Merge 2358117d39 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

@@ -446,6 +446,11 @@ from .cspan import (
     CSpanCongressIE,
     CSpanIE,
 )
+from .ctc import (
+    CTCIE,
+    CTCSeasonIE,
+    CTCSeriesIE,
+)
 from .ctsnews import CtsNewsIE
 from .ctv import CTVIE
 from .ctvnews import CTVNewsIE

yt_dlp/extractor/ctc.py

@@ -0,0 +1,164 @@
+from .common import InfoExtractor
+from ..utils import (
+    traverse_obj, 
+    int_or_none
+)
+
+class CTCIE(InfoExtractor):
+    IE_NAME = 'ctc'
+    _VALID_URL = (
+        r'https?://ctc\.ru/projects/filmi/(?P<project_name>[^/]+)/?(?:video/?)?$'
+        r'|https?://ctc\.ru/projects/(?P<category>show|multiki|serials)/(?P<project_name2>[^/]+)/video/'
+        r'(?:$'
+        r'|(?P<season_number>\d+)-sezon/(?P<episode_number>\d+)-(?:vypusk|serija)/?$'
+        r'|promo/[^/]+/?$'
+        r')'
+    )
+    _GEO_COUNTRIES = ['RU']
+
+    def _real_extract(self, url):
+        url_slug = url.split("https://ctc.ru/")[1]
+
+        item_response = self._download_json(
+            f'https://ctc.ru/api/page/v1/{url_slug}', url_slug,
+            note='Downloading item data', headers={
+                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:97.0) Gecko/20100101 Firefox/97.0"
+            }
+        )
+
+        track_hub_id = str(traverse_obj(item_response, ('content', 0, 'trackHubId'), expected_type=int))
+        if not track_hub_id:
+            self.raise_no_formats('trackHubId not found')
+
+        video_url = traverse_obj(
+                item_response, ('content', 0, 'videoUrl'), get_all=False
+            ) or traverse_obj(
+                item_response, ('content', 0, 'trackUrl'), get_all=False
+        )
+        stream_response = self._download_json(
+            video_url.replace("/player/", "/playlist/"), 
+            track_hub_id,
+            note='Downloading stream data', headers={
+                'X-Referer': 'https://ctc.ru',
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:97.0) Gecko/20100101 Firefox/97.0',
+            }
+        )
+
+        if traverse_obj(stream_response, ('playlist', 'items', 0, 'errors', 0, 'code')) == 102:
+            self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
+        elif traverse_obj(stream_response, ('playlist', 'items', 0, 'errors', 0, 'code')) == 103:
+            self.raise_login_required(msg='This video is only available for registered users with the required subscription')
+
+        formats = []
+        for stream in traverse_obj(stream_response, ('playlist', 'items', 0, 'streams')):
+            protocol = stream.get('protocol')
+            video_id = traverse_obj(stream_response, ('playlist', 'items', 0, 'track_id'))
+
+            fmts = []
+            if protocol == 'HLS':
+                fmts, _ = self._extract_m3u8_formats_and_subtitles(
+                    stream.get('url'), video_id, ext='mp4', preference=1, m3u8_id="video/hls", fatal=False)
+            formats.extend(fmts)
+
+        return {
+            'formats': formats,
+            'id': track_hub_id,
+            'title': ": ".join(filter(None, [
+                traverse_obj(stream_response, ('playlist', 'items', 0, 'project_name')),
+                traverse_obj(stream_response, ('playlist', 'items', 0, 'episode_name'))
+            ])),
+            **traverse_obj(item_response, {
+                'description': ('content', 0, 'description'),
+            }),
+            **traverse_obj(stream_response, {
+                'episode': ('playlist', 'items', 0, 'episode_name'),
+                'duration': ('playlist', 'items', 0, 'duration'),
+                'thumbnail': ('playlist', 'items', 0, 'thumbnail_url'),
+                'season': ('playlist', 'items', 0, 'season_name'),
+                'age_limit': ('playlist', 'items', 0, 'min_age'),
+            }),
+            'season_number': int_or_none(self._match_valid_url(url).group('season_number')),
+            'episode_number': int_or_none(self._match_valid_url(url).group('episode_number')),
+        }
+
+
+class CTCSeasonIE(InfoExtractor):
+    IE_NAME = 'ctc:season'
+    _VALID_URL = (
+        r'https?://ctc\.ru/projects/(?P<category>show|multiki|serials)/'
+        r'(?P<project_name>[^/]+)/video/(?P<season_number>\d+)-sezon/?$'
+    )
+    _GEO_COUNTRIES = ['RU']
+
+    def _real_extract(self, url):
+        url_slug = url.split("https://ctc.ru/")[1]
+        
+        season_data = self._download_json(f'https://ctc.ru/api/page/v1/{url_slug}', url_slug)
+
+        entries = [{
+            '_type': 'url',
+            'title': episode.get('title'),
+            'url': f"https://ctc.ru{episode.get('popupUrl')}",
+            'ie_key': CTCIE.ie_key(),
+            'season_number': self._match_valid_url(url).group('season_number'),
+            'episode_number': self._search_regex(
+                r'/(?P<episode>\d+)-(vypusk|serija)/', 
+                episode.get('popupUrl'), 
+                'episode number', 
+            )
+        } for episode in traverse_obj(season_data, ('content', 1, 'widgets')) if episode.get('popupUrl')]
+
+        return {
+            '_type': 'playlist',    
+            'entries': entries,
+            **traverse_obj(season_data, {
+                'id': ('content', 9, 'entityId'),
+                'title': ('content', 0, 'widgets', 1, 'title'),
+                'season_number': self._match_valid_url(url).group('season_number'),
+                'series': ('content', 0, 'widgets', 1, 'title'),
+                'description': ('content', 0, 'widgets', 1, 'description'),
+            }),
+        }
+
+
+class CTCSeriesIE(InfoExtractor):
+    IE_NAME = 'ctc:series'
+    _VALID_URL = (
+        r'https?://ctc\.ru/projects/(?P<category>show|multiki|serials)/'
+        r'(?P<slug>[^/]+)/?$'
+    )
+    _GEO_COUNTRIES = ['RU']
+
+    def _real_extract(self, url):
+        url_slug = url.split("https://ctc.ru/")[1]
+
+        series_data = self._download_json(f'https://ctc.ru/api/page/v1/{url_slug}', url_slug)
+
+        # cartoons doesn't indicate in the url what type it is, so
+        # if it's a movie, then redirect it to CTCIE
+        if traverse_obj(series_data, ('content', 5, 'tabs')) == []:
+            return self.url_result(f'https://ctc.ru/{url_slug}/video')
+
+        entries = [{
+            '_type': 'url',
+            'title': season.get('title'),
+            'url': f'https://ctc.ru{season.get("url")}',
+            'ie_key': CTCSeasonIE.ie_key(),
+            'season_number': self._search_regex(
+                r'/(?P<episode>\d+)-sezon/', 
+                season.get("url"), 
+                'season number', 
+            ),
+            'series': season.get('title'),
+        } for season in traverse_obj(series_data, ('content', 1, 'tabs')) if season.get("url").endswith("sezon/")]
+
+        return {
+            '_type': 'playlist',
+            'entries': entries,
+            **traverse_obj(series_data, {
+                'id': ('content', 0, 'projectId'),
+                'title': ('content', 0, 'widgets', 1, 'title'),
+                'series': ('content', 0, 'widgets', 1, 'title'),
+                'description': ('content', 0, 'widgets', 1, 'description')
+            }),
+        }