From 78ab4f447c7aa019bb73b7d5b711c78dc4dd0f73 Mon Sep 17 00:00:00 2001
From: Ashish Gupta <39122144+Ashish0804@users.noreply.github.com>
Date: Fri, 21 Jan 2022 12:31:25 +0530
Subject: [PATCH] [Newsy] Add extractor (#2416)

Closes #2346
Authored by: Ashish0804
---
 yt_dlp/extractor/extractors.py |  1 +
 yt_dlp/extractor/newsy.py      | 51 ++++++++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+)
 create mode 100644 yt_dlp/extractor/newsy.py

diff --git a/yt_dlp/extractor/extractors.py b/yt_dlp/extractor/extractors.py
index d93e36b74b..7c67879adf 100644
--- a/yt_dlp/extractor/extractors.py
+++ b/yt_dlp/extractor/extractors.py
@@ -958,6 +958,7 @@
     NewgroundsUserIE,
 )
 from .newstube import NewstubeIE
+from .newsy import NewsyIE
 from .nextmedia import (
     NextMediaIE,
     NextMediaActionNewsIE,
diff --git a/yt_dlp/extractor/newsy.py b/yt_dlp/extractor/newsy.py
new file mode 100644
index 0000000000..cf31641004
--- /dev/null
+++ b/yt_dlp/extractor/newsy.py
@@ -0,0 +1,51 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    merge_dicts,
+)
+
+
+class NewsyIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?newsy\.com/stories/(?P<id>[^/?#$&]+)'
+
+    _TESTS = [{
+        'url': 'https://www.newsy.com/stories/nft-trend-leads-to-fraudulent-art-auctions/',
+        'info_dict': {
+            'id': '609d65125b086c24fb529312',
+            'ext': 'mp4',
+            'title': 'NFT Art Auctions Have A Piracy Problem',
+            'description': 'md5:971e52ab8bc97e50305475cde8284c83',
+            'display_id': 'nft-trend-leads-to-fraudulent-art-auctions',
+            'timestamp': 1621339200,
+            'duration': 339630,
+            'thumbnail': 'https://cdn.newsy.com/images/videos/x/1620927824_xyrrP4.jpg',
+            'upload_date': '20210518'
+        },
+        'params': {'skip_download': True}
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        data_json = self._parse_json(self._html_search_regex(
+            r'data-video-player\s?=\s?"({[^"]+})">', webpage, 'data'), display_id, js_to_json)
+        ld_json = self._search_json_ld(webpage, display_id, fatal=False)
+
+        formats, subtitles = [], {}
+        if data_json.get('stream'):
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(data_json['stream'], display_id)
+            formats.extend(fmts)
+            subtitles = self._merge_subtitles(subtitles, subs)
+        self._sort_formats(formats)
+        return merge_dicts(ld_json, {
+            'id': data_json['id'],
+            'display_id': display_id,
+            'title': data_json.get('headline'),
+            'duration': data_json.get('duration'),
+            'thumbnail': data_json.get('image'),
+            'formats': formats,
+            'subtitles': subtitles,
+        })