Release 2023.06.22

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 that yt-dlp is broken on a **supported** site
           required: true
-        - label: I've verified that I'm running yt-dlp version **2023.06.21** ([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 **2023.06.22** ([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
@@ -64,7 +64,7 @@ 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 2023.06.21 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.06.22 [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
@@ -72,8 +72,8 @@ 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: 2023.06.21, Current version: 2023.06.21
+        Latest version: 2023.06.22, Current version: 2023.06.22
-        yt-dlp is up to date (2023.06.21)
+        yt-dlp is up to date (2023.06.22)
         <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 **2023.06.21** ([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 **2023.06.22** ([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
@@ -76,7 +76,7 @@ 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 2023.06.21 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.06.22 [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
@@ -84,8 +84,8 @@ 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: 2023.06.21, Current version: 2023.06.21
+        Latest version: 2023.06.22, Current version: 2023.06.22
-        yt-dlp is up to date (2023.06.21)
+        yt-dlp is up to date (2023.06.22)
         <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 **2023.06.21** ([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 **2023.06.22** ([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
@@ -72,7 +72,7 @@ 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 2023.06.21 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.06.22 [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
@@ -80,8 +80,8 @@ 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: 2023.06.21, Current version: 2023.06.21
+        Latest version: 2023.06.22, Current version: 2023.06.22
-        yt-dlp is up to date (2023.06.21)
+        yt-dlp is up to date (2023.06.22)
         <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 **2023.06.21** ([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 **2023.06.22** ([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
@@ -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 2023.06.21 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.06.22 [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
@@ -65,8 +65,8 @@ 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: 2023.06.21, Current version: 2023.06.21
+        Latest version: 2023.06.22, Current version: 2023.06.22
-        yt-dlp is up to date (2023.06.21)
+        yt-dlp is up to date (2023.06.22)
         <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 **2023.06.21** ([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 **2023.06.22** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
           required: true
@@ -53,7 +53,7 @@ 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 2023.06.21 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.06.22 [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
@@ -61,7 +61,7 @@ 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: 2023.06.21, Current version: 2023.06.21
+        Latest version: 2023.06.22, Current version: 2023.06.22
-        yt-dlp is up to date (2023.06.21)
+        yt-dlp is up to date (2023.06.22)
         <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 **2023.06.21** ([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 **2023.06.22** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar questions **including closed ones**. DO NOT post duplicates
           required: true
@@ -59,7 +59,7 @@ 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 2023.06.21 [9d339c4] (win32_exe)
+        [debug] yt-dlp version 2023.06.22 [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
@@ -67,7 +67,7 @@ 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: 2023.06.21, Current version: 2023.06.21
+        Latest version: 2023.06.22, Current version: 2023.06.22
-        yt-dlp is up to date (2023.06.21)
+        yt-dlp is up to date (2023.06.22)
         <more lines>
       render: shell

.github/workflows/potential-duplicates.yml

@@ -1,20 +0,0 @@
-name: Potential Duplicates
-on:
-  issues:
-    types: [opened, edited]
-
-jobs:
-  run:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: wow-actions/potential-duplicates@v1
-        with:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          label: potential-duplicate
-          state: all
-          threshold: 0.3
-          comment: |
-            This issue is potentially a duplicate of one of the following issues:
-            {{#issues}}
-              - #{{ number }} ({{ accuracy }}%)
-            {{/issues}}

CONTRIBUTORS

@@ -455,3 +455,8 @@ vampirefrog
 vidiot720
 viktor-enzell
 zhgwn
+barthelmannk
+berkanteber
+OverlordQ
+rexlambert22
+Ti4eeT4e

Changelog.md

@@ -4,6 +4,35 @@
 # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
 -->
 
+### 2023.06.22
+
+#### Core changes
+- [Fix bug in db3ad8a67661d7b234a6954d9c6a4a9b1749f5eb](https://github.com/yt-dlp/yt-dlp/commit/d7cd97e8d8d42b500fea9abb2aa4ac9b0f98b2ad) by [pukkandan](https://github.com/pukkandan)
+- [Improve `--download-sections`](https://github.com/yt-dlp/yt-dlp/commit/b4e0d75848e9447cee2cd3646ce54d4744a7ff56) by [pukkandan](https://github.com/pukkandan)
+- [Indicate `filesize` approximated from `tbr` better](https://github.com/yt-dlp/yt-dlp/commit/0dff8e4d1e6e9fb938f4256ea9af7d81f42fd54f) by [pukkandan](https://github.com/pukkandan)
+
+#### Extractor changes
+- [Support multiple `_VALID_URL`s](https://github.com/yt-dlp/yt-dlp/commit/5fd8367496b42c7b900b896a0d5460561a2859de) ([#5812](https://github.com/yt-dlp/yt-dlp/issues/5812)) by [nixxo](https://github.com/nixxo)
+- **dplay**: GlobalCyclingNetworkPlus: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/774aa09dd6aa61ced9ec818d1f67e53414d22762) ([#7360](https://github.com/yt-dlp/yt-dlp/issues/7360)) by [bashonly](https://github.com/bashonly)
+- **dropout**: [Fix season extraction](https://github.com/yt-dlp/yt-dlp/commit/db22142f6f817ff673d417b4b78e8db497bf8ab3) ([#7304](https://github.com/yt-dlp/yt-dlp/issues/7304)) by [OverlordQ](https://github.com/OverlordQ)
+- **motherless**: [Add gallery support, fix groups](https://github.com/yt-dlp/yt-dlp/commit/f2ff0f6f1914b82d4a51681a72cc0828115dcb4a) ([#7211](https://github.com/yt-dlp/yt-dlp/issues/7211)) by [rexlambert22](https://github.com/rexlambert22), [Ti4eeT4e](https://github.com/Ti4eeT4e)
+- **nebula**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/3f756c8c4095b942cf49788eb0862ceaf57847f2) ([#7156](https://github.com/yt-dlp/yt-dlp/issues/7156)) by [Lamieur](https://github.com/Lamieur), [rohieb](https://github.com/rohieb)
+- **rheinmaintv**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/98cb1eda7a4cf67c96078980dbd63e6c06ad7f7c) ([#7311](https://github.com/yt-dlp/yt-dlp/issues/7311)) by [barthelmannk](https://github.com/barthelmannk)
+- **youtube**
+    - [Add `ios` to default clients used](https://github.com/yt-dlp/yt-dlp/commit/1e75d97db21152acc764b30a688e516f04b8a142)
+        - IOS is affected neither by 403 nor by nsig so helps mitigate them preemptively
+        - IOS also has higher bit-rate 'premium' formats though they are not labeled as such
+    - [Improve description parsing performance](https://github.com/yt-dlp/yt-dlp/commit/71dc18fa29263a1ff0472c23d81bfc8dd4422d48) ([#7315](https://github.com/yt-dlp/yt-dlp/issues/7315)) by [berkanteber](https://github.com/berkanteber), [pukkandan](https://github.com/pukkandan)
+    - [Improve nsig function name extraction](https://github.com/yt-dlp/yt-dlp/commit/cd810afe2ac5567c822b7424800fc470ef2d0045) by [pukkandan](https://github.com/pukkandan)
+    - [Workaround 403 for android formats](https://github.com/yt-dlp/yt-dlp/commit/81ca451480051d7ce1a31c017e005358345a9149) by [pukkandan](https://github.com/pukkandan)
+
+#### Misc. changes
+- [Revert "Add automatic duplicate issue detection"](https://github.com/yt-dlp/yt-dlp/commit/a4486bfc1dc7057efca9dd3fe70d7fa25c56f700)
+- **cleanup**
+    - Miscellaneous
+        - [7f9c6a6](https://github.com/yt-dlp/yt-dlp/commit/7f9c6a63b16e145495479e9f666f5b9e2ee69e2f) by [bashonly](https://github.com/bashonly)
+        - [812cdfa](https://github.com/yt-dlp/yt-dlp/commit/812cdfa06c33a40e73a8e04b3e6f42c084666a43) by [pukkandan](https://github.com/pukkandan)
+
 ### 2023.06.21
 
 #### Important changes

README.md

@@ -76,7 +76,7 @@ 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/2dd6c6e](https://github.com/ytdl-org/youtube-dl/commit/2dd6c6e)** ([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)
+* Forked from [**yt-dlc@f9401f2**](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee) and merged with [**youtube-dl@42f2d4**](https://github.com/yt-dlp/yt-dlp/commit/42f2d4) ([exceptions](https://github.com/yt-dlp/yt-dlp/issues/21))
 
 * **[SponsorBlock Integration](#sponsorblock-options)**: You can mark/remove sponsor sections in YouTube videos by utilizing the [SponsorBlock](https://sponsor.ajay.app) API
 
@@ -610,12 +610,14 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
     --no-hls-use-mpegts             Do not use the mpegts container for HLS
                                     videos. This is default when not downloading
                                     live streams
-    --download-sections REGEX       Download only chapters whose title matches
+    --download-sections REGEX       Download only chapters that match the
-                                    the given regular expression. Time ranges
+                                    regular expression. A "*" prefix denotes
-                                    prefixed by a "*" can also be used in place
+                                    time-range instead of chapter. Negative
-                                    of chapters to download the specified range.
+                                    timestamps are calculated from the end.
-                                    Needs ffmpeg. This option can be used
+                                    "*from-url" can be used to download between
-                                    multiple times to download multiple
+                                    the "start_time" and "end_time" extracted
+                                    from the URL. Needs ffmpeg. This option can
+                                    be used multiple times to download multiple
                                     sections, e.g. --download-sections
                                     "*10:15-inf" --download-sections "intro"
     --downloader [PROTO:]NAME       Name or path of the external downloader to
@@ -1221,7 +1223,7 @@ To activate authentication with the `.netrc` file you should pass `--netrc` to y
 
 The default location of the .netrc file is `~` (see below).
 
-As an alternative to using the `.netrc` file, which has the disadvantage of keeping your passwords in a plain text file, you can configure a custom shell command to provide the credentials for an extractor. This is done by providing the `--netrc-cmd` parameter, it shall output the credentials in the netrc format and return `0` on success, other values will be treated as an error. `{}` in the command will be replaced by the name of the extractor to make it possible to select the credentials for the right extractor (To use literal braces, double them like `{{}}`).
+As an alternative to using the `.netrc` file, which has the disadvantage of keeping your passwords in a plain text file, you can configure a custom shell command to provide the credentials for an extractor. This is done by providing the `--netrc-cmd` parameter, it shall output the credentials in the netrc format and return `0` on success, other values will be treated as an error. `{}` in the command will be replaced by the name of the extractor to make it possible to select the credentials for the right extractor.
 
 E.g. To use an encrypted `.netrc` file stored as `.authinfo.gpg`
 ```
@@ -1780,7 +1782,7 @@ $ yt-dlp --parse-metadata "description:(?s)(?P<meta_comment>.+)" --embed-metadat
 $ yt-dlp --parse-metadata ":(?P<meta_synopsis>)"
 
 # Remove "formats" field from the infojson by setting it to an empty string
-$ yt-dlp --parse-metadata ":(?P<formats>)" -j
+$ yt-dlp --parse-metadata "video::(?P<formats>)" --write-info-json
 
 # Replace all spaces and "_" in title and uploader with a `-`
 $ yt-dlp --replace-in-metadata "title,uploader" "[ _]" "-"
@@ -1798,7 +1800,7 @@ The following extractors use this feature:
 #### youtube
 * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes
 * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
-* `player_client`: Clients to extract video data from. The main clients are `web`, `android` and `ios` with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mweb` and `tv_embedded` (agegate bypass) with no variants. By default, `android,web` is used, but `tv_embedded` and `creator` variants are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. You can use `all` to use all the clients, and `default` for the default clients.
+* `player_client`: Clients to extract video data from. The main clients are `web`, `android` and `ios` with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mweb` and `tv_embedded` (agegate bypass) with no variants. By default, `ios,android,web` is used, but `tv_embedded` and `creator` variants are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. You can use `all` to use all the clients, and `default` for the default clients.
 * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details
 * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)
 * `max_comments`: Limit the amount of comments to gather. Comma-separated list of integers representing `max-comments,max-parents,max-replies,max-replies-per-thread`. Default is `all,all,all,all`
@@ -1854,11 +1856,11 @@ The following extractors use this feature:
 #### twitter
 * `legacy_api`: Force usage of the legacy Twitter API instead of the GraphQL API for tweet extraction. Has no effect if login cookies are passed
 
-### wrestleuniverse
+#### wrestleuniverse
 * `device_id`: UUID value assigned by the website and used to enforce device limits for paid livestream content. Can be found in browser local storage
 
-#### twitchstream (Twitch)
+#### twitch
-* `client_id`: Client ID value to be sent with GraphQL requests, e.g. `twitchstream:client_id=kimne78kx3ncx6brgo4mv6wki5h1ko`
+* `client_id`: Client ID value to be sent with GraphQL requests, e.g. `twitch:client_id=kimne78kx3ncx6brgo4mv6wki5h1ko`
 
 #### nhkradirulive (NHK らじる★らじる LIVE)
 * `area`: Which regional variation to extract. Valid areas are: `sapporo`, `sendai`, `tokyo`, `nagoya`, `osaka`, `hiroshima`, `matsuyama`, `fukuoka`. Defaults to `tokyo`

devscripts/changelog_override.json

@@ -35,5 +35,26 @@
         "when": "8417f26b8a819cd7ffcd4e000ca3e45033e670fb",
         "short": "Add option `--color` (#6904)",
         "authors": ["Grub4K"]
+    },
+    {
+        "action": "change",
+        "when": "7b37e8b23691613f331bd4ebc9d639dd6f93c972",
+        "short": "Improve `--download-sections`\n    - Support negative time-ranges\n    - Add `*from-url` to obey time-ranges in URL"
+    },
+    {
+        "action": "change",
+        "when": "1e75d97db21152acc764b30a688e516f04b8a142",
+        "short": "[extractor/youtube] Add `ios` to default clients used\n        - IOS is affected neither by 403 nor by nsig so helps mitigate them preemptively\n        - IOS also has higher bit-rate 'premium' formats though they are not labeled as such"
+    },
+    {
+        "action": "change",
+        "when": "f2ff0f6f1914b82d4a51681a72cc0828115dcb4a",
+        "short": "[extractor/motherless] Add gallery support, fix groups (#7211)",
+        "authors": ["rexlambert22", "Ti4eeT4e"]
+    },
+    {
+        "action": "change",
+        "when": "a4486bfc1dc7057efca9dd3fe70d7fa25c56f700",
+        "short": "[misc] Revert \"Add automatic duplicate issue detection\""
     }
 ]

devscripts/lazy_load_template.py

@@ -6,6 +6,7 @@ from ..utils import (
     age_restricted,
     bug_reports_message,
     classproperty,
+    variadic,
     write_string,
 )
 

devscripts/make_changelog.py

@@ -196,7 +196,7 @@ class Changelog:
         for commit_infos in cleanup_misc_items.values():
             sorted_items.append(CommitInfo(
                 'cleanup', ('Miscellaneous',), ', '.join(
-                    self._format_message_link(None, info.commit.hash)
+                    self._format_message_link(None, info.commit.hash).strip()
                     for info in sorted(commit_infos, key=lambda item: item.commit.hash or '')),
                 [], Commit(None, '', commit_infos[0].commit.authors), []))
 
@@ -205,10 +205,10 @@ class Changelog:
     def format_single_change(self, info):
         message = self._format_message_link(info.message, info.commit.hash)
         if info.issues:
-            message = f'{message} ({self._format_issues(info.issues)})'
+            message = message.replace('\n', f' ({self._format_issues(info.issues)})\n', 1)
 
         if info.commit.authors:
-            message = f'{message} by {self._format_authors(info.commit.authors)}'
+            message = message.replace('\n', f' by {self._format_authors(info.commit.authors)}\n', 1)
 
         if info.fixes:
             fix_message = ', '.join(f'{self._format_message_link(None, fix.hash)}' for fix in info.fixes)
@@ -217,14 +217,16 @@ class Changelog:
             if authors != info.commit.authors:
                 fix_message = f'{fix_message} by {self._format_authors(authors)}'
 
-            message = f'{message} (With fixes in {fix_message})'
+            message = message.replace('\n', f' (With fixes in {fix_message})\n', 1)
 
-        return message
+        return message[:-1]
 
     def _format_message_link(self, message, hash):
         assert message or hash, 'Improperly defined commit message or override'
         message = message if message else hash[:HASH_LENGTH]
-        return f'[{message}]({self.repo_url}/commit/{hash})' if hash else message
+        if not hash:
+            return f'{message}\n'
+        return f'[{message}\n'.replace('\n', f']({self.repo_url}/commit/{hash})\n', 1)
 
     def _format_issues(self, issues):
         return ', '.join(f'[#{issue}]({self.repo_url}/issues/{issue})' for issue in issues)

supportedsites.md

@@ -515,6 +515,7 @@
  - **GlattvisionTVLive**: [*glattvisiontv*](## "netrc machine")
  - **GlattvisionTVRecordings**: [*glattvisiontv*](## "netrc machine")
  - **Glide**: Glide mobile video messages (glide.me)
+ - **GlobalCyclingNetworkPlus**
  - **GlobalPlayerAudio**
  - **GlobalPlayerAudioEpisode**
  - **GlobalPlayerLive**
@@ -814,6 +815,7 @@
  - **MonsterSirenHypergryphMusic**
  - **Morningstar**: morningstar.com
  - **Motherless**
+ - **MotherlessGallery**
  - **MotherlessGroup**
  - **Motorsport**: motorsport.com
  - **MotorTrend**
@@ -1198,6 +1200,7 @@
  - **Restudy**
  - **Reuters**
  - **ReverbNation**
+ - **RheinMainTV**
  - **RICE**
  - **RMCDecouverte**
  - **RockstarGames**

test/test_youtube_signature.py

@@ -159,6 +159,10 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/8c7583ff/player_ias.vflset/en_US/base.js',
         '1wWCVpRR96eAmMI87L', 'KSkWAVv1ZQxC3A',
     ),
+    (
+        'https://www.youtube.com/s/player/b7910ca8/player_ias.vflset/en_US/base.js',
+        '_hXMCwMt9qE310D', 'LoZMgkkofRMCZQ',
+    ),
 ]
 
 

yt_dlp/YoutubeDL.py

@@ -2666,7 +2666,8 @@ class YoutubeDL:
                 format['dynamic_range'] = 'SDR'
             if format.get('aspect_ratio') is None:
                 format['aspect_ratio'] = try_call(lambda: round(format['width'] / format['height'], 2))
-            if (info_dict.get('duration') and format.get('tbr')
+            if (not format.get('manifest_url')  # For fragmented formats, "tbr" is often max bitrate and not average
+                    and info_dict.get('duration') and format.get('tbr')
                     and not format.get('filesize') and not format.get('filesize_approx')):
                 format['filesize_approx'] = int(info_dict['duration'] * format['tbr'] * (1024 / 8))
             format['http_headers'] = self._calc_headers(collections.ChainMap(format, info_dict))
@@ -2805,11 +2806,13 @@ class YoutubeDL:
                 new_info.update(fmt)
                 offset, duration = info_dict.get('section_start') or 0, info_dict.get('duration') or float('inf')
                 end_time = offset + min(chapter.get('end_time', duration), duration)
+                # duration may not be accurate. So allow deviations <1sec
+                if end_time == float('inf') or end_time > offset + duration + 1:
+                    end_time = None
                 if chapter or offset:
                     new_info.update({
                         'section_start': offset + chapter.get('start_time', 0),
-                        # duration may not be accurate. So allow deviations <1sec
+                        'section_end': end_time,
-                        'section_end': end_time if end_time <= offset + duration + 1 else None,
                         'section_title': chapter.get('title'),
                         'section_number': chapter.get('index'),
                     })
@@ -3707,8 +3710,11 @@ class YoutubeDL:
                 format_field(f, 'fps', '\t%d', func=round),
                 format_field(f, 'dynamic_range', '%s', ignore=(None, 'SDR')).replace('HDR', ''),
                 format_field(f, 'audio_channels', '\t%s'),
-                delim,
+                delim, (
-                format_field(f, 'filesize', ' \t%s', func=format_bytes) + format_field(f, 'filesize_approx', '~\t%s', func=format_bytes),
+                    format_field(f, 'filesize', ' \t%s', func=format_bytes)
+                    or format_field(f, 'filesize_approx', '≈\t%s', func=format_bytes)
+                    or format_field(try_call(lambda: format_bytes(int(info_dict['duration'] * f['tbr'] * (1024 / 8)))),
+                                    None, self._format_out('~\t%s', self.Styles.SUPPRESS))),
                 format_field(f, 'tbr', '\t%dk', func=round),
                 shorten_protocol_name(f.get('protocol', '')),
                 delim,

yt_dlp/__init__.py

@@ -320,26 +320,49 @@ def validate_options(opts):
         opts.skip_download = None
         del opts.outtmpl['default']
 
-    def parse_chapters(name, value):
+    def parse_chapters(name, value, advanced=False):
-        chapters, ranges = [], []
         parse_timestamp = lambda x: float('inf') if x in ('inf', 'infinite') else parse_duration(x)
-        for regex in value or []:
+        TIMESTAMP_RE = r'''(?x)(?:
-            if regex.startswith('*'):
+            (?P<start_sign>-?)(?P<start>[^-]+)
-                for range_ in map(str.strip, regex[1:].split(',')):
+        )?\s*-\s*(?:
-                    mobj = range_ != '-' and re.fullmatch(r'([^-]+)?\s*-\s*([^-]+)?', range_)
+            (?P<end_sign>-?)(?P<end>[^-]+)
-                    dur = mobj and (parse_timestamp(mobj.group(1) or '0'), parse_timestamp(mobj.group(2) or 'inf'))
+        )?'''
-                    if None in (dur or [None]):
-                        raise ValueError(f'invalid {name} time range "{regex}". Must be of the form "*start-end"')
-                    ranges.append(dur)
-                continue
-            try:
-                chapters.append(re.compile(regex))
-            except re.error as err:
-                raise ValueError(f'invalid {name} regex "{regex}" - {err}')
-        return chapters, ranges
 
-    opts.remove_chapters, opts.remove_ranges = parse_chapters('--remove-chapters', opts.remove_chapters)
+        chapters, ranges, from_url = [], [], False
-    opts.download_ranges = download_range_func(*parse_chapters('--download-sections', opts.download_ranges))
+        for regex in value or []:
+            if advanced and regex == '*from-url':
+                from_url = True
+                continue
+            elif not regex.startswith('*'):
+                try:
+                    chapters.append(re.compile(regex))
+                except re.error as err:
+                    raise ValueError(f'invalid {name} regex "{regex}" - {err}')
+                continue
+
+            for range_ in map(str.strip, regex[1:].split(',')):
+                mobj = range_ != '-' and re.fullmatch(TIMESTAMP_RE, range_)
+                dur = mobj and [parse_timestamp(mobj.group('start') or '0'), parse_timestamp(mobj.group('end') or 'inf')]
+                signs = mobj and (mobj.group('start_sign'), mobj.group('end_sign'))
+
+                err = None
+                if None in (dur or [None]):
+                    err = 'Must be of the form "*start-end"'
+                elif not advanced and any(signs):
+                    err = 'Negative timestamps are not allowed'
+                else:
+                    dur[0] *= -1 if signs[0] else 1
+                    dur[1] *= -1 if signs[1] else 1
+                    if dur[1] == float('-inf'):
+                        err = '"-inf" is not a valid end'
+                if err:
+                    raise ValueError(f'invalid {name} time range "{regex}". {err}')
+                ranges.append(dur)
+
+        return chapters, ranges, from_url
+
+    opts.remove_chapters, opts.remove_ranges, _ = parse_chapters('--remove-chapters', opts.remove_chapters)
+    opts.download_ranges = download_range_func(*parse_chapters('--download-sections', opts.download_ranges, True))
 
     # Cookies from browser
     if opts.cookiesfrombrowser:

yt_dlp/extractor/_extractors.py

@@ -497,6 +497,7 @@ from .dplay import (
     DiscoveryPlusItalyIE,
     DiscoveryPlusItalyShowIE,
     DiscoveryPlusIndiaShowIE,
+    GlobalCyclingNetworkPlusIE,
 )
 from .dreisat import DreiSatIE
 from .drbonanza import DRBonanzaIE
@@ -1119,7 +1120,8 @@ from .mojvideo import MojvideoIE
 from .morningstar import MorningstarIE
 from .motherless import (
     MotherlessIE,
-    MotherlessGroupIE
+    MotherlessGroupIE,
+    MotherlessGalleryIE,
 )
 from .motorsport import MotorsportIE
 from .movieclips import MovieClipsIE
@@ -1615,6 +1617,7 @@ from .rentv import (
 from .restudy import RestudyIE
 from .reuters import ReutersIE
 from .reverbnation import ReverbNationIE
+from .rheinmaintv import RheinMainTVIE
 from .rice import RICEIE
 from .rmcdecouverte import RMCDecouverteIE
 from .rockstargames import RockstarGamesIE

yt_dlp/extractor/common.py

@@ -475,8 +475,8 @@ class InfoExtractor:
 
 
     Subclasses of this should also be added to the list of extractors and
-    should define a _VALID_URL regexp and, re-define the _real_extract() and
+    should define _VALID_URL as a regexp or a Sequence of regexps, and
-    (optionally) _real_initialize() methods.
+    re-define the _real_extract() and (optionally) _real_initialize() methods.
 
     Subclasses may also override suitable() if necessary, but ensure the function
     signature is preserved and that this function imports everything it needs
@@ -566,8 +566,8 @@ class InfoExtractor:
         # we have cached the regexp for *this* class, whereas getattr would also
         # match the superclass
         if '_VALID_URL_RE' not in cls.__dict__:
-            cls._VALID_URL_RE = re.compile(cls._VALID_URL)
+            cls._VALID_URL_RE = tuple(map(re.compile, variadic(cls._VALID_URL)))
-        return cls._VALID_URL_RE.match(url)
+        return next(filter(None, (regex.match(url) for regex in cls._VALID_URL_RE)), None)
 
     @classmethod
     def suitable(cls, url):
@@ -1297,8 +1297,9 @@ class InfoExtractor:
     def _get_netrc_login_info(self, netrc_machine=None):
         netrc_machine = netrc_machine or self._NETRC_MACHINE
 
-        cmd = self.get_param('netrc_cmd', '').format(netrc_machine)
+        cmd = self.get_param('netrc_cmd')
         if cmd:
+            cmd = cmd.replace('{}', netrc_machine)
             self.to_screen(f'Executing command: {cmd}')
             stdout, _, ret = Popen.run(cmd, text=True, shell=True, stdout=subprocess.PIPE)
             if ret != 0:

yt_dlp/extractor/dplay.py

@@ -65,6 +65,7 @@ class DPlayBaseIE(InfoExtractor):
         return streaming_list
 
     def _get_disco_api_info(self, url, display_id, disco_host, realm, country, domain=''):
+        country = self.get_param('geo_bypass_country') or country
         geo_countries = [country.upper()]
         self._initialize_geo_bypass({
             'countries': geo_countries,
@@ -1001,3 +1002,39 @@ class DiscoveryPlusIndiaShowIE(DiscoveryPlusShowBaseIE):
     _SHOW_STR = 'show'
     _INDEX = 4
     _VIDEO_IE = DiscoveryPlusIndiaIE
+
+
+class GlobalCyclingNetworkPlusIE(DiscoveryPlusBaseIE):
+    _VALID_URL = r'https?://plus\.globalcyclingnetwork\.com/watch/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://plus.globalcyclingnetwork.com/watch/1397691',
+        'info_dict': {
+            'id': '1397691',
+            'ext': 'mp4',
+            'title': 'The Athertons: Mountain Biking\'s Fastest Family',
+            'description': 'md5:75a81937fcd8b989eec6083a709cd837',
+            'thumbnail': 'https://us1-prod-images.disco-api.com/2021/03/04/eb9e3026-4849-3001-8281-9356466f0557.png',
+            'series': 'gcn',
+            'creator': 'Gcn',
+            'upload_date': '20210309',
+            'timestamp': 1615248000,
+            'duration': 2531.0,
+            'tags': [],
+        },
+        'skip': 'Subscription required',
+        'params': {'skip_download': 'm3u8'},
+    }]
+
+    _PRODUCT = 'web'
+    _DISCO_API_PARAMS = {
+        'disco_host': 'disco-api-prod.globalcyclingnetwork.com',
+        'realm': 'gcn',
+        'country': 'us',
+    }
+
+    def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
+        headers.update({
+            'x-disco-params': f'realm={realm}',
+            'x-disco-client': f'WEB:UNKNOWN:{self._PRODUCT}:27.3.2',
+            'Authorization': self._get_auth(disco_base, display_id, realm),
+        })

yt_dlp/extractor/dropout.py

@@ -1,13 +1,17 @@
+import functools
+
 from .common import InfoExtractor
 from .vimeo import VHXEmbedIE
 from ..utils import (
     ExtractorError,
+    OnDemandPagedList,
     clean_html,
+    extract_attributes,
     get_element_by_class,
     get_element_by_id,
-    get_elements_by_class,
+    get_elements_html_by_class,
     int_or_none,
-    join_nonempty,
+    traverse_obj,
     unified_strdate,
     urlencode_postdata,
 )
@@ -162,12 +166,13 @@ class DropoutIE(InfoExtractor):
 
 
 class DropoutSeasonIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?P<id>[^\/$&?#]+)(?:/?$|/season:[0-9]+/?$)'
+    _PAGE_SIZE = 24
+    _VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?P<id>[^\/$&?#]+)(?:/?$|/season:(?P<season>[0-9]+)/?$)'
     _TESTS = [
         {
             'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1',
             'note': 'Multi-season series with the season in the url',
-            'playlist_count': 17,
+            'playlist_count': 24,
             'info_dict': {
                 'id': 'dimension-20-fantasy-high-season-1',
                 'title': 'Dimension 20 Fantasy High - Season 1'
@@ -176,7 +181,7 @@ class DropoutSeasonIE(InfoExtractor):
         {
             'url': 'https://www.dropout.tv/dimension-20-fantasy-high',
             'note': 'Multi-season series with the season not in the url',
-            'playlist_count': 17,
+            'playlist_count': 24,
             'info_dict': {
                 'id': 'dimension-20-fantasy-high-season-1',
                 'title': 'Dimension 20 Fantasy High - Season 1'
@@ -190,29 +195,30 @@ class DropoutSeasonIE(InfoExtractor):
                 'id': 'dimension-20-shriek-week-season-1',
                 'title': 'Dimension 20 Shriek Week - Season 1'
             }
+        },
+        {
+            'url': 'https://www.dropout.tv/breaking-news-no-laugh-newsroom/season:3',
+            'note': 'Multi-season series with season in the url that requires pagination',
+            'playlist_count': 25,
+            'info_dict': {
+                'id': 'breaking-news-no-laugh-newsroom-season-3',
+                'title': 'Breaking News No Laugh Newsroom - Season 3'
+            }
         }
     ]
 
+    def _fetch_page(self, url, season_id, page):
+        page += 1
+        webpage = self._download_webpage(
+            f'{url}?page={page}', season_id, note=f'Downloading page {page}', expected_status={400})
+        yield from [self.url_result(item_url, DropoutIE) for item_url in traverse_obj(
+            get_elements_html_by_class('browse-item-link', webpage), (..., {extract_attributes}, 'href'))]
+
     def _real_extract(self, url):
         season_id = self._match_id(url)
+        season_num = self._match_valid_url(url).group('season') or 1
         season_title = season_id.replace('-', ' ').title()
-        webpage = self._download_webpage(url, season_id)
 
-        entries = [
+        return self.playlist_result(
-            self.url_result(
+            OnDemandPagedList(functools.partial(self._fetch_page, url, season_id), self._PAGE_SIZE),
-                url=self._search_regex(r'<a href=["\'](.+?)["\'] class=["\']browse-item-link["\']',
+            f'{season_id}-season-{season_num}', f'{season_title} - Season {season_num}')
-                                       item, 'item_url'),
-                ie=DropoutIE.ie_key()
-            ) for item in get_elements_by_class('js-collection-item', webpage)
-        ]
-
-        seasons = (get_element_by_class('select-dropdown-wrapper', webpage) or '').strip().replace('\n', '')
-        current_season = self._search_regex(r'<option[^>]+selected>([^<]+)</option>',
-                                            seasons, 'current_season', default='').strip()
-
-        return {
-            '_type': 'playlist',
-            'id': join_nonempty(season_id, current_season.lower().replace(' ', '-')),
-            'title': join_nonempty(season_title, current_season, delim=' - '),
-            'entries': entries
-        }

yt_dlp/extractor/motherless.py

@@ -1,32 +1,39 @@
 import datetime
 import re
+import urllib.parse
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
 from ..utils import (
     ExtractorError,
-    InAdvancePagedList,
+    OnDemandPagedList,
-    orderedSet,
+    remove_end,
     str_to_int,
     unified_strdate,
 )
 
 
 class MotherlessIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/|G[VIG]?[A-F0-9]+/)?(?P<id>[A-F0-9]+)'
     _TESTS = [{
-        'url': 'http://motherless.com/AC3FFE1',
+        'url': 'http://motherless.com/EE97006',
-        'md5': '310f62e325a9fafe64f68c0bccb6e75f',
+        'md5': 'cb5e7438f7a3c4e886b7bccc1292a3bc',
         'info_dict': {
-            'id': 'AC3FFE1',
+            'id': 'EE97006',
             'ext': 'mp4',
-            'title': 'Fucked in the ass while playing PS3',
+            'title': 'Dogging blond Brit getting glazed (comp)',
-            'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
+            'categories': ['UK', 'slag', 'whore', 'dogging', 'cunt', 'cumhound', 'big tits', 'Pearl Necklace'],
-            'upload_date': '20100913',
+            'upload_date': '20230519',
-            'uploader_id': 'famouslyfuckedup',
+            'uploader_id': 'deathbird',
             'thumbnail': r're:https?://.*\.jpg',
             'age_limit': 18,
-        }
+            'comment_count': int,
+            'view_count': int,
+            'like_count': int,
+        },
+        'params': {
+            # Incomplete cert chains
+            'nocheckcertificate': True,
+        },
     }, {
         'url': 'http://motherless.com/532291B',
         'md5': 'bc59a6b47d1f958e61fbd38a4d31b131',
@@ -49,16 +56,36 @@ class MotherlessIE(InfoExtractor):
             'id': '633979F',
             'ext': 'mp4',
             'title': 'Turtlette',
-            'categories': ['superheroine heroine  superher'],
+            'categories': ['superheroine heroine superher'],
             'upload_date': '20140827',
             'uploader_id': 'shade0230',
             'thumbnail': r're:https?://.*\.jpg',
             'age_limit': 18,
-        }
+            'like_count': int,
+            'comment_count': int,
+            'view_count': int,
+        },
+        'params': {
+            'nocheckcertificate': True,
+        },
     }, {
-        # no keywords
         'url': 'http://motherless.com/8B4BBC1',
-        'only_matching': True,
+        'info_dict': {
+            'id': '8B4BBC1',
+            'ext': 'mp4',
+            'title': 'VIDEO00441.mp4',
+            'categories': [],
+            'upload_date': '20160214',
+            'uploader_id': 'NMWildGirl',
+            'thumbnail': r're:https?://.*\.jpg',
+            'age_limit': 18,
+            'like_count': int,
+            'comment_count': int,
+            'view_count': int,
+        },
+        'params': {
+            'nocheckcertificate': True,
+        },
     }, {
         # see https://motherless.com/videos/recent for recent videos with
         # uploaded date in "ago" format
@@ -72,9 +99,12 @@ class MotherlessIE(InfoExtractor):
             'uploader_id': 'anonymous',
             'thumbnail': r're:https?://.*\.jpg',
             'age_limit': 18,
+            'like_count': int,
+            'comment_count': int,
+            'view_count': int,
         },
         'params': {
-            'skip_download': True,
+            'nocheckcertificate': True,
         },
     }]
 
@@ -128,10 +158,8 @@ class MotherlessIE(InfoExtractor):
             (r'''<span\b[^>]+\bclass\s*=\s*["']username\b[^>]*>([^<]+)</span>''',
              r'''(?s)['"](?:media-meta-member|thumb-member-username)\b[^>]+>\s*<a\b[^>]+\bhref\s*=\s*['"]/m/([^"']+)'''),
             webpage, 'uploader_id', fatal=False)
-
+        categories = self._html_search_meta('keywords', webpage, default='')
-        categories = self._html_search_meta('keywords', webpage, default=None)
+        categories = [cat.strip() for cat in categories.split(',') if cat.strip()]
-        if categories:
-            categories = [cat.strip() for cat in categories.split(',')]
 
         return {
             'id': video_id,
@@ -148,102 +176,97 @@ class MotherlessIE(InfoExtractor):
         }
 
 
-class MotherlessGroupIE(InfoExtractor):
+class MotherlessPaginatedIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?motherless\.com/gv?/(?P<id>[a-z0-9_]+)'
+    _PAGE_SIZE = 60
+
+    def _correct_path(self, url, item_id):
+        raise NotImplementedError('This method must be implemented by subclasses')
+
+    def _extract_entries(self, webpage, base):
+        for mobj in re.finditer(r'href="[^"]*(?P<href>/[A-F0-9]+)"\s+title="(?P<title>[^"]+)',
+                                webpage):
+            video_url = urllib.parse.urljoin(base, mobj.group('href'))
+            video_id = MotherlessIE.get_temp_id(video_url)
+
+            if video_id:
+                yield self.url_result(video_url, MotherlessIE, video_id, mobj.group('title'))
+
+    def _real_extract(self, url):
+        item_id = self._match_id(url)
+        real_url = self._correct_path(url, item_id)
+        webpage = self._download_webpage(real_url, item_id, 'Downloading page 1')
+
+        def get_page(idx):
+            page = idx + 1
+            current_page = webpage if not idx else self._download_webpage(
+                real_url, item_id, note=f'Downloading page {page}', query={'page': page})
+            yield from self._extract_entries(current_page, real_url)
+
+        return self.playlist_result(
+            OnDemandPagedList(get_page, self._PAGE_SIZE), item_id,
+            remove_end(self._html_extract_title(webpage), ' | MOTHERLESS.COM ™'))
+
+
+class MotherlessGroupIE(MotherlessPaginatedIE):
+    _VALID_URL = r'https?://(?:www\.)?motherless\.com/g[vifm]?/(?P<id>[a-z0-9_]+)/?(?:$|[#?])'
     _TESTS = [{
-        'url': 'http://motherless.com/g/movie_scenes',
+        'url': 'http://motherless.com/gv/movie_scenes',
         'info_dict': {
             'id': 'movie_scenes',
             'title': 'Movie Scenes',
-            'description': 'Hot and sexy scenes from "regular" movies... '
-                           'Beautiful actresses fully nude... A looot of '
-                           'skin! :)Enjoy!',
         },
-        'playlist_mincount': 662,
+        'playlist_mincount': 540,
     }, {
-        'url': 'http://motherless.com/gv/sex_must_be_funny',
+        'url': 'http://motherless.com/g/sex_must_be_funny',
         'info_dict': {
             'id': 'sex_must_be_funny',
             'title': 'Sex must be funny',
-            'description': 'Sex can be funny. Wide smiles,laugh, games, fun of '
-                           'any kind!'
         },
-        'playlist_mincount': 0,
+        'playlist_count': 0,
-        'expected_warnings': [
-            'This group has no videos.',
-        ]
     }, {
-        'url': 'https://motherless.com/g/beautiful_cock',
+        'url': 'https://motherless.com/gv/beautiful_cock',
         'info_dict': {
             'id': 'beautiful_cock',
             'title': 'Beautiful Cock',
-            'description': 'Group for lovely cocks yours, mine, a friends anything human',
         },
-        'playlist_mincount': 2500,
+        'playlist_mincount': 2040,
     }]
 
-    @classmethod
+    def _correct_path(self, url, item_id):
-    def suitable(cls, url):
+        return urllib.parse.urljoin(url, f'/gv/{item_id}')
-        return (False if MotherlessIE.suitable(url)
-                else super(MotherlessGroupIE, cls).suitable(url))
 
-    def _extract_entries(self, webpage, base):
-        entries = []
-        for mobj in re.finditer(
-                r'href="(?P<href>/[^"]+)"[^>]*>(?:\s*<img[^>]+alt="[^-]+-\s(?P<title>[^"]+)")?',
-                webpage):
-            video_url = compat_urlparse.urljoin(base, mobj.group('href'))
-            if not MotherlessIE.suitable(video_url):
-                continue
-            video_id = MotherlessIE._match_id(video_url)
-            title = mobj.group('title')
-            entries.append(self.url_result(
-                video_url, ie=MotherlessIE.ie_key(), video_id=video_id,
-                video_title=title))
-        # Alternative fallback
-        if not entries:
-            entries = [
-                self.url_result(
-                    compat_urlparse.urljoin(base, '/' + entry_id),
-                    ie=MotherlessIE.ie_key(), video_id=entry_id)
-                for entry_id in orderedSet(re.findall(
-                    r'data-codename=["\']([A-Z0-9]+)', webpage))]
-        return entries
 
-    def _real_extract(self, url):
+class MotherlessGalleryIE(MotherlessPaginatedIE):
-        group_id = self._match_id(url)
+    _VALID_URL = r'https?://(?:www\.)?motherless\.com/G[VIG]?(?P<id>[A-F0-9]+)/?(?:$|[#?])'
-        page_url = compat_urlparse.urljoin(url, '/gv/%s' % group_id)
+    _TESTS = [{
-        webpage = self._download_webpage(page_url, group_id)
+        'url': 'https://motherless.com/GV338999F',
-        title = self._search_regex(
+        'info_dict': {
-            r'<title>([\w\s]+\w)\s+-', webpage, 'title', fatal=False)
+            'id': '338999F',
-        description = self._html_search_meta(
+            'title': 'Random',
-            'description', webpage, fatal=False)
+        },
-        page_count = str_to_int(self._search_regex(
+        'playlist_mincount': 190,
-            r'(\d+)\s*</(?:a|span)>\s*<(?:a|span)[^>]+(?:>\s*NEXT|\brel\s*=\s*["\']?next)\b',
+    }, {
-            webpage, 'page_count', default=0))
+        'url': 'https://motherless.com/GVABD6213',
-        if not page_count:
+        'info_dict': {
-            message = self._search_regex(
+            'id': 'ABD6213',
-                r'''class\s*=\s*['"]error-page\b[^>]*>\s*<p[^>]*>\s*(?P<error_msg>[^<]+)(?<=\S)\s*''',
+            'title': 'Cuties',
-                webpage, 'error_msg', default=None) or 'This group has no videos.'
+        },
-            self.report_warning(message, group_id)
+        'playlist_mincount': 2,
-            page_count = 1
+    }, {
-        PAGE_SIZE = 80
+        'url': 'https://motherless.com/GVBCF7622',
+        'info_dict': {
+            'id': 'BCF7622',
+            'title': 'Vintage',
+        },
+        'playlist_count': 0,
+    }, {
+        'url': 'https://motherless.com/G035DE2F',
+        'info_dict': {
+            'id': '035DE2F',
+            'title': 'General',
+        },
+        'playlist_mincount': 420,
+    }]
 
-        def _get_page(idx):
+    def _correct_path(self, url, item_id):
-            if idx > 0:
+        return urllib.parse.urljoin(url, f'/GV{item_id}')
-                webpage = self._download_webpage(
-                    page_url, group_id, query={'page': idx + 1},
-                    note='Downloading page %d/%d' % (idx + 1, page_count)
-                )
-            for entry in self._extract_entries(webpage, url):
-                yield entry
-
-        playlist = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
-
-        return {
-            '_type': 'playlist',
-            'id': group_id,
-            'title': title,
-            'description': description,
-            'entries': playlist
-        }

yt_dlp/extractor/nebula.py

@@ -3,7 +3,7 @@ import json
 import urllib.error
 
 from .common import InfoExtractor
-from ..utils import ExtractorError, parse_iso8601
+from ..utils import ExtractorError, make_archive_id, parse_iso8601, remove_start
 
 _BASE_URL_RE = r'https?://(?:www\.|beta\.)?(?:watchnebula\.com|nebula\.app|nebula\.tv)'
 
@@ -65,19 +65,20 @@ class NebulaBaseIE(InfoExtractor):
         return response['token']
 
     def _fetch_video_formats(self, slug):
-        stream_info = self._call_nebula_api(f'https://content.watchnebula.com/video/{slug}/stream/',
+        stream_info = self._call_nebula_api(f'https://content.api.nebula.app/video/{slug}/stream/',
                                             video_id=slug,
                                             auth_type='bearer',
                                             note='Fetching video stream info')
         manifest_url = stream_info['manifest']
-        return self._extract_m3u8_formats_and_subtitles(manifest_url, slug)
+        return self._extract_m3u8_formats_and_subtitles(manifest_url, slug, 'mp4')
 
     def _build_video_info(self, episode):
         fmts, subs = self._fetch_video_formats(episode['slug'])
         channel_slug = episode['channel_slug']
         channel_title = episode['channel_title']
+        zype_id = episode.get('zype_id')
         return {
-            'id': episode['zype_id'],
+            'id': remove_start(episode['id'], 'video_episode:'),
             'display_id': episode['slug'],
             'formats': fmts,
             'subtitles': subs,
@@ -99,6 +100,9 @@ class NebulaBaseIE(InfoExtractor):
             'uploader_url': f'https://nebula.tv/{channel_slug}',
             'series': channel_title,
             'creator': channel_title,
+            'extractor_key': NebulaIE.ie_key(),
+            'extractor': NebulaIE.IE_NAME,
+            '_old_archive_ids': [make_archive_id(NebulaIE, zype_id)] if zype_id else None,
         }
 
     def _perform_login(self, username=None, password=None):
@@ -113,7 +117,7 @@ class NebulaIE(NebulaBaseIE):
             'url': 'https://nebula.tv/videos/that-time-disney-remade-beauty-and-the-beast',
             'md5': '14944cfee8c7beeea106320c47560efc',
             'info_dict': {
-                'id': '5c271b40b13fd613090034fd',
+                'id': '84ed544d-4afd-4723-8cd5-2b95261f0abf',
                 'ext': 'mp4',
                 'title': 'That Time Disney Remade Beauty and the Beast',
                 'description': 'Note: this video was originally posted on YouTube with the sponsor read included. We weren’t able to remove it without reducing video quality, so it’s presented here in its original context.',
@@ -137,22 +141,22 @@ class NebulaIE(NebulaBaseIE):
             'url': 'https://nebula.tv/videos/the-logistics-of-d-day-landing-craft-how-the-allies-got-ashore',
             'md5': 'd05739cf6c38c09322422f696b569c23',
             'info_dict': {
-                'id': '5e7e78171aaf320001fbd6be',
+                'id': '7e623145-1b44-4ca3-aa0b-ed25a247ea34',
                 'ext': 'mp4',
                 'title': 'Landing Craft - How The Allies Got Ashore',
                 'description': r're:^In this episode we explore the unsung heroes of D-Day, the landing craft.',
                 'upload_date': '20200327',
                 'timestamp': 1585348140,
-                'channel': 'Real Engineering',
+                'channel': 'Real Engineering — The Logistics of D-Day',
-                'channel_id': 'realengineering',
+                'channel_id': 'd-day',
-                'uploader': 'Real Engineering',
+                'uploader': 'Real Engineering — The Logistics of D-Day',
-                'uploader_id': 'realengineering',
+                'uploader_id': 'd-day',
-                'series': 'Real Engineering',
+                'series': 'Real Engineering — The Logistics of D-Day',
                 'display_id': 'the-logistics-of-d-day-landing-craft-how-the-allies-got-ashore',
-                'creator': 'Real Engineering',
+                'creator': 'Real Engineering — The Logistics of D-Day',
                 'duration': 841,
-                'channel_url': 'https://nebula.tv/realengineering',
+                'channel_url': 'https://nebula.tv/d-day',
-                'uploader_url': 'https://nebula.tv/realengineering',
+                'uploader_url': 'https://nebula.tv/d-day',
                 'thumbnail': r're:https://\w+\.cloudfront\.net/[\w-]+\.jpeg?.*',
             },
         },
@@ -160,7 +164,7 @@ class NebulaIE(NebulaBaseIE):
             'url': 'https://nebula.tv/videos/money-episode-1-the-draw',
             'md5': 'ebe28a7ad822b9ee172387d860487868',
             'info_dict': {
-                'id': '5e779ebdd157bc0001d1c75a',
+                'id': 'b96c5714-9e2b-4ec3-b3f1-20f6e89cc553',
                 'ext': 'mp4',
                 'title': 'Episode 1: The Draw',
                 'description': r'contains:There’s free money on offer… if the players can all work together.',
@@ -190,7 +194,7 @@ class NebulaIE(NebulaBaseIE):
     ]
 
     def _fetch_video_metadata(self, slug):
-        return self._call_nebula_api(f'https://content.watchnebula.com/video/{slug}/',
+        return self._call_nebula_api(f'https://content.api.nebula.app/video/{slug}/',
                                      video_id=slug,
                                      auth_type='bearer',
                                      note='Fetching video meta data')

yt_dlp/extractor/rheinmaintv.py

@@ -0,0 +1,94 @@
+from .common import InfoExtractor
+from ..utils import extract_attributes, merge_dicts, remove_end
+
+
+class RheinMainTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?rheinmaintv\.de/sendungen/(?:[\w-]+/)*(?P<video_id>(?P<display_id>[\w-]+)/vom-\d{2}\.\d{2}\.\d{4}(?:/\d+)?)'
+    _TESTS = [{
+        'url': 'https://www.rheinmaintv.de/sendungen/beitrag-video/auf-dem-weg-zur-deutschen-meisterschaft/vom-07.11.2022/',
+        'info_dict': {
+            'id': 'auf-dem-weg-zur-deutschen-meisterschaft-vom-07.11.2022',
+            'ext': 'ismv',  # ismv+isma will be merged into mp4
+            'alt_title': 'Auf dem Weg zur Deutschen Meisterschaft',
+            'title': 'Auf dem Weg zur Deutschen Meisterschaft',
+            'upload_date': '20221108',
+            'view_count': int,
+            'display_id': 'auf-dem-weg-zur-deutschen-meisterschaft',
+            'thumbnail': r're:^https://.+\.jpg',
+            'description': 'md5:48c59b74192bc819a9b34af1d5ed1eb9',
+            'timestamp': 1667933057,
+            'duration': 243.0,
+        },
+        'params': {'skip_download': 'ism'},
+    }, {
+        'url': 'https://www.rheinmaintv.de/sendungen/beitrag-video/formationsgemeinschaft-rhein-main-bei-den-deutschen-meisterschaften/vom-14.11.2022/',
+        'info_dict': {
+            'id': 'formationsgemeinschaft-rhein-main-bei-den-deutschen-meisterschaften-vom-14.11.2022',
+            'ext': 'ismv',
+            'title': 'Formationsgemeinschaft Rhein-Main bei den Deutschen Meisterschaften',
+            'timestamp': 1668526214,
+            'display_id': 'formationsgemeinschaft-rhein-main-bei-den-deutschen-meisterschaften',
+            'alt_title': 'Formationsgemeinschaft Rhein-Main bei den Deutschen Meisterschaften',
+            'view_count': int,
+            'thumbnail': r're:^https://.+\.jpg',
+            'duration': 345.0,
+            'description': 'md5:9370ba29526984006c2cba1372e5c5a0',
+            'upload_date': '20221115',
+        },
+        'params': {'skip_download': 'ism'},
+    }, {
+        'url': 'https://www.rheinmaintv.de/sendungen/beitrag-video/casino-mainz-bei-den-deutschen-meisterschaften/vom-14.11.2022/',
+        'info_dict': {
+            'id': 'casino-mainz-bei-den-deutschen-meisterschaften-vom-14.11.2022',
+            'ext': 'ismv',
+            'title': 'Casino Mainz bei den Deutschen Meisterschaften',
+            'view_count': int,
+            'timestamp': 1668527402,
+            'alt_title': 'Casino Mainz bei den Deutschen Meisterschaften',
+            'upload_date': '20221115',
+            'display_id': 'casino-mainz-bei-den-deutschen-meisterschaften',
+            'duration': 348.0,
+            'thumbnail': r're:^https://.+\.jpg',
+            'description': 'md5:70fc1660eeba96da17199e5bdff4c0aa',
+        },
+        'params': {'skip_download': 'ism'},
+    }, {
+        'url': 'https://www.rheinmaintv.de/sendungen/beitrag-video/bricks4kids/vom-22.06.2022/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        display_id = mobj.group('display_id')
+        video_id = mobj.group('video_id').replace('/', '-')
+        webpage = self._download_webpage(url, video_id)
+
+        source, img = self._search_regex(r'(?s)(?P<source><source[^>]*>)(?P<img><img[^>]*>)',
+                                         webpage, 'video', group=('source', 'img'))
+        source = extract_attributes(source)
+        img = extract_attributes(img)
+
+        raw_json_ld = list(self._yield_json_ld(webpage, video_id))
+        json_ld = self._json_ld(raw_json_ld, video_id)
+        json_ld.pop('url', None)
+
+        ism_manifest_url = (
+            source.get('src')
+            or next(json_ld.get('embedUrl') for json_ld in raw_json_ld if json_ld.get('@type') == 'VideoObject')
+        )
+        formats, subtitles = self._extract_ism_formats_and_subtitles(ism_manifest_url, video_id)
+
+        return merge_dicts({
+            'id': video_id,
+            'display_id': display_id,
+            'title':
+                self._html_search_regex(r'<h1><span class="title">([^<]*)</span>',
+                                        webpage, 'headline', default=None)
+                or img.get('title') or json_ld.get('title') or self._og_search_title(webpage)
+                or remove_end(self._html_extract_title(webpage), ' -'),
+            'alt_title': img.get('alt'),
+            'description': json_ld.get('description') or self._og_search_description(webpage),
+            'formats': formats,
+            'subtitles': subtitles,
+            'thumbnails': [{'url': img['src']}] if 'src' in img else json_ld.get('thumbnails'),
+        }, json_ld)

yt_dlp/extractor/testurl.py

@@ -8,7 +8,7 @@ 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]+))?$'
+    _VALID_URL = r'test(?:url)?:(?P<extractor>.*?)(?:_(?P<num>\d+|all))?$'
 
     def _real_extract(self, url):
         from . import gen_extractor_classes
@@ -36,6 +36,10 @@ class TestURLIE(InfoExtractor):
             extractor = matching_extractors[0]
 
         testcases = tuple(extractor.get_testcases(True))
+        if num == 'all':
+            return self.playlist_result(
+                [self.url_result(tc['url'], extractor) for tc in testcases],
+                url, f'{extractor.IE_NAME} tests')
         try:
             tc = testcases[int(num or 0)]
         except IndexError:
@@ -43,4 +47,4 @@ class TestURLIE(InfoExtractor):
                 f'Test case {num or 0} not found, got only {len(testcases)} tests', expected=True)
 
         self.to_screen(f'Test URL: {tc["url"]}')
-        return self.url_result(tc['url'])
+        return self.url_result(tc['url'], extractor)

yt_dlp/extractor/twitch.py

@@ -60,7 +60,7 @@ class TwitchBaseIE(InfoExtractor):
     @property
     def _CLIENT_ID(self):
         return self._configuration_arg(
-            'client_id', ['ue6666qo983tsx6so1t0vnawi233wa'], ie_key=TwitchStreamIE, casesense=True)[0]
+            'client_id', ['ue6666qo983tsx6so1t0vnawi233wa'], ie_key='Twitch', casesense=True)[0]
 
     def _perform_login(self, username, password):
         def fail(message):

yt_dlp/extractor/youtube.py

@@ -258,7 +258,7 @@ def build_innertube_clients():
     THIRD_PARTY = {
         'embedUrl': 'https://www.youtube.com/',  # Can be any valid URL
     }
-    BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
+    BASE_CLIENTS = ('ios', 'android', 'web', 'tv', 'mweb')
     priority = qualities(BASE_CLIENTS[::-1])
 
     for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
@@ -3140,7 +3140,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             return funcname
 
         return json.loads(js_to_json(self._search_regex(
-            rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
+            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):
@@ -3599,7 +3599,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
     def _is_unplayable(player_response):
         return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
 
-    _STORY_PLAYER_PARAMS = '8AEB'
+    _PLAYER_PARAMS = 'CgIQBg=='
 
     def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
 
@@ -3613,7 +3613,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'videoId': video_id,
         }
         if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
-            yt_query['params'] = self._STORY_PLAYER_PARAMS
+            yt_query['params'] = self._PLAYER_PARAMS
 
         yt_query.update(self._generate_player_context(sts))
         return self._extract_response(
@@ -3625,7 +3625,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
     def _get_requested_clients(self, url, smuggled_data):
         requested_clients = []
-        default = ['android', 'web']
+        default = ['ios', 'android', 'web']
         allowed_clients = sorted(
             (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
             key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
@@ -3932,6 +3932,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             elif itag:
                 f['format_id'] = itag
 
+            if itag in ('616', '235'):
+                f['format_note'] = join_nonempty(f.get('format_note'), 'Premium', delim=' ')
+                f['source_preference'] = (f.get('source_preference') or -1) + 100
+
             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']))])
@@ -4011,8 +4015,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         webpage = None
         if 'webpage' not in self._configuration_arg('player_skip'):
             query = {'bpctr': '9999999999', 'has_verified': '1'}
-            if smuggled_data.get('is_story'):
+            if smuggled_data.get('is_story'):  # XXX: Deprecated
-                query['pp'] = self._STORY_PLAYER_PARAMS
+                query['pp'] = self._PLAYER_PARAMS
             webpage = self._download_webpage(
                 webpage_url, video_id, fatal=False, query=query)
 
@@ -4342,15 +4346,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         info[d_k] = parse_duration(query[k][0])
 
         # Youtube Music Auto-generated description
-        if video_description:
+        if (video_description or '').strip().endswith('\nAuto-generated by YouTube.'):
+            # XXX: Causes catastrophic backtracking if description has "·"
+            # E.g. https://www.youtube.com/watch?v=DoPaAxMQoiI
+            # Simulating atomic groups:  (?P<a>[^xy]+)x  =>  (?=(?P<a>[^xy]+))(?P=a)x
+            # reduces it, but does not fully fix it. https://regex101.com/r/8Ssf2h/2
             mobj = re.search(
                 r'''(?xs)
-                    (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
+                    (?=(?P<track>[^\n·]+))(?P=track)·
-                    (?P<album>[^\n]+)
+                    (?=(?P<artist>[^\n]+))(?P=artist)\n+
+                    (?=(?P<album>[^\n]+))(?P=album)\n
                     (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
                     (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
-                    (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
+                    (.+?\nArtist\s*:\s*
-                    .+\nAuto-generated\ by\ YouTube\.\s*$
+                        (?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n
+                    )?.+\nAuto-generated\ by\ YouTube\.\s*$
                 ''', video_description)
             if mobj:
                 release_year = mobj.group('release_year')

yt_dlp/options.py

@@ -1012,8 +1012,9 @@ def create_parser():
         '--download-sections',
         metavar='REGEX', dest='download_ranges', action='append',
         help=(
-            'Download only chapters whose title matches the given regular expression. '
+            'Download only chapters that match the regular expression. '
-            'Time ranges prefixed by a "*" can also be used in place of chapters to download the specified range. '
+            'A "*" prefix denotes time-range instead of chapter. Negative timestamps are calculated from the end. '
+            '"*from-url" can be used to download between the "start_time" and "end_time" extracted from the URL. '
             'Needs ffmpeg. This option can be used multiple times to download multiple sections, '
             'e.g. --download-sections "*10:15-inf" --download-sections "intro"'))
     downloader.add_option(

yt_dlp/utils/_utils.py

@@ -3507,7 +3507,8 @@ def get_compatible_ext(*, vcodecs, acodecs, vexts, aexts, preferences=None):
         },
     }
 
-    sanitize_codec = functools.partial(try_get, getter=lambda x: x[0].split('.')[0].replace('0', ''))
+    sanitize_codec = functools.partial(
+        try_get, getter=lambda x: x[0].split('.')[0].replace('0', '').lower())
     vcodec, acodec = sanitize_codec(vcodecs), sanitize_codec(acodecs)
 
     for ext in preferences or COMPATIBLE_CODECS.keys():
@@ -3753,11 +3754,11 @@ def match_filter_func(filters, breaking_filters=None):
 
 
 class download_range_func:
-    def __init__(self, chapters, ranges):
+    def __init__(self, chapters, ranges, from_info=False):
-        self.chapters, self.ranges = chapters, ranges
+        self.chapters, self.ranges, self.from_info = chapters, ranges, from_info
 
     def __call__(self, info_dict, ydl):
-        if not self.ranges and not self.chapters:
+        if not any((self.ranges, self.chapters, self.from_info)):
             yield {}
 
         warning = ('There are no chapters matching the regex' if info_dict.get('chapters')
@@ -3770,7 +3771,21 @@ class download_range_func:
         if self.chapters and warning:
             ydl.to_screen(f'[info] {info_dict["id"]}: {warning}')
 
-        yield from ({'start_time': start, 'end_time': end} for start, end in self.ranges or [])
+        for start, end in self.ranges or []:
+            yield {
+                'start_time': self._handle_negative_timestamp(start, info_dict),
+                'end_time': self._handle_negative_timestamp(end, info_dict),
+            }
+
+        if self.from_info and (info_dict.get('start_time') or info_dict.get('end_time')):
+            yield {
+                'start_time': info_dict.get('start_time'),
+                'end_time': info_dict.get('end_time'),
+            }
+
+    @staticmethod
+    def _handle_negative_timestamp(time, info):
+        return max(info['duration'] + time, 0) if info.get('duration') and time < 0 else time
 
     def __eq__(self, other):
         return (isinstance(other, download_range_func)
@@ -5723,9 +5738,9 @@ class FormatSorter:
         'source': {'convert': 'float', 'field': 'source_preference', 'default': -1},
 
         'codec': {'type': 'combined', 'field': ('vcodec', 'acodec')},
-        'br': {'type': 'multiple', 'field': ('tbr', 'vbr', 'abr'),
+        'br': {'type': 'multiple', 'field': ('tbr', 'vbr', 'abr'), 'convert': 'float_none',
                'function': lambda it: next(filter(None, it), None)},
-        'size': {'type': 'multiple', 'field': ('filesize', 'fs_approx'),
+        'size': {'type': 'multiple', 'field': ('filesize', 'fs_approx'), 'convert': 'bytes',
                  'function': lambda it: next(filter(None, it), None)},
         'ext': {'type': 'combined', 'field': ('vext', 'aext')},
         'res': {'type': 'multiple', 'field': ('height', 'width'),

yt_dlp/version.py

@@ -1,8 +1,8 @@
 # Autogenerated by devscripts/update-version.py
 
-__version__ = '2023.06.21'
+__version__ = '2023.06.22'
 
-RELEASE_GIT_HEAD = '42f2d40b475db66486a4b4fe5b56751a640db5db'
+RELEASE_GIT_HEAD = '812cdfa06c33a40e73a8e04b3e6f42c084666a43'
 
 VARIANT = None