Merge bd62cdba1a into da252d9d32

Closes #6884
Authored by: bashonly, Grub4K, seproDev

Co-authored-by: Simon Sawicki <contact@grub4k.xyz>
Co-authored-by: sepro <sepro@sepr0.com>

README.md

@@ -342,8 +342,9 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
                                     extractor plugins; postprocessor plugins can
                                     only be loaded from the default plugin
                                     directories
-    --flat-playlist                 Do not extract the videos of a playlist,
+    --flat-playlist                 Do not extract a playlist's URL result
-                                    only list them
+                                    entries; some entry metadata may be missing
+                                    and downloading may be bypassed
     --no-flat-playlist              Fully extract the videos of a playlist
                                     (default)
     --live-from-start               Download livestreams from the start.
@@ -1869,6 +1870,9 @@ The following extractors use this feature:
 #### digitalconcerthall
 * `prefer_combined_hls`: Prefer extracting combined/pre-merged video and audio HLS formats. This will exclude 4K/HEVC video and lossless/FLAC audio formats, which are only available as split video/audio HLS formats
 
+#### sonylivseries
+* `sort_order`: Episode sort order for series extraction - one of `asc` (ascending, oldest first) or `desc` (descending, newest first). Default is `asc`
+
 **Note**: These options may be changed/removed in the future without concern for backward compatibility
 
 <!-- MANPAGE: MOVE "INSTALLATION" SECTION HERE -->

devscripts/changelog_override.json

@@ -234,5 +234,10 @@
         "when": "57212a5f97ce367590aaa5c3e9a135eead8f81f7",
         "short": "[ie/vimeo] Fix API retries (#11351)",
         "authors": ["bashonly"]
+    },
+    {
+        "action": "add",
+        "when": "52c0ffe40ad6e8404d93296f575007b05b04c686",
+        "short": "[priority] **Login with OAuth is no longer supported for YouTube**\nDue to a change made by the site, yt-dlp is longer able to support OAuth login for YouTube. [Read more](https://github.com/yt-dlp/yt-dlp/issues/11462#issuecomment-2471703090)"
     }
 ]

test/test_InfoExtractor.py

@@ -1381,6 +1381,175 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                         },
                     ],
                 },
+            ), (
+                # Clear Key with CENC default_KID
+                'clearkey_cenc',
+                'https://media.axprod.net/TestVectors/v7-MultiDRM-SingleKey/Manifest_1080p_ClearKey.mpd',  # mpd_url
+                'https://media.axprod.net/TestVectors/v7-MultiDRM-SingleKey/',  # mpd_base_url
+                [{
+                    'manifest_url': 'https://media.axprod.net/TestVectors/v7-MultiDRM-SingleKey/Manifest_1080p_ClearKey.mpd',
+                    'ext': 'mp4',
+                    'format_id': '1',
+                    'format_note': 'DASH video',
+                    'protocol': 'http_dash_segments',
+                    'acodec': 'none',
+                    'vcodec': 'avc1.64001f',
+                    'tbr': 389.802,
+                    'width': 512,
+                    'height': 288,
+                    'dash_cenc': {
+                        'laurl': 'https://drm-clearkey-testvectors.axtest.net/AcquireLicense',
+                        'key_ids': ['9eb4050de44b4802932e27d75083e266'],
+                    },
+                }, {
+                    'manifest_url': 'https://media.axprod.net/TestVectors/v7-MultiDRM-SingleKey/Manifest_1080p_ClearKey.mpd',
+                    'ext': 'mp4',
+                    'format_id': '2',
+                    'format_note': 'DASH video',
+                    'protocol': 'http_dash_segments',
+                    'acodec': 'none',
+                    'vcodec': 'avc1.64001f',
+                    'tbr': 764.935,
+                    'width': 640,
+                    'height': 360,
+                    'dash_cenc': {
+                        'laurl': 'https://drm-clearkey-testvectors.axtest.net/AcquireLicense',
+                        'key_ids': ['9eb4050de44b4802932e27d75083e266'],
+                    },
+                }, {
+                    'manifest_url': 'https://media.axprod.net/TestVectors/v7-MultiDRM-SingleKey/Manifest_1080p_ClearKey.mpd',
+                    'ext': 'mp4',
+                    'format_id': '3',
+                    'format_note': 'DASH video',
+                    'protocol': 'http_dash_segments',
+                    'acodec': 'none',
+                    'vcodec': 'avc1.640028',
+                    'tbr': 1120.439,
+                    'width': 852,
+                    'height': 480,
+                    'dash_cenc': {
+                        'laurl': 'https://drm-clearkey-testvectors.axtest.net/AcquireLicense',
+                        'key_ids': ['9eb4050de44b4802932e27d75083e266'],
+                    },
+                }, {
+                    'manifest_url': 'https://media.axprod.net/TestVectors/v7-MultiDRM-SingleKey/Manifest_1080p_ClearKey.mpd',
+                    'ext': 'mp4',
+                    'format_id': '4',
+                    'format_note': 'DASH video',
+                    'protocol': 'http_dash_segments',
+                    'acodec': 'none',
+                    'vcodec': 'avc1.640032',
+                    'tbr': 1945.258,
+                    'width': 1280,
+                    'height': 720,
+                    'dash_cenc': {
+                        'laurl': 'https://drm-clearkey-testvectors.axtest.net/AcquireLicense',
+                        'key_ids': ['9eb4050de44b4802932e27d75083e266'],
+                    },
+                }, {
+                    'manifest_url': 'https://media.axprod.net/TestVectors/v7-MultiDRM-SingleKey/Manifest_1080p_ClearKey.mpd',
+                    'ext': 'mp4',
+                    'format_id': '5',
+                    'format_note': 'DASH video',
+                    'protocol': 'http_dash_segments',
+                    'acodec': 'none',
+                    'vcodec': 'avc1.640033',
+                    'tbr': 2726.377,
+                    'width': 1920,
+                    'height': 1080,
+                    'dash_cenc': {
+                        'laurl': 'https://drm-clearkey-testvectors.axtest.net/AcquireLicense',
+                        'key_ids': ['9eb4050de44b4802932e27d75083e266'],
+                    },
+                }],
+                {},
+            ), (
+                # default CENC KID overridden via W3C PSSH box, no license server in manifest
+                'w3c_pssh',
+                'https://unknown/manifest.mpd',  # mpd_url
+                'https://unknown/',  # mpd_base_url
+                [{
+                    'manifest_url': 'https://unknown/manifest.mpd',
+                    'ext': 'mp4',
+                    'format_id': '1',
+                    'format_note': 'DASH video',
+                    'protocol': 'http_dash_segments',
+                    'acodec': 'none',
+                    'vcodec': 'avc1.64001f',
+                    'tbr': 389.802,
+                    'width': 512,
+                    'height': 288,
+                    'dash_cenc': {
+                        'key_ids': ['43215678123412341234123412341234'],
+                    },
+                    'has_drm': True,
+                }],
+                {},
+            ), (
+                # DASH SEA with AES-128-CBC
+                'dash_sea',
+                'https://unknown/manifest.mpd',  # mpd_url
+                'https://unknown/',  # mpd_base_url
+                [{
+                    'manifest_url': 'https://unknown/manifest.mpd',
+                    'ext': 'm4a',
+                    'format_id': '5_A_aac_eng_2_127999_2_1_1',
+                    'format_note': 'DASH audio',
+                    'protocol': 'http_dash_segments',
+                    'acodec': 'mp4a.40.2',
+                    'vcodec': 'none',
+                    'tbr': 127.999,
+                    'hls_aes': {
+                        'uri': 'https://zavideoplatform.keydelivery.eastus.media.azure.net/?kid=9280864f-064e-48c0-97e0-f2bcb1d8d012',
+                        'iv': '0x7BD31E102B0CE9CCD39691782533656C',
+                    },
+                }, {
+                    'manifest_url': 'https://unknown/manifest.mpd',
+                    'ext': 'mp4',
+                    'format_id': '1_V_video_3',
+                    'format_note': 'DASH video',
+                    'protocol': 'http_dash_segments',
+                    'acodec': 'none',
+                    'vcodec': 'avc1.64001F',
+                    'tbr': 258.591,
+                    'width': 960,
+                    'height': 540,
+                    'hls_aes': {
+                        'uri': 'https://zavideoplatform.keydelivery.eastus.media.azure.net/?kid=9280864f-064e-48c0-97e0-f2bcb1d8d012',
+                        'iv': '0x7BD31E102B0CE9CCD39691782533656C',
+                    },
+                }, {
+                    'manifest_url': 'https://unknown/manifest.mpd',
+                    'ext': 'mp4',
+                    'format_id': '1_V_video_2',
+                    'format_note': 'DASH video',
+                    'protocol': 'http_dash_segments',
+                    'acodec': 'none',
+                    'vcodec': 'avc1.64001F',
+                    'tbr': 422.519,
+                    'width': 1280,
+                    'height': 720,
+                    'hls_aes': {
+                        'uri': 'https://zavideoplatform.keydelivery.eastus.media.azure.net/?kid=9280864f-064e-48c0-97e0-f2bcb1d8d012',
+                        'iv': '0x7BD31E102B0CE9CCD39691782533656C',
+                    },
+                }, {
+                    'manifest_url': 'https://unknown/manifest.mpd',
+                    'ext': 'mp4',
+                    'format_id': '1_V_video_1',
+                    'format_note': 'DASH video',
+                    'protocol': 'http_dash_segments',
+                    'acodec': 'none',
+                    'vcodec': 'avc1.640028',
+                    'tbr': 628.102,
+                    'width': 1920,
+                    'height': 1080,
+                    'hls_aes': {
+                        'uri': 'https://zavideoplatform.keydelivery.eastus.media.azure.net/?kid=9280864f-064e-48c0-97e0-f2bcb1d8d012',
+                        'iv': '0x7BD31E102B0CE9CCD39691782533656C',
+                    },
+                }],
+                {},
             ),
         ]
 

test/testdata/mpd/clearkey_cenc.mpd

@@ -0,0 +1,29 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!--
+Version information:
+Axinom.MediaProcessing v3.0.0 targeting General Purpose Media Format specification v7
+ffmpeg version N-81423-g61fac0e Copyright (c) 2000-2016 the FFmpeg developers
+x265 [info]: HEVC encoder version 2.0+12-49a0d1176aef5bc6
+x264 0.148.2705 3f5ed56
+MP4Box - GPAC version 0.6.2-DEV-rev683-g7b29fbe-master
+MediaInfoLib - v0.7.87
+
+For more info about this video, see https://github.com/Axinom/dash-test-vectors
+-->
+<MPD xmlns="urn:mpeg:dash:schema:mpd:2011" minBufferTime="PT1.500S" type="static" mediaPresentationDuration="PT0H12M14.000S" maxSegmentDuration="PT0H0M4.000S" profiles="urn:mpeg:dash:profile:isoff-live:2011,http://dashif.org/guidelines/dash264" xmlns:cenc="urn:mpeg:cenc:2013" xmlns:clearkey="http://dashif.org/guidelines/clearKey">
+	<Period duration="PT0H12M14.000S">
+		<AdaptationSet segmentAlignment="true" group="1" maxWidth="1920" maxHeight="1080" maxFrameRate="24" par="16:9" lang="und">
+			<ContentProtection schemeIdUri="urn:mpeg:dash:mp4protection:2011" value="cenc" cenc:default_KID="9eb4050d-e44b-4802-932e-27d75083e266" />
+			<ContentProtection value="ClearKey1.0" schemeIdUri="urn:uuid:e2719d58-a985-b3c9-781a-b030af78d30e">
+				<clearkey:Laurl Lic_type="EME-1.0">https://drm-clearkey-testvectors.axtest.net/AcquireLicense</clearkey:Laurl>
+			</ContentProtection>
+			<Role schemeIdUri="urn:mpeg:dash:role:2011" value="main" />
+			<SegmentTemplate timescale="24" media="$RepresentationID$/$Number%04d$.m4s" startNumber="1" duration="96" initialization="$RepresentationID$/init.mp4" />
+			<Representation id="1" mimeType="video/mp4" codecs="avc1.64001f" width="512" height="288" frameRate="24" sar="1:1" startWithSAP="1" bandwidth="389802"></Representation>
+			<Representation id="2" mimeType="video/mp4" codecs="avc1.64001f" width="640" height="360" frameRate="24" sar="1:1" startWithSAP="1" bandwidth="764935"></Representation>
+			<Representation id="3" mimeType="video/mp4" codecs="avc1.640028" width="852" height="480" frameRate="24" sar="640:639" startWithSAP="1" bandwidth="1120439"></Representation>
+			<Representation id="4" mimeType="video/mp4" codecs="avc1.640032" width="1280" height="720" frameRate="24" sar="1:1" startWithSAP="1" bandwidth="1945258"></Representation>
+			<Representation id="5" mimeType="video/mp4" codecs="avc1.640033" width="1920" height="1080" frameRate="24" sar="1:1" startWithSAP="1" bandwidth="2726377"></Representation>
+		</AdaptationSet>
+	</Period>
+</MPD>

test/testdata/mpd/dash_sea.mpd

@@ -0,0 +1,109 @@
+<?xml version="1.0" encoding="utf-8"?>
+<MPD
+	xmlns="urn:mpeg:dash:schema:mpd:2011"
+	xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" profiles="urn:mpeg:dash:profile:isoff-live:2011" type="static"
+	xmlns:sea="urn:mpeg:dash:schema:sea:2012" mediaPresentationDuration="PT3M32.949S" minBufferTime="PT3S">
+	<Period>
+		<AdaptationSet id="1" group="5" profiles="ccff" bitstreamSwitching="false" segmentAlignment="true" contentType="audio" mimeType="audio/mp4" codecs="mp4a.40.2" lang="en">
+			<ContentProtection schemeIdUri="urn:mpeg:dash:sea:2012">
+				<sea:SegmentEncryption schemeIdUri="urn:mpeg:dash:sea:aes128-cbc:2013"/>
+				<sea:KeySystem keySystemUri="urn:mpeg:dash:sea:keysys:http:2013"/>
+				<sea:CryptoPeriod keyUriTemplate="https://zavideoplatform.keydelivery.eastus.media.azure.net/?kid=9280864f-064e-48c0-97e0-f2bcb1d8d012" IV="0x7BD31E102B0CE9CCD39691782533656C"/>
+			</ContentProtection>
+			<Label>aac_eng_2_127999_2_1</Label>
+			<SegmentTemplate timescale="10000000" media="QualityLevels($Bandwidth$)/Fragments(aac_eng_2_127999_2_1=$Time$,format=mpd-time-csf)" initialization="QualityLevels($Bandwidth$)/Fragments(aac_eng_2_127999_2_1=i,format=mpd-time-csf)">
+				<SegmentTimeline>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333" r="1"/>
+					<S d="20053334"/>
+					<S d="20053333"/>
+					<S d="3840000"/>
+				</SegmentTimeline>
+			</SegmentTemplate>
+			<Representation id="5_A_aac_eng_2_127999_2_1_1" bandwidth="127999" audioSamplingRate="48000"/>
+		</AdaptationSet>
+		<AdaptationSet id="2" group="1" profiles="ccff" bitstreamSwitching="false" segmentAlignment="true" contentType="video" mimeType="video/mp4" codecs="avc1.640028" maxWidth="1920" maxHeight="1080" startWithSAP="1">
+			<ContentProtection schemeIdUri="urn:mpeg:dash:sea:2012">
+				<sea:SegmentEncryption schemeIdUri="urn:mpeg:dash:sea:aes128-cbc:2013"/>
+				<sea:KeySystem keySystemUri="urn:mpeg:dash:sea:keysys:http:2013"/>
+				<sea:CryptoPeriod keyUriTemplate="https://zavideoplatform.keydelivery.eastus.media.azure.net/?kid=9280864f-064e-48c0-97e0-f2bcb1d8d012" IV="0x7BD31E102B0CE9CCD39691782533656C"/>
+			</ContentProtection>
+			<SegmentTemplate timescale="10000000" media="QualityLevels($Bandwidth$)/Fragments(video=$Time$,format=mpd-time-csf)" initialization="QualityLevels($Bandwidth$)/Fragments(video=i,format=mpd-time-csf)">
+				<SegmentTimeline>
+					<S d="20000000" r="105"/>
+					<S d="8666666"/>
+				</SegmentTimeline>
+			</SegmentTemplate>
+			<Representation id="1_V_video_1" bandwidth="628102" width="1920" height="1080"/>
+			<Representation id="1_V_video_2" bandwidth="422519" codecs="avc1.64001F" width="1280" height="720"/>
+			<Representation id="1_V_video_3" bandwidth="258591" codecs="avc1.64001F" width="960" height="540"/>
+		</AdaptationSet>
+	</Period>
+</MPD>

test/testdata/mpd/w3c_pssh.mpd

@@ -0,0 +1,13 @@
+<MPD xmlns="urn:mpeg:dash:schema:mpd:2011" minBufferTime="PT1.500S" type="static" mediaPresentationDuration="PT0H12M14.000S" maxSegmentDuration="PT0H0M4.000S" profiles="urn:mpeg:dash:profile:isoff-live:2011,http://dashif.org/guidelines/dash264" xmlns:cenc="urn:mpeg:cenc:2013" xmlns:clearkey="http://dashif.org/guidelines/clearKey">
+	<Period duration="PT0H12M14.000S">
+		<AdaptationSet segmentAlignment="true" group="1" maxWidth="1920" maxHeight="1080" maxFrameRate="24" par="16:9" lang="und">
+			<ContentProtection schemeIdUri="urn:mpeg:dash:mp4protection:2011" value="cenc" cenc:default_KID="9eb4050d-e44b-4802-932e-27d75083e266" />
+            <ContentProtection schemeIdUri="urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b">
+              <cenc:pssh>AAAANHBzc2gBAAAAEHfv7MCyTQKs4zweUuL7SwAAAAFDIVZ4EjQSNBI0EjQSNBI0AAAAAA==</cenc:pssh>
+            </ContentProtection>
+			<Role schemeIdUri="urn:mpeg:dash:role:2011" value="main" />
+			<SegmentTemplate timescale="24" media="$RepresentationID$/$Number%04d$.m4s" startNumber="1" duration="96" initialization="$RepresentationID$/init.mp4" />
+			<Representation id="1" mimeType="video/mp4" codecs="avc1.64001f" width="512" height="288" frameRate="24" sar="1:1" startWithSAP="1" bandwidth="389802"></Representation>
+		</AdaptationSet>
+	</Period>
+</MPD>

yt_dlp/YoutubeDL.py

@@ -48,6 +48,7 @@ from .plugins import directories as plugin_directories
 from .postprocessor import _PLUGIN_CLASSES as plugin_pps
 from .postprocessor import (
     EmbedThumbnailPP,
+    FFmpegCENCDecryptPP,
     FFmpegFixupDuplicateMoovPP,
     FFmpegFixupDurationPP,
     FFmpegFixupM3u8PP,
@@ -3379,6 +3380,8 @@ class YoutubeDL:
                         self.report_error(f'{msg}. Aborting')
                         return
 
+                decrypter = FFmpegCENCDecryptPP(self)
+                info_dict.setdefault('__files_to_cenc_decrypt', [])
                 if info_dict.get('requested_formats') is not None:
                     old_ext = info_dict['ext']
                     if self.params.get('merge_output_format') is None:
@@ -3459,8 +3462,12 @@ class YoutubeDL:
                                 downloaded.append(fname)
                             partial_success, real_download = self.dl(fname, new_info)
                             info_dict['__real_download'] = info_dict['__real_download'] or real_download
+                            if new_info.get('dash_cenc', {}).get('key'):
+                                info_dict['__files_to_cenc_decrypt'].append((fname, new_info['dash_cenc']['key']))
                             success = success and partial_success
 
+                    if downloaded and info_dict['__files_to_cenc_decrypt'] and decrypter.available:
+                        info_dict['__postprocessors'].append(decrypter)
                     if downloaded and merger.available and not self.params.get('allow_unplayable_formats'):
                         info_dict['__postprocessors'].append(merger)
                         info_dict['__files_to_merge'] = downloaded
@@ -3477,6 +3484,9 @@ class YoutubeDL:
                         # So we should try to resume the download
                         success, real_download = self.dl(temp_filename, info_dict)
                         info_dict['__real_download'] = real_download
+                        if info_dict.get('dash_cenc', {}).get('key') and decrypter.available:
+                            info_dict['__postprocessors'].append(decrypter)
+                            info_dict['__files_to_cenc_decrypt'] = [(temp_filename, info_dict['dash_cenc']['key'])]
                     else:
                         self.report_file_already_downloaded(dl_filename)
 

yt_dlp/downloader/dash.py

@@ -1,9 +1,14 @@
+import base64
+import binascii
+import json
 import time
 import urllib.parse
 
 from . import get_suitable_downloader
 from .fragment import FragmentFD
-from ..utils import update_url_query, urljoin
+from ..networking import Request
+from ..networking.exceptions import RequestError
+from ..utils import remove_start, traverse_obj, update_url_query, urljoin
 
 
 class DashSegmentsFD(FragmentFD):
@@ -49,6 +54,25 @@ class DashSegmentsFD(FragmentFD):
             if extra_param_to_segment_url:
                 extra_query = urllib.parse.parse_qs(extra_param_to_segment_url)
 
+            hls_aes = fmt.get('hls_aes', {})
+            if hls_aes:
+                decrypt_info = {'METHOD', 'AES-128'}
+                key = hls_aes.get('key')
+                if key:
+                    key = binascii.unhexlify(remove_start(key, '0x'))
+                    assert len(key) in (16, 24, 32), 'Invalid length for HLS AES-128 key'
+                    decrypt_info['KEY'] = key
+                iv = hls_aes.get('iv')
+                if iv:
+                    iv = binascii.unhexlify(remove_start(iv, '0x').zfill(32))
+                    decrypt_info['IV'] = iv
+                uri = hls_aes.get('uri')
+                if uri:
+                    if extra_query:
+                        uri = update_url_query(uri, extra_query)
+                    decrypt_info['URI'] = uri
+                ctx['decrypt_info'] = decrypt_info
+
             fragments_to_download = self._get_fragments(fmt, ctx, extra_query)
 
             if real_downloader:
@@ -60,6 +84,12 @@ class DashSegmentsFD(FragmentFD):
 
             args.append([ctx, fragments_to_download, fmt])
 
+        cenc_key = traverse_obj(info_dict, ('dash_cenc', 'key'))
+        cenc_key_ids = traverse_obj(info_dict, ('dash_cenc', 'key_ids'))
+        clearkey_laurl = traverse_obj(info_dict, ('dash_cenc', 'laurl'))
+        if not cenc_key and cenc_key_ids and clearkey_laurl:
+            self._get_clearkey_cenc(info_dict, clearkey_laurl, cenc_key_ids)
+
         return self.download_and_append_fragments_multiple(*args, is_fatal=lambda idx: idx == 0)
 
     def _resolve_fragments(self, fragments, ctx):
@@ -87,4 +117,35 @@ class DashSegmentsFD(FragmentFD):
                 'fragment_count': fragment.get('fragment_count'),
                 'index': i,
                 'url': fragment_url,
+                'decrypt_info': ctx.get('decrypt_info', {'METHOD': 'NONE'}),
             }
+
+    def _get_clearkey_cenc(self, info_dict, laurl, key_ids):
+        dash_cenc = info_dict.get('dash_cenc', {})
+        payload = json.dumps({
+            'kids': [
+                base64.urlsafe_b64encode(bytes.fromhex(k)).decode().rstrip('=')
+                for k in key_ids
+            ],
+            'type': 'temporary',
+        }).encode()
+        try:
+            response = self.ydl.urlopen(Request(
+                laurl, data=payload, headers={'Content-Type': 'application/json'}))
+            data = json.loads(response.read())
+        except (RequestError, json.JSONDecodeError) as err:
+            self.report_error(f'Failed to retrieve key from Clear Key license server: {err}')
+            return
+        keys = data.get('keys', [])
+        if len(keys) > 1:
+            self.report_warning('Clear Key license server returned multiple keys but only single key CENC is supported')
+        for key in keys:
+            k = key.get('k')
+            if k:
+                try:
+                    dash_cenc.update({'key': base64.urlsafe_b64decode(f'{k}==').hex()})
+                    info_dict['dash_cenc'] = dash_cenc
+                    return
+                except (ValueError, binascii.Error):
+                    pass
+        self.report_error('Clear key license server did not return any valid CENC keys')

yt_dlp/extractor/_extractors.py

@@ -946,6 +946,10 @@ from .kaltura import KalturaIE
 from .kankanews import KankaNewsIE
 from .karaoketv import KaraoketvIE
 from .kelbyone import KelbyOneIE
+from .kenh14 import (
+    Kenh14PlaylistIE,
+    Kenh14VideoIE,
+)
 from .khanacademy import (
     KhanAcademyIE,
     KhanAcademyUnitIE,
@@ -1135,12 +1139,6 @@ from .microsoftembed import (
     MicrosoftMediusIE,
 )
 from .microsoftstream import MicrosoftStreamIE
-from .mildom import (
-    MildomClipIE,
-    MildomIE,
-    MildomUserVodIE,
-    MildomVodIE,
-)
 from .minds import (
     MindsChannelIE,
     MindsGroupIE,
@@ -1522,8 +1520,8 @@ from .pgatour import PGATourIE
 from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
+from .pialive import PiaLiveIE
 from .piapro import PiaproIE
-from .piaulizaportal import PIAULIZAPortalIE
 from .picarto import (
     PicartoIE,
     PicartoVodIE,
@@ -1559,10 +1557,6 @@ from .podbayfm import (
 )
 from .podchaser import PodchaserIE
 from .podomatic import PodomaticIE
-from .pokemon import (
-    PokemonIE,
-    PokemonWatchIE,
-)
 from .pokergo import (
     PokerGoCollectionIE,
     PokerGoIE,
@@ -2256,6 +2250,10 @@ from .ufctv import (
 )
 from .ukcolumn import UkColumnIE
 from .uktvplay import UKTVPlayIE
+from .uliza import (
+    UlizaPlayerIE,
+    UlizaPortalIE,
+)
 from .umg import UMGDeIE
 from .unistra import UnistraIE
 from .unity import UnityIE
@@ -2284,10 +2282,6 @@ from .utreon import UtreonIE
 from .varzesh3 import Varzesh3IE
 from .vbox7 import Vbox7IE
 from .veo import VeoIE
-from .veoh import (
-    VeohIE,
-    VeohUserIE,
-)
 from .vesti import VestiIE
 from .vevo import (
     VevoIE,

yt_dlp/extractor/bandlab.py

@@ -1,4 +1,3 @@
-
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,

yt_dlp/extractor/chaturbate.py

@@ -79,7 +79,7 @@ class ChaturbateIE(InfoExtractor):
             'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True),
         }
 
-    def _extract_from_webpage(self, video_id, tld):
+    def _extract_from_html(self, video_id, tld):
         webpage = self._download_webpage(
             f'https://chaturbate.{tld}/{video_id}/', video_id,
             headers=self.geo_verification_headers(), impersonate=True)
@@ -151,4 +151,4 @@ class ChaturbateIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id, tld = self._match_valid_url(url).group('id', 'tld')
-        return self._extract_from_api(video_id, tld) or self._extract_from_webpage(video_id, tld)
+        return self._extract_from_api(video_id, tld) or self._extract_from_html(video_id, tld)

yt_dlp/extractor/common.py

@@ -14,12 +14,14 @@ import netrc
 import os
 import random
 import re
+import struct
 import subprocess
 import sys
 import time
 import types
 import urllib.parse
 import urllib.request
+import uuid
 import xml.etree.ElementTree
 
 from ..compat import (
@@ -246,7 +248,9 @@ class InfoExtractor:
                     * hls_aes    A dictionary of HLS AES-128 decryption information
                                  used by the native HLS downloader to override the
                                  values in the media playlist when an '#EXT-X-KEY' tag
-                                 is present in the playlist:
+                                 is present in the playlist. Used by the native DASH downloader
+                                 when DASH-SEA with AES-128-CBC content protection is present
+                                 in the manifest.:
                                  * uri  The URI from which the key will be downloaded
                                  * key  The key (as hex) used to decrypt fragments.
                                         If `key` is given, any key URI will be ignored
@@ -258,6 +262,16 @@ class InfoExtractor:
                                  * ffmpeg_args_out Extra arguments for ffmpeg downloader (output)
                     * is_dash_periods  Whether the format is a result of merging
                                  multiple DASH periods.
+                    * dash_cenc  A dictionary of DASH CENC decryption information
+                                 used by the native DASH downloader when MPEG CENC content protection
+                                 is present in the manifest.
+                                 * laurl    The Clear Key license server URL from which
+                                            CENC keys will be downloaded.
+                                 * key_ids  List of key IDs (as hex) to request from the ClearKey
+                                            license server.
+                                 * key      The CENC key (as hex) used to decrypt fragments.
+                                            If `key` is given, any license server URL and
+                                            key IDs will be ignored.
                     RTMP formats can also have the additional fields: page_url,
                     app, play_path, tc_url, flash_version, rtmp_live, rtmp_conn,
                     rtmp_protocol, rtmp_real_time
@@ -2679,7 +2693,11 @@ class InfoExtractor:
                 assert 'is_dash_periods' not in f, 'format already processed'
                 f['is_dash_periods'] = True
                 format_key = tuple(v for k, v in f.items() if k not in (
-                    ('format_id', 'fragments', 'manifest_stream_number')))
+                    ('format_id', 'fragments', 'manifest_stream_number', 'dash_cenc', 'hls_aes')))
+                for k in ('dash_cenc', 'hls_aes'):
+                    if k in f:
+                        format_key = format_key + tuple(
+                            tuple(v) if isinstance(v, list) else v for v in f[k].values())
                 if format_key not in formats:
                     formats[format_key] = f
                 elif 'fragments' in f:
@@ -2713,8 +2731,16 @@ class InfoExtractor:
         def _add_ns(path):
             return self._xpath_ns(path, namespace)
 
-        def is_drm_protected(element):
+        def extract_drm_info(element):
-            return element.find(_add_ns('ContentProtection')) is not None
+            info = {}
+            has_drm = False
+            for cp_e in element.findall(_add_ns('ContentProtection')):
+                has_drm = True
+                self._extract_mpd_content_protection_info(cp_e, info)
+            cenc_info = info.get('dash_cenc', {})
+            if has_drm and not ('hls_aes' in info or cenc_info.get('key') or (cenc_info.get('laurl') and cenc_info.get('key_ids'))):
+                info['has_drm'] = True
+            return info
 
         def extract_multisegment_info(element, ms_parent_info):
             ms_info = ms_parent_info.copy()
@@ -2788,6 +2814,7 @@ class InfoExtractor:
                 'timescale': 1,
             })
             for adaptation_set in period.findall(_add_ns('AdaptationSet')):
+                adaptation_set_drm_info = extract_drm_info(adaptation_set)
                 adaption_set_ms_info = extract_multisegment_info(adaptation_set, period_ms_info)
                 for representation in adaptation_set.findall(_add_ns('Representation')):
                     representation_attrib = adaptation_set.attrib.copy()
@@ -2874,8 +2901,8 @@ class InfoExtractor:
                             'acodec': 'none',
                             'vcodec': 'none',
                         }
-                    if is_drm_protected(adaptation_set) or is_drm_protected(representation):
+                    f.update(adaptation_set_drm_info)
-                        f['has_drm'] = True
+                    f.update(extract_drm_info(representation))
                     representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info)
 
                     def prepare_template(template_name, identifiers):
@@ -3036,6 +3063,86 @@ class InfoExtractor:
                         period_entry['subtitles'][lang or 'und'].append(f)
             yield period_entry
 
+    def _extract_mpd_content_protection_info(self, cp_e, info):
+        """
+        Extract supported DASH-CENC parameters for an MPD ContentProtection element.
+
+        Called multiple times per extracted format in an MPD (once per ContentProtection element
+        within AdaptationSet and Representation elements). Subclasses may override this method
+        when necessary (such as when the Clear Key license server URL is provided separately
+        from the manifest or when an extractor needs to process the optional data section in W3C
+        PSSH boxes).
+
+        Note that after all ContentProtection elements have been handled, the `has_drm` flag
+        will be set for any format that does not meet one or more of these conditions:
+
+            * `dash_cenc` is set and both `laurl` and `key_ids` are set (indicating the native
+               DASH downloader should use the specified Clear Key server URL to retreive the
+               CENC key for this format).
+            * `dash_cenc` is set and `key` is set (indicating the native DASH downloader should
+               use the specified CENC key for this format).
+            * `hls_aes` is set (indicating the native DASH downloader should use DASH SEA
+              AES-128-CBC decryption for this format).
+
+        References:
+         1. DASH-IF Content Protection Identifiers
+            https://dashif.org/identifiers/content_protection/
+         2. DASH-IF Content Protection Guidelines
+            https://dashif.org/docs/IOP-Guidelines/DASH-IF-IOP-Part6-v5.0.0.pdf
+         3. W3C "cenc" Initialization Data Format
+            https://w3c.github.io/encrypted-media/format-registry/initdata/cenc.html
+        """
+        scheme_id = cp_e.get('schemeIdUri')
+        cenc_info = info.get('dash_cenc', {})
+        if scheme_id == 'urn:mpeg:dash:mp4protection:2011':
+            if cp_e.get('value') == 'cenc':
+                # ISO/IEC 23009-1 MPEG Common Encryption (CENC)
+                if not cenc_info.get('key_ids'):
+                    try:
+                        default_kid = uuid.UUID(cp_e.get('{urn:mpeg:cenc:2013}default_KID')).hex
+                        cenc_info['key_ids'] = [default_kid]
+                    except (ValueError, TypeError):
+                        pass
+        elif scheme_id == 'urn:uuid:e2719d58-a985-b3c9-781a-b030af78d30e':
+            # Clear Key DASH-IF
+            for tag, ns in itertools.product(
+                ('Laurl', 'laurl'),
+                ('https://dashif.org/CPS', 'http://dashif.org/guidelines/clearKey'),
+            ):
+                url_e = cp_e.find(self._xpath_ns(tag, ns))
+                if url_e is not None:
+                    cenc_info['laurl'] = url_e.text
+                    break
+        elif scheme_id == 'urn:uuid:1077efec-c0b2-4d02-ace3-3c1e52e2fb4b':
+            # W3C Common System ID
+            pssh_e = cp_e.find(self._xpath_ns('pssh', 'urn:mpeg:cenc:2013'))
+            if pssh_e is not None:
+                # W3C PSSH box (may contain Clear Key KIDs but can also be used
+                # to store KIDs for other DRM systems)
+                try:
+                    pssh_box = base64.b64decode(pssh_e.text)
+                    kid_count, = struct.unpack('!L', pssh_box[28:32])
+                    kids = []
+                    for i in range(kid_count):
+                        kid = pssh_box[32 + i * 16:32 + (i + 1) * 16]
+                        kids.append(kid.hex())
+                    cenc_info['key_ids'] = kids
+                except (ValueError, TypeError, struct.error):
+                    pass
+        elif scheme_id == 'urn:mpeg:dash:sea:2012':
+            # ISO/IEC 23009-4 DASH Segment Encryption and Authentication (AES-128-CBC)
+            sea_ns = 'urn:mpeg:dash:schema:sea:2012'
+            se_e = cp_e.find(self._xpath_ns('SegmentEncryption', sea_ns))
+            ks_e = cp_e.find(self._xpath_ns('KeySystem', sea_ns))
+            crypto_e = cp_e.find(self._xpath_ns('CryptoPeriod', sea_ns))
+            if (se_e is not None and se_e.get('schemeIdUri') == 'urn:mpeg:dash:sea:aes128-cbc:2013'
+                    and ks_e is not None and ks_e.get('keySystemUri') == 'urn:mpeg:dash:sea:keysys:http:2013'
+                    and crypto_e is not None and crypto_e.get('keyUriTemplate') and crypto_e.get('IV')
+                    ):
+                info['hls_aes'] = {'uri': crypto_e.get('keyUriTemplate'), 'iv': crypto_e.get('IV')}
+        if cenc_info:
+            info['dash_cenc'] = cenc_info
+
     def _extract_ism_formats(self, *args, **kwargs):
         fmts, subs = self._extract_ism_formats_and_subtitles(*args, **kwargs)
         if subs:
@@ -3767,7 +3874,7 @@ class InfoExtractor:
         """ Merge subtitle dictionaries, language by language. """
         if target is None:
             target = {}
-        for d in dicts:
+        for d in filter(None, dicts):
             for lang, subs in d.items():
                 target[lang] = cls._merge_subtitle_items(target.get(lang, []), subs)
         return target

yt_dlp/extractor/ctvnews.py

@@ -1,14 +1,27 @@
+import json
 import re
+import urllib.parse
 
 from .common import InfoExtractor
-from ..utils import orderedSet
+from .ninecninemedia import NineCNineMediaIE
+from ..utils import extract_attributes, orderedSet
+from ..utils.traversal import find_element, traverse_obj
 
 
 class CTVNewsIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:.+?\.)?ctvnews\.ca/(?:video\?(?:clip|playlist|bin)Id=|.*?)(?P<id>[0-9.]+)'
+    _BASE_REGEX = r'https?://(?:[^.]+\.)?ctvnews\.ca/'
+    _VIDEO_ID_RE = r'(?P<id>\d{5,})'
+    _PLAYLIST_ID_RE = r'(?P<id>\d\.\d{5,})'
+    _VALID_URL = [
+        rf'{_BASE_REGEX}video/c{_VIDEO_ID_RE}',
+        rf'{_BASE_REGEX}video(?:-gallery)?/?\?clipId={_VIDEO_ID_RE}',
+        rf'{_BASE_REGEX}video/?\?(?:playlist|bin)Id={_PLAYLIST_ID_RE}',
+        rf'{_BASE_REGEX}(?!video/)[^?#]*?{_PLAYLIST_ID_RE}/?(?:$|[?#])',
+        rf'{_BASE_REGEX}(?!video/)[^?#]+\?binId={_PLAYLIST_ID_RE}',
+    ]
     _TESTS = [{
         'url': 'http://www.ctvnews.ca/video?clipId=901995',
-        'md5': '9b8624ba66351a23e0b6e1391971f9af',
+        'md5': 'b608f466c7fa24b9666c6439d766ab7e',
         'info_dict': {
             'id': '901995',
             'ext': 'flv',
@@ -16,6 +29,33 @@ class CTVNewsIE(InfoExtractor):
             'description': 'md5:958dd3b4f5bbbf0ed4d045c790d89285',
             'timestamp': 1467286284,
             'upload_date': '20160630',
+            'categories': [],
+            'season_number': 0,
+            'season': 'Season 0',
+            'tags': [],
+            'series': 'CTV News National | Archive | Stories 2',
+            'season_id': '57981',
+            'thumbnail': r're:https?://.*\.jpg$',
+            'duration': 764.631,
+        },
+    }, {
+        'url': 'https://barrie.ctvnews.ca/video/c3030933-here_s-what_s-making-news-for-nov--15?binId=1272429',
+        'md5': '8b8c2b33c5c1803e3c26bc74ff8694d5',
+        'info_dict': {
+            'id': '3030933',
+            'ext': 'flv',
+            'title': 'Here’s what’s making news for Nov. 15',
+            'description': 'Here are the top stories we’re working on for CTV News at 11 for Nov. 15',
+            'thumbnail': 'http://images2.9c9media.com/image_asset/2021_2_22_a602e68e-1514-410e-a67a-e1f7cccbacab_png_2000x1125.jpg',
+            'season_id': '58104',
+            'season_number': 0,
+            'tags': [],
+            'season': 'Season 0',
+            'categories': [],
+            'series': 'CTV News Barrie',
+            'upload_date': '20241116',
+            'duration': 42.943,
+            'timestamp': 1731722452,
         },
     }, {
         'url': 'http://www.ctvnews.ca/video?playlistId=1.2966224',
@@ -31,6 +71,72 @@ class CTVNewsIE(InfoExtractor):
             'id': '1.2876780',
         },
         'playlist_mincount': 100,
+    }, {
+        'url': 'https://www.ctvnews.ca/it-s-been-23-years-since-toronto-called-in-the-army-after-a-major-snowstorm-1.5736957',
+        'info_dict':
+        {
+            'id': '1.5736957',
+        },
+        'playlist_mincount': 6,
+    }, {
+        'url': 'https://www.ctvnews.ca/business/respondents-to-bank-of-canada-questionnaire-largely-oppose-creating-a-digital-loonie-1.6665797',
+        'md5': '24bc4b88cdc17d8c3fc01dfc228ab72c',
+        'info_dict': {
+            'id': '2695026',
+            'ext': 'flv',
+            'season_id': '89852',
+            'series': 'From CTV News Channel',
+            'description': 'md5:796a985a23cacc7e1e2fafefd94afd0a',
+            'season': '2023',
+            'title': 'Bank of Canada asks public about digital currency',
+            'categories': [],
+            'tags': [],
+            'upload_date': '20230526',
+            'season_number': 2023,
+            'thumbnail': 'http://images2.9c9media.com/image_asset/2019_3_28_35f5afc3-10f6-4d92-b194-8b9a86f55c6a_png_1920x1080.jpg',
+            'timestamp': 1685105157,
+            'duration': 253.553,
+        },
+    }, {
+        'url': 'https://stox.ctvnews.ca/video-gallery?clipId=582589',
+        'md5': '135cc592df607d29dddc931f1b756ae2',
+        'info_dict': {
+            'id': '582589',
+            'ext': 'flv',
+            'categories': [],
+            'timestamp': 1427906183,
+            'season_number': 0,
+            'duration': 125.559,
+            'thumbnail': 'http://images2.9c9media.com/image_asset/2019_3_28_35f5afc3-10f6-4d92-b194-8b9a86f55c6a_png_1920x1080.jpg',
+            'series': 'CTV News Stox',
+            'description': 'CTV original footage of the rise and fall of the Berlin Wall.',
+            'title': 'Berlin Wall',
+            'season_id': '63817',
+            'season': 'Season 0',
+            'tags': [],
+            'upload_date': '20150401',
+        },
+    }, {
+        'url': 'https://ottawa.ctvnews.ca/features/regional-contact/regional-contact-archive?binId=1.1164587#3023759',
+        'md5': 'a14c0603557decc6531260791c23cc5e',
+        'info_dict': {
+            'id': '3023759',
+            'ext': 'flv',
+            'season_number': 2024,
+            'timestamp': 1731798000,
+            'season': '2024',
+            'episode': 'Episode 125',
+            'description': 'CTV News Ottawa at Six',
+            'duration': 2712.076,
+            'episode_number': 125,
+            'upload_date': '20241116',
+            'title': 'CTV News Ottawa at Six for Saturday, November 16, 2024',
+            'thumbnail': 'http://images2.9c9media.com/image_asset/2019_3_28_35f5afc3-10f6-4d92-b194-8b9a86f55c6a_png_1920x1080.jpg',
+            'categories': [],
+            'tags': [],
+            'series': 'CTV News Ottawa at Six',
+            'season_id': '92667',
+        },
     }, {
         'url': 'http://www.ctvnews.ca/1.810401',
         'only_matching': True,
@@ -42,29 +148,35 @@ class CTVNewsIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    def _ninecninemedia_url_result(self, clip_id):
+        return self.url_result(f'9c9media:ctvnews_web:{clip_id}', NineCNineMediaIE, clip_id)
+
     def _real_extract(self, url):
         page_id = self._match_id(url)
 
-        def ninecninemedia_url_result(clip_id):
+        if mobj := re.fullmatch(self._VIDEO_ID_RE, urllib.parse.urlparse(url).fragment):
-            return {
+            page_id = mobj.group('id')
-                '_type': 'url_transparent',
-                'id': clip_id,
-                'url': f'9c9media:ctvnews_web:{clip_id}',
-                'ie_key': 'NineCNineMedia',
-            }
 
-        if page_id.isdigit():
+        if re.fullmatch(self._VIDEO_ID_RE, page_id):
-            return ninecninemedia_url_result(page_id)
+            return self._ninecninemedia_url_result(page_id)
-        else:
+
-            webpage = self._download_webpage(f'http://www.ctvnews.ca/{page_id}', page_id, query={
+        webpage = self._download_webpage(f'https://www.ctvnews.ca/{page_id}', page_id, query={
             'ot': 'example.AjaxPageLayout.ot',
             'maxItemsPerPage': 1000000,
         })
-            entries = [ninecninemedia_url_result(clip_id) for clip_id in orderedSet(
+        entries = [self._ninecninemedia_url_result(clip_id)
-                re.findall(r'clip\.id\s*=\s*(\d+);', webpage))]
+                   for clip_id in orderedSet(re.findall(r'clip\.id\s*=\s*(\d+);', webpage))]
         if not entries:
             webpage = self._download_webpage(url, page_id)
             if 'getAuthStates("' in webpage:
-                    entries = [ninecninemedia_url_result(clip_id) for clip_id in
+                entries = [self._ninecninemedia_url_result(clip_id) for clip_id in
                            self._search_regex(r'getAuthStates\("([\d+,]+)"', webpage, 'clip ids').split(',')]
+            else:
+                entries = [
+                    self._ninecninemedia_url_result(clip_id) for clip_id in
+                    traverse_obj(webpage, (
+                        {find_element(tag='jasper-player-container', html=True)},
+                        {extract_attributes}, 'axis-ids', {json.loads}, ..., 'axisId', {str}))
+                ]
+
         return self.playlist_result(entries, page_id)

yt_dlp/extractor/facebook.py

@@ -569,7 +569,7 @@ class FacebookIE(InfoExtractor):
             if dash_manifest:
                 formats.extend(self._parse_mpd_formats(
                     compat_etree_fromstring(urllib.parse.unquote_plus(dash_manifest)),
-                    mpd_url=url_or_none(video.get('dash_manifest_url')) or mpd_url))
+                    mpd_url=url_or_none(vid_data.get('dash_manifest_url')) or mpd_url))
 
         def process_formats(info):
             # Downloads with browser's User-Agent are rate limited. Working around

yt_dlp/extractor/kenh14.py

@@ -0,0 +1,160 @@
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    extract_attributes,
+    get_element_by_class,
+    get_element_html_by_attribute,
+    get_elements_html_by_class,
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+    remove_start,
+    strip_or_none,
+    unescapeHTML,
+    update_url,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class Kenh14VideoIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.kenh14\.vn/(?:video/)?[\w-]+-(?P<id>[0-9]+)\.chn'
+    _TESTS = [{
+        'url': 'https://video.kenh14.vn/video/mo-hop-iphone-14-pro-max-nguon-unbox-therapy-316173.chn',
+        'md5': '1ed67f9c3a1e74acf15db69590cf6210',
+        'info_dict': {
+            'id': '316173',
+            'ext': 'mp4',
+            'title': 'Video mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
+            'description': 'Video mở hộp iPhone 14 Pro MaxVideo mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
+            'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
+            'tags': [],
+            'uploader': 'Unbox Therapy',
+            'upload_date': '20220517',
+            'view_count': int,
+            'duration': 722.86,
+            'timestamp': 1652764468,
+        },
+    }, {
+        'url': 'https://video.kenh14.vn/video-316174.chn',
+        'md5': '2b41877d2afaf4a3f487ceda8e5c7cbd',
+        'info_dict': {
+            'id': '316174',
+            'ext': 'mp4',
+            'title': 'Khoảnh khắc VĐV nằm gục khóc sau chiến thắng: 7 năm trời Việt Nam mới có HCV kiếm chém nữ, chỉ có 8 tháng để khổ luyện trước khi lên sàn đấu',
+            'description': 'md5:de86aa22e143e2b277bce8ec9c6f17dc',
+            'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
+            'tags': [],
+            'upload_date': '20220517',
+            'view_count': int,
+            'duration': 70.04,
+            'timestamp': 1652766021,
+        },
+    }, {
+        'url': 'https://video.kenh14.vn/0-344740.chn',
+        'md5': 'b843495d5e728142c8870c09b46df2a9',
+        'info_dict': {
+            'id': '344740',
+            'ext': 'mov',
+            'title': 'Kỳ Duyên đầy căng thẳng trong buổi ra quân đi Miss Universe, nghi thức tuyên thuệ lần đầu xuất hiện gây nhiều tranh cãi',
+            'description': 'md5:2a2dbb4a7397169fb21ee68f09160497',
+            'thumbnail': r're:^https?://kenh14cdn\.com/.*\.jpg$',
+            'tags': ['kỳ duyên', 'Kỳ Duyên tuyên thuệ', 'miss universe'],
+            'uploader': 'Quang Vũ',
+            'upload_date': '20241024',
+            'view_count': int,
+            'duration': 198.88,
+            'timestamp': 1729741590,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        attrs = extract_attributes(get_element_html_by_attribute('type', 'VideoStream', webpage) or '')
+        direct_url = attrs['data-vid']
+
+        metadata = self._download_json(
+            'https://api.kinghub.vn/video/api/v1/detailVideoByGet?FileName={}'.format(
+                remove_start(direct_url, 'kenh14cdn.com/')), video_id, fatal=False)
+
+        formats = [{'url': f'https://{direct_url}', 'format_id': 'http', 'quality': 1}]
+        subtitles = {}
+        video_data = self._download_json(
+            f'https://{direct_url}.json', video_id, note='Downloading video data', fatal=False)
+        if hls_url := traverse_obj(video_data, ('hls', {url_or_none})):
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                hls_url, video_id, m3u8_id='hls', fatal=False)
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+        if dash_url := traverse_obj(video_data, ('mpd', {url_or_none})):
+            fmts, subs = self._extract_mpd_formats_and_subtitles(
+                dash_url, video_id, mpd_id='dash', fatal=False)
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+
+        return {
+            **traverse_obj(metadata, {
+                'duration': ('duration', {parse_duration}),
+                'uploader': ('author', {strip_or_none}),
+                'timestamp': ('uploadtime', {parse_iso8601(delimiter=' ')}),
+                'view_count': ('views', {int_or_none}),
+            }),
+            'id': video_id,
+            'title': (
+                traverse_obj(metadata, ('title', {strip_or_none}))
+                or clean_html(self._og_search_title(webpage))
+                or clean_html(get_element_by_class('vdbw-title', webpage))),
+            'formats': formats,
+            'subtitles': subtitles,
+            'description': (
+                clean_html(self._og_search_description(webpage))
+                or clean_html(get_element_by_class('vdbw-sapo', webpage))),
+            'thumbnail': (self._og_search_thumbnail(webpage) or attrs.get('data-thumb')),
+            'tags': traverse_obj(self._html_search_meta('keywords', webpage), (
+                {lambda x: x.split(';')}, ..., filter)),
+        }
+
+
+class Kenh14PlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.kenh14\.vn/playlist/[\w-]+-(?P<id>[0-9]+)\.chn'
+    _TESTS = [{
+        'url': 'https://video.kenh14.vn/playlist/tran-tinh-naked-love-mua-2-71.chn',
+        'info_dict': {
+            'id': '71',
+            'title': 'Trần Tình (Naked love) mùa 2',
+            'description': 'md5:e9522339304956dea931722dd72eddb2',
+            'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
+        },
+        'playlist_count': 9,
+    }, {
+        'url': 'https://video.kenh14.vn/playlist/0-72.chn',
+        'info_dict': {
+            'id': '72',
+            'title': 'Lau Lại Đầu Từ',
+            'description': 'Cùng xem xưa và nay có gì khác biệt nhé!',
+            'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
+        },
+        'playlist_count': 6,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        category_detail = get_element_by_class('category-detail', webpage) or ''
+        embed_info = traverse_obj(
+            self._yield_json_ld(webpage, playlist_id),
+            (lambda _, v: v['name'] and v['alternateName'], any)) or {}
+
+        return self.playlist_from_matches(
+            get_elements_html_by_class('video-item', webpage), playlist_id,
+            (clean_html(get_element_by_class('name', category_detail)) or unescapeHTML(embed_info.get('name'))),
+            getter=lambda x: 'https://video.kenh14.vn/video/video-{}.chn'.format(extract_attributes(x)['data-id']),
+            ie=Kenh14VideoIE, playlist_description=(
+                clean_html(get_element_by_class('description', category_detail))
+                or unescapeHTML(embed_info.get('alternateName'))),
+            thumbnail=traverse_obj(
+                self._og_search_thumbnail(webpage),
+                ({url_or_none}, {update_url(query=None)})))

yt_dlp/extractor/litv.py

@@ -1,30 +1,32 @@
 import json
+import uuid
 
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
+    join_nonempty,
     smuggle_url,
     traverse_obj,
     try_call,
     unsmuggle_url,
+    urljoin,
 )
 
 
 class LiTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?litv\.tv/(?:vod|promo)/[^/]+/(?:content\.do)?\?.*?\b(?:content_)?id=(?P<id>[^&]+)'
+    _VALID_URL = r'https?://(?:www\.)?litv\.tv/(?:[^/?#]+/watch/|vod/[^/?#]+/content\.do\?content_id=)(?P<id>[\w-]+)'
-
+    _URL_TEMPLATE = 'https://www.litv.tv/%s/watch/%s'
-    _URL_TEMPLATE = 'https://www.litv.tv/vod/%s/content.do?content_id=%s'
+    _GEO_COUNTRIES = ['TW']
-
     _TESTS = [{
-        'url': 'https://www.litv.tv/vod/drama/content.do?brc_id=root&id=VOD00041610&isUHEnabled=true&autoPlay=1',
+        'url': 'https://www.litv.tv/drama/watch/VOD00041610',
         'info_dict': {
             'id': 'VOD00041606',
             'title': '花千骨',
         },
         'playlist_count': 51,  # 50 episodes + 1 trailer
     }, {
-        'url': 'https://www.litv.tv/vod/drama/content.do?brc_id=root&id=VOD00041610&isUHEnabled=true&autoPlay=1',
+        'url': 'https://www.litv.tv/drama/watch/VOD00041610',
         'md5': 'b90ff1e9f1d8f5cfcd0a44c3e2b34c7a',
         'info_dict': {
             'id': 'VOD00041610',
@@ -32,16 +34,15 @@ class LiTVIE(InfoExtractor):
             'title': '花千骨第1集',
             'thumbnail': r're:https?://.*\.jpg$',
             'description': '《花千骨》陸劇線上看。十六年前，平靜的村莊內，一名女嬰隨異相出生，途徑此地的蜀山掌門清虛道長算出此女命運非同一般，她體內散發的異香易招惹妖魔。一念慈悲下，他在村莊周邊設下結界阻擋妖魔入侵，讓其年滿十六後去蜀山，並賜名花千骨。',
-            'categories': ['奇幻', '愛情', '中國', '仙俠'],
+            'categories': ['奇幻', '愛情', '仙俠', '古裝'],
             'episode': 'Episode 1',
             'episode_number': 1,
         },
         'params': {
             'noplaylist': True,
         },
-        'skip': 'Georestricted to Taiwan',
     }, {
-        'url': 'https://www.litv.tv/promo/miyuezhuan/?content_id=VOD00044841&',
+        'url': 'https://www.litv.tv/drama/watch/VOD00044841',
         'md5': '88322ea132f848d6e3e18b32a832b918',
         'info_dict': {
             'id': 'VOD00044841',
@@ -55,94 +56,62 @@ class LiTVIE(InfoExtractor):
     def _extract_playlist(self, playlist_data, content_type):
         all_episodes = [
             self.url_result(smuggle_url(
-                self._URL_TEMPLATE % (content_type, episode['contentId']),
+                self._URL_TEMPLATE % (content_type, episode['content_id']),
                 {'force_noplaylist': True}))  # To prevent infinite recursion
-            for episode in traverse_obj(playlist_data, ('seasons', ..., 'episode', lambda _, v: v['contentId']))]
+            for episode in traverse_obj(playlist_data, ('seasons', ..., 'episodes', lambda _, v: v['content_id']))]
 
-        return self.playlist_result(all_episodes, playlist_data['contentId'], playlist_data.get('title'))
+        return self.playlist_result(all_episodes, playlist_data['content_id'], playlist_data.get('title'))
 
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})
-
         video_id = self._match_id(url)
-
         webpage = self._download_webpage(url, video_id)
+        vod_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']
 
-        if self._search_regex(
+        program_info = traverse_obj(vod_data, ('programInformation', {dict})) or {}
-                r'(?i)<meta\s[^>]*http-equiv="refresh"\s[^>]*content="[0-9]+;\s*url=https://www\.litv\.tv/"',
+        playlist_data = traverse_obj(vod_data, ('seriesTree'))
-                webpage, 'meta refresh redirect', default=False, group=0):
+        if playlist_data and self._yes_playlist(program_info.get('series_id'), video_id, smuggled_data):
-            raise ExtractorError('No such content found', expected=True)
+            return self._extract_playlist(playlist_data, program_info.get('content_type'))
 
-        program_info = self._parse_json(self._search_regex(
+        asset_id = traverse_obj(program_info, ('assets', 0, 'asset_id', {str}))
-            r'var\s+programInfo\s*=\s*([^;]+)', webpage, 'VOD data', default='{}'),
+        if asset_id:  # This is a VOD
-            video_id)
+            media_type = 'vod'
-
+        else:  # This is a live stream
-        # In browsers `getProgramInfo` request is always issued. Usually this
+            asset_id = program_info['content_id']
-        # endpoint gives the same result as the data embedded in the webpage.
+            media_type = program_info['content_type']
-        # If, for some reason, there are no embedded data, we do an extra request.
-        if 'assetId' not in program_info:
-            program_info = self._download_json(
-                'https://www.litv.tv/vod/ajax/getProgramInfo', video_id,
-                query={'contentId': video_id},
-                headers={'Accept': 'application/json'})
-
-        series_id = program_info['seriesId']
-        if self._yes_playlist(series_id, video_id, smuggled_data):
-            playlist_data = self._download_json(
-                'https://www.litv.tv/vod/ajax/getSeriesTree', video_id,
-                query={'seriesId': series_id}, headers={'Accept': 'application/json'})
-            return self._extract_playlist(playlist_data, program_info['contentType'])
-
-        video_data = self._parse_json(self._search_regex(
-            r'uiHlsUrl\s*=\s*testBackendData\(([^;]+)\);',
-            webpage, 'video data', default='{}'), video_id)
-        if not video_data:
-            payload = {'assetId': program_info['assetId']}
         puid = try_call(lambda: self._get_cookies('https://www.litv.tv/')['PUID'].value)
         if puid:
-                payload.update({
+            endpoint = 'get-urls'
-                    'type': 'auth',
-                    'puid': puid,
-                })
-                endpoint = 'getUrl'
         else:
-                payload.update({
+            puid = str(uuid.uuid4())
-                    'watchDevices': program_info['watchDevices'],
+            endpoint = 'get-urls-no-auth'
-                    'contentType': program_info['contentType'],
-                })
-                endpoint = 'getMainUrlNoAuth'
         video_data = self._download_json(
-                f'https://www.litv.tv/vod/ajax/{endpoint}', video_id,
+            f'https://www.litv.tv/api/{endpoint}', video_id,
-                data=json.dumps(payload).encode(),
+            data=json.dumps({'AssetId': asset_id, 'MediaType': media_type, 'puid': puid}).encode(),
             headers={'Content-Type': 'application/json'})
 
-        if not video_data.get('fullpath'):
+        if error := traverse_obj(video_data, ('error', {dict})):
-            error_msg = video_data.get('errorMessage')
+            error_msg = traverse_obj(error, ('message', {str}))
-            if error_msg == 'vod.error.outsideregionerror':
+            if error_msg and 'OutsideRegionError' in error_msg:
                 self.raise_geo_restricted('This video is available in Taiwan only')
-            if error_msg:
+            elif error_msg:
                 raise ExtractorError(f'{self.IE_NAME} said: {error_msg}', expected=True)
-            raise ExtractorError(f'Unexpected result from {self.IE_NAME}')
+            raise ExtractorError(f'Unexpected error from {self.IE_NAME}')
 
         formats = self._extract_m3u8_formats(
-            video_data['fullpath'], video_id, ext='mp4',
+            video_data['result']['AssetURLs'][0], video_id, ext='mp4', m3u8_id='hls')
-            entry_protocol='m3u8_native', m3u8_id='hls')
         for a_format in formats:
             # LiTV HLS segments doesn't like compressions
             a_format.setdefault('http_headers', {})['Accept-Encoding'] = 'identity'
 
-        title = program_info['title'] + program_info.get('secondaryMark', '')
-        description = program_info.get('description')
-        thumbnail = program_info.get('imageFile')
-        categories = [item['name'] for item in program_info.get('category', [])]
-        episode = int_or_none(program_info.get('episode'))
-
         return {
             'id': video_id,
             'formats': formats,
-            'title': title,
+            'title': join_nonempty('title', 'secondary_mark', delim='', from_dict=program_info),
-            'description': description,
+            **traverse_obj(program_info, {
-            'thumbnail': thumbnail,
+                'description': ('description', {str}),
-            'categories': categories,
+                'thumbnail': ('picture', {urljoin('https://p-cdnstatic.svc.litv.tv/')}),
-            'episode_number': episode,
+                'categories': ('genres', ..., 'name', {str}),
+                'episode_number': ('episode', {int_or_none}),
+            }),
         }

yt_dlp/extractor/mildom.py

@@ -1,291 +0,0 @@
-import functools
-import json
-import uuid
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    OnDemandPagedList,
-    determine_ext,
-    dict_get,
-    float_or_none,
-    traverse_obj,
-)
-
-
-class MildomBaseIE(InfoExtractor):
-    _GUEST_ID = None
-
-    def _call_api(self, url, video_id, query=None, note='Downloading JSON metadata', body=None):
-        if not self._GUEST_ID:
-            self._GUEST_ID = f'pc-gp-{uuid.uuid4()}'
-
-        content = self._download_json(
-            url, video_id, note=note, data=json.dumps(body).encode() if body else None,
-            headers={'Content-Type': 'application/json'} if body else {},
-            query={
-                '__guest_id': self._GUEST_ID,
-                '__platform': 'web',
-                **(query or {}),
-            })
-
-        if content['code'] != 0:
-            raise ExtractorError(
-                f'Mildom says: {content["message"]} (code {content["code"]})',
-                expected=True)
-        return content['body']
-
-
-class MildomIE(MildomBaseIE):
-    IE_NAME = 'mildom'
-    IE_DESC = 'Record ongoing live by specific user in Mildom'
-    _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/(?P<id>\d+)'
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(f'https://www.mildom.com/{video_id}', video_id)
-
-        enterstudio = self._call_api(
-            'https://cloudac.mildom.com/nonolive/gappserv/live/enterstudio', video_id,
-            note='Downloading live metadata', query={'user_id': video_id})
-        result_video_id = enterstudio.get('log_id', video_id)
-
-        servers = self._call_api(
-            'https://cloudac.mildom.com/nonolive/gappserv/live/liveserver', result_video_id,
-            note='Downloading live server list', query={
-                'user_id': video_id,
-                'live_server_type': 'hls',
-            })
-
-        playback_token = self._call_api(
-            'https://cloudac.mildom.com/nonolive/gappserv/live/token', result_video_id,
-            note='Obtaining live playback token', body={'host_id': video_id, 'type': 'hls'})
-        playback_token = traverse_obj(playback_token, ('data', ..., 'token'), get_all=False)
-        if not playback_token:
-            raise ExtractorError('Failed to obtain live playback token')
-
-        formats = self._extract_m3u8_formats(
-            f'{servers["stream_server"]}/{video_id}_master.m3u8?{playback_token}',
-            result_video_id, 'mp4', headers={
-                'Referer': 'https://www.mildom.com/',
-                'Origin': 'https://www.mildom.com',
-            })
-
-        for fmt in formats:
-            fmt.setdefault('http_headers', {})['Referer'] = 'https://www.mildom.com/'
-
-        return {
-            'id': result_video_id,
-            'title': self._html_search_meta('twitter:description', webpage, default=None) or traverse_obj(enterstudio, 'anchor_intro'),
-            'description': traverse_obj(enterstudio, 'intro', 'live_intro', expected_type=str),
-            'timestamp': float_or_none(enterstudio.get('live_start_ms'), scale=1000),
-            'uploader': self._html_search_meta('twitter:title', webpage, default=None) or traverse_obj(enterstudio, 'loginname'),
-            'uploader_id': video_id,
-            'formats': formats,
-            'is_live': True,
-        }
-
-
-class MildomVodIE(MildomBaseIE):
-    IE_NAME = 'mildom:vod'
-    IE_DESC = 'VOD in Mildom'
-    _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/playback/(?P<user_id>\d+)/(?P<id>(?P=user_id)-[a-zA-Z0-9]+-?[0-9]*)'
-    _TESTS = [{
-        'url': 'https://www.mildom.com/playback/10882672/10882672-1597662269',
-        'info_dict': {
-            'id': '10882672-1597662269',
-            'ext': 'mp4',
-            'title': '始めてのミルダム配信じゃぃ！',
-            'thumbnail': r're:^https?://.*\.(png|jpg)$',
-            'upload_date': '20200817',
-            'duration': 4138.37,
-            'description': 'ゲームをしたくて！',
-            'timestamp': 1597662269.0,
-            'uploader_id': '10882672',
-            'uploader': 'kson組長(けいそん)',
-        },
-    }, {
-        'url': 'https://www.mildom.com/playback/10882672/10882672-1597758589870-477',
-        'info_dict': {
-            'id': '10882672-1597758589870-477',
-            'ext': 'mp4',
-            'title': '【kson】感染メイズ！麻酔銃で無双する',
-            'thumbnail': r're:^https?://.*\.(png|jpg)$',
-            'timestamp': 1597759093.0,
-            'uploader': 'kson組長(けいそん)',
-            'duration': 4302.58,
-            'uploader_id': '10882672',
-            'description': 'このステージ絶対乗り越えたい',
-            'upload_date': '20200818',
-        },
-    }, {
-        'url': 'https://www.mildom.com/playback/10882672/10882672-buha9td2lrn97fk2jme0',
-        'info_dict': {
-            'id': '10882672-buha9td2lrn97fk2jme0',
-            'ext': 'mp4',
-            'title': '【kson組長】CART RACER!!!',
-            'thumbnail': r're:^https?://.*\.(png|jpg)$',
-            'uploader_id': '10882672',
-            'uploader': 'kson組長(けいそん)',
-            'upload_date': '20201104',
-            'timestamp': 1604494797.0,
-            'duration': 4657.25,
-            'description': 'WTF',
-        },
-    }]
-
-    def _real_extract(self, url):
-        user_id, video_id = self._match_valid_url(url).group('user_id', 'id')
-        webpage = self._download_webpage(f'https://www.mildom.com/playback/{user_id}/{video_id}', video_id)
-
-        autoplay = self._call_api(
-            'https://cloudac.mildom.com/nonolive/videocontent/playback/getPlaybackDetail', video_id,
-            note='Downloading playback metadata', query={
-                'v_id': video_id,
-            })['playback']
-
-        formats = [{
-            'url': autoplay['audio_url'],
-            'format_id': 'audio',
-            'protocol': 'm3u8_native',
-            'vcodec': 'none',
-            'acodec': 'aac',
-            'ext': 'm4a',
-        }]
-        for fmt in autoplay['video_link']:
-            formats.append({
-                'format_id': 'video-{}'.format(fmt['name']),
-                'url': fmt['url'],
-                'protocol': 'm3u8_native',
-                'width': fmt['level'] * autoplay['video_width'] // autoplay['video_height'],
-                'height': fmt['level'],
-                'vcodec': 'h264',
-                'acodec': 'aac',
-                'ext': 'mp4',
-            })
-
-        return {
-            'id': video_id,
-            'title': self._html_search_meta(('og:description', 'description'), webpage, default=None) or autoplay.get('title'),
-            'description': traverse_obj(autoplay, 'video_intro'),
-            'timestamp': float_or_none(autoplay.get('publish_time'), scale=1000),
-            'duration': float_or_none(autoplay.get('video_length'), scale=1000),
-            'thumbnail': dict_get(autoplay, ('upload_pic', 'video_pic')),
-            'uploader': traverse_obj(autoplay, ('author_info', 'login_name')),
-            'uploader_id': user_id,
-            'formats': formats,
-        }
-
-
-class MildomClipIE(MildomBaseIE):
-    IE_NAME = 'mildom:clip'
-    IE_DESC = 'Clip in Mildom'
-    _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/clip/(?P<id>(?P<user_id>\d+)-[a-zA-Z0-9]+)'
-    _TESTS = [{
-        'url': 'https://www.mildom.com/clip/10042245-63921673e7b147ebb0806d42b5ba5ce9',
-        'info_dict': {
-            'id': '10042245-63921673e7b147ebb0806d42b5ba5ce9',
-            'title': '全然違ったよ',
-            'timestamp': 1619181890,
-            'duration': 59,
-            'thumbnail': r're:https?://.+',
-            'uploader': 'ざきんぽ',
-            'uploader_id': '10042245',
-        },
-    }, {
-        'url': 'https://www.mildom.com/clip/10111524-ebf4036e5aa8411c99fb3a1ae0902864',
-        'info_dict': {
-            'id': '10111524-ebf4036e5aa8411c99fb3a1ae0902864',
-            'title': 'かっこいい',
-            'timestamp': 1621094003,
-            'duration': 59,
-            'thumbnail': r're:https?://.+',
-            'uploader': '(ルーキー',
-            'uploader_id': '10111524',
-        },
-    }, {
-        'url': 'https://www.mildom.com/clip/10660174-2c539e6e277c4aaeb4b1fbe8d22cb902',
-        'info_dict': {
-            'id': '10660174-2c539e6e277c4aaeb4b1fbe8d22cb902',
-            'title': 'あ',
-            'timestamp': 1614769431,
-            'duration': 31,
-            'thumbnail': r're:https?://.+',
-            'uploader': 'ドルゴルスレンギーン＝ダグワドルジ',
-            'uploader_id': '10660174',
-        },
-    }]
-
-    def _real_extract(self, url):
-        user_id, video_id = self._match_valid_url(url).group('user_id', 'id')
-        webpage = self._download_webpage(f'https://www.mildom.com/clip/{video_id}', video_id)
-
-        clip_detail = self._call_api(
-            'https://cloudac-cf-jp.mildom.com/nonolive/videocontent/clip/detail', video_id,
-            note='Downloading playback metadata', query={
-                'clip_id': video_id,
-            })
-
-        return {
-            'id': video_id,
-            'title': self._html_search_meta(
-                ('og:description', 'description'), webpage, default=None) or clip_detail.get('title'),
-            'timestamp': float_or_none(clip_detail.get('create_time')),
-            'duration': float_or_none(clip_detail.get('length')),
-            'thumbnail': clip_detail.get('cover'),
-            'uploader': traverse_obj(clip_detail, ('user_info', 'loginname')),
-            'uploader_id': user_id,
-
-            'url': clip_detail['url'],
-            'ext': determine_ext(clip_detail.get('url'), 'mp4'),
-        }
-
-
-class MildomUserVodIE(MildomBaseIE):
-    IE_NAME = 'mildom:user:vod'
-    IE_DESC = 'Download all VODs from specific user in Mildom'
-    _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/profile/(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://www.mildom.com/profile/10093333',
-        'info_dict': {
-            'id': '10093333',
-            'title': 'Uploads from ねこばたけ',
-        },
-        'playlist_mincount': 732,
-    }, {
-        'url': 'https://www.mildom.com/profile/10882672',
-        'info_dict': {
-            'id': '10882672',
-            'title': 'Uploads from kson組長(けいそん)',
-        },
-        'playlist_mincount': 201,
-    }]
-
-    def _fetch_page(self, user_id, page):
-        page += 1
-        reply = self._call_api(
-            'https://cloudac.mildom.com/nonolive/videocontent/profile/playbackList',
-            user_id, note=f'Downloading page {page}', query={
-                'user_id': user_id,
-                'page': page,
-                'limit': '30',
-            })
-        if not reply:
-            return
-        for x in reply:
-            v_id = x.get('v_id')
-            if not v_id:
-                continue
-            yield self.url_result(f'https://www.mildom.com/playback/{user_id}/{v_id}')
-
-    def _real_extract(self, url):
-        user_id = self._match_id(url)
-        self.to_screen(f'This will download all VODs belonging to user. To download ongoing live video, use "https://www.mildom.com/{user_id}" instead')
-
-        profile = self._call_api(
-            'https://cloudac.mildom.com/nonolive/gappserv/user/profileV2', user_id,
-            query={'user_id': user_id}, note='Downloading user profile')['user_info']
-
-        return self.playlist_result(
-            OnDemandPagedList(functools.partial(self._fetch_page, user_id), 30),
-            user_id, f'Uploads from {profile["loginname"]}')

yt_dlp/extractor/pialive.py

@@ -0,0 +1,122 @@
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    extract_attributes,
+    get_element_by_class,
+    get_element_html_by_class,
+    multipart_encode,
+    str_or_none,
+    unified_timestamp,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class PiaLiveIE(InfoExtractor):
+    _VALID_URL = r'https?://player\.pia-live\.jp/stream/(?P<id>[\w-]+)'
+    _PLAYER_ROOT_URL = 'https://player.pia-live.jp/'
+    _PIA_LIVE_API_URL = 'https://api.pia-live.jp'
+    _API_KEY = 'kfds)FKFps-dms9e'
+    _TESTS = [{
+        'url': 'https://player.pia-live.jp/stream/4JagFBEIM14s_hK9aXHKf3k3F3bY5eoHFQxu68TC6krUDqGOwN4d61dCWQYOd6CTxl4hjya9dsfEZGsM4uGOUdax60lEI4twsXGXf7crmz8Gk__GhupTrWxA7RFRVt76',
+        'info_dict': {
+            'id': '88f3109a-f503-4d0f-a9f7-9f39ac745d84',
+            'display_id': '2431867_001',
+            'title': 'こながめでたい日２０２４の視聴ページ | PIA LIVE STREAM(ぴあライブストリーム)',
+            'live_status': 'was_live',
+            'comment_count': int,
+        },
+        'params': {
+            'getcomments': True,
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+        'skip': 'The video is no longer available',
+    }, {
+        'url': 'https://player.pia-live.jp/stream/4JagFBEIM14s_hK9aXHKf3k3F3bY5eoHFQxu68TC6krJdu0GVBVbVy01IwpJ6J3qBEm3d9TCTt1d0eWpsZGj7DrOjVOmS7GAWGwyscMgiThopJvzgWC4H5b-7XQjAfRZ',
+        'info_dict': {
+            'id': '9ce8b8ba-f6d1-4d1f-83a0-18c3148ded93',
+            'display_id': '2431867_002',
+            'title': 'こながめでたい日２０２４の視聴ページ | PIA LIVE STREAM(ぴあライブストリーム)',
+            'live_status': 'was_live',
+            'comment_count': int,
+        },
+        'params': {
+            'getcomments': True,
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+        'skip': 'The video is no longer available',
+    }]
+
+    def _extract_var(self, variable, html):
+        return self._search_regex(
+            rf'(?:var|const|let)\s+{variable}\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+            html, f'variable {variable}', group='value')
+
+    def _real_extract(self, url):
+        video_key = self._match_id(url)
+        webpage = self._download_webpage(url, video_key)
+
+        program_code = self._extract_var('programCode', webpage)
+        article_code = self._extract_var('articleCode', webpage)
+        title = self._html_extract_title(webpage)
+
+        if get_element_html_by_class('play-end', webpage):
+            raise ExtractorError('The video is no longer available', expected=True, video_id=program_code)
+
+        if start_info := clean_html(get_element_by_class('play-waiting__date', webpage)):
+            date, time = self._search_regex(
+                r'(?P<date>\d{4}/\d{1,2}/\d{1,2})\([月火水木金土日]\)(?P<time>\d{2}:\d{2})',
+                start_info, 'start_info', fatal=False, group=('date', 'time'))
+            if date and time:
+                release_timestamp_str = f'{date} {time} +09:00'
+                release_timestamp = unified_timestamp(release_timestamp_str)
+                self.raise_no_formats(f'The video will be available after {release_timestamp_str}', expected=True)
+                return {
+                    'id': program_code,
+                    'title': title,
+                    'live_status': 'is_upcoming',
+                    'release_timestamp': release_timestamp,
+                }
+
+        payload, content_type = multipart_encode({
+            'play_url': video_key,
+            'api_key': self._API_KEY,
+        })
+        api_data_and_headers = {
+            'data': payload,
+            'headers': {'Content-Type': content_type, 'Referer': self._PLAYER_ROOT_URL},
+        }
+
+        player_tag_list = self._download_json(
+            f'{self._PIA_LIVE_API_URL}/perf/player-tag-list/{program_code}', program_code,
+            'Fetching player tag list', 'Unable to fetch player tag list', **api_data_and_headers)
+
+        return self.url_result(
+            extract_attributes(player_tag_list['data']['movie_one_tag'])['src'],
+            url_transparent=True, title=title, display_id=program_code,
+            __post_extractor=self.extract_comments(program_code, article_code, api_data_and_headers))
+
+    def _get_comments(self, program_code, article_code, api_data_and_headers):
+        chat_room_url = traverse_obj(self._download_json(
+            f'{self._PIA_LIVE_API_URL}/perf/chat-tag-list/{program_code}/{article_code}', program_code,
+            'Fetching chat info', 'Unable to fetch chat info', fatal=False, **api_data_and_headers),
+            ('data', 'chat_one_tag', {extract_attributes}, 'src', {url_or_none}))
+        if not chat_room_url:
+            return
+        comment_page = self._download_webpage(
+            chat_room_url, program_code, 'Fetching comment page', 'Unable to fetch comment page',
+            fatal=False, headers={'Referer': self._PLAYER_ROOT_URL})
+        if not comment_page:
+            return
+        yield from traverse_obj(self._search_json(
+            r'var\s+_history\s*=', comment_page, 'comment list',
+            program_code, contains_pattern=r'\[(?s:.+)\]', fatal=False), (..., {
+                'timestamp': (0, {int}),
+                'author_is_uploader': (1, {lambda x: x == 2}),
+                'author': (2, {str}),
+                'text': (3, {str}),
+                'id': (4, {str_or_none}),
+            }))

yt_dlp/extractor/piaulizaportal.py

@@ -1,70 +0,0 @@
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    int_or_none,
-    parse_qs,
-    time_seconds,
-    traverse_obj,
-)
-
-
-class PIAULIZAPortalIE(InfoExtractor):
-    IE_DESC = 'ulizaportal.jp - PIA LIVE STREAM'
-    _VALID_URL = r'https?://(?:www\.)?ulizaportal\.jp/pages/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
-    _TESTS = [{
-        'url': 'https://ulizaportal.jp/pages/005f18b7-e810-5618-cb82-0987c5755d44',
-        'info_dict': {
-            'id': '005f18b7-e810-5618-cb82-0987c5755d44',
-            'title': 'プレゼンテーションプレイヤーのサンプル',
-            'live_status': 'not_live',
-        },
-        'params': {
-            'skip_download': True,
-            'ignore_no_formats_error': True,
-        },
-    }, {
-        'url': 'https://ulizaportal.jp/pages/005e1b23-fe93-5780-19a0-98e917cc4b7d?expires=4102412400&signature=f422a993b683e1068f946caf406d211c17d1ef17da8bef3df4a519502155aa91&version=1',
-        'info_dict': {
-            'id': '005e1b23-fe93-5780-19a0-98e917cc4b7d',
-            'title': '【確認用】視聴サンプルページ（ULIZA）',
-            'live_status': 'not_live',
-        },
-        'params': {
-            'skip_download': True,
-            'ignore_no_formats_error': True,
-        },
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        expires = int_or_none(traverse_obj(parse_qs(url), ('expires', 0)))
-        if expires and expires <= time_seconds():
-            raise ExtractorError('The link is expired.', video_id=video_id, expected=True)
-
-        webpage = self._download_webpage(url, video_id)
-
-        player_data = self._download_webpage(
-            self._search_regex(
-                r'<script [^>]*\bsrc="(https://player-api\.p\.uliza\.jp/v1/players/[^"]+)"',
-                webpage, 'player data url'),
-            video_id, headers={'Referer': 'https://ulizaportal.jp/'},
-            note='Fetching player data', errnote='Unable to fetch player data')
-
-        formats = self._extract_m3u8_formats(
-            self._search_regex(
-                r'["\'](https://vms-api\.p\.uliza\.jp/v1/prog-index\.m3u8[^"\']+)', player_data,
-                'm3u8 url', default=None),
-            video_id, fatal=False)
-        m3u8_type = self._search_regex(
-            r'/hls/(dvr|video)/', traverse_obj(formats, (0, 'url')), 'm3u8 type', default=None)
-
-        return {
-            'id': video_id,
-            'title': self._html_extract_title(webpage),
-            'formats': formats,
-            'live_status': {
-                'video': 'is_live',
-                'dvr': 'was_live',  # short-term archives
-            }.get(m3u8_type, 'not_live'),  # VOD or long-term archives
-        }

yt_dlp/extractor/pokemon.py

@@ -1,136 +0,0 @@
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    extract_attributes,
-    int_or_none,
-    js_to_json,
-    merge_dicts,
-)
-
-
-class PokemonIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?pokemon\.com/[a-z]{2}(?:.*?play=(?P<id>[a-z0-9]{32})|/(?:[^/]+/)+(?P<display_id>[^/?#&]+))'
-    _TESTS = [{
-        'url': 'https://www.pokemon.com/us/pokemon-episodes/20_30-the-ol-raise-and-switch/',
-        'md5': '2fe8eaec69768b25ef898cda9c43062e',
-        'info_dict': {
-            'id': 'afe22e30f01c41f49d4f1d9eab5cd9a4',
-            'ext': 'mp4',
-            'title': 'The Ol’ Raise and Switch!',
-            'description': 'md5:7db77f7107f98ba88401d3adc80ff7af',
-        },
-        'add_id': ['LimelightMedia'],
-    }, {
-        # no data-video-title
-        'url': 'https://www.pokemon.com/fr/episodes-pokemon/films-pokemon/pokemon-lascension-de-darkrai-2008',
-        'info_dict': {
-            'id': 'dfbaf830d7e54e179837c50c0c6cc0e1',
-            'ext': 'mp4',
-            'title': "Pokémon : L'ascension de Darkrai",
-            'description': 'md5:d1dbc9e206070c3e14a06ff557659fb5',
-        },
-        'add_id': ['LimelightMedia'],
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.pokemon.com/uk/pokemon-episodes/?play=2e8b5c761f1d4a9286165d7748c1ece2',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.pokemon.com/fr/episodes-pokemon/18_09-un-hiver-inattendu/',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.pokemon.com/de/pokemon-folgen/01_20-bye-bye-smettbo/',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id, display_id = self._match_valid_url(url).groups()
-        webpage = self._download_webpage(url, video_id or display_id)
-        video_data = extract_attributes(self._search_regex(
-            r'(<[^>]+data-video-id="{}"[^>]*>)'.format(video_id if video_id else '[a-z0-9]{32}'),
-            webpage, 'video data element'))
-        video_id = video_data['data-video-id']
-        title = video_data.get('data-video-title') or self._html_search_meta(
-            'pkm-title', webpage, ' title', default=None) or self._search_regex(
-            r'<h1[^>]+\bclass=["\']us-title[^>]+>([^<]+)', webpage, 'title')
-        return {
-            '_type': 'url_transparent',
-            'id': video_id,
-            'url': f'limelight:media:{video_id}',
-            'title': title,
-            'description': video_data.get('data-video-summary'),
-            'thumbnail': video_data.get('data-video-poster'),
-            'series': 'Pokémon',
-            'season_number': int_or_none(video_data.get('data-video-season')),
-            'episode': title,
-            'episode_number': int_or_none(video_data.get('data-video-episode')),
-            'ie_key': 'LimelightMedia',
-        }
-
-
-class PokemonWatchIE(InfoExtractor):
-    _VALID_URL = r'https?://watch\.pokemon\.com/[a-z]{2}-[a-z]{2}/(?:#/)?player(?:\.html)?\?id=(?P<id>[a-z0-9]{32})'
-    _API_URL = 'https://www.pokemon.com/api/pokemontv/v2/channels/{0:}'
-    _TESTS = [{
-        'url': 'https://watch.pokemon.com/en-us/player.html?id=8309a40969894a8e8d5bc1311e9c5667',
-        'md5': '62833938a31e61ab49ada92f524c42ff',
-        'info_dict': {
-            'id': '8309a40969894a8e8d5bc1311e9c5667',
-            'ext': 'mp4',
-            'title': 'Lillier and the Staff!',
-            'description': 'md5:338841b8c21b283d24bdc9b568849f04',
-        },
-    }, {
-        'url': 'https://watch.pokemon.com/en-us/#/player?id=3fe7752ba09141f0b0f7756d1981c6b2',
-        'only_matching': True,
-    }, {
-        'url': 'https://watch.pokemon.com/de-de/player.html?id=b3c402e111a4459eb47e12160ab0ba07',
-        'only_matching': True,
-    }]
-
-    def _extract_media(self, channel_array, video_id):
-        for channel in channel_array:
-            for media in channel.get('media'):
-                if media.get('id') == video_id:
-                    return media
-        return None
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        info = {
-            '_type': 'url',
-            'id': video_id,
-            'url': f'limelight:media:{video_id}',
-            'ie_key': 'LimelightMedia',
-        }
-
-        # API call can be avoided entirely if we are listing formats
-        if self.get_param('listformats', False):
-            return info
-
-        webpage = self._download_webpage(url, video_id)
-        build_vars = self._parse_json(self._search_regex(
-            r'(?s)buildVars\s*=\s*({.*?})', webpage, 'build vars'),
-            video_id, transform_source=js_to_json)
-        region = build_vars.get('region')
-        channel_array = self._download_json(self._API_URL.format(region), video_id)
-        video_data = self._extract_media(channel_array, video_id)
-
-        if video_data is None:
-            raise ExtractorError(
-                f'Video {video_id} does not exist', expected=True)
-
-        info['_type'] = 'url_transparent'
-        images = video_data.get('images')
-
-        return merge_dicts(info, {
-            'title': video_data.get('title'),
-            'description': video_data.get('description'),
-            'thumbnail': images.get('medium') or images.get('small'),
-            'series': 'Pokémon',
-            'season_number': int_or_none(video_data.get('season')),
-            'episode': video_data.get('title'),
-            'episode_number': int_or_none(video_data.get('episode')),
-        })

yt_dlp/extractor/rutube.py

@@ -13,7 +13,10 @@ from ..utils import (
     unified_timestamp,
     url_or_none,
 )
-from ..utils.traversal import traverse_obj
+from ..utils.traversal import (
+    subs_list_to_dict,
+    traverse_obj,
+)
 
 
 class RutubeBaseIE(InfoExtractor):
@@ -92,11 +95,11 @@ class RutubeBaseIE(InfoExtractor):
                 hls_url, video_id, 'mp4', fatal=False, m3u8_id='hls')
             formats.extend(fmts)
             self._merge_subtitles(subs, target=subtitles)
-        for caption in traverse_obj(options, ('captions', lambda _, v: url_or_none(v['file']))):
+        self._merge_subtitles(traverse_obj(options, ('captions', ..., {
-            subtitles.setdefault(caption.get('code') or 'ru', []).append({
+            'id': 'code',
-                'url': caption['file'],
+            'url': 'file',
-                'name': caption.get('langTitle'),
+            'name': ('langTitle', {str}),
-            })
+        }, all, {subs_list_to_dict(lang='ru')})), target=subtitles)
         return formats, subtitles
 
     def _download_and_extract_formats_and_subtitles(self, video_id, query=None):

yt_dlp/extractor/sonyliv.py

@@ -199,8 +199,9 @@ class SonyLIVSeriesIE(InfoExtractor):
         },
     }]
     _API_BASE = 'https://apiv2.sonyliv.com/AGL'
+    _SORT_ORDERS = ('asc', 'desc')
 
-    def _entries(self, show_id):
+    def _entries(self, show_id, sort_order):
         headers = {
             'Accept': 'application/json, text/plain, */*',
             'Referer': 'https://www.sonyliv.com',
@@ -215,6 +216,9 @@ class SonyLIVSeriesIE(InfoExtractor):
                 'from': '0',
                 'to': '49',
             }), ('resultObj', 'containers', 0, 'containers', lambda _, v: int_or_none(v['id'])))
+
+        if sort_order == 'desc':
+            seasons = reversed(seasons)
         for season in seasons:
             season_id = str(season['id'])
             note = traverse_obj(season, ('metadata', 'title', {str})) or 'season'
@@ -226,7 +230,7 @@ class SonyLIVSeriesIE(InfoExtractor):
                         'from': str(cursor),
                         'to': str(cursor + 99),
                         'orderBy': 'episodeNumber',
-                        'sortOrder': 'asc',
+                        'sortOrder': sort_order,
                     }), ('resultObj', 'containers', 0, 'containers', lambda _, v: int_or_none(v['id'])))
                 if not episodes:
                     break
@@ -237,4 +241,10 @@ class SonyLIVSeriesIE(InfoExtractor):
 
     def _real_extract(self, url):
         show_id = self._match_id(url)
-        return self.playlist_result(self._entries(show_id), playlist_id=show_id)
+
+        sort_order = self._configuration_arg('sort_order', [self._SORT_ORDERS[0]])[0]
+        if sort_order not in self._SORT_ORDERS:
+            raise ValueError(
+                f'Invalid sort order "{sort_order}". Allowed values are: {", ".join(self._SORT_ORDERS)}')
+
+        return self.playlist_result(self._entries(show_id, sort_order), playlist_id=show_id)

yt_dlp/extractor/soundcloud.py

@@ -241,7 +241,7 @@ class SoundcloudBaseIE(InfoExtractor):
                     format_urls.add(format_url)
                     formats.append({
                         'format_id': 'download',
-                        'ext': urlhandle_detect_ext(urlh) or 'mp3',
+                        'ext': urlhandle_detect_ext(urlh, default='mp3'),
                         'filesize': int_or_none(urlh.headers.get('Content-Length')),
                         'url': format_url,
                         'quality': 10,

yt_dlp/extractor/uliza.py

@@ -0,0 +1,113 @@
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    make_archive_id,
+    parse_qs,
+    time_seconds,
+)
+from ..utils.traversal import traverse_obj
+
+
+class UlizaPlayerIE(InfoExtractor):
+    _VALID_URL = r'https://player-api\.p\.uliza\.jp/v1/players/[^?#]+\?(?:[^#]*&)?name=(?P<id>[^#&]+)'
+    _TESTS = [{
+        'url': 'https://player-api.p.uliza.jp/v1/players/timeshift-disabled/pia/admin?type=normal&playerobjectname=ulizaPlayer&name=livestream01_dvr&repeatable=true',
+        'info_dict': {
+            'id': '88f3109a-f503-4d0f-a9f7-9f39ac745d84',
+            'ext': 'mp4',
+            'title': '88f3109a-f503-4d0f-a9f7-9f39ac745d84',
+            'live_status': 'was_live',
+            '_old_archive_ids': ['piaulizaportal 88f3109a-f503-4d0f-a9f7-9f39ac745d84'],
+        },
+    }, {
+        'url': 'https://player-api.p.uliza.jp/v1/players/uliza_jp_gallery_normal/promotion/admin?type=presentation&name=cookings&targetid=player1',
+        'info_dict': {
+            'id': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
+            'ext': 'mp4',
+            'title': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
+            'live_status': 'not_live',
+            '_old_archive_ids': ['piaulizaportal ae350126-5e22-4a7f-a8ac-8d0fd448b800'],
+        },
+    }, {
+        'url': 'https://player-api.p.uliza.jp/v1/players/default-player/pia/admin?type=normal&name=pia_movie_uliza_fix&targetid=ulizahtml5&repeatable=true',
+        'info_dict': {
+            'id': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
+            'ext': 'mp4',
+            'title': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
+            'live_status': 'not_live',
+            '_old_archive_ids': ['piaulizaportal 0644ecc8-e354-41b4-b957-3b08a2d63df1'],
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        player_data = self._download_webpage(
+            url, display_id, headers={'Referer': 'https://player-api.p.uliza.jp/'},
+            note='Fetching player data', errnote='Unable to fetch player data')
+
+        m3u8_url = self._search_regex(
+            r'["\'](https://vms-api\.p\.uliza\.jp/v1/prog-index\.m3u8[^"\']+)', player_data, 'm3u8 url')
+        video_id = parse_qs(m3u8_url).get('ss', [display_id])[0]
+
+        formats = self._extract_m3u8_formats(m3u8_url, video_id)
+        m3u8_type = self._search_regex(
+            r'/hls/(dvr|video)/', traverse_obj(formats, (0, 'url')), 'm3u8 type', default=None)
+        return {
+            'id': video_id,
+            'title': video_id,
+            'formats': formats,
+            'live_status': {
+                'video': 'is_live',
+                'dvr': 'was_live',  # short-term archives
+            }.get(m3u8_type, 'not_live'),  # VOD or long-term archives
+            '_old_archive_ids': [make_archive_id('PIAULIZAPortal', video_id)],
+        }
+
+
+class UlizaPortalIE(InfoExtractor):
+    IE_DESC = 'ulizaportal.jp'
+    _VALID_URL = r'https?://(?:www\.)?ulizaportal\.jp/pages/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
+    _TESTS = [{
+        'url': 'https://ulizaportal.jp/pages/005f18b7-e810-5618-cb82-0987c5755d44',
+        'info_dict': {
+            'id': 'ae350126-5e22-4a7f-a8ac-8d0fd448b800',
+            'display_id': '005f18b7-e810-5618-cb82-0987c5755d44',
+            'title': 'プレゼンテーションプレイヤーのサンプル',
+            'live_status': 'not_live',
+            '_old_archive_ids': ['piaulizaportal ae350126-5e22-4a7f-a8ac-8d0fd448b800'],
+        },
+        'params': {
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+    }, {
+        'url': 'https://ulizaportal.jp/pages/005e1b23-fe93-5780-19a0-98e917cc4b7d?expires=4102412400&signature=f422a993b683e1068f946caf406d211c17d1ef17da8bef3df4a519502155aa91&version=1',
+        'info_dict': {
+            'id': '0644ecc8-e354-41b4-b957-3b08a2d63df1',
+            'display_id': '005e1b23-fe93-5780-19a0-98e917cc4b7d',
+            'title': '【確認用】視聴サンプルページ（ULIZA）',
+            'live_status': 'not_live',
+            '_old_archive_ids': ['piaulizaportal 0644ecc8-e354-41b4-b957-3b08a2d63df1'],
+        },
+        'params': {
+            'skip_download': True,
+            'ignore_no_formats_error': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        expires = int_or_none(traverse_obj(parse_qs(url), ('expires', 0)))
+        if expires and expires <= time_seconds():
+            raise ExtractorError('The link is expired', video_id=video_id, expected=True)
+
+        webpage = self._download_webpage(url, video_id)
+
+        player_data_url = self._search_regex(
+            r'<script [^>]*\bsrc="(https://player-api\.p\.uliza\.jp/v1/players/[^"]+)"',
+            webpage, 'player data url')
+        return self.url_result(
+            player_data_url, UlizaPlayerIE, url_transparent=True,
+            display_id=video_id, video_title=self._html_extract_title(webpage))

yt_dlp/extractor/veoh.py

@@ -1,189 +0,0 @@
-import functools
-import json
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    OnDemandPagedList,
-    int_or_none,
-    parse_duration,
-    qualities,
-    remove_start,
-    strip_or_none,
-)
-
-
-class VeohIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?veoh\.com/(?:watch|videos|embed|iphone/#_Watch)/(?P<id>(?:v|e|yapi-)[\da-zA-Z]+)'
-
-    _TESTS = [{
-        'url': 'http://www.veoh.com/watch/v56314296nk7Zdmz3',
-        'md5': '620e68e6a3cff80086df3348426c9ca3',
-        'info_dict': {
-            'id': 'v56314296nk7Zdmz3',
-            'ext': 'mp4',
-            'title': 'Straight Backs Are Stronger',
-            'description': 'md5:203f976279939a6dc664d4001e13f5f4',
-            'thumbnail': 're:https://fcache\\.veoh\\.com/file/f/th56314296\\.jpg(\\?.*)?',
-            'uploader': 'LUMOback',
-            'duration': 46,
-            'view_count': int,
-            'average_rating': int,
-            'comment_count': int,
-            'age_limit': 0,
-            'categories': ['technology_and_gaming'],
-            'tags': ['posture', 'posture', 'sensor', 'back', 'pain', 'wearable', 'tech', 'lumo'],
-        },
-    }, {
-        'url': 'http://www.veoh.com/embed/v56314296nk7Zdmz3',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.veoh.com/watch/v27701988pbTc4wzN?h1=Chile+workers+cover+up+to+avoid+skin+damage',
-        'md5': '4a6ff84b87d536a6a71e6aa6c0ad07fa',
-        'info_dict': {
-            'id': '27701988',
-            'ext': 'mp4',
-            'title': 'Chile workers cover up to avoid skin damage',
-            'description': 'md5:2bd151625a60a32822873efc246ba20d',
-            'uploader': 'afp-news',
-            'duration': 123,
-        },
-        'skip': 'This video has been deleted.',
-    }, {
-        'url': 'http://www.veoh.com/watch/v69525809F6Nc4frX',
-        'md5': '4fde7b9e33577bab2f2f8f260e30e979',
-        'note': 'Embedded ooyala video',
-        'info_dict': {
-            'id': '69525809',
-            'ext': 'mp4',
-            'title': 'Doctors Alter Plan For Preteen\'s Weight Loss Surgery',
-            'description': 'md5:f5a11c51f8fb51d2315bca0937526891',
-            'uploader': 'newsy-videos',
-        },
-        'skip': 'This video has been deleted.',
-    }, {
-        'url': 'http://www.veoh.com/watch/e152215AJxZktGS',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.veoh.com/videos/v16374379WA437rMH',
-        'md5': 'cceb73f3909063d64f4b93d4defca1b3',
-        'info_dict': {
-            'id': 'v16374379WA437rMH',
-            'ext': 'mp4',
-            'title': 'Phantasmagoria 2, pt. 1-3',
-            'description': 'Phantasmagoria: a Puzzle of Flesh',
-            'thumbnail': 're:https://fcache\\.veoh\\.com/file/f/th16374379\\.jpg(\\?.*)?',
-            'uploader': 'davidspackage',
-            'duration': 968,
-            'view_count': int,
-            'average_rating': int,
-            'comment_count': int,
-            'age_limit': 18,
-            'categories': ['technology_and_gaming', 'gaming'],
-            'tags': ['puzzle', 'of', 'flesh'],
-        },
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        metadata = self._download_json(
-            'https://www.veoh.com/watch/getVideo/' + video_id,
-            video_id)
-        video = metadata['video']
-        title = video['title']
-
-        thumbnail_url = None
-        q = qualities(['Regular', 'HQ'])
-        formats = []
-        for f_id, f_url in video.get('src', {}).items():
-            if not f_url:
-                continue
-            if f_id == 'poster':
-                thumbnail_url = f_url
-            else:
-                formats.append({
-                    'format_id': f_id,
-                    'quality': q(f_id),
-                    'url': f_url,
-                })
-
-        categories = metadata.get('categoryPath')
-        if not categories:
-            category = remove_start(strip_or_none(video.get('category')), 'category_')
-            categories = [category] if category else None
-        tags = video.get('tags')
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': video.get('description'),
-            'thumbnail': thumbnail_url,
-            'uploader': video.get('author', {}).get('nickname'),
-            'duration': int_or_none(video.get('lengthBySec')) or parse_duration(video.get('length')),
-            'view_count': int_or_none(video.get('views')),
-            'formats': formats,
-            'average_rating': int_or_none(video.get('rating')),
-            'comment_count': int_or_none(video.get('numOfComments')),
-            'age_limit': 18 if video.get('contentRatingId') == 2 else 0,
-            'categories': categories,
-            'tags': tags.split(', ') if tags else None,
-        }
-
-
-class VeohUserIE(VeohIE):  # XXX: Do not subclass from concrete IE
-    _VALID_URL = r'https?://(?:www\.)?veoh\.com/users/(?P<id>[\w-]+)'
-    IE_NAME = 'veoh:user'
-
-    _TESTS = [
-        {
-            'url': 'https://www.veoh.com/users/valentinazoe',
-            'info_dict': {
-                'id': 'valentinazoe',
-                'title': 'valentinazoe (Uploads)',
-            },
-            'playlist_mincount': 75,
-        },
-        {
-            'url': 'https://www.veoh.com/users/PiensaLibre',
-            'info_dict': {
-                'id': 'PiensaLibre',
-                'title': 'PiensaLibre (Uploads)',
-            },
-            'playlist_mincount': 2,
-        }]
-
-    _PAGE_SIZE = 16
-
-    def _fetch_page(self, uploader, page):
-        response = self._download_json(
-            'https://www.veoh.com/users/published/videos', uploader,
-            note=f'Downloading videos page {page + 1}',
-            headers={
-                'x-csrf-token': self._TOKEN,
-                'content-type': 'application/json;charset=UTF-8',
-            },
-            data=json.dumps({
-                'username': uploader,
-                'maxResults': self._PAGE_SIZE,
-                'page': page + 1,
-                'requestName': 'userPage',
-            }).encode())
-        if not response.get('success'):
-            raise ExtractorError(response['message'])
-
-        for video in response['videos']:
-            yield self.url_result(f'https://www.veoh.com/watch/{video["permalinkId"]}', VeohIE,
-                                  video['permalinkId'], video.get('title'))
-
-    def _real_initialize(self):
-        webpage = self._download_webpage(
-            'https://www.veoh.com', None, note='Downloading authorization token')
-        self._TOKEN = self._search_regex(
-            r'csrfToken:\s*(["\'])(?P<token>[0-9a-zA-Z]{40})\1', webpage,
-            'request token', group='token')
-
-    def _real_extract(self, url):
-        uploader = self._match_id(url)
-        return self.playlist_result(OnDemandPagedList(
-            functools.partial(self._fetch_page, uploader),
-            self._PAGE_SIZE), uploader, f'{uploader} (Uploads)')

yt_dlp/extractor/youtube.py

@@ -5087,7 +5087,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
     def _rich_entries(self, rich_grid_renderer):
         renderer = traverse_obj(
             rich_grid_renderer,
-            ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer', 'shortsLockupViewModel'), any)) or {}
+            ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer', 'shortsLockupViewModel', 'lockupViewModel'), any)) or {}
         video_id = renderer.get('videoId')
         if video_id:
             yield self._extract_video(renderer)
@@ -5114,6 +5114,18 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
                 })),
                 thumbnails=self._extract_thumbnails(renderer, 'thumbnail', final_key='sources'))
             return
+        # lockupViewModel extraction
+        content_id = renderer.get('contentId')
+        if content_id and renderer.get('contentType') == 'LOCKUP_CONTENT_TYPE_PODCAST':
+            yield self.url_result(
+                f'https://www.youtube.com/playlist?list={content_id}',
+                ie=YoutubeTabIE, video_id=content_id,
+                **traverse_obj(renderer, {
+                    'title': ('metadata', 'lockupMetadataViewModel', 'title', 'content', {str}),
+                }),
+                thumbnails=self._extract_thumbnails(renderer, (
+                    'contentImage', 'collectionThumbnailViewModel', 'primaryThumbnail', 'thumbnailViewModel', 'image'), final_key='sources'))
+            return
 
     def _video_entry(self, video_renderer):
         video_id = video_renderer.get('videoId')
@@ -6706,22 +6718,22 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         },
         'playlist_count': 0,
     }, {
-        # Podcasts tab, with rich entry playlistRenderers
+        # Podcasts tab, with rich entry lockupViewModel
         'url': 'https://www.youtube.com/@99percentinvisiblepodcast/podcasts',
         'info_dict': {
             'id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
             'channel_id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
             'uploader_url': 'https://www.youtube.com/@99percentinvisiblepodcast',
             'description': 'md5:3a0ed38f1ad42a68ef0428c04a15695c',
-            'title': '99 Percent Invisible - Podcasts',
+            'title': '99% Invisible - Podcasts',
-            'uploader': '99 Percent Invisible',
+            'uploader': '99% Invisible',
             'channel_follower_count': int,
             'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw',
             'tags': [],
-            'channel': '99 Percent Invisible',
+            'channel': '99% Invisible',
             'uploader_id': '@99percentinvisiblepodcast',
         },
-        'playlist_count': 0,
+        'playlist_count': 5,
     }, {
         # Releases tab, with rich entry playlistRenderers (same as Podcasts tab)
         'url': 'https://www.youtube.com/@AHimitsu/releases',

yt_dlp/options.py

@@ -419,7 +419,9 @@ def create_parser():
     general.add_option(
         '--flat-playlist',
         action='store_const', dest='extract_flat', const='in_playlist', default=False,
-        help='Do not extract the videos of a playlist, only list them')
+        help=(
+            'Do not extract a playlist\'s URL result entries; '
+            'some entry metadata may be missing and downloading may be bypassed'))
     general.add_option(
         '--no-flat-playlist',
         action='store_false', dest='extract_flat',

yt_dlp/postprocessor/__init__.py

@@ -8,6 +8,7 @@ from .ffmpeg import (
     FFmpegCopyStreamPP,
     FFmpegEmbedSubtitlePP,
     FFmpegExtractAudioPP,
+    FFmpegCENCDecryptPP,
     FFmpegFixupDuplicateMoovPP,
     FFmpegFixupDurationPP,
     FFmpegFixupM3u8PP,

yt_dlp/postprocessor/ffmpeg.py

@@ -330,7 +330,7 @@ class FFmpegPostProcessor(PostProcessor):
             [(path, []) for path in input_paths],
             [(out_path, opts)], **kwargs)
 
-    def real_run_ffmpeg(self, input_path_opts, output_path_opts, *, expected_retcodes=(0,)):
+    def real_run_ffmpeg(self, input_path_opts, output_path_opts, *, prepend_opts=None, expected_retcodes=(0,)):
         self.check_version()
 
         oldest_mtime = min(
@@ -341,6 +341,9 @@ class FFmpegPostProcessor(PostProcessor):
         if self.basename == 'ffmpeg':
             cmd += [encodeArgument('-loglevel'), encodeArgument('repeat+info')]
 
+        if prepend_opts:
+            cmd += prepend_opts
+
         def make_args(file, args, name, number):
             keys = [f'_{name}{number}', f'_{name}']
             if name == 'o':
@@ -856,12 +859,23 @@ class FFmpegMergerPP(FFmpegPostProcessor):
         return True
 
 
+class FFmpegCENCDecryptPP(FFmpegPostProcessor):
+    @PostProcessor._restrict_to(images=False)
+    def run(self, info):
+        for filename, key in info.get('__files_to_cenc_decrypt', []):
+            temp_filename = prepend_extension(filename, 'temp')
+            self.to_screen(f'Decrypting "{filename}"')
+            self.run_ffmpeg(filename, temp_filename, self.stream_copy_opts(), prepend_opts=['-decryption_key', key])
+            os.replace(temp_filename, filename)
+        return [], info
+
+
 class FFmpegFixupPostProcessor(FFmpegPostProcessor):
-    def _fixup(self, msg, filename, options):
+    def _fixup(self, msg, filename, options, prepend_opts=None):
         temp_filename = prepend_extension(filename, 'temp')
 
         self.to_screen(f'{msg} of "{filename}"')
-        self.run_ffmpeg(filename, temp_filename, options)
+        self.run_ffmpeg(filename, temp_filename, options, prepend_opts=prepend_opts)
 
         os.replace(temp_filename, filename)
 
@@ -933,7 +947,11 @@ class FFmpegCopyStreamPP(FFmpegFixupPostProcessor):
 
     @PostProcessor._restrict_to(images=False)
     def run(self, info):
-        self._fixup(self.MESSAGE, info['filepath'], self.stream_copy_opts())
+        self._fixup(
+            self.MESSAGE,
+            info['filepath'],
+            self.stream_copy_opts(),
+        )
         return [], info