From d816fb28dcdfc27fabfa848a6c1edf20f08b7356 Mon Sep 17 00:00:00 2001
From: Kieran Eglin <kieran.eglin@gmail.com>
Date: Thu, 9 May 2024 09:39:23 -0700
Subject: [PATCH 1/4] Added 30 day singer extractor

---
 yt_dlp/extractor/_extractors.py     |   4 ++
 yt_dlp/extractor/thirtydaysinger.py | 102 ++++++++++++++++++++++++++++
 2 files changed, 106 insertions(+)
 create mode 100644 yt_dlp/extractor/thirtydaysinger.py

diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py
index 42034275b..e3824c445 100644
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@@ -1981,6 +1981,10 @@ from .theplatform import (
 from .thestar import TheStarIE
 from .thesun import TheSunIE
 from .theweatherchannel import TheWeatherChannelIE
+from .thirtydaysinger import (
+    ThirtyDaySingerIE,
+    ThirtyDaySingerPlaylistIE
+)
 from .thisamericanlife import ThisAmericanLifeIE
 from .thisoldhouse import ThisOldHouseIE
 from .thisvid import (
diff --git a/yt_dlp/extractor/thirtydaysinger.py b/yt_dlp/extractor/thirtydaysinger.py
new file mode 100644
index 000000000..43da6210a
--- /dev/null
+++ b/yt_dlp/extractor/thirtydaysinger.py
@@ -0,0 +1,102 @@
+from .wistia import WistiaIE
+from ..utils import (
+    clean_html,
+    get_elements_html_by_class
+)
+
+
+class ThirtyDaySingerBase(WistiaIE):
+    def _extract_for_url(self, url):
+        lesson_index = self._match_id(url)
+        webpage = self._download_webpage(url, lesson_index)
+        match = next(self._extract_wistia_async_embed(webpage))
+        embed_config = self._download_embed_config('medias', match.group('id'), url)
+
+        embed_infojson = self._extract_media(embed_config)
+        webpage_infojson = self._extract_webpage_data(webpage)
+
+        return {**embed_infojson, **webpage_infojson}
+
+    def _extract_webpage_data(self, webpage):
+        title = self._html_search_regex(r'<h1>([^<]+)</h1>', webpage, 'title')
+        fallback_title = self._html_extract_title(webpage)
+        description = self._html_search_meta('description', webpage, fatal=False)
+
+        return {
+            'title': title or fallback_title,
+            'description': clean_html(self._format_html_list(description))
+        }
+
+    # The site makes extensive use of HTML lists for formatting and `clean_html`
+    # doesn't handle them well. This is needed to keep lists readable.
+    def _format_html_list(self, html):
+        replacements = {
+            '<ul>': '<br>',
+            '</ul': '<br>',
+            '<li>': '<br>- ',
+            '</li>': ''
+        }
+
+        for k, v in replacements.items():
+            html = html.replace(k, v)
+
+        return html
+
+
+class ThirtyDaySingerIE(ThirtyDaySingerBase):
+    _VALID_URL = r'(https?://)?www.30daysinger.com/tutorial/[\w-]+/(?P<id>[\w-]+)'
+
+    _TESTS = [{
+        'url': 'https://www.30daysinger.com/tutorial/30-day-beginner-course-with-jonathan-estabrooks/1',
+        'md5': '56bb11529b9777899b27b599d4b16cf6',
+        'info_dict': {
+            'id': 'tegd38l3d5',
+            'ext': 'mp4',
+            'thumbnail': 'http://embed.wistia.com/deliveries/c26a85cb98e32efa8a5e12a0576e63355af66230.jpg',
+            'upload_date': '20190608',
+            'description': 'md5:d3291de8988be57b1d3e411126ba4d33',
+            'duration': 344.22,
+            'timestamp': 1559952526,
+            'title': 'Welcome to 30 Day Singer'
+        }
+    }]
+
+    def _real_extract(self, url):
+        return self._extract_for_url(url)
+
+
+class ThirtyDaySingerPlaylistIE(ThirtyDaySingerBase):
+    _URI_BASE = 'https://www.30daysinger.com'
+    _VALID_URL = r'(https?://)?www.30daysinger.com/tutorial/(?P<id>[\w-]+)'
+
+    _TESTS = [{
+        'url': 'https://www.30daysinger.com/tutorial/30-day-beginner-course-with-jonathan-estabrooks',
+        'info_dict': {
+            'id': '30-day-beginner-course-with-jonathan-estabrooks',
+            'description': 'md5:8cf6d6c7c377895653c9cde9dfc4104f',
+            'title': '30 Day Beginner Course with Jonathan Estabrooks',
+        },
+        'playlist_count': 1
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+        playlist_attrs = self._extract_webpage_data(webpage)
+
+        entries = []
+        for html_element in get_elements_html_by_class('playlist-item-link', webpage):
+            href = self._search_regex(r'href="([^"]+)"', html_element, 'href')
+
+            if not href:
+                continue
+            # Often _some_ content is free so we should still download that but warn the user
+            # when we encounter premium content.
+            # NOTE: this only applies to the playlist extractor, not the single video extractor
+            if 'upgrade' in href:
+                self.report_warning('This video is for premium members only')
+                continue
+
+            entries.append(self._extract_for_url(self._URI_BASE + href))
+
+        return self.playlist_result(entries, playlist_id, playlist_attrs['title'], playlist_attrs['description'])

From 6d236615422e7b49d82134d7c856dd5e7c8f45ee Mon Sep 17 00:00:00 2001
From: Kieran Eglin <kieran.eglin@gmail.com>
Date: Thu, 9 May 2024 10:37:51 -0700
Subject: [PATCH 2/4] Updated playlist regex

---
 yt_dlp/extractor/thirtydaysinger.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/yt_dlp/extractor/thirtydaysinger.py b/yt_dlp/extractor/thirtydaysinger.py
index 43da6210a..f653ab982 100644
--- a/yt_dlp/extractor/thirtydaysinger.py
+++ b/yt_dlp/extractor/thirtydaysinger.py
@@ -67,7 +67,7 @@ class ThirtyDaySingerIE(ThirtyDaySingerBase):
 
 class ThirtyDaySingerPlaylistIE(ThirtyDaySingerBase):
     _URI_BASE = 'https://www.30daysinger.com'
-    _VALID_URL = r'(https?://)?www.30daysinger.com/tutorial/(?P<id>[\w-]+)'
+    _VALID_URL = r'(https?://)?www.30daysinger.com/tutorial/(?P<id>[\w-]+)/?(?:$|[#?])'
 
     _TESTS = [{
         'url': 'https://www.30daysinger.com/tutorial/30-day-beginner-course-with-jonathan-estabrooks',
@@ -76,7 +76,8 @@ class ThirtyDaySingerPlaylistIE(ThirtyDaySingerBase):
             'description': 'md5:8cf6d6c7c377895653c9cde9dfc4104f',
             'title': '30 Day Beginner Course with Jonathan Estabrooks',
         },
-        'playlist_count': 1
+        'playlist_count': 1,
+        'expected_warnings': ['This video is for premium members only']
     }]
 
     def _real_extract(self, url):

From 620d72177924ad87aa1e844351999477eb7d05bb Mon Sep 17 00:00:00 2001
From: Kieran Eglin <kieran.eglin@gmail.com>
Date: Thu, 9 May 2024 10:55:22 -0700
Subject: [PATCH 3/4] Refactored based on feedback

---
 yt_dlp/extractor/thirtydaysinger.py | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/yt_dlp/extractor/thirtydaysinger.py b/yt_dlp/extractor/thirtydaysinger.py
index f653ab982..0ea779c3e 100644
--- a/yt_dlp/extractor/thirtydaysinger.py
+++ b/yt_dlp/extractor/thirtydaysinger.py
@@ -1,13 +1,17 @@
-from .wistia import WistiaIE
+import re
+
+from .wistia import WistiaBaseIE
 from ..utils import (
     clean_html,
     get_elements_html_by_class
 )
 
 
-class ThirtyDaySingerBase(WistiaIE):
+class ThirtyDaySingerBase(WistiaBaseIE):
+    _INDEX_EXTRACTION_RE = r'/tutorial/[\w-]+/(?P<index>[\w-]+)'
+
     def _extract_for_url(self, url):
-        lesson_index = self._match_id(url)
+        lesson_index = re.search(self._INDEX_EXTRACTION_RE, url).group('index')
         webpage = self._download_webpage(url, lesson_index)
         match = next(self._extract_wistia_async_embed(webpage))
         embed_config = self._download_embed_config('medias', match.group('id'), url)
@@ -44,7 +48,7 @@ class ThirtyDaySingerBase(WistiaIE):
 
 
 class ThirtyDaySingerIE(ThirtyDaySingerBase):
-    _VALID_URL = r'(https?://)?www.30daysinger.com/tutorial/[\w-]+/(?P<id>[\w-]+)'
+    _VALID_URL = r'(https?://)?www.30daysinger.com/tutorial/[\w-]+/[\w-]+'
 
     _TESTS = [{
         'url': 'https://www.30daysinger.com/tutorial/30-day-beginner-course-with-jonathan-estabrooks/1',
@@ -67,7 +71,7 @@ class ThirtyDaySingerIE(ThirtyDaySingerBase):
 
 class ThirtyDaySingerPlaylistIE(ThirtyDaySingerBase):
     _URI_BASE = 'https://www.30daysinger.com'
-    _VALID_URL = r'(https?://)?www.30daysinger.com/tutorial/(?P<id>[\w-]+)/?(?:$|[#?])'
+    _VALID_URL = r'(https?://)?www.30daysinger.com/tutorial/(?P<playlist_id>[\w-]+)/?(?:$|[#?])'
 
     _TESTS = [{
         'url': 'https://www.30daysinger.com/tutorial/30-day-beginner-course-with-jonathan-estabrooks',
@@ -81,7 +85,7 @@ class ThirtyDaySingerPlaylistIE(ThirtyDaySingerBase):
     }]
 
     def _real_extract(self, url):
-        playlist_id = self._match_id(url)
+        playlist_id = self._match_valid_url(url).group('playlist_id')
         webpage = self._download_webpage(url, playlist_id)
         playlist_attrs = self._extract_webpage_data(webpage)
 

From 311dc3d438e2b90a8a2378c4f483182e59951b31 Mon Sep 17 00:00:00 2001
From: Kieran Eglin <kieran.eglin@gmail.com>
Date: Thu, 9 May 2024 10:57:13 -0700
Subject: [PATCH 4/4] Addl. regex refactoring

---
 yt_dlp/extractor/thirtydaysinger.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/yt_dlp/extractor/thirtydaysinger.py b/yt_dlp/extractor/thirtydaysinger.py
index 0ea779c3e..9d57e9b53 100644
--- a/yt_dlp/extractor/thirtydaysinger.py
+++ b/yt_dlp/extractor/thirtydaysinger.py
@@ -48,7 +48,7 @@ class ThirtyDaySingerBase(WistiaBaseIE):
 
 
 class ThirtyDaySingerIE(ThirtyDaySingerBase):
-    _VALID_URL = r'(https?://)?www.30daysinger.com/tutorial/[\w-]+/[\w-]+'
+    _VALID_URL = r'https?://www\.30daysinger\.com/tutorial/[\w-]+/[\w-]+'
 
     _TESTS = [{
         'url': 'https://www.30daysinger.com/tutorial/30-day-beginner-course-with-jonathan-estabrooks/1',
@@ -71,7 +71,7 @@ class ThirtyDaySingerIE(ThirtyDaySingerBase):
 
 class ThirtyDaySingerPlaylistIE(ThirtyDaySingerBase):
     _URI_BASE = 'https://www.30daysinger.com'
-    _VALID_URL = r'(https?://)?www.30daysinger.com/tutorial/(?P<playlist_id>[\w-]+)/?(?:$|[#?])'
+    _VALID_URL = r'https?://www\.30daysinger\.com/tutorial/(?P<playlist_id>[\w-]+)/?(?:$|[#?])'
 
     _TESTS = [{
         'url': 'https://www.30daysinger.com/tutorial/30-day-beginner-course-with-jonathan-estabrooks',