From c13a301a94e84d581817a534875e4e2a5c0fdf19 Mon Sep 17 00:00:00 2001
From: m4tu4g <71326926+m4tu4g@users.noreply.github.com>
Date: Thu, 20 Oct 2022 03:17:18 +0530
Subject: [PATCH] [extractor/zeenews] Add extractor (#5289)

Closes #4967
Authored by: m4tu4g, pukkandan
---
 yt_dlp/extractor/_extractors.py |  1 +
 yt_dlp/extractor/common.py      |  2 +-
 yt_dlp/extractor/zeenews.py     | 58 +++++++++++++++++++++++++++++++++
 3 files changed, 60 insertions(+), 1 deletion(-)
 create mode 100644 yt_dlp/extractor/zeenews.py

diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py
index 97e1a0e02c..2b35cc9642 100644
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@@ -2296,6 +2296,7 @@
     Zee5IE,
     Zee5SeriesIE,
 )
+from .zeenews import ZeeNewsIE
 from .zhihu import ZhihuIE
 from .zingmp3 import (
     ZingMp3IE,
diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py
index ec3fb58e56..fb787a7221 100644
--- a/yt_dlp/extractor/common.py
+++ b/yt_dlp/extractor/common.py
@@ -1576,7 +1576,7 @@ def traverse_json_ld(json_ld, at_top_level=True):
                     continue
                 if at_top_level and set(e.keys()) == {'@context', '@graph'}:
                     traverse_json_ld(e['@graph'], at_top_level=False)
-                    break
+                    continue
                 if expected_type is not None and not is_type(e, expected_type):
                     continue
                 rating = traverse_obj(e, ('aggregateRating', 'ratingValue'), expected_type=float_or_none)
diff --git a/yt_dlp/extractor/zeenews.py b/yt_dlp/extractor/zeenews.py
new file mode 100644
index 0000000000..ae2cc264e7
--- /dev/null
+++ b/yt_dlp/extractor/zeenews.py
@@ -0,0 +1,58 @@
+from .common import InfoExtractor
+from ..utils import ExtractorError, traverse_obj
+
+
+class ZeeNewsIE(InfoExtractor):
+    _VALID_URL = r'https?://zeenews\.india\.com/[^#?]+/video/(?P<display_id>[^#/?]+)/(?P<id>\d+)'
+    _TESTS = [
+        {
+            'url': 'https://zeenews.india.com/hindi/india/delhi-ncr-haryana/delhi-ncr/video/greater-noida-video-viral-on-social-media-attackers-beat-businessman-and-his-son-oppose-market-closed-atdnh/1402138',
+            'info_dict': {
+                'id': '1402138',
+                'ext': 'mp4',
+                'title': 'Greater Noida Video: हमलावरों ने दिनदहाड़े दुकान में घुसकर की मारपीट, देखें वीडियो',
+                'display_id': 'greater-noida-video-viral-on-social-media-attackers-beat-businessman-and-his-son-oppose-market-closed-atdnh',
+                'upload_date': '20221019',
+                'thumbnail': r're:^https?://.*\.jpg*',
+                'timestamp': 1666174501,
+                'view_count': int,
+                'duration': 97,
+                'description': 'ग्रेटर नोएडा जारचा थाना क्षेत्र के प्याबली में दिनदहाड़े दुकान में घुसकर अज्ञात हमलावरों ने हमला कर',
+            }
+        },
+        {
+            'url': 'https://zeenews.india.com/hindi/india/video/videsh-superfast-queen-elizabeth-iis-funeral-today/1357710',
+            'info_dict': {
+                'id': '1357710',
+                'ext': 'mp4',
+                'title': 'Videsh Superfast: महारानी के अंतिम संस्कार की तैयारी शुरू',
+                'display_id': 'videsh-superfast-queen-elizabeth-iis-funeral-today',
+                'upload_date': '20220919',
+                'thumbnail': r're:^https?://.*\.jpg*',
+                'timestamp': 1663556881,
+                'view_count': int,
+                'duration': 133,
+                'description': 'सेगमेंट विदेश सुपराफास्ट में देखिए देश और दुनिया की सभी बड़ी खबरें, वो भी हर खबर फटाफट अंदाज में.',
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        content_id, display_id = self._match_valid_url(url).group('id', 'display_id')
+        webpage = self._download_webpage(url, content_id)
+        json_ld_list = list(self._yield_json_ld(webpage, display_id))
+
+        embed_url = traverse_obj(
+            json_ld_list, (lambda _, v: v['@type'] == 'VideoObject', 'embedUrl'), get_all=False)
+        if not embed_url:
+            raise ExtractorError('No video found', expected=True)
+
+        formats = self._extract_m3u8_formats(embed_url, content_id, 'mp4')
+        self._sort_formats(formats)
+
+        return {
+            **self._json_ld(json_ld_list, display_id),
+            'id': content_id,
+            'display_id': display_id,
+            'formats': formats,
+        }