[version] update

Created by: pukkandan

:ci skip all :ci run dl

.github/ISSUE_TEMPLATE/1_broken_site.yml

@@ -18,7 +18,7 @@ body:
       options:
         - label: I'm reporting a broken site
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.08.19** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2022.09.01** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
           required: true
@@ -62,7 +62,7 @@ body:
         [debug] Command-line config: ['-vU', 'test:youtube']
         [debug] Portable config "yt-dlp.conf": ['-i']
         [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] yt-dlp version 2022.08.19 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2022.09.01 [9d339c4] (win32_exe)
         [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
         [debug] Checking exe version: ffmpeg -bsfs
         [debug] Checking exe version: ffprobe -bsfs
@@ -70,8 +70,8 @@ body:
         [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
         [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
-        Latest version: 2022.08.19, Current version: 2022.08.19
+        Latest version: 2022.09.01, Current version: 2022.09.01
-        yt-dlp is up to date (2022.08.19)
+        yt-dlp is up to date (2022.09.01)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/2_site_support_request.yml

@@ -18,7 +18,7 @@ body:
       options:
         - label: I'm reporting a new site support request
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.08.19** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2022.09.01** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
           required: true
@@ -74,7 +74,7 @@ body:
         [debug] Command-line config: ['-vU', 'test:youtube']
         [debug] Portable config "yt-dlp.conf": ['-i']
         [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] yt-dlp version 2022.08.19 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2022.09.01 [9d339c4] (win32_exe)
         [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
         [debug] Checking exe version: ffmpeg -bsfs
         [debug] Checking exe version: ffprobe -bsfs
@@ -82,8 +82,8 @@ body:
         [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
         [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
-        Latest version: 2022.08.19, Current version: 2022.08.19
+        Latest version: 2022.09.01, Current version: 2022.09.01
-        yt-dlp is up to date (2022.08.19)
+        yt-dlp is up to date (2022.09.01)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/3_site_feature_request.yml

@@ -18,7 +18,7 @@ body:
       options:
         - label: I'm requesting a site-specific feature
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.08.19** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2022.09.01** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
           required: true
@@ -70,7 +70,7 @@ body:
         [debug] Command-line config: ['-vU', 'test:youtube']
         [debug] Portable config "yt-dlp.conf": ['-i']
         [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] yt-dlp version 2022.08.19 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2022.09.01 [9d339c4] (win32_exe)
         [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
         [debug] Checking exe version: ffmpeg -bsfs
         [debug] Checking exe version: ffprobe -bsfs
@@ -78,8 +78,8 @@ body:
         [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
         [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
-        Latest version: 2022.08.19, Current version: 2022.08.19
+        Latest version: 2022.09.01, Current version: 2022.09.01
-        yt-dlp is up to date (2022.08.19)
+        yt-dlp is up to date (2022.09.01)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/4_bug_report.yml

@@ -18,7 +18,7 @@ body:
       options:
         - label: I'm reporting a bug unrelated to a specific site
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.08.19** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2022.09.01** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
           required: true
@@ -55,7 +55,7 @@ body:
         [debug] Command-line config: ['-vU', 'test:youtube']
         [debug] Portable config "yt-dlp.conf": ['-i']
         [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] yt-dlp version 2022.08.19 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2022.09.01 [9d339c4] (win32_exe)
         [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
         [debug] Checking exe version: ffmpeg -bsfs
         [debug] Checking exe version: ffprobe -bsfs
@@ -63,8 +63,8 @@ body:
         [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
         [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
-        Latest version: 2022.08.19, Current version: 2022.08.19
+        Latest version: 2022.09.01, Current version: 2022.09.01
-        yt-dlp is up to date (2022.08.19)
+        yt-dlp is up to date (2022.09.01)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/5_feature_request.yml

@@ -20,7 +20,7 @@ body:
           required: true
         - label: I've looked through the [README](https://github.com/yt-dlp/yt-dlp#readme)
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.08.19** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2022.09.01** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
           required: true
@@ -51,7 +51,7 @@ body:
         [debug] Command-line config: ['-vU', 'test:youtube']
         [debug] Portable config "yt-dlp.conf": ['-i']
         [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] yt-dlp version 2022.08.19 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2022.09.01 [9d339c4] (win32_exe)
         [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
         [debug] Checking exe version: ffmpeg -bsfs
         [debug] Checking exe version: ffprobe -bsfs
@@ -59,7 +59,7 @@ body:
         [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
         [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
-        Latest version: 2022.08.19, Current version: 2022.08.19
+        Latest version: 2022.09.01, Current version: 2022.09.01
-        yt-dlp is up to date (2022.08.19)
+        yt-dlp is up to date (2022.09.01)
         <more lines>
       render: shell

.github/ISSUE_TEMPLATE/6_question.yml

@@ -26,7 +26,7 @@ body:
           required: true
         - label: I've looked through the [README](https://github.com/yt-dlp/yt-dlp#readme)
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.08.19** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2022.09.01** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar questions **including closed ones**. DO NOT post duplicates
           required: true
@@ -57,7 +57,7 @@ body:
         [debug] Command-line config: ['-vU', 'test:youtube']
         [debug] Portable config "yt-dlp.conf": ['-i']
         [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] yt-dlp version 2022.08.19 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2022.09.01 [9d339c4] (win32_exe)
         [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
         [debug] Checking exe version: ffmpeg -bsfs
         [debug] Checking exe version: ffprobe -bsfs
@@ -65,7 +65,7 @@ body:
         [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
         [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
-        Latest version: 2022.08.19, Current version: 2022.08.19
+        Latest version: 2022.09.01, Current version: 2022.09.01
-        yt-dlp is up to date (2022.08.19)
+        yt-dlp is up to date (2022.09.01)
         <more lines>
       render: shell

.github/workflows/build.yml

@@ -194,7 +194,7 @@ jobs:
     - name: Install Requirements
       run: |  # Custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds
           python -m pip install --upgrade pip setuptools wheel py2exe
-          pip install "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-5.2-py3-none-any.whl" -r requirements.txt
+          pip install "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-5.3-py3-none-any.whl" -r requirements.txt
 
     - name: Prepare
       run: |
@@ -230,7 +230,7 @@ jobs:
     - name: Install Requirements
       run: |
           python -m pip install --upgrade pip setuptools wheel
-          pip install "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-5.2-py3-none-any.whl" -r requirements.txt
+          pip install "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-5.3-py3-none-any.whl" -r requirements.txt
 
     - name: Prepare
       run: |

CONTRIBUTORS

@@ -299,3 +299,12 @@ bashonly
 jacobtruman
 masta79
 palewire
+cgrigis
+DavidH-2022
+dfaker
+jackyyf
+ohaiibuzzle
+SamantazFox
+shreyasminocha
+tejasa97
+xenov

Changelog.md

@@ -11,6 +11,54 @@
 -->
 
 
+### 2022.09.01
+
+* Add option `--use-extractors`
+* Merge youtube-dl: Upto [commit/ed5c44e](https://github.com/ytdl-org/youtube-dl/commit/ed5c44e7)
+* Add yt-dlp version to infojson
+* Fix `--break-per-url --max-downloads`
+* Fix bug in `--alias`
+* [cookies] Support firefox container in `--cookies-from-browser` by [bashonly](https://github.com/bashonly), [coletdjnz](https://github.com/coletdjnz), [pukkandan](https://github.com/pukkandan)
+* [downloader/external] Smarter detection of executable
+* [extractor/generic] Don't return JW player without formats
+* [FormatSort] Fix `aext` for `--prefer-free-formats`
+* [jsinterp] Various improvements by [pukkandan](https://github.com/pukkandan), [dirkf](https://github.com/dirkf), [elyse0](https://github.com/elyse0)
+* [cache] Mechanism to invalidate old cache
+* [utils] Add `deprecation_warning`
+* [utils] Add `orderedSet_from_options`
+* [utils] `Popen`: Restore `LD_LIBRARY_PATH` when using PyInstaller by [Lesmiscore](https://github.com/Lesmiscore)
+* [build] `make tar` should not follow `DESTDIR` by [satan1st](https://github.com/satan1st)
+* [build] Update pyinstaller by [shirt-dev](https://github.com/shirt-dev)
+* [test] Fix `test_youtube_signature`
+* [cleanup] Misc fixes and cleanup by [DavidH-2022](https://github.com/DavidH-2022), [MrRawes](https://github.com/MrRawes), [pukkandan](https://github.com/pukkandan)
+* [extractor/epoch] Add extractor by [tejasa97](https://github.com/tejasa97)
+* [extractor/eurosport] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/IslamChannel] Add extractors by [Lesmiscore](https://github.com/Lesmiscore)
+* [extractor/newspicks] Add extractor by [Lesmiscore](https://github.com/Lesmiscore)
+* [extractor/triller] Add extractor by [bashonly](https://github.com/bashonly)
+* [extractor/VQQ] Add extractors by [elyse0](https://github.com/elyse0)
+* [extractor/youtube] Improvements to nsig extraction
+* [extractor/youtube] Fix bug in format sorting
+* [extractor/youtube] Update iOS Innertube clients by [SamantazFox](https://github.com/SamantazFox)
+* [extractor/youtube] Use device-specific user agent by [coletdjnz](https://github.com/coletdjnz)
+* [extractor/youtube] Add `--compat-option no-youtube-prefer-utc-upload-date` by [coletdjnz](https://github.com/coletdjnz)
+* [extractor/arte] Bug fix by [cgrigis](https://github.com/cgrigis)
+* [extractor/bilibili] Extract `flac` with premium account by [jackyyf](https://github.com/jackyyf)
+* [extractor/BiliBiliSearch] Don't sort by date
+* [extractor/BiliBiliSearch] Fix infinite loop
+* [extractor/bitchute] Mark errors as expected
+* [extractor/crunchyroll:beta] Use anonymous access by [tejing1](https://github.com/tejing1)
+* [extractor/huya] Fix stream extraction by [ohaiibuzzle](https://github.com/ohaiibuzzle)
+* [extractor/medaltv] Fix extraction by [xenova](https://github.com/xenova)
+* [extractor/mediaset] Fix embed extraction
+* [extractor/mixcloud] All formats are audio-only
+* [extractor/rtbf] Fix jwt extraction by [elyse0](https://github.com/elyse0)
+* [extractor/screencastomatic] Support `--video-password` by [shreyasminocha](https://github.com/shreyasminocha)
+* [extractor/stripchat] Don't modify input URL by [dfaker](https://github.com/dfaker)
+* [extractor/uktv] Improve `_VALID_URL` by [dirkf](https://github.com/dirkf)
+* [extractor/vimeo:user] Fix `_VALID_URL`
+
+
 ### 2022.08.19
 
 * Fix bug in `--download-archive`

Makefile

@@ -33,7 +33,6 @@ completion-zsh: completions/zsh/_yt-dlp
 lazy-extractors: yt_dlp/extractor/lazy_extractors.py
 
 PREFIX ?= /usr/local
-DESTDIR ?= .
 BINDIR ?= $(PREFIX)/bin
 MANDIR ?= $(PREFIX)/man
 SHAREDIR ?= $(PREFIX)/share
@@ -134,7 +133,7 @@ yt_dlp/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscrip
 	$(PYTHON) devscripts/make_lazy_extractors.py $@
 
 yt-dlp.tar.gz: all
-	@tar -czf $(DESTDIR)/yt-dlp.tar.gz --transform "s|^|yt-dlp/|" --owner 0 --group 0 \
+	@tar -czf yt-dlp.tar.gz --transform "s|^|yt-dlp/|" --owner 0 --group 0 \
 		--exclude '*.DS_Store' \
 		--exclude '*.kate-swp' \
 		--exclude '*.pyc' \

README.md

@@ -71,7 +71,7 @@ yt-dlp is a [youtube-dl](https://github.com/ytdl-org/youtube-dl) fork based on t
 
 # NEW FEATURES
 
-* Merged with **youtube-dl v2021.12.17+ [commit/b0a60ce](https://github.com/ytdl-org/youtube-dl/commit/b0a60ce2032172aeaaf27fe3866ab72768f10cb2)**<!--([exceptions](https://github.com/yt-dlp/yt-dlp/issues/21))--> and **youtube-dlc v2020.11.11-3+ [commit/f9401f2](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee)**: You get all the features and patches of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) in addition to the latest [youtube-dl](https://github.com/ytdl-org/youtube-dl)
+* Merged with **youtube-dl v2021.12.17+ [commit/ed5c44e](https://github.com/ytdl-org/youtube-dl/commit/ed5c44e7b74ac77f87ca5ed6cb5e964a0c6a0678)**<!--([exceptions](https://github.com/yt-dlp/yt-dlp/issues/21))--> and **youtube-dlc v2020.11.11-3+ [commit/f9401f2](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee)**: You get all the features and patches of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) in addition to the latest [youtube-dl](https://github.com/ytdl-org/youtube-dl)
 
 * **[SponsorBlock Integration](#sponsorblock-options)**: You can mark/remove sponsor sections in youtube videos by utilizing the [SponsorBlock](https://sponsor.ajay.app) API
 
@@ -141,6 +141,7 @@ Some of yt-dlp's default options are different from that of youtube-dl and youtu
 * Live chats (if available) are considered as subtitles. Use `--sub-langs all,-live_chat` to download all subtitles except live chat. You can also use `--compat-options no-live-chat` to prevent any live chat/danmaku from downloading
 * Youtube channel URLs are automatically redirected to `/video`. Append a `/featured` to the URL to download only the videos in the home page. If the channel does not have a videos tab, we try to download the equivalent `UU` playlist instead. For all other tabs, if the channel does not show the requested tab, an error will be raised. Also, `/live` URLs raise an error if there are no live videos instead of silently downloading the entire channel. You may use `--compat-options no-youtube-channel-redirect` to revert all these redirections
 * Unavailable videos are also listed for youtube playlists. Use `--compat-options no-youtube-unavailable-videos` to remove this
+* The upload dates extracted from YouTube are in UTC [when available](https://github.com/yt-dlp/yt-dlp/blob/89e4d86171c7b7c997c77d4714542e0383bf0db0/yt_dlp/extractor/youtube.py#L3898-L3900). Use `--compat-options no-youtube-prefer-utc-upload-date` to prefer the non-UTC upload date.
 * If `ffmpeg` is used as the downloader, the downloading and merging of formats happen in a single step when possible. Use `--compat-options no-direct-merge` to revert this
 * Thumbnail embedding in `mp4` is done with mutagen if possible. Use `--compat-options embed-thumbnail-atomicparsley` to force the use of AtomicParsley instead
 * Some private fields such as filenames are removed by default from the infojson. Use `--no-clean-infojson` or `--compat-options no-clean-infojson` to revert this
@@ -320,7 +321,7 @@ To build the standalone executable, you must have Python and `pyinstaller` (plus
 
 On some systems, you may need to use `py` or `python` instead of `python3`.
 
-Note that pyinstaller [does not support](https://github.com/pyinstaller/pyinstaller#requirements-and-tested-platforms) Python installed from the Windows store without using a virtual environment.
+Note that pyinstaller with versions below 4.4 [do not support](https://github.com/pyinstaller/pyinstaller#requirements-and-tested-platforms) Python installed from the Windows store without using a virtual environment.
 
 **Important**: Running `pyinstaller` directly **without** using `pyinst.py` is **not** officially supported. This may or may not work correctly.
 
@@ -375,7 +376,13 @@ You can also fork the project on github and run your fork's [build workflow](.gi
     --list-extractors               List all supported extractors and exit
     --extractor-descriptions        Output descriptions of all supported
                                     extractors and exit
-    --force-generic-extractor       Force extraction to use the generic extractor
+    --use-extractors NAMES          Extractor names to use separated by commas.
+                                    You can also use regexes, "all", "default"
+                                    and "end" (end URL matching); e.g. --ies
+                                    "holodex.*,end,youtube". Prefix the name
+                                    with a "-" to exclude it, e.g. --ies
+                                    default,-generic. Use --list-extractors for
+                                    a list of extractor names. (Alias: --ies)
     --default-search PREFIX         Use this prefix for unqualified URLs. E.g.
                                     "gvsearch2:python" downloads two videos from
                                     google videos for the search term "python".
@@ -524,8 +531,8 @@ You can also fork the project on github and run your fork's [build workflow](.gi
                                     a file that is in the archive
     --break-on-reject               Stop the download process when encountering
                                     a file that has been filtered out
-    --break-per-input               Make --break-on-existing, --break-on-reject
+    --break-per-input               --break-on-existing, --break-on-reject,
-                                    and --max-downloads act only on the current
+                                    --max-downloads, and autonumber resets per
                                     input URL
     --no-break-per-input            --break-on-existing and similar options
                                     terminates the entire download queue
@@ -700,18 +707,20 @@ You can also fork the project on github and run your fork's [build workflow](.gi
                                     and dump cookie jar in
     --no-cookies                    Do not read/dump cookies from/to file
                                     (default)
-    --cookies-from-browser BROWSER[+KEYRING][:PROFILE]
+    --cookies-from-browser BROWSER[+KEYRING][:PROFILE][::CONTAINER]
-                                    The name of the browser and (optionally) the
+                                    The name of the browser to load cookies
-                                    name/path of the profile to load cookies
+                                    from. Currently supported browsers are:
-                                    from, separated by a ":". Currently
+                                    brave, chrome, chromium, edge, firefox,
-                                    supported browsers are: brave, chrome,
+                                    opera, safari, vivaldi. Optionally, the
-                                    chromium, edge, firefox, opera, safari,
+                                    KEYRING used for decrypting Chromium cookies
-                                    vivaldi. By default, the most recently
+                                    on Linux, the name/path of the PROFILE to
-                                    accessed profile is used. The keyring used
+                                    load cookies from, and the CONTAINER name
-                                    for decrypting Chromium cookies on Linux can
+                                    (if Firefox) ("none" for no container) can
-                                    be (optionally) specified after the browser
+                                    be given with their respective seperators.
-                                    name separated by a "+". Currently supported
+                                    By default, all containers of the most
-                                    keyrings are: basictext, gnomekeyring, kwallet
+                                    recently accessed profile are used.
+                                    Currently supported keyrings are: basictext,
+                                    gnomekeyring, kwallet
     --no-cookies-from-browser       Do not load cookies from browser (default)
     --cache-dir DIR                 Location in the filesystem where youtube-dl
                                     can store some downloaded information (such
@@ -1229,7 +1238,6 @@ The available fields are:
  - `id` (string): Video identifier
  - `title` (string): Video title
  - `fulltitle` (string): Video title ignoring live timestamp and generic title
- - `url` (string): Video URL
  - `ext` (string): Video filename extension
  - `alt_title` (string): A secondary title of the video
  - `description` (string): The description of the video
@@ -1264,26 +1272,6 @@ The available fields are:
  - `availability` (string): Whether the video is "private", "premium_only", "subscriber_only", "needs_auth", "unlisted" or "public"
  - `start_time` (numeric): Time in seconds where the reproduction should start, as specified in the URL
  - `end_time` (numeric): Time in seconds where the reproduction should end, as specified in the URL
- - `format` (string): A human-readable description of the format
- - `format_id` (string): Format code specified by `--format`
- - `format_note` (string): Additional info about the format
- - `width` (numeric): Width of the video
- - `height` (numeric): Height of the video
- - `resolution` (string): Textual description of width and height
- - `tbr` (numeric): Average bitrate of audio and video in KBit/s
- - `abr` (numeric): Average audio bitrate in KBit/s
- - `acodec` (string): Name of the audio codec in use
- - `asr` (numeric): Audio sampling rate in Hertz
- - `vbr` (numeric): Average video bitrate in KBit/s
- - `fps` (numeric): Frame rate
- - `dynamic_range` (string): The dynamic range of the video
- - `audio_channels` (numeric): The number of audio channels
- - `stretched_ratio` (float): `width:height` of the video's pixels, if not square
- - `vcodec` (string): Name of the video codec in use
- - `container` (string): Name of the container format
- - `filesize` (numeric): The number of bytes, if known in advance
- - `filesize_approx` (numeric): An estimate for the number of bytes
- - `protocol` (string): The protocol that will be used for the actual download
  - `extractor` (string): Name of the extractor
  - `extractor_key` (string): Key name of the extractor
  - `epoch` (numeric): Unix epoch of when the information extraction was completed
@@ -1302,6 +1290,8 @@ The available fields are:
  - `webpage_url_basename` (string): The basename of the webpage URL
  - `webpage_url_domain` (string): The domain of the webpage URL
  - `original_url` (string): The URL given by the user (or same as `webpage_url` for playlist entries)
+ 
+All the fields in [Filtering Formats](#filtering-formats) can also be used
 
 Available for the video that belongs to some logical chapter or section:
 
@@ -1383,13 +1373,13 @@ If you are using an output template inside a Windows batch file then you must es
 #### Output template examples
 
 ```bash
-$ yt-dlp --get-filename -o "test video.%(ext)s" BaW_jenozKc
+$ yt-dlp --print filename -o "test video.%(ext)s" BaW_jenozKc
 test video.webm    # Literal name with correct extension
 
-$ yt-dlp --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc
+$ yt-dlp --print filename -o "%(title)s.%(ext)s" BaW_jenozKc
 youtube-dl test video ''_ä↭𝕐.webm    # All kinds of weird characters
 
-$ yt-dlp --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames
+$ yt-dlp --print filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames
 youtube-dl_test_video_.webm    # Restricted file name
 
 # Download YouTube playlist videos in separate directory indexed by video order in a playlist
@@ -1478,6 +1468,7 @@ You can also filter the video formats by putting a condition in brackets, as in
 The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `>=`, `=` (equals), `!=` (not equals):
 
  - `filesize`: The number of bytes, if known in advance
+ - `filesize_approx`: An estimate for the number of bytes
  - `width`: Width of the video, if known
  - `height`: Height of the video, if known
  - `tbr`: Average bitrate of audio and video in KBit/s
@@ -1485,16 +1476,23 @@ The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `
  - `vbr`: Average video bitrate in KBit/s
  - `asr`: Audio sampling rate in Hertz
  - `fps`: Frame rate
+ - `audio_channels`: The number of audio channels
+ - `stretched_ratio`: `width:height` of the video's pixels, if not square
 
 Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends with), `*=` (contains), `~=` (matches regex) and following string meta fields:
 
+ - `url`: Video URL
  - `ext`: File extension
  - `acodec`: Name of the audio codec in use
  - `vcodec`: Name of the video codec in use
  - `container`: Name of the container format
  - `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `http_dash_segments`, `m3u8`, or `m3u8_native`)
- - `format_id`: A short description of the format
  - `language`: Language code
+ - `dynamic_range`: The dynamic range of the video
+ - `format_id`: A short description of the format
+ - `format`: A human-readable description of the format
+ - `format_note`: Additional info about the format
+ - `resolution`: Textual description of width and height
 
 Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain). The comparand of a string comparison needs to be quoted with either double or single quotes if it contains spaces or special characters other than `._-`.
 
@@ -1521,7 +1519,7 @@ The available fields are:
  - `acodec`: Audio Codec (`flac`/`alac` > `wav`/`aiff` > `opus` > `vorbis` > `aac` > `mp4a` > `mp3` > `eac3` > `ac3` > `dts` > other)
  - `codec`: Equivalent to `vcodec,acodec`
  - `vext`: Video Extension (`mp4` > `webm` > `flv` > other). If `--prefer-free-formats` is used, `webm` is preferred.
- - `aext`: Audio Extension (`m4a` > `aac` > `mp3` > `ogg` > `opus` > `webm` > other). If `--prefer-free-formats` is used, the order changes to `opus` > `ogg` > `webm` > `m4a` > `mp3` > `aac`.
+ - `aext`: Audio Extension (`m4a` > `aac` > `mp3` > `ogg` > `opus` > `webm` > other). If `--prefer-free-formats` is used, the order changes to `ogg` > `opus` > `webm` > `mp3` > `m4a` > `aac`
  - `ext`: Equivalent to `vext,aext`
  - `filesize`: Exact filesize, if known in advance
  - `fs_approx`: Approximate filesize calculated from the manifests
@@ -2058,6 +2056,7 @@ While these options are redundant, they are still expected to be used due to the
 #### Not recommended
 While these options still work, their use is not recommended since there are other alternatives to achieve the same
 
+    --force-generic-extractor        --ies generic,default
     --exec-before-download CMD       --exec "before_dl:CMD"
     --no-exec-before-download        --no-exec
     --all-formats                    -f all

devscripts/lazy_load_template.py

@@ -11,14 +11,17 @@ from ..utils import (
 
 # These bloat the lazy_extractors, so allow them to passthrough silently
 ALLOWED_CLASSMETHODS = {'get_testcases', 'extract_from_webpage'}
+_WARNED = False
 
 
 class LazyLoadMetaClass(type):
     def __getattr__(cls, name):
-        if '_real_class' not in cls.__dict__ and name not in ALLOWED_CLASSMETHODS:
+        global _WARNED
-            write_string(
+        if ('_real_class' not in cls.__dict__
-                'WARNING: Falling back to normal extractor since lazy extractor '
+                and name not in ALLOWED_CLASSMETHODS and not _WARNED):
-                f'{cls.__name__} does not have attribute {name}{bug_reports_message()}\n')
+            _WARNED = True
+            write_string('WARNING: Falling back to normal extractor since lazy extractor '
+                         f'{cls.__name__} does not have attribute {name}{bug_reports_message()}\n')
         return getattr(cls.real_class, name)
 
 

devscripts/make_lazy_extractors.py

@@ -12,7 +12,9 @@ from inspect import getsource
 from devscripts.utils import get_filename_args, read_file, write_file
 
 NO_ATTR = object()
-STATIC_CLASS_PROPERTIES = ['IE_NAME', 'IE_DESC', 'SEARCH_KEY', '_VALID_URL', '_WORKING', '_NETRC_MACHINE', 'age_limit']
+STATIC_CLASS_PROPERTIES = [
+    'IE_NAME', 'IE_DESC', 'SEARCH_KEY', '_VALID_URL', '_WORKING', '_ENABLED', '_NETRC_MACHINE', 'age_limit'
+]
 CLASS_METHODS = [
     'ie_key', 'working', 'description', 'suitable', '_match_valid_url', '_match_id', 'get_temp_id', 'is_suitable'
 ]

devscripts/run_tests.sh

@@ -1,13 +1,13 @@
 #!/usr/bin/env sh
 
-if [ -z $1 ]; then
+if [ -z "$1" ]; then
     test_set='test'
-elif [ $1 = 'core' ]; then
+elif [ "$1" = 'core' ]; then
     test_set="-m not download"
-elif [ $1 = 'download' ]; then
+elif [ "$1" = 'download' ]; then
     test_set="-m download"
 else
-    echo 'Invalid test type "'$1'". Use "core" | "download"'
+    echo 'Invalid test type "'"$1"'". Use "core" | "download"'
     exit 1
 fi
 

supportedsites.md

@@ -364,6 +364,7 @@
  - **Engadget**
  - **Epicon**
  - **EpiconSeries**
+ - **Epoch**
  - **Eporner**
  - **EroProfile**: [<abbr title="netrc machine"><em>eroprofile</em></abbr>]
  - **EroProfile:album**
@@ -377,6 +378,7 @@
  - **EsriVideo**
  - **Europa**
  - **EuropeanTour**
+ - **Eurosport**
  - **EUScreen**
  - **EWETV**: [<abbr title="netrc machine"><em>ewetv</em></abbr>]
  - **EWETVLive**: [<abbr title="netrc machine"><em>ewetv</em></abbr>]
@@ -553,6 +555,8 @@
  - **iq.com**: International version of iQiyi
  - **iq.com:album**
  - **iqiyi**: [<abbr title="netrc machine"><em>iqiyi</em></abbr>] 爱奇艺
+ - **IslamChannel**
+ - **IslamChannelSeries**
  - **ITProTV**
  - **ITProTVCourse**
  - **ITTF**
@@ -820,6 +824,7 @@
  - **Newgrounds**
  - **Newgrounds:playlist**
  - **Newgrounds:user**
+ - **NewsPicks**
  - **Newstube**
  - **Newsy**
  - **NextMedia**: 蘋果日報
@@ -1331,6 +1336,8 @@
  - **ToypicsUser**: Toypics user profile
  - **TrailerAddict**: (**Currently broken**)
  - **TravelChannel**
+ - **Triller**: [<abbr title="netrc machine"><em>triller</em></abbr>]
+ - **TrillerUser**: [<abbr title="netrc machine"><em>triller</em></abbr>]
  - **Trilulilu**
  - **Trovo**
  - **TrovoChannelClip**: All Clips of a trovo.live channel; "trovoclip:" prefix
@@ -1506,6 +1513,8 @@
  - **VoxMedia**
  - **VoxMediaVolume**
  - **vpro**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
+ - **vqq:series**
+ - **vqq:video**
  - **Vrak**
  - **VRT**: VRT NWS, Flanders News, Flandern Info and Sporza
  - **VrtNU**: [<abbr title="netrc machine"><em>vrtnu</em></abbr>] VrtNU.be

test/test_YoutubeDL.py

@@ -668,7 +668,7 @@ class TestYoutubeDL(unittest.TestCase):
     def test_prepare_outtmpl_and_filename(self):
         def test(tmpl, expected, *, info=None, **params):
             params['outtmpl'] = tmpl
-            ydl = YoutubeDL(params)
+            ydl = FakeYDL(params)
             ydl._num_downloads = 1
             self.assertEqual(ydl.validate_outtmpl(tmpl), None)
 

test/test_execution.py

@@ -11,41 +11,46 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 import contextlib
 import subprocess
 
-from yt_dlp.utils import encodeArgument
+from yt_dlp.utils import Popen
 
 rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
-
+LAZY_EXTRACTORS = 'yt_dlp/extractor/lazy_extractors.py'
-
-try:
-    _DEV_NULL = subprocess.DEVNULL
-except AttributeError:
-    _DEV_NULL = open(os.devnull, 'wb')
 
 
 class TestExecution(unittest.TestCase):
-    def test_import(self):
+    def run_yt_dlp(self, exe=(sys.executable, 'yt_dlp/__main__.py'), opts=('--version', )):
-        subprocess.check_call([sys.executable, '-c', 'import yt_dlp'], cwd=rootDir)
+        stdout, stderr, returncode = Popen.run(
-
+            [*exe, '--ignore-config', *opts], cwd=rootDir, text=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-    def test_module_exec(self):
+        print(stderr, file=sys.stderr)
-        subprocess.check_call([sys.executable, '-m', 'yt_dlp', '--ignore-config', '--version'], cwd=rootDir, stdout=_DEV_NULL)
+        self.assertEqual(returncode, 0)
+        return stdout.strip(), stderr.strip()
 
     def test_main_exec(self):
-        subprocess.check_call([sys.executable, 'yt_dlp/__main__.py', '--ignore-config', '--version'], cwd=rootDir, stdout=_DEV_NULL)
+        self.run_yt_dlp()
+
+    def test_import(self):
+        self.run_yt_dlp(exe=(sys.executable, '-c', 'import yt_dlp'))
+
+    def test_module_exec(self):
+        self.run_yt_dlp(exe=(sys.executable, '-m', 'yt_dlp'))
 
     def test_cmdline_umlauts(self):
-        p = subprocess.Popen(
+        _, stderr = self.run_yt_dlp(opts=('ä', '--version'))
-            [sys.executable, 'yt_dlp/__main__.py', '--ignore-config', encodeArgument('ä'), '--version'],
-            cwd=rootDir, stdout=_DEV_NULL, stderr=subprocess.PIPE)
-        _, stderr = p.communicate()
         self.assertFalse(stderr)
 
     def test_lazy_extractors(self):
         try:
-            subprocess.check_call([sys.executable, 'devscripts/make_lazy_extractors.py', 'yt_dlp/extractor/lazy_extractors.py'], cwd=rootDir, stdout=_DEV_NULL)
+            subprocess.check_call([sys.executable, 'devscripts/make_lazy_extractors.py', LAZY_EXTRACTORS],
-            subprocess.check_call([sys.executable, 'test/test_all_urls.py'], cwd=rootDir, stdout=_DEV_NULL)
+                                  cwd=rootDir, stdout=subprocess.DEVNULL)
+            self.assertTrue(os.path.exists(LAZY_EXTRACTORS))
+
+            _, stderr = self.run_yt_dlp(opts=('-s', 'test:'))
+            self.assertFalse(stderr)
+
+            subprocess.check_call([sys.executable, 'test/test_all_urls.py'], cwd=rootDir, stdout=subprocess.DEVNULL)
         finally:
             with contextlib.suppress(OSError):
-                os.remove('yt_dlp/extractor/lazy_extractors.py')
+                os.remove(LAZY_EXTRACTORS)
 
 
 if __name__ == '__main__':

test/test_jsinterp.py

@@ -71,6 +71,9 @@ class TestJSInterpreter(unittest.TestCase):
         jsi = JSInterpreter('function f(){return 0 ?? 42;}')
         self.assertEqual(jsi.call_function('f'), 0)
 
+        jsi = JSInterpreter('function f(){return "life, the universe and everything" < 42;}')
+        self.assertFalse(jsi.call_function('f'))
+
     def test_array_access(self):
         jsi = JSInterpreter('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2.0] = 7; return x;}')
         self.assertEqual(jsi.call_function('f'), [5, 2, 7])
@@ -129,6 +132,11 @@ class TestJSInterpreter(unittest.TestCase):
         self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50])
 
     def test_builtins(self):
+        jsi = JSInterpreter('''
+        function x() { return NaN }
+        ''')
+        self.assertTrue(math.isnan(jsi.call_function('x')))
+
         jsi = JSInterpreter('''
         function x() { return new Date('Wednesday 31 December 1969 18:01:26 MDT') - 0; }
         ''')
@@ -188,6 +196,30 @@ class TestJSInterpreter(unittest.TestCase):
         ''')
         self.assertEqual(jsi.call_function('x'), 10)
 
+    def test_catch(self):
+        jsi = JSInterpreter('''
+        function x() { try{throw 10} catch(e){return 5} }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 5)
+
+    def test_finally(self):
+        jsi = JSInterpreter('''
+        function x() { try{throw 10} finally {return 42} }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 42)
+        jsi = JSInterpreter('''
+        function x() { try{throw 10} catch(e){return 5} finally {return 42} }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 42)
+
+    def test_nested_try(self):
+        jsi = JSInterpreter('''
+        function x() {try {
+            try{throw 10} finally {throw 42}
+            } catch(e){return 5} }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 5)
+
     def test_for_loop_continue(self):
         jsi = JSInterpreter('''
         function x() { a=0; for (i=0; i-10; i++) { continue; a++ } return a }
@@ -200,6 +232,14 @@ class TestJSInterpreter(unittest.TestCase):
         ''')
         self.assertEqual(jsi.call_function('x'), 0)
 
+    def test_for_loop_try(self):
+        jsi = JSInterpreter('''
+        function x() {
+            for (i=0; i-10; i++) { try { if (i == 5) throw i} catch {return 10} finally {break} };
+            return 42 }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 42)
+
     def test_literal_list(self):
         jsi = JSInterpreter('''
         function x() { return [1, 2, "asdf", [5, 6, 7]][3] }
@@ -347,6 +387,27 @@ class TestJSInterpreter(unittest.TestCase):
         ''')
         self.assertEqual(jsi.call_function('x').flags & re.I, re.I)
 
+        jsi = JSInterpreter(R'''
+        function x() { let a=/,][}",],()}(\[)/; return a; }
+        ''')
+        self.assertEqual(jsi.call_function('x').pattern, r',][}",],()}(\[)')
+
+    def test_char_code_at(self):
+        jsi = JSInterpreter('function x(i){return "test".charCodeAt(i)}')
+        self.assertEqual(jsi.call_function('x', 0), 116)
+        self.assertEqual(jsi.call_function('x', 1), 101)
+        self.assertEqual(jsi.call_function('x', 2), 115)
+        self.assertEqual(jsi.call_function('x', 3), 116)
+        self.assertEqual(jsi.call_function('x', 4), None)
+        self.assertEqual(jsi.call_function('x', 'not_a_number'), 116)
+
+    def test_bitwise_operators_overflow(self):
+        jsi = JSInterpreter('function x(){return -524999584 << 5}')
+        self.assertEqual(jsi.call_function('x'), 379882496)
+
+        jsi = JSInterpreter('function x(){return 1236566549 << 5}')
+        self.assertEqual(jsi.call_function('x'), 915423904)
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_signature.py

@@ -110,6 +110,22 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/1f7d5369/player_ias.vflset/en_US/base.js',
         'batNX7sYqIJdkJ', 'IhOkL_zxbkOZBw',
     ),
+    (
+        'https://www.youtube.com/s/player/009f1d77/player_ias.vflset/en_US/base.js',
+        '5dwFHw8aFWQUQtffRq', 'audescmLUzI3jw',
+    ),
+    (
+        'https://www.youtube.com/s/player/dc0c6770/player_ias.vflset/en_US/base.js',
+        '5EHDMgYLV6HPGk_Mu-kk', 'n9lUJLHbxUI0GQ',
+    ),
+    (
+        'https://www.youtube.com/s/player/113ca41c/player_ias.vflset/en_US/base.js',
+        'cgYl-tlYkhjT7A', 'hI7BBr2zUgcmMg',
+    ),
+    (
+        'https://www.youtube.com/s/player/c57c113c/player_ias.vflset/en_US/base.js',
+        'M92UUMHa8PdvPd3wyM', '3hPqLJsiNZx7yA',
+    ),
 ]
 
 

yt_dlp/YoutubeDL.py

@@ -29,6 +29,7 @@ from .cookies import load_cookies
 from .downloader import FFmpegFD, get_suitable_downloader, shorten_protocol_name
 from .downloader.rtmp import rtmpdump_version
 from .extractor import gen_extractor_classes, get_info_extractor
+from .extractor.common import UnsupportedURLIE
 from .extractor.openload import PhantomJSwrapper
 from .minicurses import format_text
 from .postprocessor import _PLUGIN_CLASSES as plugin_postprocessors
@@ -47,7 +48,7 @@ from .postprocessor import (
     get_postprocessor,
 )
 from .postprocessor.ffmpeg import resolve_mapping as resolve_recode_mapping
-from .update import detect_variant
+from .update import REPOSITORY, current_git_head, detect_variant
 from .utils import (
     DEFAULT_OUTTMPL,
     IDENTITY,
@@ -89,6 +90,7 @@ from .utils import (
     args_to_str,
     bug_reports_message,
     date_from_str,
+    deprecation_warning,
     determine_ext,
     determine_protocol,
     encode_compat_str,
@@ -115,6 +117,7 @@ from .utils import (
     network_exceptions,
     number_of_digits,
     orderedSet,
+    orderedSet_from_options,
     parse_filesize,
     preferredencoding,
     prepend_extension,
@@ -236,7 +239,7 @@ class YoutubeDL:
                        Default is 'only_download' for CLI, but False for API
     skip_playlist_after_errors: Number of allowed failures until the rest of
                        the playlist is skipped
-    force_generic_extractor: Force downloader to use the generic extractor
+    allowed_extractors:  List of regexes to match against extractor names that are allowed
     overwrites:        Overwrite all video and metadata files if True,
                        overwrite only non-video files if None
                        and don't overwrite any file if False
@@ -301,8 +304,9 @@ class YoutubeDL:
                        should act on each input URL as opposed to for the entire queue
     cookiefile:        File name or text stream from where cookies should be read and dumped to
     cookiesfrombrowser:  A tuple containing the name of the browser, the profile
-                       name/path from where cookies are loaded, and the name of the
+                       name/path from where cookies are loaded, the name of the keyring,
-                       keyring, e.g. ('chrome', ) or ('vivaldi', 'default', 'BASICTEXT')
+                       and the container name, e.g. ('chrome', ) or
+                       ('vivaldi', 'default', 'BASICTEXT') or ('firefox', 'default', None, 'Meta')
     legacyserverconnect: Explicitly allow HTTPS connection to servers that do not
                        support RFC 5746 secure renegotiation
     nocheckcertificate:  Do not verify SSL certificates
@@ -476,6 +480,8 @@ class YoutubeDL:
 
     The following options are deprecated and may be removed in the future:
 
+    force_generic_extractor: Force downloader to use the generic extractor
+                       - Use allowed_extractors = ['generic', 'default']
     playliststart:     - Use playlist_items
                        Playlist item to start at.
     playlistend:       - Use playlist_items
@@ -627,7 +633,7 @@ class YoutubeDL:
         for msg in self.params.get('_warnings', []):
             self.report_warning(msg)
         for msg in self.params.get('_deprecation_warnings', []):
-            self.deprecation_warning(msg)
+            self.deprecated_feature(msg)
 
         self.params['compat_opts'] = set(self.params.get('compat_opts', ()))
         if 'list-formats' in self.params['compat_opts']:
@@ -757,13 +763,6 @@ class YoutubeDL:
             self._ies_instances[ie_key] = ie
             ie.set_downloader(self)
 
-    def _get_info_extractor_class(self, ie_key):
-        ie = self._ies.get(ie_key)
-        if ie is None:
-            ie = get_info_extractor(ie_key)
-            self.add_info_extractor(ie)
-        return ie
-
     def get_info_extractor(self, ie_key):
         """
         Get an instance of an IE with name ie_key, it will try to get one from
@@ -780,8 +779,19 @@ class YoutubeDL:
         """
         Add the InfoExtractors returned by gen_extractors to the end of the list
         """
-        for ie in gen_extractor_classes():
+        all_ies = {ie.IE_NAME.lower(): ie for ie in gen_extractor_classes()}
-            self.add_info_extractor(ie)
+        all_ies['end'] = UnsupportedURLIE()
+        try:
+            ie_names = orderedSet_from_options(
+                self.params.get('allowed_extractors', ['default']), {
+                    'all': list(all_ies),
+                    'default': [name for name, ie in all_ies.items() if ie._ENABLED],
+                }, use_regex=True)
+        except re.error as e:
+            raise ValueError(f'Wrong regex for allowed_extractors: {e.pattern}')
+        for name in ie_names:
+            self.add_info_extractor(all_ies[name])
+        self.write_debug(f'Loaded {len(ie_names)} extractors')
 
     def add_post_processor(self, pp, when='post_process'):
         """Add a PostProcessor object to the end of the chain."""
@@ -827,9 +837,11 @@ class YoutubeDL:
     def to_stdout(self, message, skip_eol=False, quiet=None):
         """Print message to stdout"""
         if quiet is not None:
-            self.deprecation_warning('"YoutubeDL.to_stdout" no longer accepts the argument quiet. Use "YoutubeDL.to_screen" instead')
+            self.deprecation_warning('"YoutubeDL.to_stdout" no longer accepts the argument quiet. '
+                                     'Use "YoutubeDL.to_screen" instead')
         if skip_eol is not False:
-            self.deprecation_warning('"YoutubeDL.to_stdout" no longer accepts the argument skip_eol. Use "YoutubeDL.to_screen" instead')
+            self.deprecation_warning('"YoutubeDL.to_stdout" no longer accepts the argument skip_eol. '
+                                     'Use "YoutubeDL.to_screen" instead')
         self._write_string(f'{self._bidi_workaround(message)}\n', self._out_files.out)
 
     def to_screen(self, message, skip_eol=False, quiet=None):
@@ -965,11 +977,14 @@ class YoutubeDL:
                 return
             self.to_stderr(f'{self._format_err("WARNING:", self.Styles.WARNING)} {message}', only_once)
 
-    def deprecation_warning(self, message):
+    def deprecation_warning(self, message, *, stacklevel=0):
+        deprecation_warning(
+            message, stacklevel=stacklevel + 1, printer=self.report_error, is_error=False)
+
+    def deprecated_feature(self, message):
         if self.params.get('logger') is not None:
-            self.params['logger'].warning(f'DeprecationWarning: {message}')
+            self.params['logger'].warning(f'Deprecated Feature: {message}')
-        else:
+        self.to_stderr(f'{self._format_err("Deprecated Feature:", self.Styles.ERROR)} {message}', True)
-            self.to_stderr(f'{self._format_err("DeprecationWarning:", self.Styles.ERROR)} {message}', True)
 
     def report_error(self, message, *args, **kwargs):
         '''
@@ -1029,7 +1044,7 @@ class YoutubeDL:
 
     def get_output_path(self, dir_type='', filename=None):
         paths = self.params.get('paths', {})
-        assert isinstance(paths, dict)
+        assert isinstance(paths, dict), '"paths" parameter must be a dictionary'
         path = os.path.join(
             expand_path(paths.get('home', '').strip()),
             expand_path(paths.get(dir_type, '').strip()) if dir_type else '',
@@ -1412,11 +1427,11 @@ class YoutubeDL:
             ie_key = 'Generic'
 
         if ie_key:
-            ies = {ie_key: self._get_info_extractor_class(ie_key)}
+            ies = {ie_key: self._ies[ie_key]} if ie_key in self._ies else {}
         else:
             ies = self._ies
 
-        for ie_key, ie in ies.items():
+        for key, ie in ies.items():
             if not ie.suitable(url):
                 continue
 
@@ -1425,14 +1440,16 @@ class YoutubeDL:
                                     'and will probably not work.')
 
             temp_id = ie.get_temp_id(url)
-            if temp_id is not None and self.in_download_archive({'id': temp_id, 'ie_key': ie_key}):
+            if temp_id is not None and self.in_download_archive({'id': temp_id, 'ie_key': key}):
-                self.to_screen(f'[{ie_key}] {temp_id}: has already been recorded in the archive')
+                self.to_screen(f'[{key}] {temp_id}: has already been recorded in the archive')
                 if self.params.get('break_on_existing', False):
                     raise ExistingVideoReached()
                 break
-            return self.__extract_info(url, self.get_info_extractor(ie_key), download, extra_info, process)
+            return self.__extract_info(url, self.get_info_extractor(key), download, extra_info, process)
         else:
-            self.report_error('no suitable InfoExtractor for URL %s' % url)
+            extractors_restricted = self.params.get('allowed_extractors') not in (None, ['default'])
+            self.report_error(f'No suitable extractor{format_field(ie_key, None, " (%s)")} found for URL {url}',
+                              tb=False if extractors_restricted else None)
 
     def _handle_extraction_exceptions(func):
         @functools.wraps(func)
@@ -2511,9 +2528,6 @@ class YoutubeDL:
                     '--live-from-start is passed, but there are no formats that can be downloaded from the start. '
                     'If you want to download from the current time, use --no-live-from-start'))
 
-        if not formats:
-            self.raise_no_formats(info_dict)
-
         def is_wellformed(f):
             url = f.get('url')
             if not url:
@@ -2526,7 +2540,10 @@ class YoutubeDL:
             return True
 
         # Filter out malformed formats for better extraction robustness
-        formats = list(filter(is_wellformed, formats))
+        formats = list(filter(is_wellformed, formats or []))
+
+        if not formats:
+            self.raise_no_formats(info_dict)
 
         formats_dict = {}
 
@@ -2728,42 +2745,26 @@ class YoutubeDL:
                 if lang not in available_subs:
                     available_subs[lang] = cap_info
 
-        if (not self.params.get('writesubtitles') and not
+        if not available_subs or (
-                self.params.get('writeautomaticsub') or not
+                not self.params.get('writesubtitles')
-                available_subs):
+                and not self.params.get('writeautomaticsub')):
             return None
 
         all_sub_langs = tuple(available_subs.keys())
         if self.params.get('allsubtitles', False):
             requested_langs = all_sub_langs
         elif self.params.get('subtitleslangs', False):
-            # A list is used so that the order of languages will be the same as
+            try:
-            # given in subtitleslangs. See https://github.com/yt-dlp/yt-dlp/issues/1041
+                requested_langs = orderedSet_from_options(
-            requested_langs = []
+                    self.params.get('subtitleslangs'), {'all': all_sub_langs}, use_regex=True)
-            for lang_re in self.params.get('subtitleslangs'):
+            except re.error as e:
-                discard = lang_re[0] == '-'
+                raise ValueError(f'Wrong regex for subtitlelangs: {e.pattern}')
-                if discard:
-                    lang_re = lang_re[1:]
-                if lang_re == 'all':
-                    if discard:
-                        requested_langs = []
-                    else:
-                        requested_langs.extend(all_sub_langs)
-                    continue
-                current_langs = filter(re.compile(lang_re + '$').match, all_sub_langs)
-                if discard:
-                    for lang in current_langs:
-                        while lang in requested_langs:
-                            requested_langs.remove(lang)
-                else:
-                    requested_langs.extend(current_langs)
-            requested_langs = orderedSet(requested_langs)
         elif normal_sub_langs:
             requested_langs = ['en'] if 'en' in normal_sub_langs else normal_sub_langs[:1]
         else:
             requested_langs = ['en'] if 'en' in all_sub_langs else all_sub_langs[:1]
         if requested_langs:
-            self.write_debug('Downloading subtitles: %s' % ', '.join(requested_langs))
+            self.to_screen(f'[info] {video_id}: Downloading subtitles: {", ".join(requested_langs)}')
 
         formats_query = self.params.get('subtitlesformat', 'best')
         formats_preference = formats_query.split('/') if formats_query else []
@@ -3271,6 +3272,7 @@ class YoutubeDL:
                 self.to_screen(f'[info] {e}')
                 if not self.params.get('break_per_url'):
                     raise
+                self._num_downloads = 0
             else:
                 if self.params.get('dump_single_json', False):
                     self.post_extract(res)
@@ -3319,6 +3321,12 @@ class YoutubeDL:
             return info_dict
         info_dict.setdefault('epoch', int(time.time()))
         info_dict.setdefault('_type', 'video')
+        info_dict.setdefault('_version', {
+            'version': __version__,
+            'current_git_head': current_git_head(),
+            'release_git_head': RELEASE_GIT_HEAD,
+            'repository': REPOSITORY,
+        })
 
         if remove_private_keys:
             reject = lambda k, v: v is None or k.startswith('__') or k in {
@@ -3683,7 +3691,8 @@ class YoutubeDL:
         if VARIANT not in (None, 'pip'):
             source += '*'
         write_debug(join_nonempty(
-            'yt-dlp version', __version__,
+            f'{"yt-dlp" if REPOSITORY == "yt-dlp/yt-dlp" else REPOSITORY} version',
+            __version__,
             f'[{RELEASE_GIT_HEAD}]' if RELEASE_GIT_HEAD else '',
             '' if source == 'unknown' else f'({source})',
             delim=' '))
@@ -3699,18 +3708,8 @@ class YoutubeDL:
         if self.params['compat_opts']:
             write_debug('Compatibility options: %s' % ', '.join(self.params['compat_opts']))
 
-        if source == 'source':
+        if current_git_head():
-            try:
+            write_debug(f'Git HEAD: {current_git_head()}')
-                stdout, _, _ = Popen.run(
-                    ['git', 'rev-parse', '--short', 'HEAD'],
-                    text=True, cwd=os.path.dirname(os.path.abspath(__file__)),
-                    stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-                if re.fullmatch('[0-9a-f]+', stdout.strip()):
-                    write_debug(f'Git HEAD: {stdout.strip()}')
-            except Exception:
-                with contextlib.suppress(Exception):
-                    sys.exc_clear()
-
         write_debug(system_identifier())
 
         exe_versions, ffmpeg_features = FFmpegPostProcessor.get_versions_and_features(self)

yt_dlp/__init__.py

@@ -63,6 +63,8 @@ from .utils import (
 )
 from .YoutubeDL import YoutubeDL
 
+_IN_CLI = False
+
 
 def _exit(status=0, *args):
     for msg in args:
@@ -344,10 +346,16 @@ def validate_options(opts):
 
     # Cookies from browser
     if opts.cookiesfrombrowser:
-        mobj = re.match(r'(?P<name>[^+:]+)(\s*\+\s*(?P<keyring>[^:]+))?(\s*:(?P<profile>.+))?', opts.cookiesfrombrowser)
+        container = None
+        mobj = re.fullmatch(r'''(?x)
+            (?P<name>[^+:]+)
+            (?:\s*\+\s*(?P<keyring>[^:]+))?
+            (?:\s*:\s*(?P<profile>.+?))?
+            (?:\s*::\s*(?P<container>.+))?
+        ''', opts.cookiesfrombrowser)
         if mobj is None:
             raise ValueError(f'invalid cookies from browser arguments: {opts.cookiesfrombrowser}')
-        browser_name, keyring, profile = mobj.group('name', 'keyring', 'profile')
+        browser_name, keyring, profile, container = mobj.group('name', 'keyring', 'profile', 'container')
         browser_name = browser_name.lower()
         if browser_name not in SUPPORTED_BROWSERS:
             raise ValueError(f'unsupported browser specified for cookies: "{browser_name}". '
@@ -357,7 +365,7 @@ def validate_options(opts):
             if keyring not in SUPPORTED_KEYRINGS:
                 raise ValueError(f'unsupported keyring specified for cookies: "{keyring}". '
                                  f'Supported keyrings are: {", ".join(sorted(SUPPORTED_KEYRINGS))}')
-        opts.cookiesfrombrowser = (browser_name, profile, keyring)
+        opts.cookiesfrombrowser = (browser_name, profile, keyring, container)
 
     # MetadataParser
     def metadataparser_actions(f):
@@ -766,6 +774,7 @@ def parse_options(argv=None):
         'windowsfilenames': opts.windowsfilenames,
         'ignoreerrors': opts.ignoreerrors,
         'force_generic_extractor': opts.force_generic_extractor,
+        'allowed_extractors': opts.allowed_extractors or ['default'],
         'ratelimit': opts.ratelimit,
         'throttledratelimit': opts.throttledratelimit,
         'overwrites': opts.overwrites,

yt_dlp/__main__.py

@@ -14,4 +14,5 @@ if __package__ is None and not hasattr(sys, 'frozen'):
 import yt_dlp
 
 if __name__ == '__main__':
+    yt_dlp._IN_CLI = True
     yt_dlp.main()

yt_dlp/cache.py

@@ -6,7 +6,8 @@ import re
 import shutil
 import traceback
 
-from .utils import expand_path, write_json_file
+from .utils import expand_path, traverse_obj, version_tuple, write_json_file
+from .version import __version__
 
 
 class Cache:
@@ -45,12 +46,20 @@ class Cache:
                 if ose.errno != errno.EEXIST:
                     raise
             self._ydl.write_debug(f'Saving {section}.{key} to cache')
-            write_json_file(data, fn)
+            write_json_file({'yt-dlp_version': __version__, 'data': data}, fn)
         except Exception:
             tb = traceback.format_exc()
             self._ydl.report_warning(f'Writing cache to {fn!r} failed: {tb}')
 
-    def load(self, section, key, dtype='json', default=None):
+    def _validate(self, data, min_ver):
+        version = traverse_obj(data, 'yt-dlp_version')
+        if not version:  # Backward compatibility
+            data, version = {'data': data}, '2022.08.19'
+        if not min_ver or version_tuple(version) >= version_tuple(min_ver):
+            return data['data']
+        self._ydl.write_debug(f'Discarding old cache from version {version} (needs {min_ver})')
+
+    def load(self, section, key, dtype='json', default=None, *, min_ver=None):
         assert dtype in ('json',)
 
         if not self.enabled:
@@ -61,8 +70,8 @@ class Cache:
             try:
                 with open(cache_fn, encoding='utf-8') as cachef:
                     self._ydl.write_debug(f'Loading {section}.{key} from cache')
-                    return json.load(cachef)
+                    return self._validate(json.load(cachef), min_ver)
-            except ValueError:
+            except (ValueError, KeyError):
                 try:
                     file_size = os.path.getsize(cache_fn)
                 except OSError as oe:

yt_dlp/cookies.py

@@ -3,6 +3,7 @@ import contextlib
 import http.cookiejar
 import json
 import os
+import re
 import shutil
 import struct
 import subprocess
@@ -24,7 +25,13 @@ from .dependencies import (
     sqlite3,
 )
 from .minicurses import MultilinePrinter, QuietMultilinePrinter
-from .utils import Popen, YoutubeDLCookieJar, error_to_str, expand_path
+from .utils import (
+    Popen,
+    YoutubeDLCookieJar,
+    error_to_str,
+    expand_path,
+    try_call,
+)
 
 CHROMIUM_BASED_BROWSERS = {'brave', 'chrome', 'chromium', 'edge', 'opera', 'vivaldi'}
 SUPPORTED_BROWSERS = CHROMIUM_BASED_BROWSERS | {'firefox', 'safari'}
@@ -85,8 +92,9 @@ def _create_progress_bar(logger):
 def load_cookies(cookie_file, browser_specification, ydl):
     cookie_jars = []
     if browser_specification is not None:
-        browser_name, profile, keyring = _parse_browser_specification(*browser_specification)
+        browser_name, profile, keyring, container = _parse_browser_specification(*browser_specification)
-        cookie_jars.append(extract_cookies_from_browser(browser_name, profile, YDLLogger(ydl), keyring=keyring))
+        cookie_jars.append(
+            extract_cookies_from_browser(browser_name, profile, YDLLogger(ydl), keyring=keyring, container=container))
 
     if cookie_file is not None:
         is_filename = YoutubeDLCookieJar.is_path(cookie_file)
@@ -101,9 +109,9 @@ def load_cookies(cookie_file, browser_specification, ydl):
     return _merge_cookie_jars(cookie_jars)
 
 
-def extract_cookies_from_browser(browser_name, profile=None, logger=YDLLogger(), *, keyring=None):
+def extract_cookies_from_browser(browser_name, profile=None, logger=YDLLogger(), *, keyring=None, container=None):
     if browser_name == 'firefox':
-        return _extract_firefox_cookies(profile, logger)
+        return _extract_firefox_cookies(profile, container, logger)
     elif browser_name == 'safari':
         return _extract_safari_cookies(profile, logger)
     elif browser_name in CHROMIUM_BASED_BROWSERS:
@@ -112,7 +120,7 @@ def extract_cookies_from_browser(browser_name, profile=None, logger=YDLLogger(),
         raise ValueError(f'unknown browser: {browser_name}')
 
 
-def _extract_firefox_cookies(profile, logger):
+def _extract_firefox_cookies(profile, container, logger):
     logger.info('Extracting cookies from firefox')
     if not sqlite3:
         logger.warning('Cannot extract cookies from firefox without sqlite3 support. '
@@ -131,11 +139,36 @@ def _extract_firefox_cookies(profile, logger):
         raise FileNotFoundError(f'could not find firefox cookies database in {search_root}')
     logger.debug(f'Extracting cookies from: "{cookie_database_path}"')
 
+    container_id = None
+    if container not in (None, 'none'):
+        containers_path = os.path.join(os.path.dirname(cookie_database_path), 'containers.json')
+        if not os.path.isfile(containers_path) or not os.access(containers_path, os.R_OK):
+            raise FileNotFoundError(f'could not read containers.json in {search_root}')
+        with open(containers_path) as containers:
+            identities = json.load(containers).get('identities', [])
+        container_id = next((context.get('userContextId') for context in identities if container in (
+            context.get('name'),
+            try_call(lambda: re.fullmatch(r'userContext([^\.]+)\.label', context['l10nID']).group())
+        )), None)
+        if not isinstance(container_id, int):
+            raise ValueError(f'could not find firefox container "{container}" in containers.json')
+
     with tempfile.TemporaryDirectory(prefix='yt_dlp') as tmpdir:
         cursor = None
         try:
             cursor = _open_database_copy(cookie_database_path, tmpdir)
-            cursor.execute('SELECT host, name, value, path, expiry, isSecure FROM moz_cookies')
+            if isinstance(container_id, int):
+                logger.debug(
+                    f'Only loading cookies from firefox container "{container}", ID {container_id}')
+                cursor.execute(
+                    'SELECT host, name, value, path, expiry, isSecure FROM moz_cookies WHERE originAttributes LIKE ? OR originAttributes LIKE ?',
+                    (f'%userContextId={container_id}', f'%userContextId={container_id}&%'))
+            elif container == 'none':
+                logger.debug('Only loading cookies not belonging to any container')
+                cursor.execute(
+                    'SELECT host, name, value, path, expiry, isSecure FROM moz_cookies WHERE NOT INSTR(originAttributes,"userContextId=")')
+            else:
+                cursor.execute('SELECT host, name, value, path, expiry, isSecure FROM moz_cookies')
             jar = YoutubeDLCookieJar()
             with _create_progress_bar(logger) as progress_bar:
                 table = cursor.fetchall()
@@ -948,11 +981,11 @@ def _is_path(value):
     return os.path.sep in value
 
 
-def _parse_browser_specification(browser_name, profile=None, keyring=None):
+def _parse_browser_specification(browser_name, profile=None, keyring=None, container=None):
     if browser_name not in SUPPORTED_BROWSERS:
         raise ValueError(f'unsupported browser: "{browser_name}"')
     if keyring not in (None, *SUPPORTED_KEYRINGS):
         raise ValueError(f'unsupported keyring: "{keyring}"')
     if profile is not None and _is_path(profile):
         profile = os.path.expanduser(profile)
-    return browser_name, profile, keyring
+    return browser_name, profile, keyring, container

yt_dlp/downloader/common.py

@@ -92,6 +92,7 @@ class FileDownloader:
 
         for func in (
             'deprecation_warning',
+            'deprecated_feature',
             'report_error',
             'report_file_already_downloaded',
             'report_warning',

yt_dlp/downloader/external.py

@@ -515,16 +515,14 @@ _BY_NAME = {
     if name.endswith('FD') and name not in ('ExternalFD', 'FragmentFD')
 }
 
-_BY_EXE = {klass.EXE_NAME: klass for klass in _BY_NAME.values()}
-
 
 def list_external_downloaders():
     return sorted(_BY_NAME.keys())
 
 
 def get_external_downloader(external_downloader):
-    """ Given the name of the executable, see whether we support the given
+    """ Given the name of the executable, see whether we support the given downloader """
-        downloader . """
-    # Drop .exe extension on Windows
     bn = os.path.splitext(os.path.basename(external_downloader))[0]
-    return _BY_NAME.get(bn, _BY_EXE.get(bn))
+    return _BY_NAME.get(bn) or next((
+        klass for klass in _BY_NAME.values() if klass.EXE_NAME in bn
+    ), None)

yt_dlp/downloader/fragment.py

@@ -65,8 +65,8 @@ class FragmentFD(FileDownloader):
     """
 
     def report_retry_fragment(self, err, frag_index, count, retries):
-        self.deprecation_warning(
+        self.deprecation_warning('yt_dlp.downloader.FragmentFD.report_retry_fragment is deprecated. '
-            'yt_dlp.downloader.FragmentFD.report_retry_fragment is deprecated. Use yt_dlp.downloader.FileDownloader.report_retry instead')
+                                 'Use yt_dlp.downloader.FileDownloader.report_retry instead')
         return self.report_retry(err, count, retries, frag_index)
 
     def report_skip_fragment(self, frag_index, err=None):

yt_dlp/extractor/_extractors.py

@@ -1,5 +1,28 @@
 # flake8: noqa: F401
 
+from .youtube import (  # Youtube is moved to the top to improve performance
+    YoutubeIE,
+    YoutubeClipIE,
+    YoutubeFavouritesIE,
+    YoutubeNotificationsIE,
+    YoutubeHistoryIE,
+    YoutubeTabIE,
+    YoutubeLivestreamEmbedIE,
+    YoutubePlaylistIE,
+    YoutubeRecommendedIE,
+    YoutubeSearchDateIE,
+    YoutubeSearchIE,
+    YoutubeSearchURLIE,
+    YoutubeMusicSearchURLIE,
+    YoutubeSubscriptionsIE,
+    YoutubeStoriesIE,
+    YoutubeTruncatedIDIE,
+    YoutubeTruncatedURLIE,
+    YoutubeYtBeIE,
+    YoutubeYtUserIE,
+    YoutubeWatchLaterIE,
+)
+
 from .abc import (
     ABCIE,
     ABCIViewIE,
@@ -470,6 +493,7 @@ from .epicon import (
     EpiconIE,
     EpiconSeriesIE,
 )
+from .epoch import EpochIE
 from .eporner import EpornerIE
 from .eroprofile import (
     EroProfileIE,
@@ -491,6 +515,7 @@ from .espn import (
 from .esri import EsriVideoIE
 from .europa import EuropaIE
 from .europeantour import EuropeanTourIE
+from .eurosport import EurosportIE
 from .euscreen import EUScreenIE
 from .expotv import ExpoTVIE
 from .expressen import ExpressenIE
@@ -720,6 +745,10 @@ from .iqiyi import (
     IqIE,
     IqAlbumIE
 )
+from .islamchannel import (
+    IslamChannelIE,
+    IslamChannelSeriesIE,
+)
 from .itprotv import (
     ITProTVIE,
     ITProTVCourseIE
@@ -1079,6 +1108,7 @@ from .newgrounds import (
     NewgroundsPlaylistIE,
     NewgroundsUserIE,
 )
+from .newspicks import NewsPicksIE
 from .newstube import NewstubeIE
 from .newsy import NewsyIE
 from .nextmedia import (
@@ -1728,6 +1758,12 @@ from .telequebec import (
 from .teletask import TeleTaskIE
 from .telewebion import TelewebionIE
 from .tempo import TempoIE
+from .tencent import (
+    VQQSeriesIE,
+    VQQVideoIE,
+    WeTvEpisodeIE,
+    WeTvSeriesIE,
+)
 from .tennistv import TennisTVIE
 from .tenplay import TenPlayIE
 from .testurl import TestURLIE
@@ -1787,6 +1823,10 @@ from .toongoggles import ToonGogglesIE
 from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
+from .triller import (
+    TrillerIE,
+    TrillerUserIE,
+)
 from .trilulilu import TriluliluIE
 from .trovo import (
     TrovoIE,
@@ -2092,7 +2132,6 @@ from .weibo import (
     WeiboMobileIE
 )
 from .weiqitv import WeiqiTVIE
-from .wetv import WeTvEpisodeIE, WeTvSeriesIE
 from .wikimedia import WikimediaIE
 from .willow import WillowIE
 from .wimtv import WimTVIE
@@ -2175,28 +2214,6 @@ from .younow import (
 from .youporn import YouPornIE
 from .yourporn import YourPornIE
 from .yourupload import YourUploadIE
-from .youtube import (
-    YoutubeIE,
-    YoutubeClipIE,
-    YoutubeFavouritesIE,
-    YoutubeNotificationsIE,
-    YoutubeHistoryIE,
-    YoutubeTabIE,
-    YoutubeLivestreamEmbedIE,
-    YoutubePlaylistIE,
-    YoutubeRecommendedIE,
-    YoutubeSearchDateIE,
-    YoutubeSearchIE,
-    YoutubeSearchURLIE,
-    YoutubeMusicSearchURLIE,
-    YoutubeSubscriptionsIE,
-    YoutubeStoriesIE,
-    YoutubeTruncatedIDIE,
-    YoutubeTruncatedURLIE,
-    YoutubeYtBeIE,
-    YoutubeYtUserIE,
-    YoutubeWatchLaterIE,
-)
 from .zapiks import ZapiksIE
 from .zattoo import (
     BBVTVIE,

yt_dlp/extractor/arte.py

@@ -95,24 +95,24 @@ class ArteTVIE(ArteTVBaseIE):
 
     # all obtained by exhaustive testing
     _COUNTRIES_MAP = {
-        'DE_FR': {
+        'DE_FR': (
             'BL', 'DE', 'FR', 'GF', 'GP', 'MF', 'MQ', 'NC',
             'PF', 'PM', 'RE', 'WF', 'YT',
-        },
+        ),
         # with both of the below 'BE' sometimes works, sometimes doesn't
-        'EUR_DE_FR': {
+        'EUR_DE_FR': (
             'AT', 'BL', 'CH', 'DE', 'FR', 'GF', 'GP', 'LI',
             'MC', 'MF', 'MQ', 'NC', 'PF', 'PM', 'RE', 'WF',
             'YT',
-        },
+        ),
-        'SAT': {
+        'SAT': (
             'AD', 'AT', 'AX', 'BG', 'BL', 'CH', 'CY', 'CZ',
             'DE', 'DK', 'EE', 'ES', 'FI', 'FR', 'GB', 'GF',
             'GR', 'HR', 'HU', 'IE', 'IS', 'IT', 'KN', 'LI',
             'LT', 'LU', 'LV', 'MC', 'MF', 'MQ', 'MT', 'NC',
             'NL', 'NO', 'PF', 'PL', 'PM', 'PT', 'RE', 'RO',
             'SE', 'SI', 'SK', 'SM', 'VA', 'WF', 'YT',
-        },
+        ),
     }
 
     def _real_extract(self, url):

yt_dlp/extractor/bilibili.py

@@ -218,6 +218,9 @@ class BiliBiliIE(InfoExtractor):
 
         durl = traverse_obj(video_info, ('dash', 'video'))
         audios = traverse_obj(video_info, ('dash', 'audio')) or []
+        flac_audio = traverse_obj(video_info, ('dash', 'flac', 'audio'))
+        if flac_audio:
+            audios.append(flac_audio)
         entries = []
 
         RENDITIONS = ('qn=80&quality=80&type=', 'quality=2&type=mp4')
@@ -620,14 +623,15 @@ class BiliBiliSearchIE(SearchInfoExtractor):
                     'keyword': query,
                     'page': page_num,
                     'context': '',
-                    'order': 'pubdate',
                     'duration': 0,
                     'tids_2': '',
                     '__refresh__': 'true',
                     'search_type': 'video',
                     'tids': 0,
                     'highlight': 1,
-                })['data'].get('result') or []
+                })['data'].get('result')
+            if not videos:
+                break
             for video in videos:
                 yield self.url_result(video['arcurl'], 'BiliBili', str(video['aid']))
 

yt_dlp/extractor/bitchute.py

@@ -65,10 +65,12 @@ class BitChuteIE(InfoExtractor):
                 error = self._html_search_regex(r'<h1 class="page-title">([^<]+)</h1>', webpage, 'error', default='Cannot find video')
                 if error == 'Video Unavailable':
                     raise GeoRestrictedError(error)
-                raise ExtractorError(error)
+                raise ExtractorError(error, expected=True)
             formats = entries[0]['formats']
 
         self._check_formats(formats, video_id)
+        if not formats:
+            raise self.raise_no_formats('Video is unavailable', expected=True, video_id=video_id)
         self._sort_formats(formats)
 
         description = self._html_search_regex(

yt_dlp/extractor/common.py

@@ -480,6 +480,9 @@ class InfoExtractor:
     will be used by geo restriction bypass mechanism similarly
     to _GEO_COUNTRIES.
 
+    The _ENABLED attribute should be set to False for IEs that
+    are disabled by default and must be explicitly enabled.
+
     The _WORKING attribute should be set to False for broken IEs
     in order to warn the users and skip the tests.
     """
@@ -491,6 +494,7 @@ class InfoExtractor:
     _GEO_COUNTRIES = None
     _GEO_IP_BLOCKS = None
     _WORKING = True
+    _ENABLED = True
     _NETRC_MACHINE = None
     IE_DESC = None
     SEARCH_KEY = None
@@ -1689,7 +1693,7 @@ class InfoExtractor:
                      'order_free': ('webm', 'mp4', 'flv', '', 'none')},
             'aext': {'type': 'ordered', 'field': 'audio_ext',
                      'order': ('m4a', 'aac', 'mp3', 'ogg', 'opus', 'webm', '', 'none'),
-                     'order_free': ('opus', 'ogg', 'webm', 'm4a', 'mp3', 'aac', '', 'none')},
+                     'order_free': ('ogg', 'opus', 'webm', 'mp3', 'm4a', 'aac', '', 'none')},
             'hidden': {'visible': False, 'forced': True, 'type': 'extractor', 'max': -1000},
             'aud_or_vid': {'visible': False, 'forced': True, 'type': 'multiple',
                            'field': ('vcodec', 'acodec'),
@@ -1762,9 +1766,8 @@ class InfoExtractor:
             if field not in self.settings:
                 if key in ('forced', 'priority'):
                     return False
-                self.ydl.deprecation_warning(
+                self.ydl.deprecated_feature(f'Using arbitrary fields ({field}) for format sorting is '
-                    f'Using arbitrary fields ({field}) for format sorting is deprecated '
+                                            'deprecated and may be removed in a future version')
-                    'and may be removed in a future version')
                 self.settings[field] = {}
             propObj = self.settings[field]
             if key not in propObj:
@@ -1849,9 +1852,8 @@ class InfoExtractor:
                 if self._get_field_setting(field, 'type') == 'alias':
                     alias, field = field, self._get_field_setting(field, 'field')
                     if self._get_field_setting(alias, 'deprecated'):
-                        self.ydl.deprecation_warning(
+                        self.ydl.deprecated_feature(f'Format sorting alias {alias} is deprecated and may '
-                            f'Format sorting alias {alias} is deprecated '
+                                                    'be removed in a future version. Please use {field} instead')
-                            f'and may be removed in a future version. Please use {field} instead')
                 reverse = match.group('reverse') is not None
                 closest = match.group('separator') == '~'
                 limit_text = match.group('limit')
@@ -3258,7 +3260,7 @@ class InfoExtractor:
                 'subtitles': {},
             }
             media_attributes = extract_attributes(media_tag)
-            src = strip_or_none(media_attributes.get('src'))
+            src = strip_or_none(dict_get(media_attributes, ('src', 'data-video-src', 'data-src', 'data-source')))
             if src:
                 f = parse_content_type(media_attributes.get('type'))
                 _, formats = _media_formats(src, media_type, f)
@@ -3269,7 +3271,7 @@ class InfoExtractor:
                     s_attr = extract_attributes(source_tag)
                     # data-video-src and data-src are non standard but seen
                     # several times in the wild
-                    src = strip_or_none(dict_get(s_attr, ('src', 'data-video-src', 'data-src')))
+                    src = strip_or_none(dict_get(s_attr, ('src', 'data-video-src', 'data-src', 'data-source')))
                     if not src:
                         continue
                     f = parse_content_type(s_attr.get('type'))
@@ -3872,7 +3874,7 @@ class InfoExtractor:
     def _extract_from_webpage(cls, url, webpage):
         for embed_url in orderedSet(
                 cls._extract_embed_urls(url, webpage) or [], lazy=True):
-            yield cls.url_result(embed_url, cls)
+            yield cls.url_result(embed_url, None if cls._VALID_URL is False else cls)
 
     @classmethod
     def _extract_embed_urls(cls, url, webpage):
@@ -3941,3 +3943,12 @@ class SearchInfoExtractor(InfoExtractor):
     @classproperty
     def SEARCH_KEY(cls):
         return cls._SEARCH_KEY
+
+
+class UnsupportedURLIE(InfoExtractor):
+    _VALID_URL = '.*'
+    _ENABLED = False
+    IE_DESC = False
+
+    def _real_extract(self, url):
+        raise UnsupportedError(url)

yt_dlp/extractor/crunchyroll.py

@@ -720,15 +720,20 @@ class CrunchyrollBetaBaseIE(CrunchyrollBaseIE):
 
     def _get_params(self, lang):
         if not CrunchyrollBetaBaseIE.params:
+            if self._get_cookies(f'https://beta.crunchyroll.com/{lang}').get('etp_rt'):
+                grant_type, key = 'etp_rt_cookie', 'accountAuthClientId'
+            else:
+                grant_type, key = 'client_id', 'anonClientId'
+
             initial_state, app_config = self._get_beta_embedded_json(self._download_webpage(
                 f'https://beta.crunchyroll.com/{lang}', None, note='Retrieving main page'), None)
             api_domain = app_config['cxApiParams']['apiDomain']
-            basic_token = str(base64.b64encode(('%s:' % app_config['cxApiParams']['accountAuthClientId']).encode('ascii')), 'ascii')
+
             auth_response = self._download_json(
-                f'{api_domain}/auth/v1/token', None, note='Authenticating with cookie',
+                f'{api_domain}/auth/v1/token', None, note=f'Authenticating with grant_type={grant_type}',
                 headers={
-                    'Authorization': 'Basic ' + basic_token
+                    'Authorization': 'Basic ' + str(base64.b64encode(('%s:' % app_config['cxApiParams'][key]).encode('ascii')), 'ascii')
-                }, data='grant_type=etp_rt_cookie'.encode('ascii'))
+                }, data=f'grant_type={grant_type}'.encode('ascii'))
             policy_response = self._download_json(
                 f'{api_domain}/index/v2', None, note='Retrieving signed policy',
                 headers={
@@ -747,21 +752,6 @@ class CrunchyrollBetaBaseIE(CrunchyrollBaseIE):
             CrunchyrollBetaBaseIE.params = (api_domain, bucket, params)
         return CrunchyrollBetaBaseIE.params
 
-    def _redirect_from_beta(self, url, lang, internal_id, display_id, is_episode, iekey):
-        initial_state, app_config = self._get_beta_embedded_json(self._download_webpage(url, display_id), display_id)
-        content_data = initial_state['content']['byId'][internal_id]
-        if is_episode:
-            video_id = content_data['external_id'].split('.')[1]
-            series_id = content_data['episode_metadata']['series_slug_title']
-        else:
-            series_id = content_data['slug_title']
-        series_id = re.sub(r'-{2,}', '-', series_id)
-        url = f'https://www.crunchyroll.com/{lang}{series_id}'
-        if is_episode:
-            url = url + f'/{display_id}-{video_id}'
-        self.to_screen(f'{display_id}: Not logged in. Redirecting to non-beta site - {url}')
-        return self.url_result(url, iekey, display_id)
-
 
 class CrunchyrollBetaIE(CrunchyrollBetaBaseIE):
     IE_NAME = 'crunchyroll:beta'
@@ -800,10 +790,6 @@ class CrunchyrollBetaIE(CrunchyrollBetaBaseIE):
 
     def _real_extract(self, url):
         lang, internal_id, display_id = self._match_valid_url(url).group('lang', 'id', 'display_id')
-
-        if not self._get_cookies(url).get('etp_rt'):
-            return self._redirect_from_beta(url, lang, internal_id, display_id, True, CrunchyrollIE.ie_key())
-
         api_domain, bucket, params = self._get_params(lang)
 
         episode_response = self._download_json(
@@ -897,10 +883,6 @@ class CrunchyrollBetaShowIE(CrunchyrollBetaBaseIE):
 
     def _real_extract(self, url):
         lang, internal_id, display_id = self._match_valid_url(url).group('lang', 'id', 'display_id')
-
-        if not self._get_cookies(url).get('etp_rt'):
-            return self._redirect_from_beta(url, lang, internal_id, display_id, False, CrunchyrollShowPlaylistIE.ie_key())
-
         api_domain, bucket, params = self._get_params(lang)
 
         series_response = self._download_json(

yt_dlp/extractor/epoch.py

@@ -0,0 +1,46 @@
+from .common import InfoExtractor
+
+
+class EpochIE(InfoExtractor):
+    _VALID_URL = r'https?://www.theepochtimes\.com/[\w-]+_(?P<id>\d+).html'
+    _TESTS = [
+        {
+            'url': 'https://www.theepochtimes.com/they-can-do-audio-video-physical-surveillance-on-you-24h-365d-a-year-rex-lee-on-intrusive-apps_4661688.html',
+            'info_dict': {
+                'id': 'a3dd732c-4750-4bc8-8156-69180668bda1',
+                'ext': 'mp4',
+                'title': '‘They Can Do Audio, Video, Physical Surveillance on You 24H/365D a Year’: Rex Lee on Intrusive Apps',
+            }
+        },
+        {
+            'url': 'https://www.theepochtimes.com/the-communist-partys-cyberattacks-on-america-explained-rex-lee-talks-tech-hybrid-warfare_4342413.html',
+            'info_dict': {
+                'id': '276c7f46-3bbf-475d-9934-b9bbe827cf0a',
+                'ext': 'mp4',
+                'title': 'The Communist Party’s Cyberattacks on America Explained; Rex Lee Talks Tech Hybrid Warfare',
+            }
+        },
+        {
+            'url': 'https://www.theepochtimes.com/kash-patel-a-6-year-saga-of-government-corruption-from-russiagate-to-mar-a-lago_4690250.html',
+            'info_dict': {
+                'id': 'aa9ceecd-a127-453d-a2de-7153d6fd69b6',
+                'ext': 'mp4',
+                'title': 'Kash Patel: A ‘6-Year-Saga’ of Government Corruption, From Russiagate to Mar-a-Lago',
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        youmaker_video_id = self._search_regex(r'data-trailer="[\w-]+" data-id="([\w-]+)"', webpage, 'url')
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            f'http://vs1.youmaker.com/assets/{youmaker_video_id}/playlist.m3u8', video_id, 'mp4', m3u8_id='hls')
+
+        return {
+            'id': youmaker_video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            'title': self._html_extract_title(webpage)
+        }

yt_dlp/extractor/eurosport.py

@@ -0,0 +1,99 @@
+from .common import InfoExtractor
+from ..utils import traverse_obj
+
+
+class EurosportIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.eurosport\.com/\w+/[\w-]+/\d+/[\w-]+_(?P<id>vid\d+)'
+    _TESTS = [{
+        'url': 'https://www.eurosport.com/tennis/roland-garros/2022/highlights-rafael-nadal-brushes-aside-caper-ruud-to-win-record-extending-14th-french-open-title_vid1694147/video.shtml',
+        'info_dict': {
+            'id': '2480939',
+            'ext': 'mp4',
+            'title': 'Highlights: Rafael Nadal brushes aside Caper Ruud to win record-extending 14th French Open title',
+            'description': 'md5:b564db73ecfe4b14ebbd8e62a3692c76',
+            'thumbnail': 'https://imgresizer.eurosport.com/unsafe/1280x960/smart/filters:format(jpeg)/origin-imgresizer.eurosport.com/2022/06/05/3388285-69245968-2560-1440.png',
+            'duration': 195.0,
+            'display_id': 'vid1694147',
+            'timestamp': 1654446698,
+            'upload_date': '20220605',
+        }
+    }, {
+        'url': 'https://www.eurosport.com/tennis/roland-garros/2022/watch-the-top-five-shots-from-men-s-final-as-rafael-nadal-beats-casper-ruud-to-seal-14th-french-open_vid1694283/video.shtml',
+        'info_dict': {
+            'id': '2481254',
+            'ext': 'mp4',
+            'title': 'md5:149dcc5dfb38ab7352acc008cc9fb071',
+            'duration': 130.0,
+            'thumbnail': 'https://imgresizer.eurosport.com/unsafe/1280x960/smart/filters:format(jpeg)/origin-imgresizer.eurosport.com/2022/06/05/3388422-69248708-2560-1440.png',
+            'description': 'md5:a0c8a7f6b285e48ae8ddbe7aa85cfee6',
+            'display_id': 'vid1694283',
+            'timestamp': 1654456090,
+            'upload_date': '20220605',
+        }
+    }, {
+        # geo-fence but can bypassed by xff
+        'url': 'https://www.eurosport.com/cycling/tour-de-france-femmes/2022/incredible-ride-marlen-reusser-storms-to-stage-4-win-at-tour-de-france-femmes_vid1722221/video.shtml',
+        'info_dict': {
+            'id': '2582552',
+            'ext': 'mp4',
+            'title': '‘Incredible ride!’ - Marlen Reusser storms to Stage 4 win at Tour de France Femmes',
+            'duration': 188.0,
+            'display_id': 'vid1722221',
+            'timestamp': 1658936167,
+            'thumbnail': 'https://imgresizer.eurosport.com/unsafe/1280x960/smart/filters:format(jpeg)/origin-imgresizer.eurosport.com/2022/07/27/3423347-69852108-2560-1440.jpg',
+            'description': 'md5:32bbe3a773ac132c57fb1e8cca4b7c71',
+            'upload_date': '20220727',
+        }
+    }]
+
+    _TOKEN = None
+
+    # actually defined in https://netsport.eurosport.io/?variables={"databaseId":<databaseId>,"playoutType":"VDP"}&extensions={"persistedQuery":{"version":1 ..
+    # but this method require to get sha256 hash
+    _GEO_COUNTRIES = ['DE', 'NL', 'EU', 'IT', 'FR']  # Not complete list but it should work
+
+    def _real_initialize(self):
+        if EurosportIE._TOKEN is None:
+            EurosportIE._TOKEN = self._download_json(
+                'https://eu3-prod-direct.eurosport.com/token?realm=eurosport', None,
+                'Trying to get token')['data']['attributes']['token']
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        json_data = self._download_json(
+            f'https://eu3-prod-direct.eurosport.com/playback/v2/videoPlaybackInfo/sourceSystemId/eurosport-{display_id}',
+            display_id, query={'usePreAuth': True}, headers={'Authorization': f'Bearer {EurosportIE._TOKEN}'})['data']
+
+        json_ld_data = self._search_json_ld(webpage, display_id)
+
+        formats, subtitles = [], {}
+        for stream_type in json_data['attributes']['streaming']:
+            if stream_type == 'hls':
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id, ext='mp4')
+            elif stream_type == 'dash':
+                fmts, subs = self._extract_mpd_formats_and_subtitles(
+                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id)
+            elif stream_type == 'mss':
+                fmts, subs = self._extract_ism_formats_and_subtitles(
+                    traverse_obj(json_data, ('attributes', 'streaming', stream_type, 'url')), display_id)
+
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': json_data['id'],
+            'title': json_ld_data.get('title') or self._og_search_title(webpage),
+            'display_id': display_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            'thumbnails': json_ld_data.get('thumbnails'),
+            'description': (json_ld_data.get('description')
+                            or self._html_search_meta(['og:description', 'description'], webpage)),
+            'duration': json_ld_data.get('duration'),
+            'timestamp': json_ld_data.get('timestamp'),
+        }

yt_dlp/extractor/generic.py

@@ -3,7 +3,6 @@ import re
 import urllib.parse
 import xml.etree.ElementTree
 
-from . import gen_extractor_classes
 from .common import InfoExtractor  # isort: split
 from .brightcove import BrightcoveLegacyIE, BrightcoveNewIE
 from .commonprotocols import RtmpIE
@@ -26,6 +25,7 @@ from ..utils import (
     parse_resolution,
     smuggle_url,
     str_or_none,
+    traverse_obj,
     try_call,
     unescapeHTML,
     unified_timestamp,
@@ -2805,7 +2805,7 @@ class GenericIE(InfoExtractor):
 
         self._downloader.write_debug('Looking for embeds')
         embeds = []
-        for ie in gen_extractor_classes():
+        for ie in self._downloader._ies.values():
             gen = ie.extract_from_webpage(self._downloader, url, webpage)
             current_embeds = []
             try:
@@ -2840,8 +2840,9 @@ class GenericIE(InfoExtractor):
             try:
                 info = self._parse_jwplayer_data(
                     jwplayer_data, video_id, require_title=False, base_url=url)
-                self.report_detected('JW Player data')
+                if traverse_obj(info, 'formats', ('entries', ..., 'formats')):
-                return merge_dicts(info, info_dict)
+                    self.report_detected('JW Player data')
+                    return merge_dicts(info, info_dict)
             except ExtractorError:
                 # See https://github.com/ytdl-org/youtube-dl/pull/16735
                 pass

yt_dlp/extractor/huya.py

@@ -6,7 +6,6 @@ from ..compat import compat_urlparse, compat_b64decode
 from ..utils import (
     ExtractorError,
     int_or_none,
-    js_to_json,
     str_or_none,
     try_get,
     unescapeHTML,
@@ -55,11 +54,7 @@ class HuyaLiveIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id=video_id)
-        json_stream = self._search_regex(r'"stream":\s+"([a-zA-Z0-9+=/]+)"', webpage, 'stream', default=None)
+        stream_data = self._search_json(r'stream:\s+', webpage, 'stream', video_id=video_id, default=None)
-        if not json_stream:
-            raise ExtractorError('Video is offline', expected=True)
-        stream_data = self._parse_json(compat_b64decode(json_stream).decode(), video_id=video_id,
-                                       transform_source=js_to_json)
         room_info = try_get(stream_data, lambda x: x['data'][0]['gameLiveInfo'])
         if not room_info:
             raise ExtractorError('Can not extract the room info', expected=True)
@@ -67,6 +62,8 @@ class HuyaLiveIE(InfoExtractor):
         screen_type = room_info.get('screenType')
         live_source_type = room_info.get('liveSourceType')
         stream_info_list = stream_data['data'][0]['gameStreamInfoList']
+        if not stream_info_list:
+            raise ExtractorError('Video is offline', expected=True)
         formats = []
         for stream_info in stream_info_list:
             stream_url = stream_info.get('sFlvUrl')

yt_dlp/extractor/islamchannel.py

@@ -0,0 +1,82 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import traverse_obj, urljoin
+
+
+class IslamChannelIE(InfoExtractor):
+    _VALID_URL = r'https?://watch\.islamchannel\.tv/watch/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://watch.islamchannel.tv/watch/38604310',
+        'info_dict': {
+            'id': '38604310',
+            'title': 'Omar - Young Omar',
+            'description': 'md5:5cc7ddecef064ea7afe52eb5e0e33b55',
+            'thumbnail': r're:https?://.+',
+            'ext': 'mp4',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        thumbnail = self._search_regex(
+            r'data-poster="([^"]+)"', webpage, 'data poster', fatal=False) or \
+            self._html_search_meta(('og:image', 'twitter:image'), webpage)
+
+        headers = {
+            'Token': self._search_regex(r'data-token="([^"]+)"', webpage, 'data token'),
+            'Token-Expiry': self._search_regex(r'data-expiry="([^"]+)"', webpage, 'data expiry'),
+            'Uvid': video_id,
+        }
+        show_stream = self._download_json(
+            f'https://v2-streams-elb.simplestreamcdn.com/api/show/stream/{video_id}', video_id,
+            query={
+                'key': self._search_regex(r'data-key="([^"]+)"', webpage, 'data key'),
+                'platform': 'chrome',
+            }, headers=headers)
+        # TODO: show_stream['stream'] and show_stream['drm'] may contain something interesting
+        streams = self._download_json(
+            traverse_obj(show_stream, ('response', 'tokenization', 'url')), video_id,
+            headers=headers)
+        formats, subs = self._extract_m3u8_formats_and_subtitles(traverse_obj(streams, ('Streams', 'Adaptive')), video_id, 'mp4')
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._html_search_meta(('og:title', 'twitter:title'), webpage),
+            'description': self._html_search_meta(('og:description', 'twitter:description', 'description'), webpage),
+            'formats': formats,
+            'subtitles': subs,
+            'thumbnails': [{
+                'id': 'unscaled',
+                'url': thumbnail.split('?')[0],
+                'ext': 'jpg',
+                'preference': 2,
+            }, {
+                'id': 'orig',
+                'url': thumbnail,
+                'ext': 'jpg',
+                'preference': 1,
+            }] if thumbnail else None,
+        }
+
+
+class IslamChannelSeriesIE(InfoExtractor):
+    _VALID_URL = r'https?://watch\.islamchannel\.tv/series/(?P<id>[a-f\d-]+)'
+    _TESTS = [{
+        'url': 'https://watch.islamchannel.tv/series/a6cccef3-3ef1-11eb-bc19-06b69c2357cd',
+        'info_dict': {
+            'id': 'a6cccef3-3ef1-11eb-bc19-06b69c2357cd',
+        },
+        'playlist_mincount': 31,
+    }]
+
+    def _real_extract(self, url):
+        pl_id = self._match_id(url)
+        webpage = self._download_webpage(url, pl_id)
+
+        return self.playlist_from_matches(
+            re.finditer(r'<a\s+href="(/watch/\d+)"[^>]+?data-video-type="show">', webpage),
+            pl_id, getter=lambda x: urljoin(url, x.group(1)), ie=IslamChannelIE)

yt_dlp/extractor/medaltv.py

@@ -8,15 +8,33 @@ from ..utils import (
     float_or_none,
     int_or_none,
     str_or_none,
-    try_get,
+    traverse_obj,
 )
 
 
 class MedalTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?medal\.tv/clips/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?medal\.tv/(?P<path>games/[^/?#&]+/clips)/(?P<id>[^/?#&]+)'
     _TESTS = [{
-        'url': 'https://medal.tv/clips/2mA60jWAGQCBH',
+        'url': 'https://medal.tv/games/valorant/clips/jTBFnLKdLy15K',
-        'md5': '7b07b064331b1cf9e8e5c52a06ae68fa',
+        'md5': '6930f8972914b6b9fdc2bb3918098ba0',
+        'info_dict': {
+            'id': 'jTBFnLKdLy15K',
+            'ext': 'mp4',
+            'title': "Mornu's clutch",
+            'description': '',
+            'uploader': 'Aciel',
+            'timestamp': 1651628243,
+            'upload_date': '20220504',
+            'uploader_id': '19335460',
+            'uploader_url': 'https://medal.tv/users/19335460',
+            'comment_count': int,
+            'view_count': int,
+            'like_count': int,
+            'duration': 13,
+        }
+    }, {
+        'url': 'https://medal.tv/games/cod%20cold%20war/clips/2mA60jWAGQCBH',
+        'md5': '3d19d426fe0b2d91c26e412684e66a06',
         'info_dict': {
             'id': '2mA60jWAGQCBH',
             'ext': 'mp4',
@@ -26,9 +44,15 @@ class MedalTVIE(InfoExtractor):
             'timestamp': 1603165266,
             'upload_date': '20201020',
             'uploader_id': '10619174',
+            'thumbnail': 'https://cdn.medal.tv/10619174/thumbnail-34934644-720p.jpg?t=1080p&c=202042&missing',
+            'uploader_url': 'https://medal.tv/users/10619174',
+            'comment_count': int,
+            'view_count': int,
+            'like_count': int,
+            'duration': 23,
         }
     }, {
-        'url': 'https://medal.tv/clips/2um24TWdty0NA',
+        'url': 'https://medal.tv/games/cod%20cold%20war/clips/2um24TWdty0NA',
         'md5': 'b6dc76b78195fff0b4f8bf4a33ec2148',
         'info_dict': {
             'id': '2um24TWdty0NA',
@@ -39,25 +63,42 @@ class MedalTVIE(InfoExtractor):
             'timestamp': 1605580939,
             'upload_date': '20201117',
             'uploader_id': '5156321',
+            'thumbnail': 'https://cdn.medal.tv/5156321/thumbnail-36787208-360p.jpg?t=1080p&c=202046&missing',
+            'uploader_url': 'https://medal.tv/users/5156321',
+            'comment_count': int,
+            'view_count': int,
+            'like_count': int,
+            'duration': 9,
         }
     }, {
-        'url': 'https://medal.tv/clips/37rMeFpryCC-9',
+        'url': 'https://medal.tv/games/valorant/clips/37rMeFpryCC-9',
         'only_matching': True,
     }, {
-        'url': 'https://medal.tv/clips/2WRj40tpY_EU9',
+        'url': 'https://medal.tv/games/valorant/clips/2WRj40tpY_EU9',
         'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        path = self._match_valid_url(url).group('path')
+
         webpage = self._download_webpage(url, video_id)
 
-        hydration_data = self._parse_json(self._search_regex(
+        next_data = self._search_json(
-            r'<script[^>]*>\s*(?:var\s*)?hydrationData\s*=\s*({.+?})\s*</script>',
+            '<script[^>]*__NEXT_DATA__[^>]*>', webpage,
-            webpage, 'hydration data', default='{}'), video_id)
+            'next data', video_id, end_pattern='</script>', fatal=False)
 
-        clip = try_get(
+        build_id = next_data.get('buildId')
-            hydration_data, lambda x: x['clips'][video_id], dict) or {}
+        if not build_id:
+            raise ExtractorError(
+                'Could not find build ID.', video_id=video_id)
+
+        locale = next_data.get('locale', 'en')
+
+        api_response = self._download_json(
+            f'https://medal.tv/_next/data/{build_id}/{locale}/{path}/{video_id}.json', video_id)
+
+        clip = traverse_obj(api_response, ('pageProps', 'clip')) or {}
         if not clip:
             raise ExtractorError(
                 'Could not find video information.', video_id=video_id)
@@ -113,9 +154,8 @@ class MedalTVIE(InfoExtractor):
 
         # Necessary because the id of the author is not known in advance.
         # Won't raise an issue if no profile can be found as this is optional.
-        author = try_get(
+        author = traverse_obj(api_response, ('pageProps', 'profile')) or {}
-            hydration_data, lambda x: list(x['profiles'].values())[0], dict) or {}
+        author_id = str_or_none(author.get('userId'))
-        author_id = str_or_none(author.get('id'))
         author_url = format_field(author_id, None, 'https://medal.tv/users/%s')
 
         return {

yt_dlp/extractor/mediaset.py

@@ -172,31 +172,27 @@ class MediasetIE(ThePlatformBaseIE):
     }]
 
     def _extract_from_webpage(self, url, webpage):
-        def _qs(url):
-            return parse_qs(url)
-
         def _program_guid(qs):
             return qs.get('programGuid', [None])[0]
 
-        entries = []
         for mobj in re.finditer(
                 r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml.*?)\1',
                 webpage):
             embed_url = mobj.group('url')
-            embed_qs = _qs(embed_url)
+            embed_qs = parse_qs(embed_url)
             program_guid = _program_guid(embed_qs)
             if program_guid:
-                entries.append(embed_url)
+                yield self.url_result(embed_url)
                 continue
+
             video_id = embed_qs.get('id', [None])[0]
             if not video_id:
                 continue
             urlh = self._request_webpage(embed_url, video_id, note='Following embed URL redirect')
             embed_url = urlh.geturl()
-            program_guid = _program_guid(_qs(embed_url))
+            program_guid = _program_guid(parse_qs(embed_url))
             if program_guid:
-                entries.append(embed_url)
+                yield self.url_result(embed_url)
-        return entries
 
     def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
         for video in smil.findall(self._xpath_ns('.//video', namespace)):

yt_dlp/extractor/mixcloud.py

@@ -159,6 +159,7 @@ class MixcloudIE(MixcloudBaseIE):
                 formats.append({
                     'format_id': 'http',
                     'url': decrypted,
+                    'vcodec': 'none',
                     'downloader_options': {
                         # Mixcloud starts throttling at >~5M
                         'http_chunk_size': 5242880,

yt_dlp/extractor/newspicks.py

@@ -0,0 +1,54 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class NewsPicksIE(InfoExtractor):
+    _VALID_URL = r'https://newspicks\.com/movie-series/(?P<channel_id>\d+)\?movieId=(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'https://newspicks.com/movie-series/11?movieId=1813',
+        'info_dict': {
+            'id': '1813',
+            'title': '日本の課題を破壊せよ【ゲスト：成田悠輔】',
+            'description': 'md5:09397aad46d6ded6487ff13f138acadf',
+            'channel': 'HORIE ONE',
+            'channel_id': '11',
+            'release_date': '20220117',
+            'thumbnail': r're:https://.+jpg',
+            'ext': 'mp4',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id, channel_id = self._match_valid_url(url).group('id', 'channel_id')
+        webpage = self._download_webpage(url, video_id)
+        entries = self._parse_html5_media_entries(
+            url, webpage.replace('movie-for-pc', 'movie'), video_id, 'hls')
+        if not entries:
+            raise ExtractorError('No HTML5 media elements found')
+        info = entries[0]
+        self._sort_formats(info['formats'])
+
+        title = self._html_search_meta('og:title', webpage, fatal=False)
+        description = self._html_search_meta(
+            ('og:description', 'twitter:title'), webpage, fatal=False)
+        channel = self._html_search_regex(
+            r'value="11".+?<div\s+class="title">(.+?)</div', webpage, 'channel name', fatal=False)
+        if not title or not channel:
+            title, channel = re.split(r'\s*|\s*', self._html_extract_title(webpage))
+
+        release_date = self._search_regex(
+            r'<span\s+class="on-air-date">\s*(\d+)年(\d+)月(\d+)日\s*</span>',
+            webpage, 'release date', fatal=False, group=(1, 2, 3))
+
+        info.update({
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'channel': channel,
+            'channel_id': channel_id,
+            'release_date': ('%04d%02d%02d' % tuple(map(int, release_date))) if release_date else None,
+        })
+        return info

yt_dlp/extractor/openload.py

@@ -52,6 +52,8 @@ class PhantomJSwrapper:
     This class is experimental.
     """
 
+    INSTALL_HINT = 'Please download it from https://phantomjs.org/download.html'
+
     _BASE_JS = R'''
         phantom.onError = function(msg, trace) {{
           var msgStack = ['PHANTOM ERROR: ' + msg];
@@ -110,8 +112,7 @@ class PhantomJSwrapper:
 
         self.exe = check_executable('phantomjs', ['-v'])
         if not self.exe:
-            raise ExtractorError(
+            raise ExtractorError(f'PhantomJS not found, {self.INSTALL_HINT}', expected=True)
-                'PhantomJS not found, Please download it from https://phantomjs.org/download.html', expected=True)
 
         self.extractor = extractor
 
@@ -219,7 +220,7 @@ class PhantomJSwrapper:
 
         return html, stdout
 
-    def execute(self, jscode, video_id=None, note='Executing JS'):
+    def execute(self, jscode, video_id=None, *, note='Executing JS'):
         """Execute JS and return stdout"""
         if 'phantom.exit();' not in jscode:
             jscode += ';\nphantom.exit();'
@@ -231,8 +232,12 @@ class PhantomJSwrapper:
 
         cmd = [self.exe, '--ssl-protocol=any', self._TMP_FILES['script'].name]
         self.extractor.write_debug(f'PhantomJS command line: {shell_quote(cmd)}')
-        stdout, stderr, returncode = Popen.run(cmd, text=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        try:
+            stdout, stderr, returncode = Popen.run(cmd, timeout=self.options['timeout'] / 1000,
+                                                   text=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        except Exception as e:
+            raise ExtractorError(f'{note} failed: Unable to run PhantomJS binary', cause=e)
         if returncode:
-            raise ExtractorError(f'Executing JS failed:\n{stderr.strip()}')
+            raise ExtractorError(f'{note} failed with returncode {returncode}:\n{stderr.strip()}')
 
         return stdout

yt_dlp/extractor/redbee.py

@@ -11,6 +11,7 @@ from ..utils import (
     int_or_none,
     strip_or_none,
     traverse_obj,
+    try_call,
     unified_timestamp,
 )
 
@@ -255,7 +256,7 @@ class RTBFIE(RedBeeBaseIE):
         if not login_token:
             self.raise_login_required()
 
-        session_jwt = self._download_json(
+        session_jwt = try_call(lambda: self._get_cookies(url)['rtbf_jwt'].value) or self._download_json(
             'https://login.rtbf.be/accounts.getJWT', media_id, query={
                 'login_token': login_token.value,
                 'APIKey': self._GIGYA_API_KEY,

yt_dlp/extractor/screencastomatic.py

@@ -1,10 +1,12 @@
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     get_element_by_class,
     int_or_none,
     remove_start,
     strip_or_none,
     unified_strdate,
+    urlencode_postdata,
 )
 
 
@@ -34,6 +36,28 @@ class ScreencastOMaticIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(
             'https://screencast-o-matic.com/player/' + video_id, video_id)
+
+        if (self._html_extract_title(webpage) == 'Protected Content'
+                or 'This video is private and requires a password' in webpage):
+            password = self.get_param('videopassword')
+
+            if not password:
+                raise ExtractorError('Password protected video, use --video-password <password>', expected=True)
+
+            form = self._search_regex(
+                r'(?is)<form[^>]*>(?P<form>.+?)</form>', webpage, 'login form', group='form')
+            form_data = self._hidden_inputs(form)
+            form_data.update({
+                'scPassword': password,
+            })
+
+            webpage = self._download_webpage(
+                'https://screencast-o-matic.com/player/password', video_id, 'Logging in',
+                data=urlencode_postdata(form_data))
+
+            if '<small class="text-danger">Invalid password</small>' in webpage:
+                raise ExtractorError('Unable to login: Invalid password', expected=True)
+
         info = self._parse_html5_media_entries(url, webpage, video_id)[0]
         info.update({
             'id': video_id,

yt_dlp/extractor/stripchat.py

@@ -29,9 +29,7 @@ class StripchatIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(
+        webpage = self._download_webpage(url, video_id, headers=self.geo_verification_headers())
-            'https://stripchat.com/%s/' % video_id, video_id,
-            headers=self.geo_verification_headers())
 
         data = self._parse_json(
             self._search_regex(

yt_dlp/extractor/tencent.py

@@ -0,0 +1,369 @@
+import functools
+import random
+import re
+import string
+import time
+
+from .common import InfoExtractor
+from ..aes import aes_cbc_encrypt_bytes
+from ..utils import (
+    ExtractorError,
+    determine_ext,
+    int_or_none,
+    js_to_json,
+    traverse_obj,
+    urljoin,
+)
+
+
+class TencentBaseIE(InfoExtractor):
+    """Subclasses must set _API_URL, _APP_VERSION, _PLATFORM, _HOST, _REFERER"""
+
+    def _get_ckey(self, video_id, url, guid):
+        ua = self.get_param('http_headers')['User-Agent']
+
+        payload = (f'{video_id}|{int(time.time())}|mg3c3b04ba|{self._APP_VERSION}|{guid}|'
+                   f'{self._PLATFORM}|{url[:48]}|{ua.lower()[:48]}||Mozilla|Netscape|Windows x86_64|00|')
+
+        return aes_cbc_encrypt_bytes(
+            bytes(f'|{sum(map(ord, payload))}|{payload}', 'utf-8'),
+            b'Ok\xda\xa3\x9e/\x8c\xb0\x7f^r-\x9e\xde\xf3\x14',
+            b'\x01PJ\xf3V\xe6\x19\xcf.B\xbb\xa6\x8c?p\xf9',
+            padding_mode='whitespace').hex().upper()
+
+    def _get_video_api_response(self, video_url, video_id, series_id, subtitle_format, video_format, video_quality):
+        guid = ''.join([random.choice(string.digits + string.ascii_lowercase) for _ in range(16)])
+        ckey = self._get_ckey(video_id, video_url, guid)
+        query = {
+            'vid': video_id,
+            'cid': series_id,
+            'cKey': ckey,
+            'encryptVer': '8.1',
+            'spcaptiontype': '1' if subtitle_format == 'vtt' else '0',
+            'sphls': '2' if video_format == 'hls' else '0',
+            'dtype': '3' if video_format == 'hls' else '0',
+            'defn': video_quality,
+            'spsrt': '2',  # Enable subtitles
+            'sphttps': '1',  # Enable HTTPS
+            'otype': 'json',
+            'spwm': '1',
+            # For SHD
+            'host': self._HOST,
+            'referer': self._REFERER,
+            'ehost': video_url,
+            'appVer': self._APP_VERSION,
+            'platform': self._PLATFORM,
+            # For VQQ
+            'guid': guid,
+            'flowid': ''.join(random.choice(string.digits + string.ascii_lowercase) for _ in range(32)),
+        }
+
+        return self._search_json(r'QZOutputJson=', self._download_webpage(
+            self._API_URL, video_id, query=query), 'api_response', video_id)
+
+    def _extract_video_formats_and_subtitles(self, api_response, video_id):
+        video_response = api_response['vl']['vi'][0]
+        video_width, video_height = video_response.get('vw'), video_response.get('vh')
+
+        formats, subtitles = [], {}
+        for video_format in video_response['ul']['ui']:
+            if video_format.get('hls'):
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                    video_format['url'] + video_format['hls']['pt'], video_id, 'mp4', fatal=False)
+                for f in fmts:
+                    f.update({'width': video_width, 'height': video_height})
+
+                formats.extend(fmts)
+                self._merge_subtitles(subs, target=subtitles)
+            else:
+                formats.append({
+                    'url': f'{video_format["url"]}{video_response["fn"]}?vkey={video_response["fvkey"]}',
+                    'width': video_width,
+                    'height': video_height,
+                    'ext': 'mp4',
+                })
+
+        return formats, subtitles
+
+    def _extract_video_native_subtitles(self, api_response, subtitles_format):
+        subtitles = {}
+        for subtitle in traverse_obj(api_response, ('sfl', 'fi')) or ():
+            subtitles.setdefault(subtitle['lang'].lower(), []).append({
+                'url': subtitle['url'],
+                'ext': subtitles_format,
+                'protocol': 'm3u8_native' if determine_ext(subtitle['url']) == 'm3u8' else 'http',
+            })
+
+        return subtitles
+
+    def _extract_all_video_formats_and_subtitles(self, url, video_id, series_id):
+        formats, subtitles = [], {}
+        for video_format, subtitle_format, video_quality in (
+                # '': 480p, 'shd': 720p, 'fhd': 1080p
+                ('mp4', 'srt', ''), ('hls', 'vtt', 'shd'), ('hls', 'vtt', 'fhd')):
+            api_response = self._get_video_api_response(
+                url, video_id, series_id, subtitle_format, video_format, video_quality)
+
+            if api_response.get('em') != 0 and api_response.get('exem') != 0:
+                if '您所在区域暂无此内容版权' in api_response.get('msg'):
+                    self.raise_geo_restricted()
+                raise ExtractorError(f'Tencent said: {api_response.get("msg")}')
+
+            fmts, subs = self._extract_video_formats_and_subtitles(api_response, video_id)
+            native_subtitles = self._extract_video_native_subtitles(api_response, subtitle_format)
+
+            formats.extend(fmts)
+            self._merge_subtitles(subs, native_subtitles, target=subtitles)
+
+        self._sort_formats(formats)
+        return formats, subtitles
+
+    def _get_clean_title(self, title):
+        return re.sub(
+            r'\s*[_\-]\s*(?:Watch online|腾讯视频|(?:高清)?1080P在线观看平台).*?$',
+            '', title or '').strip() or None
+
+
+class VQQBaseIE(TencentBaseIE):
+    _VALID_URL_BASE = r'https?://v\.qq\.com'
+
+    _API_URL = 'https://h5vv6.video.qq.com/getvinfo'
+    _APP_VERSION = '3.5.57'
+    _PLATFORM = '10901'
+    _HOST = 'v.qq.com'
+    _REFERER = 'v.qq.com'
+
+    def _get_webpage_metadata(self, webpage, video_id):
+        return self._parse_json(
+            self._search_regex(
+                r'(?s)<script[^>]*>[^<]*window\.__pinia\s*=\s*([^<]+)</script>',
+                webpage, 'pinia data', fatal=False),
+            video_id, transform_source=js_to_json, fatal=False)
+
+
+class VQQVideoIE(VQQBaseIE):
+    IE_NAME = 'vqq:video'
+    _VALID_URL = VQQBaseIE._VALID_URL_BASE + r'/x/(?:page|cover/(?P<series_id>\w+))/(?P<id>\w+)'
+
+    _TESTS = [{
+        'url': 'https://v.qq.com/x/page/q326831cny0.html',
+        'md5': '826ef93682df09e3deac4a6e6e8cdb6e',
+        'info_dict': {
+            'id': 'q326831cny0',
+            'ext': 'mp4',
+            'title': '我是选手：雷霆裂阵，终极时刻',
+            'description': 'md5:e7ed70be89244017dac2a835a10aeb1e',
+            'thumbnail': r're:^https?://[^?#]+q326831cny0',
+        },
+    }, {
+        'url': 'https://v.qq.com/x/page/o3013za7cse.html',
+        'md5': 'b91cbbeada22ef8cc4b06df53e36fa21',
+        'info_dict': {
+            'id': 'o3013za7cse',
+            'ext': 'mp4',
+            'title': '欧阳娜娜VLOG',
+            'description': 'md5:29fe847497a98e04a8c3826e499edd2e',
+            'thumbnail': r're:^https?://[^?#]+o3013za7cse',
+        },
+    }, {
+        'url': 'https://v.qq.com/x/cover/7ce5noezvafma27/a00269ix3l8.html',
+        'md5': '71459c5375c617c265a22f083facce67',
+        'info_dict': {
+            'id': 'a00269ix3l8',
+            'ext': 'mp4',
+            'title': '鸡毛飞上天 第01集',
+            'description': 'md5:8cae3534327315b3872fbef5e51b5c5b',
+            'thumbnail': r're:^https?://[^?#]+7ce5noezvafma27',
+            'series': '鸡毛飞上天',
+        },
+    }, {
+        'url': 'https://v.qq.com/x/cover/mzc00200p29k31e/s0043cwsgj0.html',
+        'md5': '96b9fd4a189fdd4078c111f21d7ac1bc',
+        'info_dict': {
+            'id': 's0043cwsgj0',
+            'ext': 'mp4',
+            'title': '第1集：如何快乐吃糖？',
+            'description': 'md5:1d8c3a0b8729ae3827fa5b2d3ebd5213',
+            'thumbnail': r're:^https?://[^?#]+s0043cwsgj0',
+            'series': '青年理工工作者生活研究所',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id, series_id = self._match_valid_url(url).group('id', 'series_id')
+        webpage = self._download_webpage(url, video_id)
+        webpage_metadata = self._get_webpage_metadata(webpage, video_id)
+
+        formats, subtitles = self._extract_all_video_formats_and_subtitles(url, video_id, series_id)
+        return {
+            'id': video_id,
+            'title': self._get_clean_title(self._og_search_title(webpage)
+                                           or traverse_obj(webpage_metadata, ('global', 'videoInfo', 'title'))),
+            'description': (self._og_search_description(webpage)
+                            or traverse_obj(webpage_metadata, ('global', 'videoInfo', 'desc'))),
+            'formats': formats,
+            'subtitles': subtitles,
+            'thumbnail': (self._og_search_thumbnail(webpage)
+                          or traverse_obj(webpage_metadata, ('global', 'videoInfo', 'pic160x90'))),
+            'series': traverse_obj(webpage_metadata, ('global', 'coverInfo', 'title')),
+        }
+
+
+class VQQSeriesIE(VQQBaseIE):
+    IE_NAME = 'vqq:series'
+    _VALID_URL = VQQBaseIE._VALID_URL_BASE + r'/x/cover/(?P<id>\w+)\.html/?(?:[?#]|$)'
+
+    _TESTS = [{
+        'url': 'https://v.qq.com/x/cover/7ce5noezvafma27.html',
+        'info_dict': {
+            'id': '7ce5noezvafma27',
+            'title': '鸡毛飞上天',
+            'description': 'md5:8cae3534327315b3872fbef5e51b5c5b',
+        },
+        'playlist_count': 55,
+    }, {
+        'url': 'https://v.qq.com/x/cover/oshd7r0vy9sfq8e.html',
+        'info_dict': {
+            'id': 'oshd7r0vy9sfq8e',
+            'title': '恋爱细胞2',
+            'description': 'md5:9d8a2245679f71ca828534b0f95d2a03',
+        },
+        'playlist_count': 12,
+    }]
+
+    def _real_extract(self, url):
+        series_id = self._match_id(url)
+        webpage = self._download_webpage(url, series_id)
+        webpage_metadata = self._get_webpage_metadata(webpage, series_id)
+
+        episode_paths = [f'/x/cover/{series_id}/{video_id}.html' for video_id in re.findall(
+            r'<div[^>]+data-vid="(?P<video_id>[^"]+)"[^>]+class="[^"]+episode-item-rect--number',
+            webpage)]
+
+        return self.playlist_from_matches(
+            episode_paths, series_id, ie=VQQVideoIE, getter=functools.partial(urljoin, url),
+            title=self._get_clean_title(traverse_obj(webpage_metadata, ('coverInfo', 'title'))
+                                        or self._og_search_title(webpage)),
+            description=(traverse_obj(webpage_metadata, ('coverInfo', 'description'))
+                         or self._og_search_description(webpage)))
+
+
+class WeTvBaseIE(TencentBaseIE):
+    _VALID_URL_BASE = r'https?://(?:www\.)?wetv\.vip/(?:[^?#]+/)?play'
+
+    _API_URL = 'https://play.wetv.vip/getvinfo'
+    _APP_VERSION = '3.5.57'
+    _PLATFORM = '4830201'
+    _HOST = 'wetv.vip'
+    _REFERER = 'wetv.vip'
+
+    def _get_webpage_metadata(self, webpage, video_id):
+        return self._parse_json(
+            traverse_obj(self._search_nextjs_data(webpage, video_id), ('props', 'pageProps', 'data')),
+            video_id, fatal=False)
+
+
+class WeTvEpisodeIE(WeTvBaseIE):
+    IE_NAME = 'wetv:episode'
+    _VALID_URL = WeTvBaseIE._VALID_URL_BASE + r'/(?P<series_id>\w+)(?:-[^?#]+)?/(?P<id>\w+)(?:-[^?#]+)?'
+
+    _TESTS = [{
+        'url': 'https://wetv.vip/en/play/air11ooo2rdsdi3-Cute-Programmer/v0040pr89t9-EP1-Cute-Programmer',
+        'md5': '0c70fdfaa5011ab022eebc598e64bbbe',
+        'info_dict': {
+            'id': 'v0040pr89t9',
+            'ext': 'mp4',
+            'title': 'EP1: Cute Programmer',
+            'description': 'md5:e87beab3bf9f392d6b9e541a63286343',
+            'thumbnail': r're:^https?://[^?#]+air11ooo2rdsdi3',
+            'series': 'Cute Programmer',
+            'episode': 'Episode 1',
+            'episode_number': 1,
+            'duration': 2835,
+        },
+    }, {
+        'url': 'https://wetv.vip/en/play/u37kgfnfzs73kiu/p0039b9nvik',
+        'md5': '3b3c15ca4b9a158d8d28d5aa9d7c0a49',
+        'info_dict': {
+            'id': 'p0039b9nvik',
+            'ext': 'mp4',
+            'title': 'EP1: You Are My Glory',
+            'description': 'md5:831363a4c3b4d7615e1f3854be3a123b',
+            'thumbnail': r're:^https?://[^?#]+u37kgfnfzs73kiu',
+            'series': 'You Are My Glory',
+            'episode': 'Episode 1',
+            'episode_number': 1,
+            'duration': 2454,
+        },
+    }, {
+        'url': 'https://wetv.vip/en/play/lcxgwod5hapghvw-WeTV-PICK-A-BOO/i0042y00lxp-Zhao-Lusi-Describes-The-First-Experiences-She-Had-In-Who-Rules-The-World-%7C-WeTV-PICK-A-BOO',
+        'md5': '71133f5c2d5d6cad3427e1b010488280',
+        'info_dict': {
+            'id': 'i0042y00lxp',
+            'ext': 'mp4',
+            'title': 'md5:f7a0857dbe5fbbe2e7ad630b92b54e6a',
+            'description': 'md5:76260cb9cdc0ef76826d7ca9d92fadfa',
+            'thumbnail': r're:^https?://[^?#]+lcxgwod5hapghvw',
+            'series': 'WeTV PICK-A-BOO',
+            'episode': 'Episode 0',
+            'episode_number': 0,
+            'duration': 442,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id, series_id = self._match_valid_url(url).group('id', 'series_id')
+        webpage = self._download_webpage(url, video_id)
+        webpage_metadata = self._get_webpage_metadata(webpage, video_id)
+
+        formats, subtitles = self._extract_all_video_formats_and_subtitles(url, video_id, series_id)
+        return {
+            'id': video_id,
+            'title': self._get_clean_title(self._og_search_title(webpage)
+                                           or traverse_obj(webpage_metadata, ('coverInfo', 'title'))),
+            'description': (traverse_obj(webpage_metadata, ('coverInfo', 'description'))
+                            or self._og_search_description(webpage)),
+            'formats': formats,
+            'subtitles': subtitles,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'duration': int_or_none(traverse_obj(webpage_metadata, ('videoInfo', 'duration'))),
+            'series': traverse_obj(webpage_metadata, ('coverInfo', 'title')),
+            'episode_number': int_or_none(traverse_obj(webpage_metadata, ('videoInfo', 'episode'))),
+        }
+
+
+class WeTvSeriesIE(WeTvBaseIE):
+    _VALID_URL = WeTvBaseIE._VALID_URL_BASE + r'/(?P<id>\w+)(?:-[^/?#]+)?/?(?:[?#]|$)'
+
+    _TESTS = [{
+        'url': 'https://wetv.vip/play/air11ooo2rdsdi3-Cute-Programmer',
+        'info_dict': {
+            'id': 'air11ooo2rdsdi3',
+            'title': 'Cute Programmer',
+            'description': 'md5:e87beab3bf9f392d6b9e541a63286343',
+        },
+        'playlist_count': 30,
+    }, {
+        'url': 'https://wetv.vip/en/play/u37kgfnfzs73kiu-You-Are-My-Glory',
+        'info_dict': {
+            'id': 'u37kgfnfzs73kiu',
+            'title': 'You Are My Glory',
+            'description': 'md5:831363a4c3b4d7615e1f3854be3a123b',
+        },
+        'playlist_count': 32,
+    }]
+
+    def _real_extract(self, url):
+        series_id = self._match_id(url)
+        webpage = self._download_webpage(url, series_id)
+        webpage_metadata = self._get_webpage_metadata(webpage, series_id)
+
+        episode_paths = ([f'/play/{series_id}/{episode["vid"]}' for episode in webpage_metadata.get('videoList')]
+                         or re.findall(r'<a[^>]+class="play-video__link"[^>]+href="(?P<path>[^"]+)', webpage))
+
+        return self.playlist_from_matches(
+            episode_paths, series_id, ie=WeTvEpisodeIE, getter=functools.partial(urljoin, url),
+            title=self._get_clean_title(traverse_obj(webpage_metadata, ('coverInfo', 'title'))
+                                        or self._og_search_title(webpage)),
+            description=(traverse_obj(webpage_metadata, ('coverInfo', 'description'))
+                         or self._og_search_description(webpage)))

yt_dlp/extractor/testurl.py

@@ -8,12 +8,14 @@ class TestURLIE(InfoExtractor):
     """ Allows addressing of the test cases as test:yout.*be_1 """
 
     IE_DESC = False  # Do not list
-    _VALID_URL = r'test(?:url)?:(?P<extractor>.+?)(?:_(?P<num>[0-9]+))?$'
+    _VALID_URL = r'test(?:url)?:(?P<extractor>.*?)(?:_(?P<num>[0-9]+))?$'
 
     def _real_extract(self, url):
         from . import gen_extractor_classes
 
         extractor_id, num = self._match_valid_url(url).group('extractor', 'num')
+        if not extractor_id:
+            return {'id': ':test', 'title': '', 'url': url}
 
         rex = re.compile(extractor_id, flags=re.IGNORECASE)
         matching_extractors = [e for e in gen_extractor_classes() if rex.search(e.IE_NAME)]

yt_dlp/extractor/triller.py

@@ -0,0 +1,304 @@
+import itertools
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    str_or_none,
+    traverse_obj,
+    unified_strdate,
+    unified_timestamp,
+    url_basename,
+)
+
+
+class TrillerBaseIE(InfoExtractor):
+    _NETRC_MACHINE = 'triller'
+    _AUTH_TOKEN = None
+    _API_BASE_URL = 'https://social.triller.co/v1.5'
+
+    def _perform_login(self, username, password):
+        if self._AUTH_TOKEN:
+            return
+
+        user_check = self._download_json(
+            f'{self._API_BASE_URL}/api/user/is-valid-username', None, note='Checking username',
+            fatal=False, expected_status=400, headers={
+                'Content-Type': 'application/json',
+                'Origin': 'https://triller.co',
+            }, data=json.dumps({'username': username}, separators=(',', ':')).encode('utf-8'))
+        if user_check.get('status'):  # endpoint returns "status":false if username exists
+            raise ExtractorError('Unable to login: Invalid username', expected=True)
+
+        credentials = {
+            'username': username,
+            'password': password,
+        }
+        login = self._download_json(
+            f'{self._API_BASE_URL}/user/auth', None, note='Logging in',
+            fatal=False, expected_status=400, headers={
+                'Content-Type': 'application/json',
+                'Origin': 'https://triller.co',
+            }, data=json.dumps(credentials, separators=(',', ':')).encode('utf-8'))
+        if not login.get('auth_token'):
+            if login.get('error') == 1008:
+                raise ExtractorError('Unable to login: Incorrect password', expected=True)
+            raise ExtractorError('Unable to login')
+
+        self._AUTH_TOKEN = login['auth_token']
+
+    def _get_comments(self, video_id, limit=15):
+        comment_info = self._download_json(
+            f'{self._API_BASE_URL}/api/videos/{video_id}/comments_v2',
+            video_id, fatal=False, note='Downloading comments API JSON',
+            headers={'Origin': 'https://triller.co'}, query={'limit': limit}) or {}
+        if not comment_info.get('comments'):
+            return
+        for comment_dict in comment_info['comments']:
+            yield {
+                'author': traverse_obj(comment_dict, ('author', 'username')),
+                'author_id': traverse_obj(comment_dict, ('author', 'user_id')),
+                'id': comment_dict.get('id'),
+                'text': comment_dict.get('body'),
+                'timestamp': unified_timestamp(comment_dict.get('timestamp')),
+            }
+
+    def _check_user_info(self, user_info):
+        if not user_info:
+            self.report_warning('Unable to extract user info')
+        elif user_info.get('private') and not user_info.get('followed_by_me'):
+            raise ExtractorError('This video is private', expected=True)
+        elif traverse_obj(user_info, 'blocked_by_user', 'blocking_user'):
+            raise ExtractorError('The author of the video is blocked', expected=True)
+        return user_info
+
+    def _parse_video_info(self, video_info, username, user_info=None):
+        video_uuid = video_info.get('video_uuid')
+        video_id = video_info.get('id')
+
+        formats = []
+        video_url = traverse_obj(video_info, 'video_url', 'stream_url')
+        if video_url:
+            formats.append({
+                'url': video_url,
+                'ext': 'mp4',
+                'vcodec': 'h264',
+                'width': video_info.get('width'),
+                'height': video_info.get('height'),
+                'format_id': url_basename(video_url).split('.')[0],
+                'filesize': video_info.get('filesize'),
+            })
+        video_set = video_info.get('video_set') or []
+        for video in video_set:
+            resolution = video.get('resolution') or ''
+            formats.append({
+                'url': video['url'],
+                'ext': 'mp4',
+                'vcodec': video.get('codec'),
+                'vbr': int_or_none(video.get('bitrate'), 1000),
+                'width': int_or_none(resolution.split('x')[0]),
+                'height': int_or_none(resolution.split('x')[1]),
+                'format_id': url_basename(video['url']).split('.')[0],
+            })
+        audio_url = video_info.get('audio_url')
+        if audio_url:
+            formats.append({
+                'url': audio_url,
+                'ext': 'm4a',
+                'format_id': url_basename(audio_url).split('.')[0],
+            })
+
+        manifest_url = video_info.get('transcoded_url')
+        if manifest_url:
+            formats.extend(self._extract_m3u8_formats(
+                manifest_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls', fatal=False))
+        self._sort_formats(formats)
+
+        comment_count = int_or_none(video_info.get('comment_count'))
+
+        user_info = user_info or traverse_obj(video_info, 'user', default={})
+
+        return {
+            'id': str_or_none(video_id) or video_uuid,
+            'title': video_info.get('description') or f'Video by {username}',
+            'thumbnail': video_info.get('thumbnail_url'),
+            'description': video_info.get('description'),
+            'uploader': str_or_none(username),
+            'uploader_id': str_or_none(user_info.get('user_id')),
+            'creator': str_or_none(user_info.get('name')),
+            'timestamp': unified_timestamp(video_info.get('timestamp')),
+            'upload_date': unified_strdate(video_info.get('timestamp')),
+            'duration': int_or_none(video_info.get('duration')),
+            'view_count': int_or_none(video_info.get('play_count')),
+            'like_count': int_or_none(video_info.get('likes_count')),
+            'artist': str_or_none(video_info.get('song_artist')),
+            'track': str_or_none(video_info.get('song_title')),
+            'webpage_url': f'https://triller.co/@{username}/video/{video_uuid}',
+            'uploader_url': f'https://triller.co/@{username}',
+            'extractor_key': TrillerIE.ie_key(),
+            'extractor': TrillerIE.IE_NAME,
+            'formats': formats,
+            'comment_count': comment_count,
+            '__post_extractor': self.extract_comments(video_id, comment_count),
+        }
+
+
+class TrillerIE(TrillerBaseIE):
+    _VALID_URL = r'''(?x)
+            https?://(?:www\.)?triller\.co/
+            @(?P<username>[\w\._]+)/video/
+            (?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})
+        '''
+    _TESTS = [{
+        'url': 'https://triller.co/@theestallion/video/2358fcd7-3df2-4c77-84c8-1d091610a6cf',
+        'md5': '228662d783923b60d78395fedddc0a20',
+        'info_dict': {
+            'id': '71595734',
+            'ext': 'mp4',
+            'title': 'md5:9a2bf9435c5c4292678996a464669416',
+            'thumbnail': r're:^https://uploads\.cdn\.triller\.co/.+\.jpg$',
+            'description': 'md5:9a2bf9435c5c4292678996a464669416',
+            'uploader': 'theestallion',
+            'uploader_id': '18992236',
+            'creator': 'Megan Thee Stallion',
+            'timestamp': 1660598222,
+            'upload_date': '20220815',
+            'duration': 47,
+            'height': 3840,
+            'width': 2160,
+            'view_count': int,
+            'like_count': int,
+            'artist': 'Megan Thee Stallion',
+            'track': 'Her',
+            'webpage_url': 'https://triller.co/@theestallion/video/2358fcd7-3df2-4c77-84c8-1d091610a6cf',
+            'uploader_url': 'https://triller.co/@theestallion',
+            'comment_count': int,
+        }
+    }, {
+        'url': 'https://triller.co/@charlidamelio/video/46c6fcfa-aa9e-4503-a50c-68444f44cddc',
+        'md5': '874055f462af5b0699b9dbb527a505a0',
+        'info_dict': {
+            'id': '71621339',
+            'ext': 'mp4',
+            'title': 'md5:4c91ea82760fe0fffb71b8c3aa7295fc',
+            'thumbnail': r're:^https://uploads\.cdn\.triller\.co/.+\.jpg$',
+            'description': 'md5:4c91ea82760fe0fffb71b8c3aa7295fc',
+            'uploader': 'charlidamelio',
+            'uploader_id': '1875551',
+            'creator': 'charli damelio',
+            'timestamp': 1660773354,
+            'upload_date': '20220817',
+            'duration': 16,
+            'height': 1920,
+            'width': 1080,
+            'view_count': int,
+            'like_count': int,
+            'artist': 'Dixie',
+            'track': 'Someone to Blame',
+            'webpage_url': 'https://triller.co/@charlidamelio/video/46c6fcfa-aa9e-4503-a50c-68444f44cddc',
+            'uploader_url': 'https://triller.co/@charlidamelio',
+            'comment_count': int,
+        }
+    }]
+
+    def _real_extract(self, url):
+        username, video_uuid = self._match_valid_url(url).group('username', 'id')
+
+        video_info = traverse_obj(self._download_json(
+            f'{self._API_BASE_URL}/api/videos/{video_uuid}',
+            video_uuid, note='Downloading video info API JSON',
+            errnote='Unable to download video info API JSON',
+            headers={
+                'Origin': 'https://triller.co',
+            }), ('videos', 0))
+        if not video_info:
+            raise ExtractorError('No video info found in API response')
+
+        user_info = self._check_user_info(video_info.get('user') or {})
+        return self._parse_video_info(video_info, username, user_info)
+
+
+class TrillerUserIE(TrillerBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?triller\.co/@(?P<id>[\w\._]+)/?(?:$|[#?])'
+    _TESTS = [{
+        # first videos request only returns 2 videos
+        'url': 'https://triller.co/@theestallion',
+        'playlist_mincount': 9,
+        'info_dict': {
+            'id': '18992236',
+            'title': 'theestallion',
+            'thumbnail': r're:^https://uploads\.cdn\.triller\.co/.+\.jpg$',
+        }
+    }, {
+        'url': 'https://triller.co/@charlidamelio',
+        'playlist_mincount': 25,
+        'info_dict': {
+            'id': '1875551',
+            'title': 'charlidamelio',
+            'thumbnail': r're:^https://uploads\.cdn\.triller\.co/.+\.jpg$',
+        }
+    }]
+
+    def _real_initialize(self):
+        if not self._AUTH_TOKEN:
+            guest = self._download_json(
+                f'{self._API_BASE_URL}/user/create_guest',
+                None, note='Creating guest session', data=b'', headers={
+                    'Origin': 'https://triller.co',
+                }, query={
+                    'platform': 'Web',
+                    'app_version': '',
+                })
+            if not guest.get('auth_token'):
+                raise ExtractorError('Unable to fetch required auth token for user extraction')
+
+            self._AUTH_TOKEN = guest['auth_token']
+
+    def _extract_video_list(self, username, user_id, limit=6):
+        query = {
+            'limit': limit,
+        }
+        for page in itertools.count(1):
+            for retry in self.RetryManager():
+                try:
+                    video_list = self._download_json(
+                        f'{self._API_BASE_URL}/api/users/{user_id}/videos',
+                        username, note=f'Downloading user video list page {page}',
+                        errnote='Unable to download user video list', headers={
+                            'Authorization': f'Bearer {self._AUTH_TOKEN}',
+                            'Origin': 'https://triller.co',
+                        }, query=query)
+                except ExtractorError as e:
+                    if isinstance(e.cause, json.JSONDecodeError) and e.cause.pos == 0:
+                        retry.error = e
+                        continue
+                    raise
+            if not video_list.get('videos'):
+                break
+            yield from video_list['videos']
+            query['before_time'] = traverse_obj(video_list, ('videos', -1, 'timestamp'))
+            if not query['before_time']:
+                break
+
+    def _entries(self, videos, username, user_info):
+        for video in videos:
+            yield self._parse_video_info(video, username, user_info)
+
+    def _real_extract(self, url):
+        username = self._match_id(url)
+        user_info = self._check_user_info(self._download_json(
+            f'{self._API_BASE_URL}/api/users/by_username/{username}',
+            username, note='Downloading user info',
+            errnote='Failed to download user info', headers={
+                'Authorization': f'Bearer {self._AUTH_TOKEN}',
+                'Origin': 'https://triller.co',
+            }).get('user', {}))
+
+        user_id = str_or_none(user_info.get('user_id'))
+        videos = self._extract_video_list(username, user_id)
+        thumbnail = user_info.get('avatar_url')
+
+        return self.playlist_result(
+            self._entries(videos, username, user_info), user_id, username, thumbnail=thumbnail)

yt_dlp/extractor/uktvplay.py

@@ -2,7 +2,7 @@ from .common import InfoExtractor
 
 
 class UKTVPlayIE(InfoExtractor):
-    _VALID_URL = r'https?://uktvplay\.uktv\.co\.uk/(?:.+?\?.*?\bvideo=|([^/]+/)*watch-online/)(?P<id>\d+)'
+    _VALID_URL = r'https?://uktvplay\.(?:uktv\.)?co\.uk/(?:.+?\?.*?\bvideo=|([^/]+/)*watch-online/)(?P<id>\d+)'
     _TESTS = [{
         'url': 'https://uktvplay.uktv.co.uk/shows/world-at-war/c/200/watch-online/?video=2117008346001',
         'info_dict': {

yt_dlp/extractor/vimeo.py

@@ -1131,7 +1131,7 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
 
 class VimeoUserIE(VimeoChannelIE):
     IE_NAME = 'vimeo:user'
-    _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
+    _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos)?/?(?:$|[?#])'
     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
     _TESTS = [{
         'url': 'https://vimeo.com/nkistudio/videos',
@@ -1140,6 +1140,9 @@ class VimeoUserIE(VimeoChannelIE):
             'id': 'nkistudio',
         },
         'playlist_mincount': 66,
+    }, {
+        'url': 'https://vimeo.com/nkistudio/',
+        'only_matching': True,
     }]
     _BASE_URL_TEMPL = 'https://vimeo.com/%s'
 

yt_dlp/extractor/wetv.py

@@ -1,208 +0,0 @@
-import functools
-import re
-import time
-
-from .common import InfoExtractor
-from ..aes import aes_cbc_encrypt_bytes
-from ..utils import determine_ext, int_or_none, traverse_obj, urljoin
-
-
-class WeTvBaseIE(InfoExtractor):
-    _VALID_URL_BASE = r'https?://(?:www\.)?wetv\.vip/(?:[^?#]+/)?play'
-
-    def _get_ckey(self, video_id, url, app_version, platform):
-        ua = self.get_param('http_headers')['User-Agent']
-
-        payload = (f'{video_id}|{int(time.time())}|mg3c3b04ba|{app_version}|0000000000000000|'
-                   f'{platform}|{url[:48]}|{ua.lower()[:48]}||Mozilla|Netscape|Win32|00|')
-
-        return aes_cbc_encrypt_bytes(
-            bytes(f'|{sum(map(ord, payload))}|{payload}', 'utf-8'),
-            b'Ok\xda\xa3\x9e/\x8c\xb0\x7f^r-\x9e\xde\xf3\x14',
-            b'\x01PJ\xf3V\xe6\x19\xcf.B\xbb\xa6\x8c?p\xf9',
-            padding_mode='whitespace').hex()
-
-    def _get_video_api_response(self, video_url, video_id, series_id, subtitle_format, video_format, video_quality):
-        app_version = '3.5.57'
-        platform = '4830201'
-
-        ckey = self._get_ckey(video_id, video_url, app_version, platform)
-        query = {
-            'vid': video_id,
-            'cid': series_id,
-            'cKey': ckey,
-            'encryptVer': '8.1',
-            'spcaptiontype': '1' if subtitle_format == 'vtt' else '0',  # 0 - SRT, 1 - VTT
-            'sphls': '1' if video_format == 'hls' else '0',  # 0 - MP4, 1 - HLS
-            'defn': video_quality,  # '': 480p, 'shd': 720p, 'fhd': 1080p
-            'spsrt': '1',  # Enable subtitles
-            'sphttps': '1',  # Enable HTTPS
-            'otype': 'json',  # Response format: xml, json,
-            'dtype': '1',
-            'spwm': '1',
-            'host': 'wetv.vip',  # These three values are needed for SHD
-            'referer': 'wetv.vip',
-            'ehost': video_url,
-            'appVer': app_version,
-            'platform': platform,
-        }
-
-        return self._search_json(r'QZOutputJson=', self._download_webpage(
-            'https://play.wetv.vip/getvinfo', video_id, query=query), 'api_response', video_id)
-
-    def _get_webpage_metadata(self, webpage, video_id):
-        return self._parse_json(
-            traverse_obj(self._search_nextjs_data(webpage, video_id), ('props', 'pageProps', 'data')),
-            video_id, fatal=False)
-
-
-class WeTvEpisodeIE(WeTvBaseIE):
-    IE_NAME = 'wetv:episode'
-    _VALID_URL = WeTvBaseIE._VALID_URL_BASE + r'/(?P<series_id>\w+)(?:-[^?#]+)?/(?P<id>\w+)(?:-[^?#]+)?'
-
-    _TESTS = [{
-        'url': 'https://wetv.vip/en/play/air11ooo2rdsdi3-Cute-Programmer/v0040pr89t9-EP1-Cute-Programmer',
-        'md5': 'a046f565c9dce9b263a0465a422cd7bf',
-        'info_dict': {
-            'id': 'v0040pr89t9',
-            'ext': 'mp4',
-            'title': 'EP1: Cute Programmer',
-            'description': 'md5:e87beab3bf9f392d6b9e541a63286343',
-            'thumbnail': r're:^https?://[^?#]+air11ooo2rdsdi3',
-            'series': 'Cute Programmer',
-            'episode': 'Episode 1',
-            'episode_number': 1,
-            'duration': 2835,
-        },
-    }, {
-        'url': 'https://wetv.vip/en/play/u37kgfnfzs73kiu/p0039b9nvik',
-        'md5': '4d9d69bcfd11da61f4aae64fc6b316b3',
-        'info_dict': {
-            'id': 'p0039b9nvik',
-            'ext': 'mp4',
-            'title': 'EP1: You Are My Glory',
-            'description': 'md5:831363a4c3b4d7615e1f3854be3a123b',
-            'thumbnail': r're:^https?://[^?#]+u37kgfnfzs73kiu',
-            'series': 'You Are My Glory',
-            'episode': 'Episode 1',
-            'episode_number': 1,
-            'duration': 2454,
-        },
-    }, {
-        'url': 'https://wetv.vip/en/play/lcxgwod5hapghvw-WeTV-PICK-A-BOO/i0042y00lxp-Zhao-Lusi-Describes-The-First-Experiences-She-Had-In-Who-Rules-The-World-%7C-WeTV-PICK-A-BOO',
-        'md5': '71133f5c2d5d6cad3427e1b010488280',
-        'info_dict': {
-            'id': 'i0042y00lxp',
-            'ext': 'mp4',
-            'title': 'md5:f7a0857dbe5fbbe2e7ad630b92b54e6a',
-            'description': 'md5:76260cb9cdc0ef76826d7ca9d92fadfa',
-            'thumbnail': r're:^https?://[^?#]+lcxgwod5hapghvw',
-            'series': 'WeTV PICK-A-BOO',
-            'episode': 'Episode 0',
-            'episode_number': 0,
-            'duration': 442,
-        },
-    }]
-
-    def _extract_video_formats_and_subtitles(self, api_response, video_id, video_quality):
-        video_response = api_response['vl']['vi'][0]
-        video_width = video_response.get('vw')
-        video_height = video_response.get('vh')
-
-        formats, subtitles = [], {}
-        for video_format in video_response['ul']['ui']:
-            if video_format.get('hls'):
-                fmts, subs = self._extract_m3u8_formats_and_subtitles(
-                    video_format['url'] + video_format['hls']['pname'], video_id, 'mp4', fatal=False)
-                for f in fmts:
-                    f['width'] = video_width
-                    f['height'] = video_height
-
-                formats.extend(fmts)
-                self._merge_subtitles(subs, target=subtitles)
-            else:
-                formats.append({
-                    'url': f'{video_format["url"]}{video_response["fn"]}?vkey={video_response["fvkey"]}',
-                    'width': video_width,
-                    'height': video_height,
-                    'ext': 'mp4',
-                })
-
-        return formats, subtitles
-
-    def _extract_video_subtitles(self, api_response, subtitles_format):
-        subtitles = {}
-        for subtitle in traverse_obj(api_response, ('sfl', 'fi')):
-            subtitles.setdefault(subtitle['lang'].lower(), []).append({
-                'url': subtitle['url'],
-                'ext': subtitles_format,
-                'protocol': 'm3u8_native' if determine_ext(subtitle['url']) == 'm3u8' else 'http',
-            })
-
-        return subtitles
-
-    def _real_extract(self, url):
-        video_id, series_id = self._match_valid_url(url).group('id', 'series_id')
-        webpage = self._download_webpage(url, video_id)
-
-        formats, subtitles = [], {}
-        for video_format, subtitle_format, video_quality in (('mp4', 'srt', ''), ('hls', 'vtt', 'shd'), ('hls', 'vtt', 'fhd')):
-            api_response = self._get_video_api_response(url, video_id, series_id, subtitle_format, video_format, video_quality)
-
-            fmts, subs = self._extract_video_formats_and_subtitles(api_response, video_id, video_quality)
-            native_subtitles = self._extract_video_subtitles(api_response, subtitle_format)
-
-            formats.extend(fmts)
-            self._merge_subtitles(subs, native_subtitles, target=subtitles)
-
-        self._sort_formats(formats)
-        webpage_metadata = self._get_webpage_metadata(webpage, video_id)
-
-        return {
-            'id': video_id,
-            'title': (self._og_search_title(webpage)
-                      or traverse_obj(webpage_metadata, ('coverInfo', 'description'))),
-            'description': (self._og_search_description(webpage)
-                            or traverse_obj(webpage_metadata, ('coverInfo', 'description'))),
-            'formats': formats,
-            'subtitles': subtitles,
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'duration': int_or_none(traverse_obj(webpage_metadata, ('videoInfo', 'duration'))),
-            'series': traverse_obj(webpage_metadata, ('coverInfo', 'title')),
-            'episode_number': int_or_none(traverse_obj(webpage_metadata, ('videoInfo', 'episode'))),
-        }
-
-
-class WeTvSeriesIE(WeTvBaseIE):
-    _VALID_URL = WeTvBaseIE._VALID_URL_BASE + r'/(?P<id>\w+)(?:-[^/?#]+)?/?(?:[?#]|$)'
-
-    _TESTS = [{
-        'url': 'https://wetv.vip/play/air11ooo2rdsdi3-Cute-Programmer',
-        'info_dict': {
-            'id': 'air11ooo2rdsdi3',
-            'title': 'Cute Programmer',
-            'description': 'md5:e87beab3bf9f392d6b9e541a63286343',
-        },
-        'playlist_count': 30,
-    }, {
-        'url': 'https://wetv.vip/en/play/u37kgfnfzs73kiu-You-Are-My-Glory',
-        'info_dict': {
-            'id': 'u37kgfnfzs73kiu',
-            'title': 'You Are My Glory',
-            'description': 'md5:831363a4c3b4d7615e1f3854be3a123b',
-        },
-        'playlist_count': 32,
-    }]
-
-    def _real_extract(self, url):
-        series_id = self._match_id(url)
-        webpage = self._download_webpage(url, series_id)
-        webpage_metadata = self._get_webpage_metadata(webpage, series_id)
-
-        episode_paths = (re.findall(r'<a[^>]+class="play-video__link"[^>]+href="(?P<path>[^"]+)', webpage)
-                         or [f'/{series_id}/{episode["vid"]}' for episode in webpage_metadata.get('videoList')])
-
-        return self.playlist_from_matches(
-            episode_paths, series_id, ie=WeTvEpisodeIE, getter=functools.partial(urljoin, url),
-            title=traverse_obj(webpage_metadata, ('coverInfo', 'title')) or self._og_search_title(webpage),
-            description=traverse_obj(webpage_metadata, ('coverInfo', 'description')) or self._og_search_description(webpage))

yt_dlp/extractor/youtube.py

@@ -110,8 +110,9 @@ INNERTUBE_CLIENTS = {
         'INNERTUBE_CONTEXT': {
             'client': {
                 'clientName': 'ANDROID',
-                'clientVersion': '17.29.34',
+                'clientVersion': '17.31.35',
-                'androidSdkVersion': 30
+                'androidSdkVersion': 30,
+                'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
             }
         },
         'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
@@ -122,8 +123,9 @@ INNERTUBE_CLIENTS = {
         'INNERTUBE_CONTEXT': {
             'client': {
                 'clientName': 'ANDROID_EMBEDDED_PLAYER',
-                'clientVersion': '17.29.34',
+                'clientVersion': '17.31.35',
-                'androidSdkVersion': 30
+                'androidSdkVersion': 30,
+                'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
             },
         },
         'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
@@ -135,7 +137,8 @@ INNERTUBE_CLIENTS = {
             'client': {
                 'clientName': 'ANDROID_MUSIC',
                 'clientVersion': '5.16.51',
-                'androidSdkVersion': 30
+                'androidSdkVersion': 30,
+                'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
             }
         },
         'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
@@ -146,8 +149,9 @@ INNERTUBE_CLIENTS = {
         'INNERTUBE_CONTEXT': {
             'client': {
                 'clientName': 'ANDROID_CREATOR',
-                'clientVersion': '22.28.100',
+                'clientVersion': '22.30.100',
-                'androidSdkVersion': 30
+                'androidSdkVersion': 30,
+                'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
             },
         },
         'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
@@ -160,8 +164,9 @@ INNERTUBE_CLIENTS = {
         'INNERTUBE_CONTEXT': {
             'client': {
                 'clientName': 'IOS',
-                'clientVersion': '17.30.1',
+                'clientVersion': '17.33.2',
                 'deviceModel': 'iPhone14,3',
+                'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
             }
         },
         'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
@@ -171,8 +176,9 @@ INNERTUBE_CLIENTS = {
         'INNERTUBE_CONTEXT': {
             'client': {
                 'clientName': 'IOS_MESSAGES_EXTENSION',
-                'clientVersion': '17.30.1',
+                'clientVersion': '17.33.2',
                 'deviceModel': 'iPhone14,3',
+                'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
             },
         },
         'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
@@ -183,7 +189,9 @@ INNERTUBE_CLIENTS = {
         'INNERTUBE_CONTEXT': {
             'client': {
                 'clientName': 'IOS_MUSIC',
-                'clientVersion': '5.18',
+                'clientVersion': '5.21',
+                'deviceModel': 'iPhone14,3',
+                'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
             },
         },
         'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
@@ -193,7 +201,9 @@ INNERTUBE_CLIENTS = {
         'INNERTUBE_CONTEXT': {
             'client': {
                 'clientName': 'IOS_CREATOR',
-                'clientVersion': '22.29.101',
+                'clientVersion': '22.33.101',
+                'deviceModel': 'iPhone14,3',
+                'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
             },
         },
         'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
@@ -555,7 +565,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'Origin': origin,
             'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
             'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
-            'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
+            'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
+            'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
         }
         if session_index is None:
             session_index = self._extract_session_index(ytcfg)
@@ -2148,6 +2159,35 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'comment_count': int,
                 'channel_follower_count': int
             }
+        }, {
+            # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
+            'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
+            'info_dict': {
+                'id': '2NUZ8W2llS4',
+                'ext': 'mp4',
+                'title': 'The NP that test your phone performance 🙂',
+                'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
+                'uploader': 'Leon Nguyen',
+                'uploader_id': 'VNSXIII',
+                'uploader_url': 'http://www.youtube.com/user/VNSXIII',
+                'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
+                'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
+                'duration': 21,
+                'view_count': int,
+                'age_limit': 0,
+                'categories': ['Gaming'],
+                'tags': 'count:23',
+                'playable_in_embed': True,
+                'live_status': 'not_live',
+                'upload_date': '20220102',
+                'like_count': int,
+                'availability': 'public',
+                'channel': 'Leon Nguyen',
+                'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
+                'comment_count': int,
+                'channel_follower_count': int
+            },
+            'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
         }, {
             # date text is premiered video, ensure upload date in UTC (published 1641172509)
             'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
@@ -2621,7 +2661,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             raise ExtractorError('Cannot decrypt nsig without player_url')
         player_url = urljoin('https://www.youtube.com', player_url)
 
-        jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
+        try:
+            jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
+        except ExtractorError as e:
+            raise ExtractorError('Unable to extract nsig function code', cause=e)
         if self.get_param('youtube_print_sig_code'):
             self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
 
@@ -2630,7 +2673,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             ret = extract_nsig(jsi, func_code)(s)
         except JSInterpreter.Exception as e:
             try:
-                jsi = PhantomJSwrapper(self)
+                jsi = PhantomJSwrapper(self, timeout=5000)
             except ExtractorError:
                 raise e
             self.report_warning(
@@ -2646,24 +2689,40 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         self.write_debug(f'Decrypted nsig {s} => {ret}')
         return ret
 
+    def _extract_n_function_name(self, jscode):
+        funcname, idx = self._search_regex(
+            r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
+            jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
+        if not idx:
+            return funcname
+
+        return json.loads(js_to_json(self._search_regex(
+            rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
+            f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
+
     def _extract_n_function_code(self, video_id, player_url):
         player_id = self._extract_player_info(player_url)
-        func_code = self.cache.load('youtube-nsig', player_id)
+        func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
         jscode = func_code or self._load_player(video_id, player_url)
         jsi = JSInterpreter(jscode)
 
         if func_code:
             return jsi, player_id, func_code
 
-        funcname, idx = self._search_regex(
+        func_name = self._extract_n_function_name(jscode)
-            r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
+
-            jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
+        # For redundancy
-        if idx:
+        func_code = self._search_regex(
-            funcname = json.loads(js_to_json(self._search_regex(
+            r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
-                rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
+                     # NB: The end of the regex is intentionally kept strict
-                f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
+                     {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
+            jscode, 'nsig function', group=('var', 'code'), default=None)
+        if func_code:
+            func_code = ([func_code[0]], func_code[1])
+        else:
+            self.write_debug('Extracting nsig function with jsinterp')
+            func_code = jsi.extract_function_code(func_name)
 
-        func_code = jsi.extract_function_code(funcname)
         self.cache.store('youtube-nsig', player_id, func_code)
         return jsi, player_id, func_code
 
@@ -2945,8 +3004,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         # YouTube comments have a max depth of 2
         max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
         if max_depth:
-            self._downloader.deprecation_warning(
+            self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
-                '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
+                                                'Set max replies in the max-comments extractor argument instead')
         if max_depth == 1 and parent:
             return
 
@@ -3068,7 +3127,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
     def _is_unplayable(player_response):
         return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
 
-    def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
+    _STORY_PLAYER_PARAMS = '8AEB'
+
+    def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
 
         session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
         syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
@@ -3078,8 +3139,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
         yt_query = {
             'videoId': video_id,
-            'params': '8AEB'  # enable stories
         }
+        if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
+            yt_query['params'] = self._STORY_PLAYER_PARAMS
+
         yt_query.update(self._generate_player_context(sts))
         return self._extract_response(
             item_id=video_id, ep='player', query=yt_query,
@@ -3112,7 +3175,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
         return orderedSet(requested_clients)
 
-    def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
+    def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
         initial_pr = None
         if webpage:
             initial_pr = self._search_json(
@@ -3162,7 +3225,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
             try:
                 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
-                    client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
+                    client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
             except ExtractorError as e:
                 if last_error:
                     self.report_warning(last_error)
@@ -3196,7 +3259,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
     def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, is_live, duration):
         itags, stream_ids = {}, []
-        itag_qualities, res_qualities = {}, {0: -1}
+        itag_qualities, res_qualities = {}, {0: None}
         q = qualities([
             # Normally tiny is the smallest video-only formats. But
             # audio-only formats with unknown quality may get tagged as tiny
@@ -3264,7 +3327,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 except ExtractorError as e:
                     phantomjs_hint = ''
                     if isinstance(e, JSInterpreter.Exception):
-                        phantomjs_hint = f'         Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} to workaround the issue\n'
+                        phantomjs_hint = (f'         Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
+                                          f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
                     self.report_warning(
                         f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
                         f'         n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
@@ -3354,7 +3418,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 f['format_id'] = itag
                 itags[itag] = proto
 
-            f['quality'] = itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1)
+            f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
             if f['quality'] == -1 and f.get('height'):
                 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
             return True
@@ -3425,14 +3489,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
     def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
         webpage = None
         if 'webpage' not in self._configuration_arg('player_skip'):
+            query = {'bpctr': '9999999999', 'has_verified': '1'}
+            if smuggled_data.get('is_story'):
+                query['pp'] = self._STORY_PLAYER_PARAMS
             webpage = self._download_webpage(
-                webpage_url + '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id, fatal=False)
+                webpage_url, video_id, fatal=False, query=query)
 
         master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
 
         player_responses, player_url = self._extract_player_responses(
             self._get_requested_clients(url, smuggled_data),
-            video_id, webpage, master_ytcfg)
+            video_id, webpage, master_ytcfg, smuggled_data)
 
         return webpage, master_ytcfg, player_responses, player_url
 
@@ -3898,7 +3965,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         upload_date = (
             unified_strdate(get_first(microformats, 'uploadDate'))
             or unified_strdate(search_meta('uploadDate')))
-        if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
+        if not upload_date or (
+            not info.get('is_live')
+            and not info.get('was_live')
+            and info.get('live_status') != 'is_upcoming'
+            and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
+        ):
             upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
         info['upload_date'] = upload_date
 
@@ -6005,7 +6077,7 @@ class YoutubeStoriesIE(InfoExtractor):
     def _real_extract(self, url):
         playlist_id = f'RLTD{self._match_id(url)}'
         return self.url_result(
-            f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
+            smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
             ie=YoutubeTabIE, video_id=playlist_id)
 
 

yt_dlp/jsinterp.py

@@ -18,10 +18,11 @@ from .utils import (
 
 
 def _js_bit_op(op):
+    def zeroise(x):
+        return 0 if x in (None, JS_Undefined) else x
+
     def wrapped(a, b):
-        def zeroise(x):
+        return op(zeroise(a), zeroise(b)) & 0xffffffff
-            return 0 if x in (None, JS_Undefined) else x
-        return op(zeroise(a), zeroise(b))
 
     return wrapped
 
@@ -71,6 +72,8 @@ def _js_comp_op(op):
     def wrapped(a, b):
         if JS_Undefined in (a, b):
             return False
+        if isinstance(a, str) or isinstance(b, str):
+            return op(str(a or 0), str(b or 0))
         return op(a or 0, b or 0)
 
     return wrapped
@@ -98,8 +101,8 @@ _OPERATORS = {  # None => Defined in JSInterpreter._operator
     '&': _js_bit_op(operator.and_),
 
     '===': operator.is_,
-    '==': _js_eq_op(operator.eq),
     '!==': operator.is_not,
+    '==': _js_eq_op(operator.eq),
     '!=': _js_eq_op(operator.ne),
 
     '<=': _js_comp_op(operator.le),
@@ -172,7 +175,14 @@ class Debugger:
         def interpret_statement(self, stmt, local_vars, allow_recursion, *args, **kwargs):
             if cls.ENABLED and stmt.strip():
                 cls.write(stmt, level=allow_recursion)
-            ret, should_ret = f(self, stmt, local_vars, allow_recursion, *args, **kwargs)
+            try:
+                ret, should_ret = f(self, stmt, local_vars, allow_recursion, *args, **kwargs)
+            except Exception as e:
+                if cls.ENABLED:
+                    if isinstance(e, ExtractorError):
+                        e = e.orig_msg
+                    cls.write('=> Raises:', e, '<-|', stmt, level=allow_recursion)
+                raise
             if cls.ENABLED and stmt.strip():
                 cls.write(['->', '=>'][should_ret], repr(ret), '<-|', stmt, level=allow_recursion)
             return ret, should_ret
@@ -226,7 +236,7 @@ class JSInterpreter:
 
     @staticmethod
     def _separate(expr, delim=',', max_split=None):
-        OP_CHARS = '+-*/%&|^=<>!,;'
+        OP_CHARS = '+-*/%&|^=<>!,;{}:'
         if not expr:
             return
         counters = {k: 0 for k in _MATCHING_PARENS.values()}
@@ -237,13 +247,14 @@ class JSInterpreter:
                 counters[_MATCHING_PARENS[char]] += 1
             elif not in_quote and char in counters:
                 counters[char] -= 1
-            elif not escaping and char in _QUOTES and in_quote in (char, None):
+            elif not escaping:
-                if in_quote or after_op or char != '/':
+                if char in _QUOTES and in_quote in (char, None):
-                    in_quote = None if in_quote and not in_regex_char_group else char
+                    if in_quote or after_op or char != '/':
-            elif in_quote == '/' and char in '[]':
+                        in_quote = None if in_quote and not in_regex_char_group else char
-                in_regex_char_group = char == '['
+                elif in_quote == '/' and char in '[]':
+                    in_regex_char_group = char == '['
             escaping = not escaping and in_quote and char == '\\'
-            after_op = not in_quote and char in OP_CHARS or (char == ' ' and after_op)
+            after_op = not in_quote and char in OP_CHARS or (char.isspace() and after_op)
 
             if char != delim[pos] or any(counters.values()) or in_quote:
                 pos = 0
@@ -259,7 +270,9 @@ class JSInterpreter:
         yield expr[start:]
 
     @classmethod
-    def _separate_at_paren(cls, expr, delim):
+    def _separate_at_paren(cls, expr, delim=None):
+        if delim is None:
+            delim = expr and _MATCHING_PARENS[expr[0]]
         separated = list(cls._separate(expr, delim, 1))
         if len(separated) < 2:
             raise cls.Exception(f'No terminating paren {delim}', expr)
@@ -338,7 +351,7 @@ class JSInterpreter:
         if expr.startswith('new '):
             obj = expr[4:]
             if obj.startswith('Date('):
-                left, right = self._separate_at_paren(obj[4:], ')')
+                left, right = self._separate_at_paren(obj[4:])
                 expr = unified_timestamp(
                     self.interpret_expression(left, local_vars, allow_recursion), False)
                 if not expr:
@@ -352,8 +365,8 @@ class JSInterpreter:
             return None, should_return
 
         if expr.startswith('{'):
-            inner, outer = self._separate_at_paren(expr, '}')
+            inner, outer = self._separate_at_paren(expr)
-            # Look for Map first
+            # try for object expression (Map)
             sub_expressions = [list(self._separate(sub_expr.strip(), ':', 1)) for sub_expr in self._separate(inner)]
             if all(len(sub_expr) == 2 for sub_expr in sub_expressions):
                 def dict_item(key, val):
@@ -371,7 +384,7 @@ class JSInterpreter:
                 expr = self._dump(inner, local_vars) + outer
 
         if expr.startswith('('):
-            inner, outer = self._separate_at_paren(expr, ')')
+            inner, outer = self._separate_at_paren(expr)
             inner, should_abort = self.interpret_statement(inner, local_vars, allow_recursion)
             if not outer or should_abort:
                 return inner, should_abort or should_return
@@ -379,53 +392,62 @@ class JSInterpreter:
                 expr = self._dump(inner, local_vars) + outer
 
         if expr.startswith('['):
-            inner, outer = self._separate_at_paren(expr, ']')
+            inner, outer = self._separate_at_paren(expr)
             name = self._named_object(local_vars, [
                 self.interpret_expression(item, local_vars, allow_recursion)
                 for item in self._separate(inner)])
             expr = name + outer
 
-        m = re.match(rf'''(?x)
+        m = re.match(r'''(?x)
-            (?P<try>try|finally)\s*|
+                (?P<try>try)\s*\{|
-            (?P<catch>catch\s*(?P<err>\(\s*{_NAME_RE}\s*\)))|
+                (?P<switch>switch)\s*\(|
-            (?P<switch>switch)\s*\(|
+                (?P<for>for)\s*\(
-            (?P<for>for)\s*\(|''', expr)
+                ''', expr)
-        if m and m.group('try'):
+        md = m.groupdict() if m else {}
-            if expr[m.end()] == '{':
+        if md.get('try'):
-                try_expr, expr = self._separate_at_paren(expr[m.end():], '}')
+            try_expr, expr = self._separate_at_paren(expr[m.end() - 1:])
-            else:
+            err = None
-                try_expr, expr = expr[m.end() - 1:], ''
             try:
                 ret, should_abort = self.interpret_statement(try_expr, local_vars, allow_recursion)
                 if should_abort:
                     return ret, True
-            except JS_Throw as e:
-                local_vars[self._EXC_NAME] = e.error
             except Exception as e:
                 # XXX: This works for now, but makes debugging future issues very hard
-                local_vars[self._EXC_NAME] = e
+                err = e
-            ret, should_abort = self.interpret_statement(expr, local_vars, allow_recursion)
-            return ret, should_abort or should_return
 
-        elif m and m.group('catch'):
+            pending = (None, False)
-            catch_expr, expr = self._separate_at_paren(expr[m.end():], '}')
+            m = re.match(r'catch\s*(?P<err>\(\s*{_NAME_RE}\s*\))?\{{'.format(**globals()), expr)
-            if self._EXC_NAME in local_vars:
+            if m:
-                catch_vars = local_vars.new_child({m.group('err'): local_vars.pop(self._EXC_NAME)})
+                sub_expr, expr = self._separate_at_paren(expr[m.end() - 1:])
-                ret, should_abort = self.interpret_statement(catch_expr, catch_vars, allow_recursion)
+                if err:
+                    catch_vars = {}
+                    if m.group('err'):
+                        catch_vars[m.group('err')] = err.error if isinstance(err, JS_Throw) else err
+                    catch_vars = local_vars.new_child(catch_vars)
+                    err, pending = None, self.interpret_statement(sub_expr, catch_vars, allow_recursion)
+
+            m = re.match(r'finally\s*\{', expr)
+            if m:
+                sub_expr, expr = self._separate_at_paren(expr[m.end() - 1:])
+                ret, should_abort = self.interpret_statement(sub_expr, local_vars, allow_recursion)
                 if should_abort:
                     return ret, True
 
-            ret, should_abort = self.interpret_statement(expr, local_vars, allow_recursion)
+            ret, should_abort = pending
-            return ret, should_abort or should_return
+            if should_abort:
+                return ret, True
 
-        elif m and m.group('for'):
+            if err:
-            constructor, remaining = self._separate_at_paren(expr[m.end() - 1:], ')')
+                raise err
+
+        elif md.get('for'):
+            constructor, remaining = self._separate_at_paren(expr[m.end() - 1:])
             if remaining.startswith('{'):
-                body, expr = self._separate_at_paren(remaining, '}')
+                body, expr = self._separate_at_paren(remaining)
             else:
                 switch_m = re.match(r'switch\s*\(', remaining)  # FIXME
                 if switch_m:
-                    switch_val, remaining = self._separate_at_paren(remaining[switch_m.end() - 1:], ')')
+                    switch_val, remaining = self._separate_at_paren(remaining[switch_m.end() - 1:])
                     body, expr = self._separate_at_paren(remaining, '}')
                     body = 'switch(%s){%s}' % (switch_val, body)
                 else:
@@ -444,11 +466,9 @@ class JSInterpreter:
                 except JS_Continue:
                     pass
                 self.interpret_expression(increment, local_vars, allow_recursion)
-            ret, should_abort = self.interpret_statement(expr, local_vars, allow_recursion)
-            return ret, should_abort or should_return
 
-        elif m and m.group('switch'):
+        elif md.get('switch'):
-            switch_val, remaining = self._separate_at_paren(expr[m.end() - 1:], ')')
+            switch_val, remaining = self._separate_at_paren(expr[m.end() - 1:])
             switch_val = self.interpret_expression(switch_val, local_vars, allow_recursion)
             body, expr = self._separate_at_paren(remaining, '}')
             items = body.replace('default:', 'case default:').split('case ')[1:]
@@ -471,6 +491,8 @@ class JSInterpreter:
                         break
                 if matched:
                     break
+
+        if md:
             ret, should_abort = self.interpret_statement(expr, local_vars, allow_recursion)
             return ret, should_abort or should_return
 
@@ -504,7 +526,7 @@ class JSInterpreter:
                 (?P<op>{"|".join(map(re.escape, set(_OPERATORS) - _COMP_OPERATORS))})?
                 =(?!=)(?P<expr>.*)$
             )|(?P<return>
-                (?!if|return|true|false|null|undefined)(?P<name>{_NAME_RE})$
+                (?!if|return|true|false|null|undefined|NaN)(?P<name>{_NAME_RE})$
             )|(?P<indexing>
                 (?P<in>{_NAME_RE})\[(?P<idx>.+)\]$
             )|(?P<attribute>
@@ -539,6 +561,8 @@ class JSInterpreter:
             raise JS_Continue()
         elif expr == 'undefined':
             return JS_Undefined, should_return
+        elif expr == 'NaN':
+            return float('NaN'), should_return
 
         elif m and m.group('return'):
             return local_vars.get(m.group('name'), JS_Undefined), should_return
@@ -573,7 +597,7 @@ class JSInterpreter:
                 member = self.interpret_expression(m.group('member2'), local_vars, allow_recursion)
             arg_str = expr[m.end():]
             if arg_str.startswith('('):
-                arg_str, remaining = self._separate_at_paren(arg_str, ')')
+                arg_str, remaining = self._separate_at_paren(arg_str)
             else:
                 arg_str, remaining = None, arg_str
 
@@ -683,6 +707,13 @@ class JSInterpreter:
                         return obj.index(idx, start)
                     except ValueError:
                         return -1
+                elif member == 'charCodeAt':
+                    assertion(isinstance(obj, str), 'must be applied on a string')
+                    assertion(len(argvals) == 1, 'takes exactly one argument')
+                    idx = argvals[0] if isinstance(argvals[0], int) else 0
+                    if idx >= len(obj):
+                        return None
+                    return ord(obj[idx])
 
                 idx = int(member) if isinstance(obj, list) else member
                 return obj[idx](argvals, allow_recursion=allow_recursion)
@@ -751,7 +782,7 @@ class JSInterpreter:
                 \((?P<args>[^)]*)\)\s*
                 (?P<code>{.+})''' % {'name': re.escape(funcname)},
             self.code)
-        code, _ = self._separate_at_paren(func_m.group('code'), '}')
+        code, _ = self._separate_at_paren(func_m.group('code'))
         if func_m is None:
             raise self.Exception(f'Could not find JS function "{funcname}"')
         return [x.strip() for x in func_m.group('args').split(',')], code
@@ -766,7 +797,7 @@ class JSInterpreter:
             if mobj is None:
                 break
             start, body_start = mobj.span()
-            body, remaining = self._separate_at_paren(code[body_start - 1:], '}')
+            body, remaining = self._separate_at_paren(code[body_start - 1:])
             name = self._named_object(local_vars, self.extract_function_from_code(
                 [x.strip() for x in mobj.group('args').split(',')],
                 body, local_vars, *global_stack))
@@ -784,7 +815,7 @@ class JSInterpreter:
             global_stack[0].update(itertools.zip_longest(argnames, args, fillvalue=None))
             global_stack[0].update(kwargs)
             var_stack = LocalNameSpace(*global_stack)
-            ret, should_abort = self.interpret_statement(code.replace('\n', ''), var_stack, allow_recursion - 1)
+            ret, should_abort = self.interpret_statement(code.replace('\n', ' '), var_stack, allow_recursion - 1)
             if should_abort:
                 return ret
         return resf

yt_dlp/options.py

@@ -25,10 +25,12 @@ from .utils import (
     OUTTMPL_TYPES,
     POSTPROCESS_WHEN,
     Config,
+    deprecation_warning,
     expand_path,
     format_field,
     get_executable_path,
     join_nonempty,
+    orderedSet_from_options,
     remove_end,
     write_string,
 )
@@ -163,6 +165,7 @@ class _YoutubeDLHelpFormatter(optparse.IndentedHelpFormatter):
 
 class _YoutubeDLOptionParser(optparse.OptionParser):
     # optparse is deprecated since python 3.2. So assume a stable interface even for private methods
+    ALIAS_DEST = '_triggered_aliases'
     ALIAS_TRIGGER_LIMIT = 100
 
     def __init__(self):
@@ -174,6 +177,7 @@ class _YoutubeDLOptionParser(optparse.OptionParser):
             formatter=_YoutubeDLHelpFormatter(),
             conflict_handler='resolve',
         )
+        self.set_default(self.ALIAS_DEST, collections.defaultdict(int))
 
     _UNKNOWN_OPTION = (optparse.BadOptionError, optparse.AmbiguousOptionError)
     _BAD_OPTION = optparse.OptionValueError
@@ -232,30 +236,16 @@ def create_parser():
             current + value if append is True else value + current)
 
     def _set_from_options_callback(
-            option, opt_str, value, parser, delim=',', allowed_values=None, aliases={},
+            option, opt_str, value, parser, allowed_values, delim=',', aliases={},
             process=lambda x: x.lower().strip()):
-        current = set(getattr(parser.values, option.dest))
+        values = [process(value)] if delim is None else map(process, value.split(delim))
-        values = [process(value)] if delim is None else list(map(process, value.split(delim)[::-1]))
+        try:
-        while values:
+            requested = orderedSet_from_options(values, collections.ChainMap(aliases, {'all': allowed_values}),
-            actual_val = val = values.pop()
+                                                start=getattr(parser.values, option.dest))
-            if not val:
+        except ValueError as e:
-                raise optparse.OptionValueError(f'Invalid {option.metavar} for {opt_str}: {value}')
+            raise optparse.OptionValueError(f'wrong {option.metavar} for {opt_str}: {e.args[0]}')
-            if val == 'all':
-                current.update(allowed_values)
-            elif val == '-all':
-                current = set()
-            elif val in aliases:
-                values.extend(aliases[val])
-            else:
-                if val[0] == '-':
-                    val = val[1:]
-                    current.discard(val)
-                else:
-                    current.update([val])
-                if allowed_values is not None and val not in allowed_values:
-                    raise optparse.OptionValueError(f'wrong {option.metavar} for {opt_str}: {actual_val}')
 
-        setattr(parser.values, option.dest, current)
+        setattr(parser.values, option.dest, set(requested))
 
     def _dict_from_options_callback(
             option, opt_str, value, parser,
@@ -305,8 +295,7 @@ def create_parser():
         aliases = (x if x.startswith('-') else f'--{x}' for x in map(str.strip, aliases.split(',')))
         try:
             alias_group.add_option(
-                *aliases, help=opts, nargs=nargs, type='str' if nargs else None,
+                *aliases, help=opts, nargs=nargs, dest=parser.ALIAS_DEST, type='str' if nargs else None,
-                dest='_triggered_aliases', default=collections.defaultdict(int),
                 metavar=' '.join(f'ARG{i}' for i in range(nargs)), action='callback',
                 callback=_alias_callback, callback_kwargs={'opts': opts, 'nargs': nargs})
         except Exception as err:
@@ -365,10 +354,20 @@ def create_parser():
         '--extractor-descriptions',
         action='store_true', dest='list_extractor_descriptions', default=False,
         help='Output descriptions of all supported extractors and exit')
+    general.add_option(
+        '--use-extractors', '--ies',
+        action='callback', dest='allowed_extractors', metavar='NAMES', type='str',
+        default=[], callback=_list_from_options_callback,
+        help=(
+            'Extractor names to use separated by commas. '
+            'You can also use regexes, "all", "default" and "end" (end URL matching); '
+            'e.g. --ies "holodex.*,end,youtube". '
+            'Prefix the name with a "-" to exclude it, e.g. --ies default,-generic. '
+            'Use --list-extractors for a list of extractor names. (Alias: --ies)'))
     general.add_option(
         '--force-generic-extractor',
         action='store_true', dest='force_generic_extractor', default=False,
-        help='Force extraction to use the generic extractor')
+        help=optparse.SUPPRESS_HELP)
     general.add_option(
         '--default-search',
         dest='default_search', metavar='PREFIX',
@@ -443,11 +442,12 @@ def create_parser():
             'allowed_values': {
                 'filename', 'filename-sanitization', 'format-sort', 'abort-on-error', 'format-spec', 'no-playlist-metafiles',
                 'multistreams', 'no-live-chat', 'playlist-index', 'list-formats', 'no-direct-merge',
-                'no-youtube-channel-redirect', 'no-youtube-unavailable-videos', 'no-attach-info-json', 'embed-metadata',
+                'no-attach-info-json', 'embed-metadata', 'embed-thumbnail-atomicparsley',
-                'embed-thumbnail-atomicparsley', 'seperate-video-versions', 'no-clean-infojson', 'no-keep-subs', 'no-certifi',
+                'seperate-video-versions', 'no-clean-infojson', 'no-keep-subs', 'no-certifi',
+                'no-youtube-channel-redirect', 'no-youtube-unavailable-videos', 'no-youtube-prefer-utc-upload-date',
             }, 'aliases': {
-                'youtube-dl': ['-multistreams', 'all'],
+                'youtube-dl': ['all', '-multistreams'],
-                'youtube-dlc': ['-no-youtube-channel-redirect', '-no-live-chat', 'all'],
+                'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat'],
             }
         }, help=(
             'Options that can help keep compatibility with youtube-dl or youtube-dlc '
@@ -634,7 +634,7 @@ def create_parser():
     selection.add_option(
         '--break-per-input',
         action='store_true', dest='break_per_url', default=False,
-        help='Make --break-on-existing, --break-on-reject and --max-downloads act only on the current input URL')
+        help='--break-on-existing, --break-on-reject, --max-downloads, and autonumber resets per input URL')
     selection.add_option(
         '--no-break-per-input',
         action='store_false', dest='break_per_url',
@@ -1401,14 +1401,15 @@ def create_parser():
         help='Do not read/dump cookies from/to file (default)')
     filesystem.add_option(
         '--cookies-from-browser',
-        dest='cookiesfrombrowser', metavar='BROWSER[+KEYRING][:PROFILE]',
+        dest='cookiesfrombrowser', metavar='BROWSER[+KEYRING][:PROFILE][::CONTAINER]',
         help=(
-            'The name of the browser and (optionally) the name/path of '
+            'The name of the browser to load cookies from. '
-            'the profile to load cookies from, separated by a ":". '
             f'Currently supported browsers are: {", ".join(sorted(SUPPORTED_BROWSERS))}. '
-            'By default, the most recently accessed profile is used. '
+            'Optionally, the KEYRING used for decrypting Chromium cookies on Linux, '
-            'The keyring used for decrypting Chromium cookies on Linux can be '
+            'the name/path of the PROFILE to load cookies from, '
-            '(optionally) specified after the browser name separated by a "+". '
+            'and the CONTAINER name (if Firefox) ("none" for no container) '
+            'can be given with their respective seperators. '
+            'By default, all containers of the most recently accessed profile are used. '
             f'Currently supported keyrings are: {", ".join(map(str.lower, sorted(SUPPORTED_KEYRINGS)))}'))
     filesystem.add_option(
         '--no-cookies-from-browser',
@@ -1866,7 +1867,6 @@ def create_parser():
 
 
 def _hide_login_info(opts):
-    write_string(
+    deprecation_warning(f'"{__name__}._hide_login_info" is deprecated and may be removed '
-        'DeprecationWarning: "yt_dlp.options._hide_login_info" is deprecated and may be removed in a future version. '
+                        'in a future version. Use "yt_dlp.utils.Config.hide_login_info" instead')
-        'Use "yt_dlp.utils.Config.hide_login_info" instead\n')
     return Config.hide_login_info(opts)

yt_dlp/postprocessor/common.py

@@ -7,10 +7,10 @@ from ..utils import (
     PostProcessingError,
     RetryManager,
     _configuration_args,
+    deprecation_warning,
     encodeFilename,
     network_exceptions,
     sanitized_Request,
-    write_string,
 )
 
 
@@ -73,10 +73,14 @@ class PostProcessor(metaclass=PostProcessorMetaClass):
         if self._downloader:
             return self._downloader.report_warning(text, *args, **kwargs)
 
-    def deprecation_warning(self, text):
+    def deprecation_warning(self, msg):
+        warn = getattr(self._downloader, 'deprecation_warning', deprecation_warning)
+        return warn(msg, stacklevel=1)
+
+    def deprecated_feature(self, msg):
         if self._downloader:
-            return self._downloader.deprecation_warning(text)
+            return self._downloader.deprecated_feature(msg)
-        write_string(f'DeprecationWarning: {text}')
+        return deprecation_warning(msg, stacklevel=1)
 
     def report_error(self, text, *args, **kwargs):
         self.deprecation_warning('"yt_dlp.postprocessor.PostProcessor.report_error" is deprecated. '

yt_dlp/postprocessor/ffmpeg.py

@@ -15,6 +15,7 @@ from ..utils import (
     Popen,
     PostProcessingError,
     _get_exe_version_output,
+    deprecation_warning,
     detect_exe_version,
     determine_ext,
     dfxp2srt,
@@ -30,7 +31,6 @@ from ..utils import (
     traverse_obj,
     variadic,
     write_json_file,
-    write_string,
 )
 
 EXT_TO_OUT_FORMATS = {
@@ -187,8 +187,8 @@ class FFmpegPostProcessor(PostProcessor):
         else:
             self.probe_basename = basename
         if basename == self._ffmpeg_to_avconv[kind]:
-            self.deprecation_warning(
+            self.deprecated_feature(f'Support for {self._ffmpeg_to_avconv[kind]} is deprecated and '
-                f'Support for {self._ffmpeg_to_avconv[kind]} is deprecated and may be removed in a future version. Use {kind} instead')
+                                    f'may be removed in a future version. Use {kind} instead')
         return version
 
     @functools.cached_property
@@ -1064,7 +1064,7 @@ class FFmpegThumbnailsConvertorPP(FFmpegPostProcessor):
 
     @classmethod
     def is_webp(cls, path):
-        write_string(f'DeprecationWarning: {cls.__module__}.{cls.__name__}.is_webp is deprecated')
+        deprecation_warning(f'{cls.__module__}.{cls.__name__}.is_webp is deprecated')
         return imghdr.what(path) == 'webp'
 
     def fixup_webp(self, info, idx=-1):

yt_dlp/update.py

@@ -1,4 +1,5 @@
 import atexit
+import contextlib
 import hashlib
 import json
 import os
@@ -13,6 +14,7 @@ from .compat import compat_realpath, compat_shlex_quote
 from .utils import (
     Popen,
     cached_method,
+    deprecation_warning,
     shell_quote,
     system_identifier,
     traverse_obj,
@@ -50,6 +52,19 @@ def detect_variant():
     return VARIANT or _get_variant_and_executable_path()[0]
 
 
+@functools.cache
+def current_git_head():
+    if detect_variant() != 'source':
+        return
+    with contextlib.suppress(Exception):
+        stdout, _, _ = Popen.run(
+            ['git', 'rev-parse', '--short', 'HEAD'],
+            text=True, cwd=os.path.dirname(os.path.abspath(__file__)),
+            stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        if re.fullmatch('[0-9a-f]+', stdout.strip()):
+            return stdout.strip()
+
+
 _FILE_SUFFIXES = {
     'zip': '',
     'py2exe': '_min.exe',
@@ -288,11 +303,8 @@ def run_update(ydl):
 def update_self(to_screen, verbose, opener):
     import traceback
 
-    from .utils import write_string
+    deprecation_warning(f'"{__name__}.update_self" is deprecated and may be removed '
-
+                        f'in a future version. Use "{__name__}.run_update(ydl)" instead')
-    write_string(
-        'DeprecationWarning: "yt_dlp.update.update_self" is deprecated and may be removed in a future version. '
-        'Use "yt_dlp.update.run_update(ydl)" instead\n')
 
     printfn = to_screen
 

yt_dlp/utils.py

@@ -828,8 +828,8 @@ def escapeHTML(text):
 
 
 def process_communicate_or_kill(p, *args, **kwargs):
-    write_string('DeprecationWarning: yt_dlp.utils.process_communicate_or_kill is deprecated '
+    deprecation_warning(f'"{__name__}.process_communicate_or_kill" is deprecated and may be removed '
-                 'and may be removed in a future version. Use yt_dlp.utils.Popen.communicate_or_kill instead')
+                        f'in a future version. Use "{__name__}.Popen.communicate_or_kill" instead')
     return Popen.communicate_or_kill(p, *args, **kwargs)
 
 
@@ -840,12 +840,35 @@ class Popen(subprocess.Popen):
     else:
         _startupinfo = None
 
-    def __init__(self, *args, text=False, **kwargs):
+    @staticmethod
+    def _fix_pyinstaller_ld_path(env):
+        """Restore LD_LIBRARY_PATH when using PyInstaller
+            Ref: https://github.com/pyinstaller/pyinstaller/blob/develop/doc/runtime-information.rst#ld_library_path--libpath-considerations
+                 https://github.com/yt-dlp/yt-dlp/issues/4573
+        """
+        if not hasattr(sys, '_MEIPASS'):
+            return
+
+        def _fix(key):
+            orig = env.get(f'{key}_ORIG')
+            if orig is None:
+                env.pop(key, None)
+            else:
+                env[key] = orig
+
+        _fix('LD_LIBRARY_PATH')  # Linux
+        _fix('DYLD_LIBRARY_PATH')  # macOS
+
+    def __init__(self, *args, env=None, text=False, **kwargs):
+        if env is None:
+            env = os.environ.copy()
+        self._fix_pyinstaller_ld_path(env)
+
         if text is True:
             kwargs['universal_newlines'] = True  # For 3.6 compatibility
             kwargs.setdefault('encoding', 'utf-8')
             kwargs.setdefault('errors', 'replace')
-        super().__init__(*args, **kwargs, startupinfo=self._startupinfo)
+        super().__init__(*args, env=env, **kwargs, startupinfo=self._startupinfo)
 
     def communicate_or_kill(self, *args, **kwargs):
         try:
@@ -860,9 +883,9 @@ class Popen(subprocess.Popen):
             self.wait(timeout=timeout)
 
     @classmethod
-    def run(cls, *args, **kwargs):
+    def run(cls, *args, timeout=None, **kwargs):
         with cls(*args, **kwargs) as proc:
-            stdout, stderr = proc.communicate_or_kill()
+            stdout, stderr = proc.communicate_or_kill(timeout=timeout)
             return stdout or '', stderr or '', proc.returncode
 
 
@@ -1934,7 +1957,7 @@ class DateRange:
 
 def platform_name():
     """ Returns the platform name as a str """
-    write_string('DeprecationWarning: yt_dlp.utils.platform_name is deprecated, use platform.platform instead')
+    deprecation_warning(f'"{__name__}.platform_name" is deprecated, use "platform.platform" instead')
     return platform.platform()
 
 
@@ -1980,6 +2003,23 @@ def write_string(s, out=None, encoding=None):
     out.flush()
 
 
+def deprecation_warning(msg, *, printer=None, stacklevel=0, **kwargs):
+    from . import _IN_CLI
+    if _IN_CLI:
+        if msg in deprecation_warning._cache:
+            return
+        deprecation_warning._cache.add(msg)
+        if printer:
+            return printer(f'{msg}{bug_reports_message()}', **kwargs)
+        return write_string(f'ERROR: {msg}{bug_reports_message()}\n', **kwargs)
+    else:
+        import warnings
+        warnings.warn(DeprecationWarning(msg), stacklevel=stacklevel + 3)
+
+
+deprecation_warning._cache = set()
+
+
 def bytes_to_intlist(bs):
     if not bs:
         return []
@@ -4862,8 +4902,8 @@ def decode_base_n(string, n=None, table=None):
 
 
 def decode_base(value, digits):
-    write_string('DeprecationWarning: yt_dlp.utils.decode_base is deprecated '
+    deprecation_warning(f'{__name__}.decode_base is deprecated and may be removed '
-                 'and may be removed in a future version. Use yt_dlp.decode_base_n instead')
+                        f'in a future version. Use {__name__}.decode_base_n instead')
     return decode_base_n(value, table=digits)
 
 
@@ -5332,8 +5372,8 @@ def traverse_obj(
 
 
 def traverse_dict(dictn, keys, casesense=True):
-    write_string('DeprecationWarning: yt_dlp.utils.traverse_dict is deprecated '
+    deprecation_warning(f'"{__name__}.traverse_dict" is deprecated and may be removed '
-                 'and may be removed in a future version. Use yt_dlp.utils.traverse_obj instead')
+                        f'in a future version. Use "{__name__}.traverse_obj" instead')
     return traverse_obj(dictn, keys, casesense=casesense, is_user_input=True, traverse_string=True)
 
 
@@ -5785,6 +5825,36 @@ def truncate_string(s, left, right=0):
     return f'{s[:left-3]}...{s[-right:]}'
 
 
+def orderedSet_from_options(options, alias_dict, *, use_regex=False, start=None):
+    assert 'all' in alias_dict, '"all" alias is required'
+    requested = list(start or [])
+    for val in options:
+        discard = val.startswith('-')
+        if discard:
+            val = val[1:]
+
+        if val in alias_dict:
+            val = alias_dict[val] if not discard else [
+                i[1:] if i.startswith('-') else f'-{i}' for i in alias_dict[val]]
+            # NB: Do not allow regex in aliases for performance
+            requested = orderedSet_from_options(val, alias_dict, start=requested)
+            continue
+
+        current = (filter(re.compile(val, re.I).fullmatch, alias_dict['all']) if use_regex
+                   else [val] if val in alias_dict['all'] else None)
+        if current is None:
+            raise ValueError(val)
+
+        if discard:
+            for item in current:
+                while item in requested:
+                    requested.remove(item)
+        else:
+            requested.extend(current)
+
+    return orderedSet(requested)
+
+
 # Deprecated
 has_certifi = bool(certifi)
 has_websockets = bool(websockets)

yt_dlp/version.py

@@ -1,8 +1,8 @@
 # Autogenerated by devscripts/update-version.py
 
-__version__ = '2022.08.19'
+__version__ = '2022.09.01'
 
-RELEASE_GIT_HEAD = '48c88e088'
+RELEASE_GIT_HEAD = '5d7c7d656'
 
 VARIANT = None