From 625a551f84f7a59a1abb4de1d1f50ea51b4e75f3 Mon Sep 17 00:00:00 2001
From: Breno Lipi <brenorlipi@hotmail.com>
Date: Thu, 11 Mar 2021 00:16:56 -0300
Subject: [PATCH] captiongenerator.com extractor

---
 youtube_dl/extractor/captiongenerator.py | 40 ++++++++++++++++++++++++
 1 file changed, 40 insertions(+)
 create mode 100644 youtube_dl/extractor/captiongenerator.py

diff --git a/youtube_dl/extractor/captiongenerator.py b/youtube_dl/extractor/captiongenerator.py
new file mode 100644
index 000000000..0d6ba0600
--- /dev/null
+++ b/youtube_dl/extractor/captiongenerator.py
@@ -0,0 +1,40 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class CaptionGeneratorIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?captiongenerator\.com/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'https://d34ov3vwfhhb30.cloudfront.net/Hitler+Reacts+-+No+Subtitles.mp4',
+        'info_dict': {
+            'id': '128',
+            'ext': 'mp4',
+            'title': 'Team building...',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._html_search_regex(r'(https?://[a-z0-9]+\.cloudfront\.net/.+?\.mp4)', webpage, 'videoUrl')
+        print(video_url)
+
+        vtt_page = self._download_webpage('https://www.captiongenerator.com/videos/%s.vtt' % video_id, video_id)
+
+        vtt_captions = open("128.vtt", "w")
+        vtt_captions.write(vtt_page)
+        vtt_captions.close()
+
+        title = self._html_search_regex(r'<title>(.*)</title>', webpage, 'videoTitle')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'description': self._og_search_description(webpage),
+            'http_headers': {"Referer": "https://www.captiongenerator.com/"}
+        }