[version] update

Created by: pukkandan

:ci skip all :ci run dl

.github/ISSUE_TEMPLATE/1_broken_site.yml

@@ -11,7 +11,7 @@ body:
       options:
         - label: I'm reporting a broken site
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.06.29** ([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 **2022.07.18** ([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 2022.06.29 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2022.07.18 [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: 2022.06.29, Current version: 2022.06.29
+        Latest version: 2022.07.18, Current version: 2022.07.18
-        yt-dlp is up to date (2022.06.29)
+        yt-dlp is up to date (2022.07.18)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/2_site_support_request.yml

@@ -11,7 +11,7 @@ body:
       options:
         - label: I'm reporting a new site support request
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.06.29** ([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 **2022.07.18** ([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
@@ -67,7 +67,7 @@ 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 2022.06.29 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2022.07.18 [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
@@ -75,8 +75,8 @@ 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: 2022.06.29, Current version: 2022.06.29
+        Latest version: 2022.07.18, Current version: 2022.07.18
-        yt-dlp is up to date (2022.06.29)
+        yt-dlp is up to date (2022.07.18)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/3_site_feature_request.yml

@@ -11,7 +11,7 @@ body:
       options:
         - label: I'm requesting a site-specific feature
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.06.29** ([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 **2022.07.18** ([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
@@ -63,7 +63,7 @@ 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 2022.06.29 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2022.07.18 [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
@@ -71,8 +71,8 @@ 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: 2022.06.29, Current version: 2022.06.29
+        Latest version: 2022.07.18, Current version: 2022.07.18
-        yt-dlp is up to date (2022.06.29)
+        yt-dlp is up to date (2022.07.18)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/4_bug_report.yml

@@ -11,7 +11,7 @@ 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 **2022.06.29** ([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 **2022.07.18** ([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
@@ -48,7 +48,7 @@ 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 2022.06.29 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2022.07.18 [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
@@ -56,8 +56,8 @@ 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: 2022.06.29, Current version: 2022.06.29
+        Latest version: 2022.07.18, Current version: 2022.07.18
-        yt-dlp is up to date (2022.06.29)
+        yt-dlp is up to date (2022.07.18)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/5_feature_request.yml

@@ -13,7 +13,7 @@ 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 **2022.06.29** ([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 **2022.07.18** ([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
@@ -44,7 +44,7 @@ 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 2022.06.29 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2022.07.18 [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
@@ -52,7 +52,7 @@ 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: 2022.06.29, Current version: 2022.06.29
+        Latest version: 2022.07.18, Current version: 2022.07.18
-        yt-dlp is up to date (2022.06.29)
+        yt-dlp is up to date (2022.07.18)
         <more lines>
       render: shell

.github/ISSUE_TEMPLATE/6_question.yml

@@ -19,7 +19,7 @@ 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 **2022.06.29** ([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 **2022.07.18** ([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
@@ -50,7 +50,7 @@ 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 2022.06.29 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2022.07.18 [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
@@ -58,7 +58,7 @@ 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: 2022.06.29, Current version: 2022.06.29
+        Latest version: 2022.07.18, Current version: 2022.07.18
-        yt-dlp is up to date (2022.06.29)
+        yt-dlp is up to date (2022.07.18)
         <more lines>
       render: shell

.github/workflows/build.yml

@@ -456,6 +456,7 @@ jobs:
     - name: Make Update spec
       run: |
         echo "# This file is used for regulating self-update" >> _update_spec
+        echo "lock 2022.07.18 .+ Python 3.6" >> _update_spec
     - name: Upload update spec
       uses: actions/upload-release-asset@v1
       env:

.gitignore

@@ -27,11 +27,13 @@ cookies
 *.ass
 *.avi
 *.desktop
+*.f4v
 *.flac
 *.flv
 *.jpeg
 *.jpg
 *.m4a
+*.mpga
 *.m4v
 *.mhtml
 *.mkv

CONTRIBUTORS

@@ -272,3 +272,16 @@ crazymoose77756
 nomevi
 Brett824
 pingiun
+dosy4ev
+EhtishamSabir
+Ferdi265
+FirefoxMetzger
+ftk
+lamby
+llamasblade
+lockmatrix
+misaelaguayo
+odo2063
+pritam20ps05
+scy
+sheerluck

Changelog.md

@@ -11,6 +11,73 @@
 -->
 
 
+### 2022.07.18
+
+* Allow users to specify encoding in each config files by [Lesmiscore](https://github.com/Lesmiscore)
+* Discard infodict from memory if no longer needed
+* Do not allow extractors to return `None`
+* Do not load system certificates when `certifi` is used
+* Fix rounding of integers in format table
+* Improve chapter sanitization
+* Skip some fixup if remux/recode is needed by [Lesmiscore](https://github.com/Lesmiscore)
+* Support `--no-progress` for `--wait-for-video`
+* Fix bug in [612f2be](https://github.com/yt-dlp/yt-dlp/commit/612f2be5d3924540158dfbe5f25d841f04cff8c6)
+* [outtmpl] Add alternate form `h` for HTML escaping
+* [aes] Add multiple padding modes in CBC by [elyse0](https://github.com/elyse0)
+* [extractor/common] Passthrough `errnote=False` to parsers
+* [extractor/generic] Remove HEAD request
+* [http] Ensure the file handle is always closed
+* [ModifyChapters] Modify duration in infodict
+* [options] Fix aliases to `--config-location`
+* [utils] Fix `get_domain`
+* [build] Consistent order for lazy extractors by [lamby](https://github.com/lamby)
+* [build] Fix architecture suffix of executables by [odo2063](https://github.com/odo2063)
+* [build] Improve `setup.py`
+* [update] Do not check `_update_spec` when up to date
+* [update] Prepare to remove Python 3.6 support
+* [compat] Let PyInstaller detect _legacy module
+* [devscripts/update-formulae] Do not change dependency section
+* [test] Split download tests so they can be more easily run in CI
+* [docs] Improve docstring of `download_ranges` by [FirefoxMetzger](https://github.com/FirefoxMetzger)
+* [docs] Improve issue templates
+* [build] Fix bug in [6d916fe](https://github.com/yt-dlp/yt-dlp/commit/6d916fe709a38e8c4c69b73843acf170b5165931)
+* [cleanup, utils] Refactor parse_codecs
+* [cleanup] Misc fixes and cleanup
+* [extractor/acfun] Add extractors by [lockmatrix](https://github.com/lockmatrix)
+* [extractor/Audiodraft] Add extractors by [Ashish0804](https://github.com/Ashish0804), [fstirlitz](https://github.com/fstirlitz)
+* [extractor/cellebrite] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/detik] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/hytale] Add extractor by [llamasblade](https://github.com/llamasblade), [pukkandan](https://github.com/pukkandan)
+* [extractor/liputan6] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/mocha] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/rtl.lu] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/rtvsl] Add extractor by [iw0nderhow](https://github.com/iw0nderhow), [pukkandan](https://github.com/pukkandan)
+* [extractor/StarTrek] Add extractor by [scy](https://github.com/scy)
+* [extractor/syvdk] Add extractor by [misaelaguayo](https://github.com/misaelaguayo)
+* [extractor/theholetv] Add extractor by [dosy4ev](https://github.com/dosy4ev)
+* [extractor/TubeTuGraz] Add extractor by [Ferdi265](https://github.com/Ferdi265), [pukkandan](https://github.com/pukkandan)
+* [extractor/tviplayer] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/wetv] Add extractors by [elyse0](https://github.com/elyse0)
+* [extractor/wikimedia] Add extractor by [EhtishamSabir](https://github.com/EhtishamSabir), [pukkandan](https://github.com/pukkandan)
+* [extractor/youtube] Fix duration check for post-live manifestless mode
+* [extractor/youtube] More metadata for storyboards by [ftk](https://github.com/ftk)
+* [extractor/bigo] Fix extractor by [Lesmiscore](https://github.com/Lesmiscore)
+* [extractor/BiliIntl] Fix subtitle extraction by [MinePlayersPE](https://github.com/MinePlayersPE)
+* [extractor/crunchyroll] Improve `_VALID_URL`
+* [extractor/fifa] Fix extractor by [ischmidt20](https://github.com/ischmidt20)
+* [extractor/instagram] Fix post/story extractors by [pritam20ps05](https://github.com/pritam20ps05), [pukkandan](https://github.com/pukkandan)
+* [extractor/iq] Set language correctly for Korean subtitles
+* [extractor/MangoTV] Fix subtitle languages
+* [extractor/Netverse] Improve playlist extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/philharmoniedeparis] Fix extractor by [sqrtNOT](https://github.com/sqrtNOT)
+* [extractor/Trovo] Fix extractor by [u-spec-png](https://github.com/u-spec-png)
+* [extractor/twitch] Support storyboards for VODs by [ftk](https://github.com/ftk)
+* [extractor/WatchESPN] Improve `_VALID_URL` by [IONECarter](https://github.com/IONECarter), [dirkf](https://github.com/dirkf)
+* [extractor/WSJArticle] Fix video id extraction by [sqrtNOT](https://github.com/sqrtNOT)
+* [extractor/Ximalaya] Fix extractors by [lockmatrix](https://github.com/lockmatrix)
+* [cleanup, extractor/youtube] Fix tests by [sheerluck](https://github.com/sheerluck)
+
+
 ### 2022.06.29
 
 * Fix `--downloader native`

Makefile

@@ -17,8 +17,8 @@ pypi-files: AUTHORS Changelog.md LICENSE README.md README.txt supportedsites \
 clean-test:
 	rm -rf test/testdata/sigs/player-*.js tmp/ *.annotations.xml *.aria2 *.description *.dump *.frag \
 	*.frag.aria2 *.frag.urls *.info.json *.live_chat.json *.meta *.part* *.tmp *.temp *.unknown_video *.ytdl \
-	*.3gp *.ape *.ass *.avi *.desktop *.flac *.flv *.jpeg *.jpg *.m4a *.m4v *.mhtml *.mkv *.mov *.mp3 \
+	*.3gp *.ape *.ass *.avi *.desktop *.f4v *.flac *.flv *.jpeg *.jpg *.m4a *.mpga *.m4v *.mhtml *.mkv *.mov \
-	*.mp4 *.ogg *.opus *.png *.sbv *.srt *.swf *.swp *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
+	*.mp3 *.mp4 *.ogg *.opus *.png *.sbv *.srt *.swf *.swp *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
 clean-dist:
 	rm -rf yt-dlp.1.temp.md yt-dlp.1 README.txt MANIFEST build/ dist/ .coverage cover/ yt-dlp.tar.gz completions/ \
 	yt_dlp/extractor/lazy_extractors.py *.spec CONTRIBUTING.md.tmp yt-dlp yt-dlp.exe yt_dlp.egg-info/ AUTHORS .mailmap

supportedsites.md

@@ -4,6 +4,7 @@
  - **17live**
  - **17live:clip**
  - **1tv**: Первый канал
+ - **20.detik.com**
  - **20min**
  - **23video**
  - **247sports**
@@ -31,6 +32,8 @@
  - **AcademicEarth:Course**
  - **acast**
  - **acast:channel**
+ - **AcFunBangumi**
+ - **AcFunVideo**
  - **ADN**: [<abbr title="netrc machine"><em>animedigitalnetwork</em></abbr>] Anime Digital Network
  - **AdobeConnect**
  - **adobetv**
@@ -94,6 +97,8 @@
  - **ATVAt**
  - **AudiMedia**
  - **AudioBoom**
+ - **Audiodraft:custom**
+ - **Audiodraft:generic**
  - **audiomack**
  - **audiomack:album**
  - **Audius**: Audius.co
@@ -205,6 +210,7 @@
  - **CCMA**
  - **CCTV**: 央视网
  - **CDA**
+ - **Cellebrite**
  - **CeskaTelevize**
  - **CGTN**
  - **channel9**: Channel 9
@@ -503,6 +509,7 @@
  - **HungamaSong**
  - **huya:live**: huya.com
  - **Hypem**
+ - **Hytale**
  - **Icareus**
  - **ign.com**
  - **IGNArticle**
@@ -615,6 +622,7 @@
  - **linkedin:learning**: [<abbr title="netrc machine"><em>linkedin</em></abbr>]
  - **linkedin:learning:course**: [<abbr title="netrc machine"><em>linkedin</em></abbr>]
  - **LinuxAcademy**: [<abbr title="netrc machine"><em>linuxacademy</em></abbr>]
+ - **Liputan6**
  - **LiTV**
  - **LiveJournal**
  - **livestream**
@@ -698,6 +706,7 @@
  - **MLSSoccer**
  - **Mnet**
  - **MNetTV**: [<abbr title="netrc machine"><em>mnettv</em></abbr>]
+ - **MochaVideo**
  - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
  - **Mofosex**
  - **MofosexEmbed**
@@ -1068,10 +1077,14 @@
  - **RTDocumentryPlaylist**
  - **rte**: Raidió Teilifís Éireann TV
  - **rte:radio**: Raidió Teilifís Éireann radio
+ - **rtl.lu:article**
+ - **rtl.lu:tele-vod**
  - **rtl.nl**: rtl.nl and rtlxl.nl
  - **rtl2**
  - **rtl2:you**
  - **rtl2:you:series**
+ - **RTLLuLive**
+ - **RTLLuRadio**
  - **RTNews**
  - **RTP**
  - **RTRFM**
@@ -1083,6 +1096,7 @@
  - **rtve.es:television**
  - **RTVNH**
  - **RTVS**
+ - **rtvslo.si**
  - **RUHD**
  - **Rule34Video**
  - **RumbleChannel**
@@ -1191,6 +1205,7 @@
  - **SRGSSR**
  - **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
  - **stanfordoc**: Stanford Open ClassRoom
+ - **StarTrek**
  - **startv**
  - **Steam**
  - **SteamCommunityBroadcast**
@@ -1218,6 +1233,7 @@
  - **SVTSeries**
  - **SWRMediathek**
  - **Syfy**
+ - **SYVDK**
  - **SztvHu**
  - **t-online.de**
  - **Tagesschau**
@@ -1256,6 +1272,7 @@
  - **TenPlay**: [<abbr title="netrc machine"><em>10play</em></abbr>]
  - **TF1**
  - **TFO**
+ - **TheHoleTv**
  - **TheIntercept**
  - **ThePlatform**
  - **ThePlatformFeed**
@@ -1298,6 +1315,8 @@
  - **TruNews**
  - **TruTV**
  - **Tube8**
+ - **TubeTuGraz**: [<abbr title="netrc machine"><em>tubetugraz</em></abbr>] tube.tugraz.at
+ - **TubeTuGrazSeries**: [<abbr title="netrc machine"><em>tubetugraz</em></abbr>]
  - **TubiTv**: [<abbr title="netrc machine"><em>tubitv</em></abbr>]
  - **TubiTvShow**
  - **Tumblr**: [<abbr title="netrc machine"><em>tumblr</em></abbr>]
@@ -1326,6 +1345,7 @@
  - **TVCArticle**
  - **TVer**
  - **tvigle**: Интернет-телевидение Tvigle.ru
+ - **TVIPlayer**
  - **tvland.com**
  - **TVN24**
  - **TVNet**
@@ -1498,7 +1518,10 @@
  - **Weibo**
  - **WeiboMobile**
  - **WeiqiTV**: WQTV
+ - **wetv:episode**
+ - **WeTvSeries**
  - **whowatch**
+ - **wikimedia.org**
  - **Willow**
  - **WimTV**
  - **Wistia**

yt_dlp/YoutubeDL.py

@@ -306,7 +306,7 @@ class YoutubeDL:
     client_certificate_password:  Password for client certificate private key, if encrypted.
                         If not provided and the key is encrypted, yt-dlp will ask interactively
     prefer_insecure:   Use HTTP instead of HTTPS to retrieve information.
-                       At the moment, this is only supported by YouTube.
+                       (Only supported by some extractors)
     http_headers:      A dictionary of custom headers to be used for all requests
     proxy:             URL of the proxy server to use
     geo_verification_proxy:  URL of the proxy to use for IP address verification
@@ -589,7 +589,7 @@ class YoutubeDL:
         if current_version < MIN_RECOMMENDED:
             msg = ('Support for Python version %d.%d has been deprecated. '
                    'See  https://github.com/yt-dlp/yt-dlp/issues/3764  for more details.'
-                   '\n                    You will no longer recieve updates on this version')
+                   '\n                    You will no longer receive updates on this version')
             if current_version < MIN_SUPPORTED:
                 msg = 'Python version %d.%d is no longer supported'
             self.deprecation_warning(
@@ -1693,7 +1693,7 @@ class YoutubeDL:
         assert ie_result['_type'] in ('playlist', 'multi_video')
 
         title = ie_result.get('title') or ie_result.get('id') or '<Untitled>'
-        self.to_screen(f'[download] Downloading playlist: {title}')
+        self.to_screen(f'[download] Downloading {ie_result["_type"]}: {title}')
 
         all_entries = PlaylistEntries(self, ie_result)
         entries = orderedSet(all_entries.get_requested_items(), lazy=True)

yt_dlp/aes.py

@@ -24,6 +24,10 @@ else:
         return intlist_to_bytes(aes_gcm_decrypt_and_verify(*map(bytes_to_intlist, (data, key, tag, nonce))))
 
 
+def aes_cbc_encrypt_bytes(data, key, iv, **kwargs):
+    return intlist_to_bytes(aes_cbc_encrypt(*map(bytes_to_intlist, (data, key, iv)), **kwargs))
+
+
 def unpad_pkcs7(data):
     return data[:-compat_ord(data[-1])]
 
@@ -164,7 +168,7 @@ def aes_cbc_decrypt(data, key, iv):
     return decrypted_data
 
 
-def aes_cbc_encrypt(data, key, iv, padding_mode='pkcs7'):
+def aes_cbc_encrypt(data, key, iv, *, padding_mode='pkcs7'):
     """
     Encrypt with aes in CBC mode
 
@@ -530,13 +534,21 @@ def ghash(subkey, data):
 
 
 __all__ = [
-    'aes_ctr_decrypt',
     'aes_cbc_decrypt',
     'aes_cbc_decrypt_bytes',
+    'aes_ctr_decrypt',
     'aes_decrypt_text',
-    'aes_encrypt',
+    'aes_decrypt',
+    'aes_ecb_decrypt',
     'aes_gcm_decrypt_and_verify',
     'aes_gcm_decrypt_and_verify_bytes',
+
+    'aes_cbc_encrypt',
+    'aes_cbc_encrypt_bytes',
+    'aes_ctr_encrypt',
+    'aes_ecb_encrypt',
+    'aes_encrypt',
+
     'key_expansion',
     'pad_block',
     'unpad_pkcs7',

yt_dlp/extractor/_extractors.py

@@ -1446,7 +1446,7 @@ from .rtbf import RTBFIE
 from .rte import RteIE, RteRadioIE
 from .rtlnl import (
     RtlNlIE,
-    RTLLuTeleVODIE, 
+    RTLLuTeleVODIE,
     RTLLuArticleIE,
     RTLLuLiveIE,
     RTLLuRadioIE,
@@ -1474,6 +1474,7 @@ from .rtve import (
 )
 from .rtvnh import RTVNHIE
 from .rtvs import RTVSIE
+from .rtvslo import RTVSLOIE
 from .ruhd import RUHDIE
 from .rule34video import Rule34VideoIE
 from .rumble import (
@@ -2087,6 +2088,8 @@ 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
 from .whowatch import WhoWatchIE

yt_dlp/extractor/bilibili.py

@@ -795,12 +795,14 @@ class BiliIntlBaseIE(InfoExtractor):
 
     def _get_subtitles(self, *, ep_id=None, aid=None):
         sub_json = self._call_api(
-            '/web/v2/subtitle', ep_id or aid, note='Downloading subtitles list',
+            '/web/v2/subtitle', ep_id or aid, fatal=False,
-            errnote='Unable to download subtitles list', query=filter_dict({
+            note='Downloading subtitles list', errnote='Unable to download subtitles list',
+            query=filter_dict({
                 'platform': 'web',
+                's_locale': 'en_US',
                 'episode_id': ep_id,
                 'aid': aid,
-            }))
+            })) or {}
         subtitles = {}
         for sub in sub_json.get('subtitles') or []:
             sub_url = sub.get('url')

yt_dlp/extractor/common.py

@@ -931,9 +931,9 @@ class InfoExtractor:
 
     def __print_error(self, errnote, fatal, video_id, err):
         if fatal:
-            raise ExtractorError(f'{video_id}: {errnote} ', cause=err)
+            raise ExtractorError(f'{video_id}: {errnote}', cause=err)
         elif errnote:
-            self.report_warning(f'{video_id}: {errnote} {err}')
+            self.report_warning(f'{video_id}: {errnote}: {err}')
 
     def _parse_xml(self, xml_string, video_id, transform_source=None, fatal=True, errnote=None):
         if transform_source:

yt_dlp/extractor/mgtv.py

@@ -67,7 +67,7 @@ class MGTVIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         tk2 = base64.urlsafe_b64encode(
-            f'did={compat_str(uuid.uuid4()).encode()}|pno=1030|ver=0.3.0301|clit={int(time.time())}'.encode())[::-1]
+            f'did={str(uuid.uuid4())}|pno=1030|ver=0.3.0301|clit={int(time.time())}'.encode())[::-1]
         try:
             api_data = self._download_json(
                 'https://pcweb.api.mgtv.com/player/video', video_id, query={
@@ -137,14 +137,15 @@ class MGTVIE(InfoExtractor):
             url_sub = sub.get('url')
             if not url_sub:
                 continue
-            locale = sub.get('captionCountrySimpleName')
+            locale = sub.get('captionSimpleName') or 'en'
             sub = self._download_json(f'{domain}{url_sub}', video_id, fatal=False,
                                       note=f'Download subtitle for locale {sub.get("name")} ({locale})') or {}
             sub_url = url_or_none(sub.get('info'))
             if not sub_url:
                 continue
-            subtitles.setdefault(locale or 'en', []).append({
+            subtitles.setdefault(locale.lower(), []).append({
                 'url': sub_url,
+                'name': sub.get('name'),
                 'ext': 'srt'
             })
         return subtitles

yt_dlp/extractor/netverse.py

@@ -1,12 +1,6 @@
-import functools
-
 from .common import InfoExtractor
 from .dailymotion import DailymotionIE
-from ..utils import (
+from ..utils import smuggle_url, traverse_obj
-    InAdvancePagedList,
-    smuggle_url,
-    traverse_obj,
-)
 
 
 class NetverseBaseIE(InfoExtractor):
@@ -14,16 +8,13 @@ class NetverseBaseIE(InfoExtractor):
         'watch': 'watchvideo',
         'video': 'watchvideo',
         'webseries': 'webseries',
+        'season': 'webseason_videos',
     }
 
-    def _call_api(self, url, query={}):
+    def _call_api(self, slug, endpoint, query={}, season_id='', display_id=None):
-        display_id, sites_type = self._match_valid_url(url).group('display_id', 'type')
+        return self._download_json(
-
+            f'https://api.netverse.id/medias/api/v2/{self._ENDPOINTS[endpoint]}/{slug}/{season_id}',
-        json_data = self._download_json(
+            display_id or slug, query=query)
-            f'https://api.netverse.id/medias/api/v2/{self._ENDPOINTS[sites_type]}/{display_id}',
-            display_id, query=query)
-
-        return display_id, json_data
 
 
 class NetverseIE(NetverseBaseIE):
@@ -36,10 +27,9 @@ class NetverseIE(NetverseBaseIE):
             'title': 'Waktu Indonesia Bercanda - Edisi Spesial Lebaran 2016',
             'ext': 'mp4',
             'season': 'Season 2016',
-            'description': 'md5:fc27747c0aa85067b6967c816f01617c',
+            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
-            'thumbnail': 'https://vplayed-uat.s3-ap-southeast-1.amazonaws.com/images/webseries/thumbnails/2021/11/619cfce45c827.jpeg',
+            'thumbnail': r're:https?://s\d+\.dmcdn\.net/v/T7aV31Y0eGRWBbwkK/x1080',
             'episode_number': 22,
-            'series': 'Waktu Indonesia Bercanda',
             'episode': 'Episode 22',
             'uploader_id': 'x2ir3vq',
             'age_limit': 0,
@@ -60,10 +50,9 @@ class NetverseIE(NetverseBaseIE):
             'title': 'Jadoo Seorang Model',
             'ext': 'mp4',
             'season': 'Season 2',
-            'description': 'md5:c616e8e59d3edf2d3d506e3736120d99',
+            'description': 'md5:8a74f70812cca267e19ee0635f0af835',
-            'thumbnail': 'https://storage.googleapis.com/netprime-live/images/webseries/thumbnails/2021/11/619cf63f105d3.jpeg',
+            'thumbnail': r're:https?://s\d+\.dmcdn\.net/v/Thwuy1YURicFmGu0v/x1080',
             'episode_number': 2,
-            'series': 'Hello Jadoo',
             'episode': 'Episode 2',
             'view_count': int,
             'like_count': int,
@@ -85,10 +74,9 @@ class NetverseIE(NetverseBaseIE):
             'ext': 'mp4',
             'title': 'Tetangga Baru',
             'season': 'Season 1',
-            'description': 'md5:ed6dd355bed84d139b1154c3d8d65957',
+            'description': 'md5:23fcf70e97d461d3029d25d59b2ccfb9',
-            'thumbnail': 'https://vplayed-uat.s3-ap-southeast-1.amazonaws.com/images/webseries/thumbnails/2021/11/619cfd9d32c5f.jpeg',
+            'thumbnail': r're:https?://s\d+\.dmcdn\.net/v/T3Ogm1YEnnyjVKAFF/x1080',
             'episode_number': 1,
-            'series': 'Tetangga Masa Gitu',
             'episode': 'Episode 1',
             'timestamp': 1624538169,
             'view_count': int,
@@ -108,12 +96,11 @@ class NetverseIE(NetverseBaseIE):
         'info_dict': {
             'id': 'x887jzz',
             'ext': 'mp4',
-            'thumbnail': 'https://storage.googleapis.com/netprime-live/images/webseries/thumbnails/2021/11/619cf63f105d3.jpeg',
+            'thumbnail': r're:https?://s\d+\.dmcdn\.net/v/TfuZ_1Y6PboJ5An_s/x1080',
             'season': 'Season 1',
             'episode_number': 1,
-            'description': 'md5:c616e8e59d3edf2d3d506e3736120d99',
+            'description': 'md5:d4f627b3e7a3f9acdc55f6cdd5ea41d5',
             'title': 'Namaku Choi Jadoo',
-            'series': 'Hello Jadoo',
             'episode': 'Episode 1',
             'age_limit': 0,
             'like_count': int,
@@ -130,7 +117,8 @@ class NetverseIE(NetverseBaseIE):
     }]
 
     def _real_extract(self, url):
-        display_id, program_json = self._call_api(url)
+        display_id, sites_type = self._match_valid_url(url).group('display_id', 'type')
+        program_json = self._call_api(display_id, sites_type)
         videos = program_json['response']['videos']
 
         return {
@@ -143,34 +131,46 @@ class NetverseIE(NetverseBaseIE):
             'thumbnail': traverse_obj(videos, ('program_detail', 'thumbnail_image')),
             'description': traverse_obj(videos, ('program_detail', 'description')),
             'episode_number': videos.get('episode_order'),
-            'series': traverse_obj(videos, ('program_detail', 'title')),
         }
 
 
 class NetversePlaylistIE(NetverseBaseIE):
     _VALID_URL = r'https?://(?:\w+\.)?netverse\.id/(?P<type>webseries)/(?P<display_id>[^/?#&]+)'
-    _TEST = {
+    _TESTS = [{
+        # multiple season
         'url': 'https://netverse.id/webseries/tetangga-masa-gitu',
         'info_dict': {
             'id': 'tetangga-masa-gitu',
             'title': 'Tetangga Masa Gitu',
         },
-        'playlist_count': 46,
+        'playlist_count': 519,
-    }
+    }, {
+        # single season
+        'url': 'https://netverse.id/webseries/kelas-internasional',
+        'info_dict': {
+            'id': 'kelas-internasional',
+            'title': 'Kelas Internasional',
+        },
+        'playlist_count': 203,
+    }]
 
-    def parse_playlist(self, url, page_num):
+    def parse_playlist(self, json_data, playlist_id):
-        _, playlist_json = self._call_api(url, query={'page': page_num + 1})
+        slug_sample = traverse_obj(json_data, ('related', 'data', ..., 'slug'))[0]
-        for slug in traverse_obj(playlist_json, ('response', 'related', 'data', ..., 'slug')):
+        for season in traverse_obj(json_data, ('seasons', ..., 'id')):
-            yield self.url_result(f'https://www.netverse.id/video/{slug}', NetverseIE)
+            playlist_json = self._call_api(
+                slug_sample, 'season', display_id=playlist_id, season_id=season)
+
+            for current_page in range(playlist_json['response']['season_list']['last_page']):
+                playlist_json = self._call_api(slug_sample, 'season', query={'page': current_page + 1},
+                                               season_id=season, display_id=playlist_id)
+                for slug in traverse_obj(playlist_json, ('response', ..., 'data', ..., 'slug')):
+                    yield self.url_result(f'https://www.netverse.id/video/{slug}', NetverseIE)
 
     def _real_extract(self, url):
-        _, playlist_data = self._call_api(url)
+        playlist_id, sites_type = self._match_valid_url(url).group('display_id', 'type')
-        webseries_related_info = playlist_data['response']['related']
+        playlist_data = self._call_api(playlist_id, sites_type)
-        # TODO: get video from other season
+
-        # The season has id and the next season video is located at api_url/<season_id>?page=<page>
         return self.playlist_result(
-            InAdvancePagedList(functools.partial(self.parse_playlist, url),
+            self.parse_playlist(playlist_data['response'], playlist_id),
-                               webseries_related_info['last_page'],
-                               webseries_related_info['to'] - webseries_related_info['from'] + 1),
             traverse_obj(playlist_data, ('response', 'webseries_info', 'slug')),
             traverse_obj(playlist_data, ('response', 'webseries_info', 'title')))

yt_dlp/extractor/openload.py

@@ -104,9 +104,8 @@ class PhantomJSwrapper:
 
         self.exe = check_executable('phantomjs', ['-v'])
         if not self.exe:
-            raise ExtractorError('PhantomJS executable not found in PATH, '
+            raise ExtractorError(
-                                 'download it from http://phantomjs.org',
+                'PhantomJS not found, Please download it from https://phantomjs.org/download.html', expected=True)
-                                 expected=True)
 
         self.extractor = extractor
 

yt_dlp/extractor/rtvslo.py

@@ -0,0 +1,151 @@
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    parse_duration,
+    traverse_obj,
+    unified_timestamp,
+    url_or_none,
+)
+
+
+class RTVSLOIE(InfoExtractor):
+    IE_NAME = 'rtvslo.si'
+    _VALID_URL = r'''(?x)
+        https?://(?:
+            (?:365|4d)\.rtvslo.si/arhiv/[^/?#&;]+|
+            (?:www\.)?rtvslo\.si/rtv365/arhiv
+        )/(?P<id>\d+)'''
+    _GEO_COUNTRIES = ['SI']
+
+    _API_BASE = 'https://api.rtvslo.si/ava/{}/{}?client_id=82013fb3a531d5414f478747c1aca622'
+    SUB_LANGS_MAP = {'Slovenski': 'sl'}
+
+    _TESTS = [
+        {
+            'url': 'https://www.rtvslo.si/rtv365/arhiv/174842550?s=tv',
+            'info_dict': {
+                'id': '174842550',
+                'ext': 'flv',
+                'release_timestamp': 1643140032,
+                'upload_date': '20220125',
+                'series': 'Dnevnik',
+                'thumbnail': 'https://img.rtvcdn.si/_up/ava/ava_misc/show_logos/92/dnevnik_3_wide2.jpg',
+                'description': 'md5:76a18692757aeb8f0f51221106277dd2',
+                'timestamp': 1643137046,
+                'title': 'Dnevnik',
+                'series_id': '92',
+                'release_date': '20220125',
+                'duration': 1789,
+            },
+        }, {
+            'url': 'https://365.rtvslo.si/arhiv/utrip/174843754',
+            'info_dict': {
+                'id': '174843754',
+                'ext': 'mp4',
+                'series_id': '94',
+                'release_date': '20220129',
+                'timestamp': 1643484455,
+                'title': 'Utrip',
+                'duration': 813,
+                'thumbnail': 'https://img.rtvcdn.si/_up/ava/ava_misc/show_logos/94/utrip_1_wide2.jpg',
+                'description': 'md5:77f2892630c7b17bb7a5bb84319020c9',
+                'release_timestamp': 1643485825,
+                'upload_date': '20220129',
+                'series': 'Utrip',
+            },
+        }, {
+            'url': 'https://365.rtvslo.si/arhiv/il-giornale-della-sera/174844609',
+            'info_dict': {
+                'id': '174844609',
+                'ext': 'mp3',
+                'series_id': '106615841',
+                'title': 'Il giornale della sera',
+                'duration': 1328,
+                'series': 'Il giornale della sera',
+                'timestamp': 1643743800,
+                'release_timestamp': 1643745424,
+                'thumbnail': 'https://img.rtvcdn.si/_up/ava/ava_misc/show_logos/il-giornale-della-sera_wide2.jpg',
+                'upload_date': '20220201',
+                'tbr': 128000,
+                'release_date': '20220201',
+            },
+
+        }, {
+            'url': 'https://4d.rtvslo.si/arhiv/dnevnik/174842550',
+            'only_matching': True
+        }
+    ]
+
+    def _real_extract(self, url):
+        v_id = self._match_id(url)
+        meta = self._download_json(self._API_BASE.format('getRecordingDrm', v_id), v_id)['response']
+
+        thumbs = [{'id': k, 'url': v, 'http_headers': {'Accept': 'image/jpeg'}}
+                  for k, v in (meta.get('images') or {}).items()]
+
+        subs = {}
+        for s in traverse_obj(meta, 'subs', 'subtitles', default=[]):
+            lang = self.SUB_LANGS_MAP.get(s.get('language'), s.get('language') or 'und')
+            subs.setdefault(lang, []).append({
+                'url': s.get('file'),
+                'ext': traverse_obj(s, 'format', expected_type=str.lower),
+            })
+
+        jwt = meta.get('jwt')
+        if not jwt:
+            raise ExtractorError('Site did not provide an authentication token, cannot proceed.')
+
+        media = self._download_json(self._API_BASE.format('getMedia', v_id), v_id, query={'jwt': jwt})['response']
+
+        formats = []
+        adaptive_url = traverse_obj(media, ('addaptiveMedia', 'hls_sec'), expected_type=url_or_none)
+        if adaptive_url:
+            formats = self._extract_wowza_formats(adaptive_url, v_id, skip_protocols=['smil'])
+
+        adaptive_url = traverse_obj(media, ('addaptiveMedia_sl', 'hls_sec'), expected_type=url_or_none)
+        if adaptive_url:
+            for f in self._extract_wowza_formats(adaptive_url, v_id, skip_protocols=['smil']):
+                formats.append({
+                    **f,
+                    'format_id': 'sign-' + f['format_id'],
+                    'format_note': 'Sign language interpretation', 'preference': -10,
+                    'language': (
+                        'slv' if f.get('language') == 'eng' and f.get('acodec') != 'none'
+                        else f.get('language'))
+                })
+
+        formats.extend(
+            {
+                'url': f['streams'][strm],
+                'ext': traverse_obj(f, 'mediaType', expected_type=str.lower),
+                'width': f.get('width'),
+                'height': f.get('height'),
+                'tbr': f.get('bitrate'),
+                'filesize': f.get('filesize'),
+            }
+            for strm in ('http', 'https')
+            for f in media.get('mediaFiles') or []
+            if traverse_obj(f, ('streams', strm))
+        )
+
+        if any('intermission.mp4' in x['url'] for x in formats):
+            self.raise_geo_restricted(countries=self._GEO_COUNTRIES, metadata_available=True)
+        if any('dummy_720p.mp4' in x.get('manifest_url', '') for x in formats) and meta.get('stub') == 'error':
+            raise ExtractorError(f'{self.IE_NAME} said: Clip not available', expected=True)
+
+        self._sort_formats(formats)
+        return {
+            'id': v_id,
+            'webpage_url': ''.join(traverse_obj(meta, ('canonical', ('domain', 'path')))),
+            'title': meta.get('title'),
+            'formats': formats,
+            'subtitles': subs,
+            'thumbnails': thumbs,
+            'description': meta.get('description'),
+            'timestamp': unified_timestamp(traverse_obj(meta, 'broadcastDate', ('broadcastDates', 0))),
+            'release_timestamp': unified_timestamp(meta.get('recordingDate')),
+            'duration': meta.get('duration') or parse_duration(meta.get('length')),
+            'tags': meta.get('genre'),
+            'series': meta.get('showName'),
+            'series_id': meta.get('showId'),
+        }

yt_dlp/extractor/wetv.py

@@ -0,0 +1,208 @@
+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/wikimedia.py

@@ -0,0 +1,55 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    get_element_by_class,
+    parse_qs,
+    remove_start,
+    unescapeHTML,
+    urljoin,
+)
+
+
+class WikimediaIE(InfoExtractor):
+    IE_NAME = 'wikimedia.org'
+    _VALID_URL = r'https?://commons\.wikimedia\.org/wiki/File:(?P<id>[^/#?]+)\.\w+'
+    _TESTS = [{
+        'url': 'https://commons.wikimedia.org/wiki/File:Die_Temperaturkurve_der_Erde_(ZDF,_Terra_X)_720p_HD_50FPS.webm',
+        'info_dict': {
+            'url': 're:https?://upload.wikimedia.org/wikipedia',
+            'ext': 'webm',
+            'id': 'Die_Temperaturkurve_der_Erde_(ZDF,_Terra_X)_720p_HD_50FPS',
+            'title': 'Die Temperaturkurve der Erde (ZDF, Terra X) 720p HD 50FPS.webm - Wikimedia Commons',
+            'description': 'md5:7cd84f76e7081f1be033d0b155b4a460',
+            'license': 'Creative Commons Attribution 4.0 International',
+            'uploader': 'ZDF/Terra X/Gruppe 5/Luise Wagner, Jonas Sichert, Andreas Hougardy',
+            'subtitles': 'count:4'
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        subtitles = {}
+        for sub in set(re.findall(r'\bsrc\s*=\s*["\'](/w/api[^"]+)["\']', webpage)):
+            sub = urljoin('https://commons.wikimedia.org', unescapeHTML(sub))
+            qs = parse_qs(sub)
+            lang = qs.get('lang', [None])[-1]
+            sub_ext = qs.get('trackformat', [None])[-1]
+            if lang and sub_ext:
+                subtitles.setdefault(lang, []).append({'ext': sub_ext, 'url': sub})
+
+        return {
+            'id': video_id,
+            'url': self._html_search_regex(r'<source\s[^>]*\bsrc="([^"]+)"', webpage, 'video URL'),
+            'description': clean_html(get_element_by_class('description', webpage)),
+            'title': remove_start(self._og_search_title(webpage), 'File:'),
+            'license': self._html_search_regex(
+                r'licensed under(?: the)? (.+?) license',
+                get_element_by_class('licensetpl', webpage), 'license', default=None),
+            'uploader': self._html_search_regex(
+                r'>\s*Author\s*</td>\s*<td\b[^>]*>\s*([^<]+)\s*</td>', webpage, 'video author', default=None),
+            'subtitles': subtitles,
+        }

yt_dlp/version.py

@@ -1,5 +1,5 @@
 # Autogenerated by devscripts/update-version.py
 
-__version__ = '2022.06.29'
+__version__ = '2022.07.18'
 
-RELEASE_GIT_HEAD = '9d339c41e'
+RELEASE_GIT_HEAD = '135f05ef6'