From 30d22d775bc9abdbd301132b6cb7a57badb796dc Mon Sep 17 00:00:00 2001
From: HobbyistDev <105957301+HobbyistDev@users.noreply.github.com>
Date: Sat, 25 Jun 2022 23:43:32 +0900
Subject: [PATCH] [extractor/premiershiprugby] Add extractor (#4129)

Closes #2980
Authored by: HobbyistDev
---
 yt_dlp/extractor/_extractors.py      |  1 +
 yt_dlp/extractor/premiershiprugby.py | 39 ++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+)
 create mode 100644 yt_dlp/extractor/premiershiprugby.py

diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py
index 3447914f7..37328dfc8 100644
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@@ -1330,6 +1330,7 @@ from .puhutv import (
     PuhuTVIE,
     PuhuTVSerieIE,
 )
+from .premiershiprugby import PremiershipRugbyIE
 from .presstv import PressTVIE
 from .projectveritas import ProjectVeritasIE
 from .prosiebensat1 import ProSiebenSat1IE
diff --git a/yt_dlp/extractor/premiershiprugby.py b/yt_dlp/extractor/premiershiprugby.py
new file mode 100644
index 000000000..67d41fdfd
--- /dev/null
+++ b/yt_dlp/extractor/premiershiprugby.py
@@ -0,0 +1,39 @@
+from .common import InfoExtractor
+from ..utils import int_or_none, traverse_obj
+
+
+class PremiershipRugbyIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:\w+\.)premiershiprugby\.(?:com)/watch/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://www.premiershiprugby.com/watch/full-match-harlequins-v-newcastle-falcons',
+        'info_dict': {
+            'id': '0_mbkb7ldt',
+            'title': 'Full Match: Harlequins v Newcastle Falcons',
+            'ext': 'mp4',
+            'thumbnail': 'https://open.http.mp.streamamg.com/p/3000914/sp/300091400/thumbnail/entry_id/0_mbkb7ldt//width/960/height/540/type/1/quality/75',
+            'duration': 6093.0,
+            'tags': ['video'],
+            'categories': ['Full Match', 'Harlequins', 'Newcastle Falcons', 'gallaher premiership'],
+        }
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        json_data = self._download_json(
+            f'https://article-cms-api.incrowdsports.com/v2/articles/slug/{display_id}',
+            display_id, query={'clientId': 'PRL'})['data']['article']
+
+        formats, subs = self._extract_m3u8_formats_and_subtitles(
+            json_data['heroMedia']['content']['videoLink'], display_id)
+
+        return {
+            'id': json_data['heroMedia']['content']['sourceSystemId'],
+            'display_id': display_id,
+            'title': traverse_obj(json_data, ('heroMedia', 'title')),
+            'formats': formats,
+            'subtitles': subs,
+            'thumbnail': traverse_obj(json_data, ('heroMedia', 'content', 'videoThumbnail')),
+            'duration': int_or_none(traverse_obj(json_data, ('heroMedia', 'content', 'metadata', 'msDuration')), scale=1000),
+            'tags': json_data.get('tags'),
+            'categories': traverse_obj(json_data, ('categories', ..., 'text')),
+        }