/extractor/scientology.py
@@ -0,0 +1,42 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+import re
+
+
+class ScientologyIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?scientology\.tv/series/(?P<series_path>[^/?#]+)/(?P<id>[^/?#]+).html'
+    _TEST = {
+        'url': 'https://www.scientology.tv/series/l-ron-hubbard-in-his-own-voice/life-as-an-author.html',
+        'info_dict': {
+            'id': 'life-as-an-author',
+            'ext': 'm3u8',
+            'title': 'Life as an Author | L. Ron Hubbard: In his Own Voice',
+            'description': 'The author on his real life adventures that thrilled millions, to his discoveries behind Dianetics.'
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title').strip()
+        description = self._html_search_regex(r'<meta name="description" content="(.+?)" />', webpage, 'description').strip()
+        description = re.sub("[^a-zA-Z0-9.,_\s-]+", " ", description)
+
+        # changing address for extration url
+        extract_ext = re.search(r'<episode-video>(.*?)</episode-video>', webpage).group(0)
+        extract_ext = extract_ext.replace('<episode-video>', '').replace('</episode-video>', '')
+        url = url[:url.find('/', 10)] + extract_ext
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'url': url,
+        }