From dc3c44f349ba85af320e706e2a27ad81a78b1c6e Mon Sep 17 00:00:00 2001
From: Mohamed Al Mehairbi <62325490+ItzMaxTV@users.noreply.github.com>
Date: Mon, 29 May 2023 19:19:13 +0400
Subject: [PATCH] [extractor/Mzaalo] Add extractor (#7163)

Authored by: ItzMaxTV
---
 yt_dlp/extractor/_extractors.py |  1 +
 yt_dlp/extractor/mzaalo.py      | 92 +++++++++++++++++++++++++++++++++
 2 files changed, 93 insertions(+)
 create mode 100644 yt_dlp/extractor/mzaalo.py

diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py
index 2963998cb..5b4ed44ef 100644
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@@ -1162,6 +1162,7 @@
 )
 from .myvideoge import MyVideoGeIE
 from .myvidster import MyVidsterIE
+from .mzaalo import MzaaloIE
 from .n1 import (
     N1InfoAssetIE,
     N1InfoIIE,
diff --git a/yt_dlp/extractor/mzaalo.py b/yt_dlp/extractor/mzaalo.py
new file mode 100644
index 000000000..c6f420cea
--- /dev/null
+++ b/yt_dlp/extractor/mzaalo.py
@@ -0,0 +1,92 @@
+from .common import InfoExtractor
+from ..utils import (
+    parse_age_limit,
+    parse_duration,
+    traverse_obj,
+    url_or_none,
+)
+
+
+class MzaaloIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?mzaalo\.com/play/(?P<type>movie|original|clip)/(?P<id>[a-fA-F0-9-]+)/[\w-]+'
+    _TESTS = [{
+        # Movies
+        'url': 'https://www.mzaalo.com/play/movie/c0958d9f-f90e-4503-a755-44358758921d/Jamun',
+        'info_dict': {
+            'id': 'c0958d9f-f90e-4503-a755-44358758921d',
+            'title': 'Jamun',
+            'ext': 'mp4',
+            'description': 'md5:24fe9ebb9bbe5b36f7b54b90ab1e2f31',
+            'thumbnails': 'count:15',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 5527.0,
+            'language': 'hin',
+            'categories': ['Drama'],
+            'age_limit': 13,
+        },
+        'params': {'skip_download': 'm3u8'}
+    }, {
+        # Shows
+        'url': 'https://www.mzaalo.com/play/original/93d42b2b-f373-4c2d-bca4-997412cb069d/Modi-Season-2-CM-TO-PM/Episode-1:Decision,-Not-Promises',
+        'info_dict': {
+            'id': '93d42b2b-f373-4c2d-bca4-997412cb069d',
+            'title': 'Episode 1:Decision, Not Promises',
+            'ext': 'mp4',
+            'description': 'md5:16f76058432a54774fbb2561a1955652',
+            'thumbnails': 'count:22',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 2040.0,
+            'language': 'hin',
+            'categories': ['Drama'],
+            'age_limit': 13,
+        },
+        'params': {'skip_download': 'm3u8'}
+    }, {
+        # Streams/Clips
+        'url': 'https://www.mzaalo.com/play/clip/83cdbcb5-400a-42f1-a1d2-459053cfbda5/Manto-Ki-Kahaaniya',
+        'info_dict': {
+            'id': '83cdbcb5-400a-42f1-a1d2-459053cfbda5',
+            'title': 'Manto Ki Kahaaniya',
+            'ext': 'mp4',
+            'description': 'md5:c3c5f1d05f0fd1bfcb05b673d1cc9f2f',
+            'thumbnails': 'count:3',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 1937.0,
+            'language': 'hin',
+        },
+        'params': {'skip_download': 'm3u8'}
+    }]
+
+    def _real_extract(self, url):
+        video_id, type_ = self._match_valid_url(url).group('id', 'type')
+        path = (f'partner/streamurl?&assetId={video_id}&getClipDetails=YES' if type_ == 'clip'
+                else f'api/v2/player/details?assetType={type_.upper()}&assetId={video_id}')
+        data = self._download_json(
+            f'https://production.mzaalo.com/platform/{path}', video_id, headers={
+                'Ocp-Apim-Subscription-Key': '1d0caac2702049b89a305929fdf4cbae',
+            })['data']
+
+        formats = self._extract_m3u8_formats(data['streamURL'], video_id)
+
+        subtitles = {}
+        for subs_lang, subs_url in traverse_obj(data, ('subtitles', {dict.items}, ...)):
+            if url_or_none(subs_url):
+                subtitles[subs_lang] = [{'url': subs_url, 'ext': 'vtt'}]
+
+        lang = traverse_obj(data, ('language', {str.lower}))
+        for f in formats:
+            f['language'] = lang
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            **traverse_obj(data, {
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+                'duration': ('duration', {parse_duration}),
+                'age_limit': ('maturity_rating', {parse_age_limit}),
+                'thumbnails': ('images', ..., {'url': {url_or_none}}),
+                'categories': ('genre', ..., {str}),
+            }),
+        }