Merge 94e2a94b75 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

@@ -217,6 +217,7 @@ from .bbc import (
     BBCCoUkIPlayerGroupIE,
     BBCCoUkPlaylistIE,
 )
+from .bbcmaestro import BBCMaestroComIE
 from .beacon import BeaconTvIE
 from .beatbump import (
     BeatBumpPlaylistIE,

yt_dlp/extractor/bbcmaestro.py

@@ -0,0 +1,122 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import orderedSet, smuggle_url, unsmuggle_url
+
+
+class BBCMaestroComIE(InfoExtractor):
+    _VALID_URL = (
+        r'https?://(?:www\.)?bbcmaestro\.com/courses/(?P<id>[^?]+)'
+    )
+    _TESTS = [{
+        'url': 'https://www.bbcmaestro.com/courses/julia-donaldson/writing-children-s-picture-books/trailer',
+        'info_dict': {
+            'id': 'julia-donaldson/writing-children-s-picture-books/trailer',
+            'ext': 'mp4',
+            'title': 'Course trailer',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _do_extract_video(self, url, webpage, video_id):
+        if '/lessons/' not in url:
+            title = 'Course trailer'
+        else:
+            title = self._html_search_regex(
+                r'<h1\b[^>]*lesson[^>]*title[^>]*>\s*(.+?)\s*</h1>',
+                webpage,
+                name='title',
+                flags=re.RegexFlag.S,
+            )
+
+        m3u8_url = self._html_search_regex(
+            r'<source[^>]+src="?\'?(\S+\.m3u8)',
+            webpage,
+            'video URL',
+        )
+        formats = []
+        if m3u8_url:
+            formats = self._extract_m3u8_formats(
+                m3u8_url=m3u8_url,
+                video_id=video_id,
+                ext='mp4',
+                m3u8_id='hls',
+                fatal=False,
+            )
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+        }
+
+    def _do_extract_playlist(self, url, webpage):
+        # Twitter Title usually: <Lesson Title> - <Author> | <Course Title>
+        twitter_title = self._html_search_meta(
+            ['twitter:title'],
+            webpage,
+            fatal=True,
+        )
+        playlist_title = (
+            twitter_title
+            .split('-', maxsplit=1)[-1]
+            .replace('|', '-')
+        )
+
+        url_without_query_parameters = url.split('?', maxsplit=1)[0]
+        self.write_debug(f'url_without_query_parameters: {url_without_query_parameters}')
+        playlist_id = self._search_regex(
+            pattern=r'.*/courses/([^/]+/[^/]+).*',
+            string=url_without_query_parameters,
+            name='Playlist ID (from URL)',
+            fatal=True,
+        )
+        self.write_debug(f'playlist_id: {playlist_id}')
+        entries = [
+            self.url_result(
+                smuggle_url(
+                    f'https://www.bbcmaestro.com/courses/{playlist_id}/lessons/{item_video_id}',
+                    {'forcevideo': True},
+                ),
+                ie=BBCMaestroComIE.ie_key(),
+            )
+            for item_video_id in orderedSet(re.findall(
+                r'href=[^>]*/courses/' + re.escape(playlist_id) + r'/lessons/([^?]+)',
+                webpage,
+            ))
+        ]
+        # self.write_debug('entries: %r' % entries)
+        return self.playlist_result(
+            entries=entries,
+            playlist_id=playlist_id,
+            playlist_title=playlist_title,
+        )
+
+    def _check_login_provided(self):
+        if not self._cookies_passed:
+            self.raise_login_required('Login details are needed to download this content', method='cookies')
+
+    def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+        self.write_debug(f'Extracting from: {url}')
+        video_id = self._match_id(url)
+        self.write_debug(f'Video ID: {video_id}')
+        webpage = self._download_webpage(url, video_id)
+
+        is_private_course_content = ('/lessons/' in url)
+        is_login_required = is_private_course_content
+        if is_login_required:
+            # Note: We can only download the course trailer without login
+            self._check_login_provided()
+
+        is_playlist = (
+            is_private_course_content
+            and not smuggled_data.get('forcevideo')
+            and not self.get_param('noplaylist')
+        )
+
+        if is_playlist:
+            return self._do_extract_playlist(url, webpage=webpage)
+        return self._do_extract_video(url, webpage=webpage, video_id=video_id)