From 62cba8a1bedbfc0ddde7267ae57b72bf5f7ea7b1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Elan=20Ruusam=C3=A4e?= <glen@pld-linux.org>
Date: Mon, 2 Dec 2024 00:33:11 +0200
Subject: [PATCH] [ie/duoplay] Fix extractor (#11588)

Authored by: glensc, bashonly

Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>
---
 yt_dlp/extractor/duoplay.py | 60 +++++++++++++++++++++++++++++--------
 1 file changed, 47 insertions(+), 13 deletions(-)

diff --git a/yt_dlp/extractor/duoplay.py b/yt_dlp/extractor/duoplay.py
index 18642fea39..75650c3a64 100644
--- a/yt_dlp/extractor/duoplay.py
+++ b/yt_dlp/extractor/duoplay.py
@@ -5,15 +5,16 @@ from ..utils import (
     get_element_text_and_html_by_tag,
     int_or_none,
     join_nonempty,
+    parse_qs,
     str_or_none,
     try_call,
     unified_timestamp,
 )
-from ..utils.traversal import traverse_obj
+from ..utils.traversal import traverse_obj, value
 
 
 class DuoplayIE(InfoExtractor):
-    _VALID_URL = r'https?://duoplay\.ee/(?P<id>\d+)/[\w-]+/?(?:\?(?:[^#]+&)?ep=(?P<ep>\d+))?'
+    _VALID_URL = r'https?://duoplay\.ee/(?P<id>\d+)(?:[/?#]|$)'
     _TESTS = [{
         'note': 'Siberi võmm S02E12',
         'url': 'https://duoplay.ee/4312/siberi-vomm?ep=24',
@@ -34,15 +35,16 @@ class DuoplayIE(InfoExtractor):
             'episode_number': 12,
             'episode_id': '24',
         },
+        'skip': 'No video found',
     }, {
         'note': 'Empty title',
         'url': 'https://duoplay.ee/17/uhikarotid?ep=14',
-        'md5': '6aca68be71112314738dd17cced7f8bf',
+        'md5': 'cba9f5dabf2582b224d80ac44fb80e47',
         'info_dict': {
             'id': '17_14',
             'ext': 'mp4',
-            'title': 'Ühikarotid',
-            'thumbnail': r're:https://.+\.jpg(?:\?c=\d+)?$',
+            'title': 'Episode 14',
+            'thumbnail': r're:https?://.+\.jpg',
             'description': 'md5:4719b418e058c209def41d48b601276e',
             'upload_date': '20100916',
             'timestamp': 1284661800,
@@ -52,6 +54,8 @@ class DuoplayIE(InfoExtractor):
             'season_number': 2,
             'episode_id': '14',
             'release_year': 2010,
+            'episode': 'Episode 14',
+            'episode_number': 14,
         },
     }, {
         'note': 'Movie without expiry',
@@ -68,10 +72,32 @@ class DuoplayIE(InfoExtractor):
             'timestamp': 1671054000,
             'release_year': 2018,
         },
+        'skip': 'No video found',
+    }, {
+        'note': 'Episode url without show name',
+        'url': 'https://duoplay.ee/9644?ep=185',
+        'md5': '63f324b4fe2dbd8194dca16a6d52184a',
+        'info_dict': {
+            'id': '9644_185',
+            'ext': 'mp4',
+            'title': 'Episode 185',
+            'thumbnail': r're:https?://.+\.jpg',
+            'description': 'md5:ed25ba4e9e5d54bc291a4a0cdd241467',
+            'upload_date': '20241120',
+            'timestamp': 1732077000,
+            'episode': 'Episode 63',
+            'episode_id': '185',
+            'episode_number': 63,
+            'season': 'Season 2',
+            'season_number': 2,
+            'series': 'Telehommik',
+            'series_id': '9644',
+        },
     }]
 
     def _real_extract(self, url):
-        telecast_id, episode = self._match_valid_url(url).group('id', 'ep')
+        telecast_id = self._match_id(url)
+        episode = traverse_obj(parse_qs(url), ('ep', 0, {int_or_none}, {str_or_none}))
         video_id = join_nonempty(telecast_id, episode, delim='_')
         webpage = self._download_webpage(url, video_id)
         video_player = try_call(lambda: extract_attributes(
@@ -79,25 +105,33 @@ class DuoplayIE(InfoExtractor):
         if not video_player or not video_player.get('manifest-url'):
             raise ExtractorError('No video found', expected=True)
 
+        manifest_url = video_player['manifest-url']
+        session_token = self._download_json(
+            'https://sts.postimees.ee/session/register', video_id, 'Registering session',
+            'Unable to register session', headers={
+                'Accept': 'application/json',
+                'X-Original-URI': manifest_url,
+            })['session']
+
         episode_attr = self._parse_json(video_player.get(':episode') or '', video_id, fatal=False) or {}
 
         return {
             'id': video_id,
-            'formats': self._extract_m3u8_formats(video_player['manifest-url'], video_id, 'mp4'),
+            'formats': self._extract_m3u8_formats(manifest_url, video_id, 'mp4', query={'s': session_token}),
             **traverse_obj(episode_attr, {
-                'title': 'title',
-                'description': 'synopsis',
+                'title': ('title', {str}),
+                'description': ('synopsis', {str}),
                 'thumbnail': ('images', 'original'),
                 'timestamp': ('airtime', {lambda x: unified_timestamp(x + ' +0200')}),
-                'cast': ('cast', {lambda x: x.split(', ')}),
+                'cast': ('cast', filter, {lambda x: x.split(', ')}),
                 'release_year': ('year', {int_or_none}),
             }),
             **(traverse_obj(episode_attr, {
-                'title': (None, ('subtitle', ('episode_nr', {lambda x: f'Episode {x}' if x else None}))),
-                'series': 'title',
+                'title': (None, (('subtitle', {str}, filter), {value(f'Episode {episode}' if episode else None)})),
+                'series': ('title', {str}),
                 'series_id': ('telecast_id', {str_or_none}),
                 'season_number': ('season_id', {int_or_none}),
-                'episode': 'subtitle',
+                'episode': ('subtitle', {str}, filter),
                 'episode_number': ('episode_nr', {int_or_none}),
                 'episode_id': ('episode_id', {str_or_none}),
             }, get_all=False) if episode_attr.get('category') != 'movies' else {}),