From c0edd1c19483bfc2ca120cf6893984968860fbce Mon Sep 17 00:00:00 2001
From: zer0-delta <172248380+zer0-delta@users.noreply.github.com>
Date: Wed, 12 Jun 2024 05:37:34 +0100
Subject: [PATCH] Added BBC Maestro extractor

---
 yt_dlp/extractor/_extractors.py |   3 +
 yt_dlp/extractor/bbcmaestro.py  | 126 ++++++++++++++++++++++++++++++++
 2 files changed, 129 insertions(+)
 create mode 100644 yt_dlp/extractor/bbcmaestro.py

diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py
index e9cd38a65..68a51ea2e 100644
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@@ -216,6 +216,9 @@
     BBCCoUkIPlayerGroupIE,
     BBCCoUkPlaylistIE,
 )
+from .bbcmaestro import (
+    BBCMaestroComIE,
+)
 from .beatbump import (
     BeatBumpPlaylistIE,
     BeatBumpVideoIE,
diff --git a/yt_dlp/extractor/bbcmaestro.py b/yt_dlp/extractor/bbcmaestro.py
new file mode 100644
index 000000000..df3f74bf1
--- /dev/null
+++ b/yt_dlp/extractor/bbcmaestro.py
@@ -0,0 +1,126 @@
+# coding: utf-8
+from __future__ import unicode_literals
+import re
+
+from ..utils import orderedSet, smuggle_url, unsmuggle_url
+from .common import InfoExtractor
+
+
+class BBCMaestroComIE(InfoExtractor):
+    _VALID_URL = (
+        r'https?://(?:www\.)?bbcmaestro\.com/courses/(?P<id>[^?]+)'
+    )
+    _TESTS = [{
+        'url': 'https://www.bbcmaestro.com/courses/julia-donaldson/writing-children-s-picture-books/trailer',
+        'info_dict': {
+            'id': 'julia-donaldson/writing-children-s-picture-books/trailer',
+            'ext': 'mp4',
+            'title': 'Course trailer'
+        },
+        'params': {
+            'skip_download': True
+        }
+    }]
+
+    def _do_extract_video(self, url, webpage, video_id):
+        if '/lessons/' not in url:
+            title = 'Course trailer'
+        else:
+            title = self._html_search_regex(
+                r'<h1\b[^>]*lesson[^>]*title[^>]*>\s*(.+?)\s*</h1>',
+                webpage,
+                name='title',
+                flags=re.RegexFlag.S
+            )
+
+        m3u8_url = self._html_search_regex(
+            r'<source[^>]+src="?\'?(\S+\.m3u8)',
+            webpage,
+            'video URL'
+        )
+        formats = []
+        if m3u8_url:
+            formats = self._extract_m3u8_formats(
+                m3u8_url=m3u8_url,
+                video_id=video_id,
+                ext='mp4',
+                m3u8_id='hls',
+                fatal=False
+            )
+
+        video_dict = {
+            'id': video_id,
+            'title': title,
+            'formats': formats
+        }
+
+        return video_dict
+
+    def _do_extract_playlist(self, url, webpage):
+        # Twitter Title usually: <Lesson Title> - <Author> | <Course Title>
+        twitter_title = self._html_search_meta(
+            ['twitter:title'],
+            webpage,
+            fatal=True
+        )
+        playlist_title = (
+            twitter_title
+            .split('-', maxsplit=1)[-1]
+            .replace('|', '-')
+        )
+
+        url_without_query_parameters = url.split('?', maxsplit=1)[0]
+        self.write_debug('url_without_query_parameters: %r' % url_without_query_parameters)
+        playlist_id = self._search_regex(
+            pattern=r'.*/courses/([^/]+/[^/]+).*',
+            string=url_without_query_parameters,
+            name='Playlist ID (from URL)',
+            fatal=True
+        )
+        self.write_debug('playlist_id: %r' % playlist_id)
+        entries = [
+            self.url_result(
+                smuggle_url(
+                    f'https://www.bbcmaestro.com/courses/{playlist_id}/lessons/{item_video_id}',
+                    {'forcevideo': True}
+                ),
+                ie=BBCMaestroComIE.ie_key()
+            )
+            for item_video_id in orderedSet(re.findall(
+                r'href=[^>]*/courses/' + re.escape(playlist_id) + r'/lessons/([^?]+)',
+                webpage
+            ))
+        ]
+        # self.write_debug('entries: %r' % entries)
+        return self.playlist_result(
+            entries=entries,
+            playlist_id=playlist_id,
+            playlist_title=playlist_title
+        )
+
+    def _check_login_provided(self):
+        if not self._cookies_passed:
+            self.raise_login_required('Login details are needed to download this content', method='cookies')
+
+    def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+        self.write_debug('Extracting from: %r' % url)
+        video_id = self._match_id(url)
+        self.write_debug('Video ID: %r' % video_id)
+        webpage = self._download_webpage(url, video_id)
+
+        is_private_course_content = ('/lessons/' in url)
+        is_login_required = is_private_course_content
+        if is_login_required:
+            # Note: We can only download the course trailer without login
+            self._check_login_provided()
+
+        is_playlist =  (
+            is_private_course_content
+            and not smuggled_data.get('forcevideo')
+            and not self.get_param('noplaylist')
+        )
+
+        if is_playlist:
+            return self._do_extract_playlist(url, webpage=webpage)
+        return self._do_extract_video(url, webpage=webpage, video_id=video_id)