Merge 311dc3d438 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

@@ -2084,6 +2084,10 @@ from .theplatform import (
 from .thestar import TheStarIE
 from .thesun import TheSunIE
 from .theweatherchannel import TheWeatherChannelIE
+from .thirtydaysinger import (
+    ThirtyDaySingerIE,
+    ThirtyDaySingerPlaylistIE
+)
 from .thisamericanlife import ThisAmericanLifeIE
 from .thisoldhouse import ThisOldHouseIE
 from .thisvid import (

yt_dlp/extractor/thirtydaysinger.py

@@ -0,0 +1,107 @@
+import re
+
+from .wistia import WistiaBaseIE
+from ..utils import (
+    clean_html,
+    get_elements_html_by_class
+)
+
+
+class ThirtyDaySingerBase(WistiaBaseIE):
+    _INDEX_EXTRACTION_RE = r'/tutorial/[\w-]+/(?P<index>[\w-]+)'
+
+    def _extract_for_url(self, url):
+        lesson_index = re.search(self._INDEX_EXTRACTION_RE, url).group('index')
+        webpage = self._download_webpage(url, lesson_index)
+        match = next(self._extract_wistia_async_embed(webpage))
+        embed_config = self._download_embed_config('medias', match.group('id'), url)
+
+        embed_infojson = self._extract_media(embed_config)
+        webpage_infojson = self._extract_webpage_data(webpage)
+
+        return {**embed_infojson, **webpage_infojson}
+
+    def _extract_webpage_data(self, webpage):
+        title = self._html_search_regex(r'<h1>([^<]+)</h1>', webpage, 'title')
+        fallback_title = self._html_extract_title(webpage)
+        description = self._html_search_meta('description', webpage, fatal=False)
+
+        return {
+            'title': title or fallback_title,
+            'description': clean_html(self._format_html_list(description))
+        }
+
+    # The site makes extensive use of HTML lists for formatting and `clean_html`
+    # doesn't handle them well. This is needed to keep lists readable.
+    def _format_html_list(self, html):
+        replacements = {
+            '<ul>': '<br>',
+            '</ul': '<br>',
+            '<li>': '<br>- ',
+            '</li>': ''
+        }
+
+        for k, v in replacements.items():
+            html = html.replace(k, v)
+
+        return html
+
+
+class ThirtyDaySingerIE(ThirtyDaySingerBase):
+    _VALID_URL = r'https?://www\.30daysinger\.com/tutorial/[\w-]+/[\w-]+'
+
+    _TESTS = [{
+        'url': 'https://www.30daysinger.com/tutorial/30-day-beginner-course-with-jonathan-estabrooks/1',
+        'md5': '56bb11529b9777899b27b599d4b16cf6',
+        'info_dict': {
+            'id': 'tegd38l3d5',
+            'ext': 'mp4',
+            'thumbnail': 'http://embed.wistia.com/deliveries/c26a85cb98e32efa8a5e12a0576e63355af66230.jpg',
+            'upload_date': '20190608',
+            'description': 'md5:d3291de8988be57b1d3e411126ba4d33',
+            'duration': 344.22,
+            'timestamp': 1559952526,
+            'title': 'Welcome to 30 Day Singer'
+        }
+    }]
+
+    def _real_extract(self, url):
+        return self._extract_for_url(url)
+
+
+class ThirtyDaySingerPlaylistIE(ThirtyDaySingerBase):
+    _URI_BASE = 'https://www.30daysinger.com'
+    _VALID_URL = r'https?://www\.30daysinger\.com/tutorial/(?P<playlist_id>[\w-]+)/?(?:$|[#?])'
+
+    _TESTS = [{
+        'url': 'https://www.30daysinger.com/tutorial/30-day-beginner-course-with-jonathan-estabrooks',
+        'info_dict': {
+            'id': '30-day-beginner-course-with-jonathan-estabrooks',
+            'description': 'md5:8cf6d6c7c377895653c9cde9dfc4104f',
+            'title': '30 Day Beginner Course with Jonathan Estabrooks',
+        },
+        'playlist_count': 1,
+        'expected_warnings': ['This video is for premium members only']
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_valid_url(url).group('playlist_id')
+        webpage = self._download_webpage(url, playlist_id)
+        playlist_attrs = self._extract_webpage_data(webpage)
+
+        entries = []
+        for html_element in get_elements_html_by_class('playlist-item-link', webpage):
+            href = self._search_regex(r'href="([^"]+)"', html_element, 'href')
+
+            if not href:
+                continue
+            # Often _some_ content is free so we should still download that but warn the user
+            # when we encounter premium content.
+            # NOTE: this only applies to the playlist extractor, not the single video extractor
+            if 'upgrade' in href:
+                self.report_warning('This video is for premium members only')
+                continue
+
+            entries.append(self._extract_for_url(self._URI_BASE + href))
+
+        return self.playlist_result(entries, playlist_id, playlist_attrs['title'], playlist_attrs['description'])