Merge a44a1a86b9 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

@@ -708,6 +708,7 @@ from .gab import (
     GabTVIE,
 )
 from .gaia import GaiaIE
+from .gamedevtv import GameDevTVDashboardIE
 from .gamejolt import (
     GameJoltCommunityIE,
     GameJoltGameIE,

yt_dlp/extractor/adobepass.py

@@ -1362,7 +1362,7 @@ class AdobePassIE(InfoExtractor):  # XXX: Conventionally, base classes should en
 
     def _download_webpage_handle(self, *args, **kwargs):
         headers = self.geo_verification_headers()
-        headers.update(kwargs.get('headers', {}))
+        headers.update(kwargs.get('headers') or {})
         kwargs['headers'] = headers
         return super()._download_webpage_handle(
             *args, **kwargs)

yt_dlp/extractor/gamedevtv.py

@@ -0,0 +1,141 @@
+import json
+
+from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    int_or_none,
+    join_nonempty,
+    parse_iso8601,
+    str_or_none,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class GameDevTVDashboardIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?gamedev\.tv/dashboard/courses/(?P<course_id>\d+)(?:/(?P<lecture_id>\d+))?'
+    _NETRC_MACHINE = 'gamedevtv'
+    _TESTS = [{
+        'url': 'https://www.gamedev.tv/dashboard/courses/25',
+        'info_dict': {
+            'id': '25',
+            'title': 'Complete Blender Creator 3: Learn 3D Modelling for Beginners',
+            'tags': ['blender', 'course', 'all', 'box modelling', 'sculpting'],
+            'categories': ['Blender', '3D Art'],
+            'thumbnail': 'https://gamedev-files.b-cdn.net/courses/qisc9pmu1jdc.jpg',
+            'upload_date': '20220516',
+            'timestamp': 1652694420,
+            'modified_date': '20241027',
+            'modified_timestamp': 1730049658,
+        },
+        'playlist_count': 100,
+    }, {
+        'url': 'https://www.gamedev.tv/dashboard/courses/63/2279',
+        'info_dict': {
+            'id': 'df04f4d8-68a4-4756-a71b-9ca9446c3a01',
+            'ext': 'mp4',
+            'modified_timestamp': 1701695752,
+            'upload_date': '20230504',
+            'episode': 'MagicaVoxel Community Course Introduction',
+            'series_id': '63',
+            'title': 'MagicaVoxel Community Course Introduction',
+            'timestamp': 1683195397,
+            'modified_date': '20231204',
+            'categories': ['3D Art', 'MagicaVoxel'],
+            'season': 'MagicaVoxel Community Course',
+            'tags': ['MagicaVoxel', 'all', 'course'],
+            'series': 'MagicaVoxel 3D Art Mini Course',
+            'duration': 1405,
+            'episode_number': 1,
+            'season_number': 1,
+            'season_id': '219',
+            'description': 'md5:a378738c5bbec1c785d76c067652d650',
+            'display_id': '63-219-2279',
+            'alt_title': '1_CC_MVX MagicaVoxel Community Course Introduction.mp4',
+            'thumbnail': 'https://vz-23691c65-6fa.b-cdn.net/df04f4d8-68a4-4756-a71b-9ca9446c3a01/thumbnail.jpg',
+        },
+    }]
+    _API_HEADERS = {}
+
+    def _perform_login(self, username, password):
+        try:
+            response = self._download_json(
+                'https://api.gamedev.tv/api/students/login', None, 'Logging in',
+                headers={'Content-Type': 'application/json'},
+                data=json.dumps({
+                    'email': username,
+                    'password': password,
+                    'cart_items': [],
+                }).encode())
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 401:
+                raise ExtractorError('Invalid username/password', expected=True)
+            raise
+
+        self._API_HEADERS['Authorization'] = f'{response["token_type"]} {response["access_token"]}'
+
+    def _real_initialize(self):
+        if not self._API_HEADERS.get('Authorization'):
+            self.raise_login_required(
+                'This content is only available with purchase', method='password')
+
+    def _entries(self, data, course_id, course_info, selected_lecture):
+        for section in traverse_obj(data, ('sections', ..., {dict})):
+            section_info = traverse_obj(section, {
+                'season_id': ('id', {str_or_none}),
+                'season': ('title', {str}),
+                'season_number': ('order', {int_or_none}),
+            })
+            for lecture in traverse_obj(section, ('lectures', lambda _, v: url_or_none(v['video']['playListUrl']))):
+                if selected_lecture and str(lecture.get('id')) != selected_lecture:
+                    continue
+                display_id = join_nonempty(course_id, section_info.get('season_id'), lecture.get('id'))
+                formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+                    lecture['video']['playListUrl'], display_id, 'mp4', m3u8_id='hls')
+                yield {
+                    **course_info,
+                    **section_info,
+                    'id': display_id,  # fallback
+                    'display_id': display_id,
+                    'formats': formats,
+                    'subtitles': subtitles,
+                    'series': course_info.get('title'),
+                    'series_id': course_id,
+                    **traverse_obj(lecture, {
+                        'id': ('video', 'guid', {str}),
+                        'title': ('title', {str}),
+                        'alt_title': ('video', 'title', {str}),
+                        'description': ('description', {clean_html}),
+                        'episode': ('title', {str}),
+                        'episode_number': ('order', {int_or_none}),
+                        'duration': ('video', 'duration_in_sec', {int_or_none}),
+                        'timestamp': ('video', 'created_at', {parse_iso8601}),
+                        'modified_timestamp': ('video', 'updated_at', {parse_iso8601}),
+                        'thumbnail': ('video', 'thumbnailUrl', {url_or_none}),
+                    }),
+                }
+
+    def _real_extract(self, url):
+        course_id, lecture_id = self._match_valid_url(url).group('course_id', 'lecture_id')
+        data = self._download_json(
+            f'https://api.gamedev.tv/api/courses/my/{course_id}', course_id,
+            headers=self._API_HEADERS)['data']
+
+        course_info = traverse_obj(data, {
+            'title': ('title', {str}),
+            'tags': ('tags', ..., 'name', {str}),
+            'categories': ('categories', ..., 'title', {str}),
+            'timestamp': ('created_at', {parse_iso8601}),
+            'modified_timestamp': ('updated_at', {parse_iso8601}),
+            'thumbnail': ('image', {url_or_none}),
+        })
+
+        entries = self._entries(data, course_id, course_info, lecture_id)
+        if lecture_id:
+            lecture = next(entries, None)
+            if not lecture:
+                raise ExtractorError('Lecture not found')
+            return lecture
+        return self.playlist_result(entries, course_id, **course_info)

yt_dlp/extractor/nzonscreen.py

@@ -2,25 +2,27 @@ from .common import InfoExtractor
 from ..utils import (
     float_or_none,
     int_or_none,
-    remove_end,
     strip_or_none,
     traverse_obj,
     url_or_none,
+    urlhandle_detect_ext,
 )
 
 
 class NZOnScreenIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.nzonscreen\.com/title/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://www\.nzonscreen\.com/title/(?P<id>[^/?#]+)/?(?!series)'
     _TESTS = [{
         'url': 'https://www.nzonscreen.com/title/shoop-shoop-diddy-wop-cumma-cumma-wang-dang-1982',
         'info_dict': {
             'id': '726ed6585c6bfb30',
             'ext': 'mp4',
             'format_id': 'hi',
+            'height': 480,
+            'width': 640,
             'display_id': 'shoop-shoop-diddy-wop-cumma-cumma-wang-dang-1982',
             'title': 'Monte Video - "Shoop Shoop, Diddy Wop"',
             'description': 'Monte Video - "Shoop Shoop, Diddy Wop"',
-            'alt_title': 'Shoop Shoop Diddy Wop Cumma Cumma Wang Dang | Music Video',
+            'alt_title': 'Shoop Shoop Diddy Wop Cumma Cumma Wang Dang',
             'thumbnail': r're:https://www\.nzonscreen\.com/content/images/.+\.jpg',
             'duration': 158,
         },
@@ -31,10 +33,12 @@ class NZOnScreenIE(InfoExtractor):
             'id': '3dbe709ff03c36f1',
             'ext': 'mp4',
             'format_id': 'hi',
+            'height': 480,
+            'width': 640,
             'display_id': 'shes-a-mod-1964',
             'title': 'Ray Columbus - \'She\'s A Mod\'',
             'description': 'Ray Columbus - \'She\'s A Mod\'',
-            'alt_title': 'She\'s a Mod | Music Video',
+            'alt_title': 'She\'s a Mod',
             'thumbnail': r're:https://www\.nzonscreen\.com/content/images/.+\.jpg',
             'duration': 130,
         },
@@ -45,49 +49,109 @@ class NZOnScreenIE(InfoExtractor):
             'id': 'f86342544385ad8a',
             'ext': 'mp4',
             'format_id': 'hi',
+            'height': 540,
+            'width': 718,
             'display_id': 'puha-and-pakeha-1968',
             'title': 'Looking At New Zealand - Puha and Pakeha',
-            'alt_title': 'Looking at New Zealand - \'Pūhā and Pākehā\' | Television',
+            'alt_title': 'Looking at New Zealand - \'Pūhā and Pākehā\'',
             'description': 'An excerpt from this television programme.',
             'duration': 212,
             'thumbnail': r're:https://www\.nzonscreen\.com/content/images/.+\.jpg',
         },
         'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://www.nzonscreen.com/title/flatmates-episode-one-1997',
+        'playlist': [{
+            'info_dict': {
+                'id': '8f4941d243e42210',
+                'ext': 'mp4',
+                'format_id': 'hd',
+                'height': 574,
+                'width': 740,
+                'title': 'Flatmates ep 1',
+                'display_id': 'flatmates-episode-one-1997',
+                'thumbnail': r're:https://www\.nzonscreen\.com/content/images/.+\.jpg',
+                'duration': 1355.0,
+                'description': 'Episode 1',
+            },
+        }],
+        'info_dict': {
+            'id': 'flatmates-episode-one-1997',
+            'title': 'Flatmates - 1, First Episode',
+        },
+        'playlist_count': 5,
+    }, {
+        'url': 'https://www.nzonscreen.com/title/reluctant-hero-2008',
+        'info_dict': {
+            'id': '847f5c91af65d44b',
+            'ext': 'mp4',
+            'format_id': 'hi',
+            'height': 360,
+            'width': 640,
+            'subtitles': {
+                'en': [{'ext': 'SRT', 'data': 'md5:c2469f71020a32e55e228b532ded908f'}],
+            },
+            'title': 'Reluctant Hero (clip 1)',
+            'description': 'Part one of four from this full length documentary.',
+            'display_id': 'reluctant-hero-2008',
+            'duration': 1108.0,
+            'thumbnail': r're:https://www\.nzonscreen\.com/content/images/.+\.jpg',
+        },
+        'params': {'writesubtitles': True},
     }]
 
     def _extract_formats(self, playlist):
+        formats = []
         for quality, (id_, url) in enumerate(traverse_obj(
-                playlist, ('h264', {'lo': 'lo_res', 'hi': 'hi_res'}), expected_type=url_or_none).items()):
-            yield {
-                'url': url,
-                'format_id': id_,
-                'ext': 'mp4',
-                'quality': quality,
-                'height': int_or_none(playlist.get('height')) if id_ == 'hi' else None,
-                'width': int_or_none(playlist.get('width')) if id_ == 'hi' else None,
-                'filesize_approx': float_or_none(traverse_obj(playlist, ('h264', f'{id_}_res_mb')), invscale=1024**2),
-            }
+                playlist, ('h264', {'lo': 'lo_res', 'hi': 'hi_res', 'hd': 'hd_res'}),
+                expected_type=url_or_none).items()):
+            if traverse_obj(playlist, ('h264', f'{id_}_res_mb', {float_or_none})):
+                formats.append({
+                    'url': url,
+                    'format_id': id_,
+                    'ext': 'mp4',
+                    'quality': quality,
+                    'filesize_approx': float_or_none(traverse_obj(
+                        playlist, ('h264', f'{id_}_res_mb')), invscale=1024**2),
+                })
+        if formats:
+            formats[-1].update(traverse_obj(playlist, {
+                'height': ('height', {int_or_none}),
+                'width': ('width', {int_or_none}),
+            }))
+        return formats
+
+    def _get_subtitles(self, playinfo, video_id):
+        if caption := traverse_obj(playinfo, ('h264', 'caption_url')):
+            subtitle, urlh = self._download_webpage_handle(
+                'https://www.nzonscreen.com' + caption, video_id, 'Downloading subtitles')
+            if subtitle:
+                return {'en': [{'ext': urlhandle_detect_ext(urlh), 'data': subtitle}]}
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
+        title = strip_or_none((
+            self._html_extract_title(webpage, default=None)
+            or self._og_search_title(webpage)).rsplit('|', 2)[0])
+        playlist = self._download_json(
+            f'https://www.nzonscreen.com/html5/video_data/{video_id}', video_id,
+            'Downloading media data')
 
-        playlist = self._parse_json(self._html_search_regex(
-            r'data-video-config=\'([^\']+)\'', webpage, 'media data'), video_id)
-
-        return {
-            'id': playlist['uuid'],
+        return self.playlist_result([{
+            'alt_title': title if len(playlist) == 1 else None,
             'display_id': video_id,
-            'title': strip_or_none(playlist.get('label')),
-            'description': strip_or_none(playlist.get('description')),
-            'alt_title': strip_or_none(remove_end(
-                self._html_extract_title(webpage, default=None) or self._og_search_title(webpage),
-                ' | NZ On Screen')),
-            'thumbnail': traverse_obj(playlist, ('thumbnail', 'path')),
-            'duration': float_or_none(playlist.get('duration')),
-            'formats': list(self._extract_formats(playlist)),
             'http_headers': {
                 'Referer': 'https://www.nzonscreen.com/',
                 'Origin': 'https://www.nzonscreen.com/',
             },
-        }
+            'subtitles': self.extract_subtitles(playinfo, video_id),
+            **traverse_obj(playinfo, {
+                'formats': {self._extract_formats},
+                'id': 'uuid',
+                'title': ('label', {strip_or_none}),
+                'description': ('description', {strip_or_none}),
+                'thumbnail': ('thumbnail', 'path'),
+                'duration': ('duration', {float_or_none}),
+            }),
+        } for playinfo in playlist], video_id, title)