flexget 3.20.2__tar.gz → 3.20.4__tar.gz

{flexget-3.20.2 → flexget-3.20.4}/.gitignore

@@ -25,6 +25,7 @@
 /.Python
 /lib64
 FlexGet.egg-info/
+__pycache__/
 bin/
 build/
 cached_resources/

{flexget-3.20.2 → flexget-3.20.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: flexget
-Version: 3.20.2
+Version: 3.20.4
 Summary: FlexGet is a program aimed to automate downloading or processing content (torrents, podcasts, etc.) from different sources like RSS-feeds, html-pages, various sites and more.
 Project-URL: Issue Tracker, https://github.com/Flexget/Flexget/issues
 Project-URL: Forum, https://github.com/Flexget/Flexget/discussions
@@ -28,6 +28,8 @@ Requires-Python: >=3.10
 Requires-Dist: apscheduler~=3.11
 Requires-Dist: beautifulsoup4~=4.12
 Requires-Dist: cherrypy~=18.10
+Requires-Dist: cryptography~=50.0
+Requires-Dist: curl-cffi~=0.16
 Requires-Dist: feedparser~=6.0
 Requires-Dist: flask-compress~=1.17
 Requires-Dist: flask-cors~=6.0
@@ -45,6 +47,7 @@ Requires-Dist: psutil~=7.0
 Requires-Dist: pynzb~=0.1.0
 Requires-Dist: pyparsing~=3.2
 Requires-Dist: pyrss2gen~=1.1
+Requires-Dist: pyscrypt~=1.6
 Requires-Dist: python-dateutil~=2.9
 Requires-Dist: pyyaml~=6.0
 Requires-Dist: rebulk~=3.2
@@ -56,7 +59,7 @@ Requires-Dist: typing-extensions>=4.16; python_version <= '3.12'
 Requires-Dist: werkzeug~=3.1
 Requires-Dist: zxcvbn~=4.4
 Provides-Extra: all
-Requires-Dist: aiofiles==24.1.0; extra == 'all'
+Requires-Dist: aiofiles==25.1.0; extra == 'all'
 Requires-Dist: aiohappyeyeballs==2.7.1; extra == 'all'
 Requires-Dist: aiohttp-socks==0.11.0; extra == 'all'
 Requires-Dist: aiohttp==3.14.3; extra == 'all'
@@ -67,11 +70,11 @@ Requires-Dist: attrs==26.1.0; extra == 'all'
 Requires-Dist: babelfish==0.6.1; extra == 'all'
 Requires-Dist: bcrypt==5.0.0; extra == 'all'
 Requires-Dist: beautifulsoup4==4.15.0; extra == 'all'
-Requires-Dist: boto3==1.43.63; extra == 'all'
-Requires-Dist: botocore==1.43.63; extra == 'all'
+Requires-Dist: boto3==1.43.67; extra == 'all'
+Requires-Dist: botocore==1.43.67; extra == 'all'
 Requires-Dist: certifi==2026.7.22; extra == 'all'
 Requires-Dist: cffi==2.1.1; (platform_python_implementation != 'PyPy') and extra == 'all'
-Requires-Dist: chardet==7.4.3; extra == 'all'
+Requires-Dist: chardet==7.5.1; extra == 'all'
 Requires-Dist: charset-normalizer==3.4.9; extra == 'all'
 Requires-Dist: click-option-group==0.5.9; extra == 'all'
 Requires-Dist: click==8.4.2; extra == 'all'
@@ -96,12 +99,12 @@ Requires-Dist: idna==3.18; extra == 'all'
 Requires-Dist: jmespath==1.1.0; extra == 'all'
 Requires-Dist: jsonschema-specifications==2025.9.1; extra == 'all'
 Requires-Dist: jsonschema==4.26.0; extra == 'all'
-Requires-Dist: knowit==0.5.11; extra == 'all'
+Requires-Dist: knowit==0.6.1; extra == 'all'
 Requires-Dist: matrix-nio==0.26.0; extra == 'all'
 Requires-Dist: multidict==6.7.1; extra == 'all'
-Requires-Dist: packaging==26.2; extra == 'all'
+Requires-Dist: packaging==26.3; extra == 'all'
 Requires-Dist: paramiko==3.5.1; extra == 'all'
-Requires-Dist: platformdirs==4.11.0; extra == 'all'
+Requires-Dist: platformdirs==4.11.1; extra == 'all'
 Requires-Dist: plexapi==4.18.2; extra == 'all'
 Requires-Dist: propcache==0.5.2; extra == 'all'
 Requires-Dist: pycparser==3.0; (implementation_name != 'PyPy' and platform_python_implementation != 'PyPy') and extra == 'all'
@@ -124,21 +127,21 @@ Requires-Dist: rpds-py==2026.6.3; (python_full_version >= '3.11') and extra == '
 Requires-Dist: s3transfer==0.19.2; extra == 'all'
 Requires-Dist: six==1.17.0; extra == 'all'
 Requires-Dist: socksio==1.0.0; extra == 'all'
-Requires-Dist: soupsieve==2.9.1; extra == 'all'
+Requires-Dist: soupsieve==2.9.2; extra == 'all'
 Requires-Dist: srt==3.5.3; extra == 'all'
 Requires-Dist: stevedore==5.8.0; (python_full_version < '3.11') and extra == 'all'
 Requires-Dist: stevedore==5.9.0; (python_full_version >= '3.11') and extra == 'all'
 Requires-Dist: subliminal==2.7.1; extra == 'all'
 Requires-Dist: tomlkit==0.15.1; extra == 'all'
-Requires-Dist: trakit==0.2.5; extra == 'all'
-Requires-Dist: transmission-rpc==7.0.11; extra == 'all'
+Requires-Dist: trakit==0.3.0; extra == 'all'
+Requires-Dist: transmission-rpc==7.0.12; extra == 'all'
 Requires-Dist: typing-extensions==4.16.0; extra == 'all'
 Requires-Dist: unpaddedbase64==2.1.0; extra == 'all'
 Requires-Dist: urllib3==2.7.0; extra == 'all'
 Requires-Dist: yarl==1.24.5; extra == 'all'
 Provides-Extra: boto3
-Requires-Dist: boto3==1.43.63; extra == 'boto3'
-Requires-Dist: botocore==1.43.63; extra == 'boto3'
+Requires-Dist: boto3==1.43.67; extra == 'boto3'
+Requires-Dist: botocore==1.43.67; extra == 'boto3'
 Requires-Dist: jmespath==1.1.0; extra == 'boto3'
 Requires-Dist: python-dateutil==2.9.0.post0; extra == 'boto3'
 Requires-Dist: s3transfer==0.19.2; extra == 'boto3'
@@ -161,13 +164,15 @@ Requires-Dist: blinker==1.9.0; extra == 'locked'
 Requires-Dist: brotli==1.2.0; (platform_python_implementation != 'PyPy') and extra == 'locked'
 Requires-Dist: brotlicffi==1.2.0.1; (platform_python_implementation == 'PyPy') and extra == 'locked'
 Requires-Dist: certifi==2026.7.22; extra == 'locked'
-Requires-Dist: cffi==2.1.1; (platform_python_implementation == 'PyPy') and extra == 'locked'
+Requires-Dist: cffi==2.1.1; extra == 'locked'
 Requires-Dist: charset-normalizer==3.4.9; extra == 'locked'
 Requires-Dist: cheroot==11.1.2; extra == 'locked'
 Requires-Dist: cherrypy==18.10.0; extra == 'locked'
 Requires-Dist: click==8.4.2; extra == 'locked'
 Requires-Dist: colorama==0.4.6; (sys_platform == 'win32') and extra == 'locked'
-Requires-Dist: coverage==7.15.3; extra == 'locked'
+Requires-Dist: coverage==7.15.4; extra == 'locked'
+Requires-Dist: cryptography==50.0.0; extra == 'locked'
+Requires-Dist: curl-cffi==0.16.0; extra == 'locked'
 Requires-Dist: exceptiongroup==1.3.1; (python_full_version < '3.11') and extra == 'locked'
 Requires-Dist: execnet==2.1.2; extra == 'locked'
 Requires-Dist: feedparser-sgmllib==2.1.0; extra == 'locked'
@@ -196,18 +201,19 @@ Requires-Dist: markdown-it-py==4.2.0; extra == 'locked'
 Requires-Dist: markupsafe==3.0.3; extra == 'locked'
 Requires-Dist: mdurl==0.1.2; extra == 'locked'
 Requires-Dist: more-itertools==11.1.0; extra == 'locked'
-Requires-Dist: packaging==26.2; extra == 'locked'
+Requires-Dist: packaging==26.3; extra == 'locked'
 Requires-Dist: pendulum==3.2.0; extra == 'locked'
 Requires-Dist: pluggy==1.6.0; extra == 'locked'
 Requires-Dist: plumbum==2.0.2; extra == 'locked'
 Requires-Dist: portend==3.2.1; extra == 'locked'
-Requires-Dist: prek==0.4.12; extra == 'locked'
+Requires-Dist: prek==0.4.13; extra == 'locked'
 Requires-Dist: psutil==7.2.2; extra == 'locked'
-Requires-Dist: pycparser==3.0; (implementation_name != 'PyPy' and platform_python_implementation == 'PyPy') and extra == 'locked'
+Requires-Dist: pycparser==3.0; (implementation_name != 'PyPy') and extra == 'locked'
 Requires-Dist: pygments==2.20.0; extra == 'locked'
 Requires-Dist: pynzb==0.1.0; extra == 'locked'
 Requires-Dist: pyparsing==3.3.2; extra == 'locked'
 Requires-Dist: pyrss2gen==1.1; extra == 'locked'
+Requires-Dist: pyscrypt==1.6.2; extra == 'locked'
 Requires-Dist: pytest-cov==7.1.0; extra == 'locked'
 Requires-Dist: pytest-socket==0.8.0; extra == 'locked'
 Requires-Dist: pytest-xdist==3.8.0; extra == 'locked'
@@ -221,11 +227,11 @@ Requires-Dist: rich==15.0.0; extra == 'locked'
 Requires-Dist: rpds-py==0.30.0; (python_full_version < '3.11') and extra == 'locked'
 Requires-Dist: rpds-py==2026.6.3; (python_full_version >= '3.11') and extra == 'locked'
 Requires-Dist: rpyc==6.0.2; extra == 'locked'
-Requires-Dist: ruff==0.16.0; extra == 'locked'
-Requires-Dist: setuptools==83.0.0; extra == 'locked'
+Requires-Dist: ruff==0.16.2; extra == 'locked'
+Requires-Dist: setuptools==84.0.0; extra == 'locked'
 Requires-Dist: shellingham==1.5.4; extra == 'locked'
 Requires-Dist: six==1.17.0; extra == 'locked'
-Requires-Dist: soupsieve==2.9.1; extra == 'locked'
+Requires-Dist: soupsieve==2.9.2; extra == 'locked'
 Requires-Dist: sqlalchemy==2.0.51; extra == 'locked'
 Requires-Dist: tempora==5.12.0; extra == 'locked'
 Requires-Dist: tomli==2.4.1; (python_full_version <= '3.11') and extra == 'locked'
@@ -243,7 +249,7 @@ Requires-Dist: wrapt==2.3.0; extra == 'locked'
 Requires-Dist: zc-lockfile==4.0; extra == 'locked'
 Requires-Dist: zxcvbn==4.5.0; extra == 'locked'
 Provides-Extra: matrix
-Requires-Dist: aiofiles==24.1.0; extra == 'matrix'
+Requires-Dist: aiofiles==25.1.0; extra == 'matrix'
 Requires-Dist: aiohappyeyeballs==2.7.1; extra == 'matrix'
 Requires-Dist: aiohttp-socks==0.11.0; extra == 'matrix'
 Requires-Dist: aiohttp==3.14.3; extra == 'matrix'
@@ -280,7 +286,7 @@ Provides-Extra: qbittorrent
 Requires-Dist: certifi==2026.7.22; extra == 'qbittorrent'
 Requires-Dist: charset-normalizer==3.4.9; extra == 'qbittorrent'
 Requires-Dist: idna==3.18; extra == 'qbittorrent'
-Requires-Dist: packaging==26.2; extra == 'qbittorrent'
+Requires-Dist: packaging==26.3; extra == 'qbittorrent'
 Requires-Dist: qbittorrent-api==2026.8.0; extra == 'qbittorrent'
 Requires-Dist: requests==2.34.2; extra == 'qbittorrent'
 Requires-Dist: urllib3==2.7.0; extra == 'qbittorrent'
@@ -299,7 +305,7 @@ Provides-Extra: subliminal
 Requires-Dist: babelfish==0.6.1; extra == 'subliminal'
 Requires-Dist: beautifulsoup4==4.15.0; extra == 'subliminal'
 Requires-Dist: certifi==2026.7.22; extra == 'subliminal'
-Requires-Dist: chardet==7.4.3; extra == 'subliminal'
+Requires-Dist: chardet==7.5.1; extra == 'subliminal'
 Requires-Dist: charset-normalizer==3.4.9; extra == 'subliminal'
 Requires-Dist: click-option-group==0.5.9; extra == 'subliminal'
 Requires-Dist: click==8.4.2; extra == 'subliminal'
@@ -310,8 +316,8 @@ Requires-Dist: dogpile-cache==1.5.0; extra == 'subliminal'
 Requires-Dist: enzyme==0.5.2; extra == 'subliminal'
 Requires-Dist: guessit==3.8.0; extra == 'subliminal'
 Requires-Dist: idna==3.18; extra == 'subliminal'
-Requires-Dist: knowit==0.5.11; extra == 'subliminal'
-Requires-Dist: platformdirs==4.11.0; extra == 'subliminal'
+Requires-Dist: knowit==0.6.1; extra == 'subliminal'
+Requires-Dist: platformdirs==4.11.1; extra == 'subliminal'
 Requires-Dist: pymediainfo==7.0.1; extra == 'subliminal'
 Requires-Dist: pysubs2==1.8.1; extra == 'subliminal'
 Requires-Dist: python-dateutil==2.9.0.post0; extra == 'subliminal'
@@ -319,13 +325,13 @@ Requires-Dist: pyyaml==6.0.3; extra == 'subliminal'
 Requires-Dist: rebulk==3.2.0; extra == 'subliminal'
 Requires-Dist: requests==2.34.2; extra == 'subliminal'
 Requires-Dist: six==1.17.0; extra == 'subliminal'
-Requires-Dist: soupsieve==2.9.1; extra == 'subliminal'
+Requires-Dist: soupsieve==2.9.2; extra == 'subliminal'
 Requires-Dist: srt==3.5.3; extra == 'subliminal'
 Requires-Dist: stevedore==5.8.0; (python_full_version < '3.11') and extra == 'subliminal'
 Requires-Dist: stevedore==5.9.0; (python_full_version >= '3.11') and extra == 'subliminal'
 Requires-Dist: subliminal==2.7.1; extra == 'subliminal'
 Requires-Dist: tomlkit==0.15.1; extra == 'subliminal'
-Requires-Dist: trakit==0.2.5; extra == 'subliminal'
+Requires-Dist: trakit==0.3.0; extra == 'subliminal'
 Requires-Dist: typing-extensions==4.16.0; extra == 'subliminal'
 Requires-Dist: urllib3==2.7.0; extra == 'subliminal'
 Provides-Extra: telegram
@@ -347,7 +353,7 @@ Requires-Dist: certifi==2026.7.22; extra == 'transmission'
 Requires-Dist: charset-normalizer==3.4.9; extra == 'transmission'
 Requires-Dist: idna==3.18; extra == 'transmission'
 Requires-Dist: requests==2.34.2; extra == 'transmission'
-Requires-Dist: transmission-rpc==7.0.11; extra == 'transmission'
+Requires-Dist: transmission-rpc==7.0.12; extra == 'transmission'
 Requires-Dist: typing-extensions==4.16.0; extra == 'transmission'
 Requires-Dist: urllib3==2.7.0; extra == 'transmission'
 Description-Content-Type: text/x-rst

{flexget-3.20.2 → flexget-3.20.4}/flexget/_version.py

@@ -10,4 +10,4 @@ and update the version again for continued development.
 NOTE: Should always have all three parts of the version, even on major and minor bumps. i.e. 4.0.0.dev, not 4.0.dev
 """
 
-__version__ = '3.20.2'
+__version__ = '3.20.4'

{flexget-3.20.2 → flexget-3.20.4}/flexget/components/imdb/imdb_watchlist.py

@@ -1,19 +1,14 @@
 from loguru import logger
 
 from flexget import plugin
+from flexget.components.imdb.waf import imdb_get
 from flexget.config_schema import one_or_more
 from flexget.entry import Entry
 from flexget.event import event
 from flexget.utils import json
 from flexget.utils.cached_input import cached
-from flexget.utils.requests import RequestException
 from flexget.utils.soup import get_soup
 
-try:
-    from playwright.sync_api import sync_playwright
-except ImportError:
-    sync_playwright = None
-
 logger = logger.bind(name='imdb_watchlist')
 USER_ID_RE = r'^ur\d{7,9}$'
 CUSTOM_LIST_RE = r'^ls\d{7,10}$'
@@ -34,9 +29,6 @@ TITLE_TYPE_MAP = {
 class ImdbWatchlist:
     """Creates an entry for each movie in your imdb list."""
 
-    def __init__(self):
-        self._waf_cookies = None
-
     schema = {
         'type': 'object',
         'properties': {
@@ -109,80 +101,14 @@ class ImdbWatchlist:
             params['title_type'] = ','.join(title_types)
             params['sort'] = 'list_order%2Casc'
 
-        if config['list'] == 'watchlist':
-            entries = self.parse_html_list(
-                task, config, url, params, headers, kind='predefinedList'
-            )
-        else:
-            entries = self.parse_html_list(task, config, url, params, headers)
-        return entries
-
-    def _solve_waf(self, url, params, headers):
-        """Bypass AWS WAF JS challenge using Playwright (optional dep).
-
-        Returns cookies dict with aws-waf-token, or None on failure.
-        """
-        if sync_playwright is None:
-            logger.warning(
-                'AWS WAF challenge detected. Install playwright to bypass: '
-                'pip install playwright && playwright install chromium'
-            )
-            return None
-
-        logger.info('Solving AWS WAF challenge via Playwright headless browser...')
-        try:
-            with sync_playwright() as pw:
-                browser = pw.chromium.launch(headless=True)
-                context = browser.new_context(
-                    user_agent=headers.get('User-Agent', self.default_user_agent),
-                    locale=headers.get('Accept-Language', 'en-us').replace('-', '_'),
-                )
-                page = context.new_page()
-                page.set_extra_http_headers({
-                    'Accept-Language': headers.get('Accept-Language', 'en-us')
-                })
-                page.goto(
-                    url + '?' + '&'.join(f'{k}={v}' for k, v in params.items()),
-                    wait_until='networkidle',
-                    timeout=30000,
-                )
-                cookies = page.context.cookies()
-                browser.close()
-
-            cookie_dict = {c['name']: c['value'] for c in cookies}
-            if 'aws-waf-token' in cookie_dict:
-                logger.debug('Successfully obtained aws-waf-token from Playwright')
-                return cookie_dict
-            logger.warning('Playwright did not receive aws-waf-token cookie')
-            return None  # noqa: TRY300
-        except Exception as e:
-            logger.warning('Failed to solve AWS WAF challenge with Playwright: {}', e)
-            return None
+        return self.parse_html_list(task, config, url, params, headers)
 
     def fetch_page(self, task, url, params, headers):
         logger.debug('Requesting: {} {}', url, headers)
-
-        # If we have cached WAF cookies from a previous solve, attach them
-        if self._waf_cookies:
-            task.requests.cookies.update(self._waf_cookies)
-
         try:
-            page = task.requests.get(url, params=params, headers=headers)
-        except RequestException as e:
-            raise plugin.PluginError(str(e))
-
-        # AWS WAF JS challenge detected — solve it via Playwright
-        if page.status_code == 202 and page.headers.get('x-amzn-waf-action') == 'challenge':
-            logger.info('IMDB WAF challenge triggered, attempting to bypass...')
-            waf_cookies = self._solve_waf(url, params, headers)
-            if waf_cookies:
-                self._waf_cookies = waf_cookies
-                task.requests.cookies.update(waf_cookies)
-                try:
-                    page = task.requests.get(url, params=params, headers=headers)
-                except RequestException as e:
-                    raise plugin.PluginError(str(e))
-
+            page = imdb_get(url, params=params, headers=headers, raise_status=False)
+        except Exception as e:
+            raise plugin.PluginError(str(e)) from e
         if page.status_code != 200:
             raise plugin.PluginError(
                 f'Unable to get imdb list. Either list is private or does not exist. '
@@ -190,7 +116,7 @@ class ImdbWatchlist:
             )
         return page
 
-    def parse_html_list(self, task, config, url, params, headers, kind='list') -> list[Entry]:
+    def parse_html_list(self, task, config, url, params, headers) -> list[Entry]:
         logger.debug('Parsing imdb list: {}', url)
         page = self.fetch_page(task, url, params, headers)
         soup = get_soup(page.text)
@@ -198,22 +124,14 @@ class ImdbWatchlist:
             query_result = json.loads(
                 soup.find('script', id='__NEXT_DATA__', type='application/json').string
             )
-
-            # Handle different JSON structures for different list types
+            advanced_search = query_result['props']['pageProps']['mainColumnData'][
+                'advancedTitleSearch'
+            ]
             if config['list'] == 'ratings':
-                # Ratings use advancedTitleSearch structure
-                advanced_search = query_result['props']['pageProps']['mainColumnData'][
-                    'advancedTitleSearch'
-                ]
                 total_item_count = advanced_search['total']
-                items = advanced_search['edges']
             else:
-                # Watchlists and other lists use the existing structure
                 total_item_count = query_result['props']['pageProps']['totalItems']
-                items = query_result['props']['pageProps']['mainColumnData'][kind][
-                    'titleListItemSearch'
-                ]['edges']
-
+            items = advanced_search['edges']
             logger.verbose('imdb list contains {} items', total_item_count)
         except Exception:
             total_item_count = 0
@@ -234,26 +152,15 @@ class ImdbWatchlist:
                 query_result = json.loads(
                     soup.find('script', id='__NEXT_DATA__', type='application/json').string
                 )
-
-                # Handle pagination for different structures
-                if config['list'] == 'ratings':
-                    new_items = query_result['props']['pageProps']['mainColumnData'][
-                        'advancedTitleSearch'
-                    ]['edges']
-                else:
-                    new_items = query_result['props']['pageProps']['mainColumnData'][kind][
-                        'titleListItemSearch'
-                    ]['edges']
-                items.extend(new_items)
+                items.extend(
+                    query_result['props']['pageProps']['mainColumnData']['advancedTitleSearch'][
+                        'edges'
+                    ]
+                )
             except Exception:
                 raise plugin.PluginError('Received invalid list data')
 
-        # Extract the actual list items from the different structures
-        if config['list'] == 'ratings':
-            # For ratings, items are directly in edges with 'node' containing the title
-            return [self.parse_entry(item['node']['title'], config) for item in items]
-        # For other lists, items are in edges with 'listItem' structure
-        return [self.parse_entry(item['listItem'], config) for item in items]
+        return [self.parse_entry(item['node']['title'], config) for item in items]
 
     def parse_entry(self, item, config) -> Entry:
         entry = Entry()

{flexget-3.20.2 → flexget-3.20.4}/flexget/components/imdb/utils.py

@@ -8,6 +8,7 @@ from loguru import logger
 from requests import RequestException
 
 from flexget import plugin
+from flexget.components.imdb.waf import imdb_get, set_domain_limiter
 from flexget.utils.requests import Session, TimedLimiter
 from flexget.utils.soup import get_soup
 from flexget.utils.tools import str_to_int
@@ -28,7 +29,9 @@ requests.headers.update({
 })
 
 # give imdb a little break between requests
-requests.add_domain_limiter(TimedLimiter('imdb.com', '3 seconds'))
+imdb_limiter = TimedLimiter('imdb.com', '3 seconds')
+requests.add_domain_limiter(imdb_limiter)
+set_domain_limiter(imdb_limiter)
 
 # Title pages are often served as an AWS WAF challenge to non-browser clients; use the same
 # GraphQL endpoint the site uses.
@@ -312,7 +315,7 @@ class ImdbParser:
                     self.votes,
                 )
                 return
-            page = requests.get(url)
+            page = imdb_get(url)
             soup = get_soup(page.text)
         else:
             logger.debug('IMDb parsing {} from provided HTML', self.imdb_id)
@@ -588,27 +591,48 @@ class ImdbParser:
         if not self.plot_outline:
             logger.debug('No storyline found for {}', self.imdb_id)
 
-        storyline_keywords = data.get('keywords') or ''
-        if storyline_keywords:
-            self.plot_keywords = storyline_keywords.split(',')
-
         genres = (above_the_fold_data.get('genres', {}) or {}).get('genres', [])
         self.genres = [g['text'].lower() for g in genres]
 
-        # Cast section
-        cast_data = main_column_data.get('cast', {}) or {}
-        for cast_node in cast_data.get('edges') or []:
-            actor_node = (cast_node.get('node') or {}).get('name') or {}
-            actor_id = actor_node.get('id')
-            actor_name = (actor_node.get('nameText') or {}).get('text')
-            if actor_id and actor_name:
-                self.actors[actor_id] = actor_name
-
-        principal_cast_data = main_column_data.get('principalCast', []) or []
-        if principal_cast_data:
-            for cast_node in principal_cast_data[0].get('credits') or []:
-                actor_node = cast_node.get('name') or {}
+        keywords_data = above_the_fold_data.get('keywords')
+        if keywords_data and keywords_data.get('edges'):
+            self.plot_keywords = [
+                edge['node']['text']
+                for edge in keywords_data['edges']
+                if edge.get('node', {}).get('text')
+            ]
+        elif storyline_keywords := data.get('keywords') or '':
+            self.plot_keywords = storyline_keywords.split(',')
+
+        # Cast section (castV2 is the current format)
+        for cast_group in main_column_data.get('castV2') or []:
+            self._parse_person_credits(cast_group.get('credits'), self.actors)
+
+        # Legacy cast formats
+        if not self.actors:
+            cast_data = main_column_data.get('cast', {}) or {}
+            for cast_node in cast_data.get('edges') or []:
+                actor_node = (cast_node.get('node') or {}).get('name') or {}
                 actor_id = actor_node.get('id')
                 actor_name = (actor_node.get('nameText') or {}).get('text')
                 if actor_id and actor_name:
                     self.actors[actor_id] = actor_name
+
+        if not self.actors:
+            principal_cast_data = main_column_data.get('principalCast', []) or []
+            if principal_cast_data:
+                for cast_node in principal_cast_data[0].get('credits') or []:
+                    actor_node = cast_node.get('name') or {}
+                    actor_id = actor_node.get('id')
+                    actor_name = (actor_node.get('nameText') or {}).get('text')
+                    if actor_id and actor_name:
+                        self.actors[actor_id] = actor_name
+
+    @staticmethod
+    def _parse_person_credits(credits, persons):
+        for credit in credits or []:
+            name_node = credit.get('name') or {}
+            person_id = name_node.get('id')
+            person_name = (name_node.get('nameText') or {}).get('text')
+            if person_id and person_name:
+                persons[person_id] = person_name

flexget-3.20.4/flexget/components/imdb/waf.py

@@ -0,0 +1,70 @@
+"""AWS WAF challenge handling for IMDB requests."""
+
+from __future__ import annotations
+
+import threading
+from typing import TYPE_CHECKING
+
+from loguru import logger
+
+from flexget.utils.waf import waf_get
+
+if TYPE_CHECKING:
+    from curl_cffi.requests import Response
+
+logger = logger.bind(name='imdb.waf')
+
+IMDB_USER_AGENT = (
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 '
+    '(KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36'
+)
+
+IMDB_BROWSER_HEADERS = {
+    'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+    'accept-language': 'en-US,en;q=0.9',
+    'sec-ch-ua': '"Chromium";v="136", "Google Chrome";v="136", "Not.A/Brand";v="99"',
+    'sec-ch-ua-mobile': '?0',
+    'sec-ch-ua-platform': '"Windows"',
+    'sec-fetch-dest': 'document',
+    'sec-fetch-mode': 'navigate',
+    'sec-fetch-site': 'none',
+    'sec-fetch-user': '?1',
+    'upgrade-insecure-requests': '1',
+    'user-agent': IMDB_USER_AGENT,
+}
+
+_session = None
+_session_lock = threading.Lock()
+_domain_limiter = None
+
+
+def _get_session():
+    from curl_cffi import requests as curl_requests
+
+    global _session
+    if _session is None:
+        with _session_lock:
+            if _session is None:
+                _session = curl_requests.Session(impersonate='chrome')
+                _session.headers.update(IMDB_BROWSER_HEADERS)
+    return _session
+
+
+def set_domain_limiter(limiter) -> None:
+    """Register a rate limiter to run before each IMDB page request."""
+    global _domain_limiter
+    _domain_limiter = limiter
+
+
+def imdb_get(url: str, *, raise_status: bool = True, **kwargs) -> Response:
+    """GET an IMDB page, solving AWS WAF challenges when needed."""
+    return waf_get(
+        _get_session(),
+        url,
+        domain='imdb.com',
+        cookie_domain='.imdb.com',
+        user_agent=IMDB_USER_AGENT,
+        limiter=_domain_limiter,
+        raise_status=raise_status,
+        **kwargs,
+    )

flexget-3.20.4/flexget/utils/waf/README.md

@@ -0,0 +1,7 @@
+# AWS waf
+
+Source:
+
+https://github.com/xKiian/awswaf
+
+License: MIT

flexget-3.20.4/flexget/utils/waf/__init__.py

@@ -0,0 +1,63 @@
+"""Generic AWS WAF challenge handling."""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any
+
+from loguru import logger
+
+from flexget.utils.waf.aws import AwsWaf
+
+if TYPE_CHECKING:
+    from curl_cffi.requests import Response, Session
+
+logger = logger.bind(name='utils.waf')
+
+__all__ = ['AwsWaf', 'is_waf_challenge', 'solve_waf', 'waf_get']
+
+
+def is_waf_challenge(response: Any) -> bool:
+    if response.status_code == 202:
+        return True
+    if response.headers.get('x-amzn-waf-action') == 'challenge':
+        return True
+    return bool(response.text and 'window.gokuProps' in response.text)
+
+
+def solve_waf(response: Any, domain: str, user_agent: str | None = None) -> str:
+    goku, host = AwsWaf.extract(response.text)
+    logger.debug('Solving AWS WAF challenge for {}', domain)
+    kwargs = {'user_agent': user_agent} if user_agent else {}
+    token = AwsWaf(goku, host, domain, **kwargs)()
+    logger.debug('AWS WAF challenge solved for {}', domain)
+    return token
+
+
+def waf_get(
+    session: Session,
+    url: str,
+    *,
+    domain: str,
+    cookie_domain: str | None = None,
+    user_agent: str | None = None,
+    limiter=None,
+    raise_status: bool = True,
+    **kwargs,
+) -> Response:
+    """GET a URL, solving an AWS WAF challenge and retrying once if one is served."""
+    if limiter is not None:
+        limiter()
+
+    headers = kwargs.pop('headers', None)
+    req_headers = {**session.headers, **headers} if headers else None
+
+    response = session.get(url, headers=req_headers, **kwargs)
+    if is_waf_challenge(response):
+        token = solve_waf(response, domain, user_agent)
+        session.cookies.set('aws-waf-token', token, domain=cookie_domain or f'.{domain}')
+        response = session.get(url, headers=req_headers, **kwargs)
+
+    if raise_status and response.status_code >= 400:
+        response.raise_for_status()
+
+    return response