From 5bcccbfec3de4bc69d529016f784d04db7b11e04 Mon Sep 17 00:00:00 2001
From: Ha Tien Loi <loiht.b17vt220@stu.ptit.edu.vn>
Date: Fri, 4 Mar 2022 18:18:46 +0700
Subject: [PATCH] [telegram] Add extractor (#2922)

Closes #2910

Authored by: hatienl0i261299
---
 yt_dlp/extractor/extractors.py |  1 +
 yt_dlp/extractor/telegram.py   | 37 ++++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)
 create mode 100644 yt_dlp/extractor/telegram.py

diff --git a/yt_dlp/extractor/extractors.py b/yt_dlp/extractor/extractors.py
index 0f26dc24f..c9e1a3f4e 100644
--- a/yt_dlp/extractor/extractors.py
+++ b/yt_dlp/extractor/extractors.py
@@ -1593,6 +1593,7 @@ from .tele13 import Tele13IE
 from .telebruxelles import TeleBruxellesIE
 from .telecinco import TelecincoIE
 from .telegraaf import TelegraafIE
+from .telegram import TelegramEmbedIE
 from .telemb import TeleMBIE
 from .telemundo import TelemundoIE
 from .telequebec import (
diff --git a/yt_dlp/extractor/telegram.py b/yt_dlp/extractor/telegram.py
new file mode 100644
index 000000000..2dfa261e9
--- /dev/null
+++ b/yt_dlp/extractor/telegram.py
@@ -0,0 +1,37 @@
+from .common import InfoExtractor
+
+
+class TelegramEmbedIE(InfoExtractor):
+    IE_NAME = 'telegram:embed'
+    _VALID_URL = r'https?://t\.me/(?P<channel_name>[^/]+)/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://t.me/europa_press/613',
+        'info_dict': {
+            'id': '613',
+            'ext': 'mp4',
+            'title': 'Europa Press',
+            'description': '6ce2d7e8d56eda16d80607b23db7b252',
+            'thumbnail': r're:^https?:\/\/cdn.*?telesco\.pe\/file\/\w+',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        webpage_embed = self._download_webpage(f'{url}?embed=1', video_id)
+
+        formats = [{
+            'url': self._proto_relative_url(self._search_regex(
+                '<video[^>]+src="([^"]+)"', webpage_embed, 'source')),
+            'ext': 'mp4',
+        }]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._html_search_meta(['og:title', 'twitter:title'], webpage, fatal=True),
+            'description': self._html_search_meta(['og:description', 'twitter:description'], webpage, fatal=True),
+            'thumbnail': self._search_regex(r'tgme_widget_message_video_thumb"[^>]+background-image:url\(\'([^\']+)\'\)',
+                                            webpage_embed, 'thumbnail'),
+            'formats': formats,
+        }