Merge 2be0c24897 into b83ca24eb7

Authored by: seproDev

.github/workflows/build.yml

@@ -504,7 +504,8 @@ jobs:
       - windows32
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/download-artifact@v4
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
         with:
           path: artifact
           pattern: build-bin-*

.github/workflows/release-master.yml

@@ -28,3 +28,20 @@ jobs:
       actions: write  # For cleaning up cache
       id-token: write  # mandatory for trusted publishing
     secrets: inherit
+
+  publish_pypi:
+    needs: [release]
+    if: vars.MASTER_PYPI_PROJECT != ''
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write  # mandatory for trusted publishing
+    steps:
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: dist
+          name: build-pypi
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          verbose: true

.github/workflows/release-nightly.yml

@@ -41,3 +41,20 @@ jobs:
       actions: write  # For cleaning up cache
       id-token: write  # mandatory for trusted publishing
     secrets: inherit
+
+  publish_pypi:
+    needs: [release]
+    if: vars.NIGHTLY_PYPI_PROJECT != ''
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write  # mandatory for trusted publishing
+    steps:
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: dist
+          name: build-pypi
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          verbose: true

.github/workflows/release.yml

@@ -2,10 +2,6 @@ name: Release
 on:
   workflow_call:
     inputs:
-      prerelease:
-        required: false
-        default: true
-        type: boolean
       source:
         required: false
         default: ''
@@ -18,6 +14,10 @@ on:
         required: false
         default: ''
         type: string
+      prerelease:
+        required: false
+        default: true
+        type: boolean
   workflow_dispatch:
     inputs:
       source:
@@ -278,11 +278,20 @@ jobs:
           make clean-cache
           python -m build --no-isolation .
 
+      - name: Upload artifacts
+        if: github.event_name != 'workflow_dispatch'
+        uses: actions/upload-artifact@v4
+        with:
+          name: build-pypi
+          path: |
+            dist/*
+          compression-level: 0
+
       - name: Publish to PyPI
+        if: github.event_name == 'workflow_dispatch'
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
           verbose: true
-          attestations: false  # Currently doesn't work w/ reusable workflows (breaks nightly)
 
   publish:
     needs: [prepare, build]

pyproject.toml

@@ -52,7 +52,7 @@ default = [
     "pycryptodomex",
     "requests>=2.32.2,<3",
     "urllib3>=1.26.17,<3",
-    "websockets>=13.0",
+    "websockets>=13.0,<14",
 ]
 curl-cffi = [
     "curl-cffi==0.5.10; os_name=='nt' and implementation_name=='cpython'",

yt_dlp/dependencies/Cryptodome.py

@@ -24,7 +24,7 @@ try:
         from Crypto.Cipher import AES, PKCS1_OAEP, Blowfish, PKCS1_v1_5  # noqa: F401
         from Crypto.Hash import CMAC, SHA1  # noqa: F401
         from Crypto.PublicKey import RSA  # noqa: F401
-except ImportError:
+except (ImportError, OSError):
     __version__ = f'broken {__version__}'.strip()
 
 

yt_dlp/extractor/_extractors.py

@@ -1984,6 +1984,7 @@ from .stretchinternet import StretchInternetIE
 from .stripchat import StripchatIE
 from .stv import STVPlayerIE
 from .substack import SubstackIE
+from .suno import SunoIE, SunoPlaylistIE
 from .sunporno import SunPornoIE
 from .sverigesradio import (
     SverigesRadioEpisodeIE,

yt_dlp/extractor/suno.py

@@ -0,0 +1,152 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError, unescapeHTML
+
+
+class SunoBaseIE(InfoExtractor):
+    def _get_title(self, webpage):
+        return self._html_search_meta(
+            ['og:title', 'twitter:title'], webpage, 'title',
+            default=None) or self._html_extract_title(webpage)
+
+    def _get_description(self, webpage):
+        return self._html_search_meta(
+            ['og:description', 'description', 'twitter:description'],
+            webpage, 'description', default=None)
+
+    def _get_thumbnail(self, webpage):
+        return self._html_search_meta(
+            ['og:image', 'twitter:image'], webpage, 'thumbnail', default=None)
+
+
+class SunoIE(SunoBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?suno\.com/song/(?P<id>[-a-f0-9]+)'
+    _TESTS = [
+        {
+            'url': 'https://suno.com/song/ab39a04d-b2e6-463b-9b8e-ddea725422f5',
+            'md5': 'ef850763b175d8a3c7fba5e2dbdc6bc5',
+            'info_dict': {
+                'id': 'ab39a04d-b2e6-463b-9b8e-ddea725422f5',
+                'title': 'Life\'s a Soundtrack · AI Funk Factory @ YT by @funk | Suno',
+                'description': 'groovy funk, melodic song. Listen and make your own with Suno.',
+                'thumbnail': r're:https?://.*903f2bd7-ccc0-4029-a76a-887f07ebc2df.*\.jpeg$',
+                'ext': 'mp3',
+            },
+        },
+        {
+            'url': 'https://suno.com/song/9cbcb5f4-f367-4f1c-8a32-23ec62bdc47e',
+            'md5': '2f038badef88d189891d5f8cd8d8804d',
+            'info_dict': {
+                'id': '9cbcb5f4-f367-4f1c-8a32-23ec62bdc47e',
+                'title': 'Pequenos Prazeres da Vida by @groovebot | Suno',
+                'description': 'pop bossa nova song. Listen and make your own with Suno.',
+                'thumbnail': r're:https?://.*9cbcb5f4-f367-4f1c-8a32-23ec62bdc47e.*\.jpeg$',
+                'ext': 'mp3',
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        url = self._html_search_meta(
+            ['og:audio', 'twitter:player:stream'], webpage, 'url', default=None)
+
+        return {
+            'id': video_id,
+            'title': self._get_title(webpage),
+            'description': self._get_description(webpage),
+            'thumbnail': self._get_thumbnail(webpage),
+            'url': url,
+        }
+
+
+class SunoPlaylistIE(SunoBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?suno\.com/playlist/(?P<id>[-a-f0-9]+)'
+    _TESTS = [
+        {
+            'url': 'https://suno.com/playlist/01f2ac32-c32e-4d26-b10c-221107c02946',
+            'info_dict': {
+                'id': '01f2ac32-c32e-4d26-b10c-221107c02946',
+                'title': 'Main 0 by @contemplativetranspositions367 | Suno',
+                'description': 'Hopefully the test case passed',
+                'thumbnail': r're:https?://.*19d6d518-1b87-43b3-90b9-2a476ca5824a.*\.jpeg$',
+            },
+            'playlist': [{
+                'info_dict': {
+                    'id': '19d6d518-1b87-43b3-90b9-2a476ca5824a',
+                    'title': 'Ceaseless <Echoes>',
+                    'ext': 'mp3',
+                },
+            }],
+            'playlist_count': 1,
+        },
+        {
+            'url': 'https://www.suno.com/playlist/568eeaab-dfbf-4da6-aa0a-0fb1a32330de',
+            'info_dict': {
+                'id': '568eeaab-dfbf-4da6-aa0a-0fb1a32330de',
+                'title': 'Piano by @kunal | Suno',
+                'description': 'Here are some good piano',
+                'thumbnail': r're:https?://.*0ecc0956-3b17-4d4b-8504-55849dd75e22.*\.jpeg$',
+            },
+            'playlist': [
+                {
+                    'info_dict': {
+                        'id': '0ecc0956-3b17-4d4b-8504-55849dd75e22',
+                        'title': 'ST',
+                        'ext': 'mp3',
+                    },
+                },
+                {
+                    'info_dict': {
+                        'id': '3fef7d44-c5a3-4181-9de3-d81542af23ef',
+                        'title': 'ST',
+                        'ext': 'mp3',
+                    },
+                },
+                {
+                    'info_dict': {
+                        'id': '15e797fa-06c0-4e11-8cc0-3b2580476039',
+                        'title': 'ST - 2',
+                        'ext': 'mp3',
+                    },
+                },
+            ],
+            'playlist_count': 3,
+        },
+    ]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        # There are <a>s whose href is a song/ID path. The <span>s directly
+        # within them have the respective song title as their innerHTML.
+        # Alternatively, this info can be extracted through parsing an escaped
+        # JSON object inside a <script> array, though that seems even less stable
+        # than this HTML.
+        songs_regex = r'/song/(?P<id>[-a-f0-9]+)["\'][^>]*>\s*<span[^>]*>\s*(?P<title>[^<]+)</span>'
+        songs = re.findall(songs_regex, webpage)
+
+        og_audio_regex = self._og_regexes('audio')[0]
+        audio_urls = [matches[0] for matches in re.findall(og_audio_regex, webpage)]
+
+        if len(songs) != len(audio_urls):
+            raise ExtractorError('Unexpected mismatch between song HTML list and og audio URLs')
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': self._get_title(webpage),
+            'description': self._get_description(webpage),
+            'thumbnail': self._get_thumbnail(webpage),
+
+            'entries': [{
+                'id': song_tuple[0],
+                'title': unescapeHTML(song_tuple[1]),
+                'url': audio_urls[i],
+
+            } for i, song_tuple in enumerate(songs)],
+        }