Merge branch 'yt-dlp:master' into cr-lang

.github/workflows/build.yml

@@ -125,11 +125,12 @@ jobs:
           sudo apt -y install zip pandoc man sed
           cat > ./requirements.txt << EOF
           python=3.10.*
+          pyinstaller
           brotli-python
           EOF
           python devscripts/install_deps.py --print \
             --exclude brotli --exclude brotlicffi \
-            --include secretstorage --include pyinstaller >> ./requirements.txt
+            --include secretstorage >> ./requirements.txt
           mamba create -n build --file ./requirements.txt
 
       - name: Prepare
@@ -250,6 +251,22 @@ jobs:
           python3 devscripts/install_deps.py --print --include pyinstaller > requirements.txt
           # We need to ignore wheels otherwise we break universal2 builds
           python3 -m pip install -U --user --no-binary :all: -r requirements.txt
+          # We need to fuse our own universal2 wheels for curl_cffi
+          python3 -m pip install -U --user delocate
+          mkdir curl_cffi_whls curl_cffi_universal2
+          python3 devscripts/install_deps.py --print -o --include curl_cffi > requirements.txt
+          for platform in "macosx_11_0_arm64" "macosx_11_0_x86_64"; do
+            python3 -m pip download \
+              --only-binary=:all: \
+              --platform "${platform}" \
+              --pre -d curl_cffi_whls \
+              -r requirements.txt
+          done
+          python3 -m delocate.cmd.delocate_fuse curl_cffi_whls/curl_cffi*.whl -w curl_cffi_universal2
+          python3 -m delocate.cmd.delocate_fuse curl_cffi_whls/cffi*.whl -w curl_cffi_universal2
+          cd curl_cffi_universal2
+          for wheel in *cffi*.whl; do mv -n -- "${wheel}" "${wheel/x86_64/universal2}"; done
+          python3 -m pip install -U --user *cffi*.whl
 
       - name: Prepare
         run: |
@@ -303,7 +320,7 @@ jobs:
         run: |
           brew install coreutils
           python3 devscripts/install_deps.py --user -o --include build
-          python3 devscripts/install_deps.py --user --include pyinstaller
+          python3 devscripts/install_deps.py --user --include pyinstaller --include curl_cffi
 
       - name: Prepare
         run: |
@@ -345,7 +362,7 @@ jobs:
       - name: Install Requirements
         run: | # Custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds
           python devscripts/install_deps.py -o --include build
-          python devscripts/install_deps.py --include py2exe
+          python devscripts/install_deps.py --include py2exe --include curl_cffi
           python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-5.8.0-py3-none-any.whl"
 
       - name: Prepare
@@ -450,8 +467,9 @@ jobs:
       - name: Make SHA2-SUMS files
         run: |
           cd ./artifact/
-          sha256sum * > ../SHA2-256SUMS
-          sha512sum * > ../SHA2-512SUMS
+          # make sure SHA sums are also printed to stdout
+          sha256sum * | tee ../SHA2-256SUMS
+          sha512sum * | tee ../SHA2-512SUMS
 
       - name: Make Update spec
         run: |

.github/workflows/core.yml

@@ -53,7 +53,7 @@ jobs:
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install test requirements
-      run: python3 ./devscripts/install_deps.py --include dev
+      run: python3 ./devscripts/install_deps.py --include dev --include curl_cffi
     - name: Run tests
       continue-on-error: False
       run: |

README.md

@@ -17,7 +17,7 @@
 </div>
 <!-- MANPAGE: END EXCLUDED SECTION -->
 
-yt-dlp is a [youtube-dl](https://github.com/ytdl-org/youtube-dl) fork based on the now inactive [youtube-dlc](https://github.com/blackjack4494/yt-dlc). The main focus of this project is adding new features and patches while also keeping up to date with the original project
+yt-dlp is a feature-rich command-line audio/video downloader with support for [thousands of sites](supportedsites.md). The project is a fork of [youtube-dl](https://github.com/ytdl-org/youtube-dl) based on the now inactive [youtube-dlc](https://github.com/blackjack4494/yt-dlc).
 
 <!-- MANPAGE: MOVE "USAGE AND OPTIONS" SECTION HERE -->
 
@@ -196,6 +196,15 @@ While all the other dependencies are optional, `ffmpeg` and `ffprobe` are highly
 * [**websockets**](https://github.com/aaugustin/websockets)\* - For downloading over websocket. Licensed under [BSD-3-Clause](https://github.com/aaugustin/websockets/blob/main/LICENSE)
 * [**requests**](https://github.com/psf/requests)\* - HTTP library. For HTTPS proxy and persistent connections support. Licensed under [Apache-2.0](https://github.com/psf/requests/blob/main/LICENSE)
 
+#### Impersonation
+
+The following provide support for impersonating browser requests. This may be required for some sites that employ TLS fingerprinting. 
+
+* [**curl_cffi**](https://github.com/yifeikong/curl_cffi) (recommended) - Python binding for [curl-impersonate](https://github.com/lwthiker/curl-impersonate). Provides impersonation targets for Chrome, Edge and Safari. Licensed under [MIT](https://github.com/yifeikong/curl_cffi/blob/main/LICENSE)
+  * Can be installed with the `curl_cffi` group, e.g. `pip install yt-dlp[default,curl_cffi]`
+  * Only included in `yt-dlp.exe`, `yt-dlp_macos` and `yt-dlp_macos_legacy` builds
+
+
 ### Metadata
 
 * [**mutagen**](https://github.com/quodlibet/mutagen)\* - For `--embed-thumbnail` in certain formats. Licensed under [GPLv2+](https://github.com/quodlibet/mutagen/blob/master/COPYING)
@@ -389,6 +398,10 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
                                     direct connection
     --socket-timeout SECONDS        Time to wait before giving up, in seconds
     --source-address IP             Client-side IP address to bind to
+    --impersonate CLIENT[:OS]       Client to impersonate for requests. E.g.
+                                    chrome, chrome-110, chrome:windows-10. Pass
+                                    --impersonate="" to impersonate any client.
+    --list-impersonate-targets      List available clients to impersonate.
     -4, --force-ipv4                Make all connections via IPv4
     -6, --force-ipv6                Make all connections via IPv6
     --enable-file-urls              Enable file:// URLs. This is disabled by
@@ -468,6 +481,9 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
     --max-downloads NUMBER          Abort after downloading NUMBER files
     --break-on-existing             Stop the download process when encountering
                                     a file that is in the archive
+    --no-break-on-existing          Do not stop the download process when
+                                    encountering a file that is in the archive
+                                    (default)
     --break-per-input               Alters --max-downloads, --break-on-existing,
                                     --break-match-filter, and autonumber to
                                     reset per input URL
@@ -1459,9 +1475,9 @@ The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `
  - `width`: Width of the video, if known
  - `height`: Height of the video, if known
  - `aspect_ratio`: Aspect ratio of the video, if known
- - `tbr`: Average bitrate of audio and video in KBit/s
- - `abr`: Average audio bitrate in KBit/s
- - `vbr`: Average video bitrate in KBit/s
+ - `tbr`: Average bitrate of audio and video in [kbps](## "1000 bits/sec")
+ - `abr`: Average audio bitrate in [kbps](## "1000 bits/sec")
+ - `vbr`: Average video bitrate in [kbps](## "1000 bits/sec")
  - `asr`: Audio sampling rate in Hertz
  - `fps`: Frame rate
  - `audio_channels`: The number of audio channels
@@ -1486,7 +1502,7 @@ Any string comparison may be prefixed with negation `!` in order to produce an o
 
 **Note**: None of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the website. Any other field made available by the extractor can also be used for filtering.
 
-Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "bv[height<=?720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. You can also use the filters with `all` to download all formats that satisfy the filter, e.g. `-f "all[vcodec=none]"` selects all audio-only formats.
+Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "bv[height<=?720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 kbps. You can also use the filters with `all` to download all formats that satisfy the filter, e.g. `-f "all[vcodec=none]"` selects all audio-only formats.
 
 Format selectors can also be grouped using parentheses; e.g. `-f "(mp4,webm)[height<480]"` will download the best pre-merged mp4 and webm formats with a height lower than 480.
 
@@ -1518,10 +1534,10 @@ The available fields are:
  - `fps`: Framerate of video
  - `hdr`: The dynamic range of the video (`DV` > `HDR12` > `HDR10+` > `HDR10` > `HLG` > `SDR`)
  - `channels`: The number of audio channels
- - `tbr`: Total average bitrate in KBit/s
- - `vbr`: Average video bitrate in KBit/s
- - `abr`: Average audio bitrate in KBit/s
- - `br`: Average bitrate in KBit/s, `tbr`/`vbr`/`abr`
+ - `tbr`: Total average bitrate in [kbps](## "1000 bits/sec")
+ - `vbr`: Average video bitrate in [kbps](## "1000 bits/sec")
+ - `abr`: Average audio bitrate in [kbps](## "1000 bits/sec")
+ - `br`: Average bitrate in [kbps](## "1000 bits/sec"), `tbr`/`vbr`/`abr`
  - `asr`: Audio sample rate in Hz
 
 **Deprecation warning**: Many of these fields have (currently undocumented) aliases, that may be removed in a future version. It is recommended to use only the documented field names.
@@ -1792,9 +1808,12 @@ The following extractors use this feature:
 * `max_comments`: Maximum number of comments to extract - default is `120`
 
 #### tiktok
-* `api_hostname`: Hostname to use for mobile API requests, e.g. `api-h2.tiktokv.com`
-* `app_version`: App version to call mobile APIs with - should be set along with `manifest_app_version`, e.g. `20.2.1`
-* `manifest_app_version`: Numeric app version to call mobile APIs with, e.g. `221`
+* `api_hostname`: Hostname to use for mobile API calls, e.g. `api22-normal-c-alisg.tiktokv.com`
+* `app_name`: Default app name to use with mobile API calls, e.g. `trill`
+* `app_version`: Default app version to use with mobile API calls - should be set along with `manifest_app_version`, e.g. `34.1.2`
+* `manifest_app_version`: Default numeric app version to use with mobile API calls, e.g. `2023401020`
+* `aid`: Default app ID to use with API calls, e.g. `1180`
+* `app_info`: One or more app info strings in the format of `<iid>/[app_name]/[app_version]/[manifest_app_version]/[aid]`, where `iid` is the unique app install ID. `iid` is the only required value; all other values and their `/` separators can be omitted, e.g. `tiktok:app_info=1234567890123456789` or `tiktok:app_info=123,456/trill///1180,789//34.0.1/340001`
 
 #### rokfinchannel
 * `tab`: Which tab to download - one of `new`, `top`, `videos`, `podcasts`, `streams`, `stacks`

bundle/py2exe.py

@@ -28,7 +28,7 @@ def main():
         }],
         version_info={
             'version': VERSION,
-            'description': 'A youtube-dl fork with additional features and patches',
+            'description': 'A feature-rich command-line audio/video downloader',
             'comments': 'Official repository: <https://github.com/yt-dlp/yt-dlp>',
             'product_name': 'yt-dlp',
             'product_version': VERSION,

devscripts/changelog_override.json

@@ -126,5 +126,9 @@
         "when": "4ce57d3b873c2887814cbec03d029533e82f7db5",
         "short": "[ie] Support multi-period MPD streams (#6654)",
         "authors": ["alard", "pukkandan"]
+    },
+    {
+        "action": "remove",
+        "when": "22e4dfacb61f62dfbb3eb41b31c7b69ba1059b80"
     }
 ]

devscripts/install_deps.py

@@ -10,24 +10,32 @@
 import re
 import subprocess
 
+from pathlib import Path
+
 from devscripts.tomlparse import parse_toml
 from devscripts.utils import read_file
 
 
 def parse_args():
     parser = argparse.ArgumentParser(description='Install dependencies for yt-dlp')
     parser.add_argument(
-        'input', nargs='?', metavar='TOMLFILE', default='pyproject.toml', help='Input file (default: %(default)s)')
+        'input', nargs='?', metavar='TOMLFILE', default=Path(__file__).parent.parent / 'pyproject.toml',
+        help='input file (default: %(default)s)')
     parser.add_argument(
-        '-e', '--exclude', metavar='DEPENDENCY', action='append', help='Exclude a dependency')
+        '-e', '--exclude', metavar='DEPENDENCY', action='append',
+        help='exclude a dependency')
     parser.add_argument(
-        '-i', '--include', metavar='GROUP', action='append', help='Include an optional dependency group')
+        '-i', '--include', metavar='GROUP', action='append',
+        help='include an optional dependency group')
     parser.add_argument(
-        '-o', '--only-optional', action='store_true', help='Only install optional dependencies')
+        '-o', '--only-optional', action='store_true',
+        help='only install optional dependencies')
     parser.add_argument(
-        '-p', '--print', action='store_true', help='Only print a requirements.txt to stdout')
+        '-p', '--print', action='store_true',
+        help='only print requirements to stdout')
     parser.add_argument(
-        '-u', '--user', action='store_true', help='Install with pip as --user')
+        '-u', '--user', action='store_true',
+        help='install with pip as --user')
     return parser.parse_args()
 
 
@@ -37,24 +45,16 @@ def main():
     optional_groups = project_table['optional-dependencies']
     excludes = args.exclude or []
 
-    deps = []
+    targets = []
     if not args.only_optional:  # `-o` should exclude 'dependencies' and the 'default' group
-        deps.extend(project_table['dependencies'])
+        targets.extend(project_table['dependencies'])
         if 'default' not in excludes:  # `--exclude default` should exclude entire 'default' group
-            deps.extend(optional_groups['default'])
-
-    def name(dependency):
-        return re.match(r'[\w-]+', dependency)[0].lower()
-
-    target_map = {name(dep): dep for dep in deps}
+            targets.extend(optional_groups['default'])
 
     for include in filter(None, map(optional_groups.get, args.include or [])):
-        target_map.update(zip(map(name, include), include))
-
-    for exclude in map(name, excludes):
-        target_map.pop(exclude, None)
+        targets.extend(include)
 
-    targets = list(target_map.values())
+    targets = [t for t in targets if re.match(r'[\w-]+', t).group(0).lower() not in excludes]
 
     if args.print:
         for target in targets:

devscripts/prepare_manpage.py

@@ -24,7 +24,7 @@
 
 # NAME
 
-yt\-dlp \- A youtube-dl fork with additional features and patches
+yt\-dlp \- A feature\-rich command\-line audio/video downloader
 
 # SYNOPSIS
 

devscripts/tomlparse.py

@@ -11,7 +11,7 @@
 
 from __future__ import annotations
 
-import datetime
+import datetime as dt
 import json
 import re
 
@@ -115,9 +115,9 @@ def parse_value(data: str, index: int):
     for func in [
         int,
         float,
-        datetime.time.fromisoformat,
-        datetime.date.fromisoformat,
-        datetime.datetime.fromisoformat,
+        dt.time.fromisoformat,
+        dt.date.fromisoformat,
+        dt.datetime.fromisoformat,
         {'true': True, 'false': False}.get,
     ]:
         try:
@@ -179,7 +179,7 @@ def main():
         data = file.read()
 
     def default(obj):
-        if isinstance(obj, (datetime.date, datetime.time, datetime.datetime)):
+        if isinstance(obj, (dt.date, dt.time, dt.datetime)):
             return obj.isoformat()
 
     print(json.dumps(parse_toml(data), default=default))

devscripts/update-version.py

@@ -9,15 +9,15 @@
 
 import argparse
 import contextlib
+import datetime as dt
 import sys
-from datetime import datetime, timezone
 
 from devscripts.utils import read_version, run_process, write_file
 
 
 def get_new_version(version, revision):
     if not version:
-        version = datetime.now(timezone.utc).strftime('%Y.%m.%d')
+        version = dt.datetime.now(dt.timezone.utc).strftime('%Y.%m.%d')
 
     if revision:
         assert revision.isdecimal(), 'Revision must be a number'

pyproject.toml

@@ -10,7 +10,7 @@ maintainers = [
     {name = "bashonly", email = "[email protected]"},
     {name = "coletdjnz", email = "[email protected]"},
 ]
-description = "A youtube-dl fork with additional features and patches"
+description = "A feature-rich command-line audio/video downloader"
 readme = "README.md"
 requires-python = ">=3.8"
 keywords = [
@@ -53,6 +53,7 @@ dependencies = [
 
 [project.optional-dependencies]
 default = []
+curl_cffi = ["curl-cffi==0.5.10; implementation_name=='cpython'"]
 secretstorage = [
     "cffi",
     "secretstorage",
@@ -68,7 +69,10 @@ dev = [
     "isort",
     "pytest",
 ]
-pyinstaller = ["pyinstaller>=6.3"]
+pyinstaller = [
+    "pyinstaller>=6.3; sys_platform!='darwin'",
+    "pyinstaller==5.13.2; sys_platform=='darwin'",  # needed for curl_cffi
+]
 py2exe = ["py2exe>=0.12"]
 
 [project.urls]

test/test_YoutubeDL.py

@@ -183,7 +183,7 @@ def test_format_selection_audio_exts(self):
         ]
 
         info_dict = _make_result(formats)
-        ydl = YDL({'format': 'best'})
+        ydl = YDL({'format': 'best', 'format_sort': ['abr', 'ext']})
         ydl.sort_formats(info_dict)
         ydl.process_ie_result(copy.deepcopy(info_dict))
         downloaded = ydl.downloaded_info_dicts[0]
@@ -195,7 +195,7 @@ def test_format_selection_audio_exts(self):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'mp3-64')
 
-        ydl = YDL({'prefer_free_formats': True})
+        ydl = YDL({'prefer_free_formats': True, 'format_sort': ['abr', 'ext']})
         ydl.sort_formats(info_dict)
         ydl.process_ie_result(copy.deepcopy(info_dict))
         downloaded = ydl.downloaded_info_dicts[0]

test/test_cookies.py

@@ -1,5 +1,5 @@
+import datetime as dt
 import unittest
-from datetime import datetime, timezone
 
 from yt_dlp import cookies
 from yt_dlp.cookies import (
@@ -138,7 +138,7 @@ def test_safari_cookie_parsing(self):
         self.assertEqual(cookie.name, 'foo')
         self.assertEqual(cookie.value, 'test%20%3Bcookie')
         self.assertFalse(cookie.secure)
-        expected_expiration = datetime(2021, 6, 18, 21, 39, 19, tzinfo=timezone.utc)
+        expected_expiration = dt.datetime(2021, 6, 18, 21, 39, 19, tzinfo=dt.timezone.utc)
         self.assertEqual(cookie.expires, int(expected_expiration.timestamp()))
 
     def test_pbkdf2_sha1(self):