crawlee 1.0.3b6__py3-none-any.whl → 1.2.2b24__py3-none-any.whl

crawlee/__init__.py

@@ -1,6 +1,6 @@
 from importlib import metadata
 
-from ._request import Request, RequestOptions
+from ._request import Request, RequestOptions, RequestState
 from ._service_locator import service_locator
 from ._types import ConcurrencySettings, EnqueueStrategy, HttpHeaders, RequestTransformAction, SkippedReason
 from ._utils.globs import Glob
@@ -14,6 +14,7 @@ __all__ = [
     'HttpHeaders',
     'Request',
     'RequestOptions',
+    'RequestState',
     'RequestTransformAction',
     'SkippedReason',
     'service_locator',

crawlee/_browserforge_workaround.py

@@ -1,4 +1,8 @@
 # ruff: noqa: N802, PLC0415
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from collections.abc import Callable
 
 
 def patch_browserforge() -> None:
@@ -12,7 +16,7 @@ def patch_browserforge() -> None:
     import apify_fingerprint_datapoints
     from browserforge import download
 
-    download.DATA_DIRS: dict[str, Path] = {  # type:ignore[misc]
+    download.DATA_DIRS = {
         'headers': apify_fingerprint_datapoints.get_header_network().parent,
         'fingerprints': apify_fingerprint_datapoints.get_fingerprint_network().parent,
     }
@@ -20,7 +24,7 @@ def patch_browserforge() -> None:
     def DownloadIfNotExists(**flags: bool) -> None:
         pass
 
-    download.DownloadIfNotExists = DownloadIfNotExists
+    download.DownloadIfNotExists: Callable[..., None] = DownloadIfNotExists
 
     import browserforge.bayesian_network
 
@@ -33,7 +37,7 @@ def patch_browserforge() -> None:
                 path = download.DATA_DIRS['fingerprints'] / download.DATA_FILES['fingerprints'][path.name]
             super().__init__(path)
 
-    browserforge.bayesian_network.BayesianNetwork = BayesianNetwork  # type:ignore[misc]
+    browserforge.bayesian_network.BayesianNetwork: BayesianNetwork = BayesianNetwork
     import browserforge.headers.generator
 
     browserforge.headers.generator.DATA_DIR = download.DATA_DIRS['headers']

crawlee/_request.py

@@ -34,14 +34,14 @@ class RequestState(IntEnum):
 class CrawleeRequestData(BaseModel):
     """Crawlee-specific configuration stored in the `user_data`."""
 
-    max_retries: Annotated[int | None, Field(alias='maxRetries')] = None
+    max_retries: Annotated[int | None, Field(alias='maxRetries', frozen=True)] = None
     """Maximum number of retries for this request. Allows to override the global `max_request_retries` option of
     `BasicCrawler`."""
 
     enqueue_strategy: Annotated[EnqueueStrategy | None, Field(alias='enqueueStrategy')] = None
     """The strategy that was used for enqueuing the request."""
 
-    state: RequestState | None = None
+    state: RequestState = RequestState.UNPROCESSED
     """Describes the request's current lifecycle state."""
 
     session_rotation_count: Annotated[int | None, Field(alias='sessionRotationCount')] = None
@@ -93,7 +93,7 @@ class UserData(BaseModel, MutableMapping[str, JsonSerializable]):
     def __delitem__(self, key: str) -> None:
         del self.__pydantic_extra__[key]
 
-    def __iter__(self) -> Iterator[str]:  # type: ignore[override]
+    def __iter__(self) -> Iterator[str]:  # ty: ignore[invalid-method-override]
         yield from self.__pydantic_extra__
 
     def __len__(self) -> int:
@@ -137,6 +137,8 @@ class RequestOptions(TypedDict):
     always_enqueue: NotRequired[bool]
     user_data: NotRequired[dict[str, JsonSerializable]]
     no_retry: NotRequired[bool]
+    enqueue_strategy: NotRequired[EnqueueStrategy]
+    max_retries: NotRequired[int | None]
 
 
 @docs_group('Storage data')
@@ -166,7 +168,7 @@ class Request(BaseModel):
 
     model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
-    unique_key: Annotated[str, Field(alias='uniqueKey')]
+    unique_key: Annotated[str, Field(alias='uniqueKey', frozen=True)]
     """A unique key identifying the request. Two requests with the same `unique_key` are considered as pointing
     to the same URL.
 
@@ -178,21 +180,22 @@ class Request(BaseModel):
     and specify which URLs shall be considered equal.
     """
 
-    url: Annotated[str, BeforeValidator(validate_http_url), Field()]
+    url: Annotated[str, BeforeValidator(validate_http_url), Field(frozen=True)]
     """The URL of the web page to crawl. Must be a valid HTTP or HTTPS URL, and may include query parameters
     and fragments."""
 
-    method: HttpMethod = 'GET'
+    method: Annotated[HttpMethod, Field(frozen=True)] = 'GET'
     """HTTP request method."""
 
     payload: Annotated[
         HttpPayload | None,
         BeforeValidator(lambda v: v.encode() if isinstance(v, str) else v),
         PlainSerializer(lambda v: v.decode() if isinstance(v, bytes) else v),
+        Field(frozen=True),
     ] = None
     """HTTP request payload."""
 
-    # Workaround for pydantic 2.12 and mypy type checking issue for Annotated with default_factory
+    # Workaround for Pydantic and type checkers when using Annotated with default_factory
     if TYPE_CHECKING:
         headers: HttpHeaders = HttpHeaders()
         """HTTP request headers."""
@@ -250,6 +253,8 @@ class Request(BaseModel):
         keep_url_fragment: bool = False,
         use_extended_unique_key: bool = False,
         always_enqueue: bool = False,
+        enqueue_strategy: EnqueueStrategy | None = None,
+        max_retries: int | None = None,
         **kwargs: Any,
     ) -> Self:
         """Create a new `Request` instance from a URL.
@@ -277,6 +282,9 @@ class Request(BaseModel):
                 `unique_key` computation. This is only relevant when `unique_key` is not provided.
             always_enqueue: If set to `True`, the request will be enqueued even if it is already present in the queue.
                 Using this is not allowed when a custom `unique_key` is also provided and will result in a `ValueError`.
+            enqueue_strategy: The strategy that will be used for enqueuing the request.
+            max_retries: Maximum number of retries for this request. Allows to override the global `max_request_retries`
+                option of `BasicCrawler`.
             **kwargs: Additional request properties.
         """
         if unique_key is not None and always_enqueue:
@@ -299,7 +307,21 @@ class Request(BaseModel):
         )
 
         if always_enqueue:
-            unique_key = f'{unique_key}_{crypto_random_object_id()}'
+            unique_key = f'{crypto_random_object_id()}|{unique_key}'
+
+        user_data_dict = kwargs.pop('user_data', {}) or {}
+        crawlee_data_dict = user_data_dict.get('__crawlee', {})
+
+        if max_retries is not None:
+            crawlee_data_dict['maxRetries'] = max_retries
+
+        if enqueue_strategy is not None:
+            crawlee_data_dict['enqueueStrategy'] = enqueue_strategy
+
+        crawlee_data = CrawleeRequestData(**crawlee_data_dict)
+
+        if crawlee_data:
+            user_data_dict['__crawlee'] = crawlee_data
 
         request = cls(
             url=url,
@@ -307,6 +329,7 @@ class Request(BaseModel):
             method=method,
             headers=headers,
             payload=payload,
+            user_data=user_data_dict,
             **kwargs,
         )
 
@@ -352,7 +375,7 @@ class Request(BaseModel):
         self.crawlee_data.crawl_depth = new_value
 
     @property
-    def state(self) -> RequestState | None:
+    def state(self) -> RequestState:
         """Crawlee-specific request handling state."""
         return self.crawlee_data.state
 
@@ -365,10 +388,6 @@ class Request(BaseModel):
         """Crawlee-specific limit on the number of retries of the request."""
         return self.crawlee_data.max_retries
 
-    @max_retries.setter
-    def max_retries(self, new_max_retries: int) -> None:
-        self.crawlee_data.max_retries = new_max_retries
-
     @property
     def session_rotation_count(self) -> int | None:
         """Crawlee-specific number of finished session rotations for the request."""

crawlee/_service_locator.py

@@ -38,7 +38,7 @@ class ServiceLocator:
     def get_configuration(self) -> Configuration:
         """Get the configuration."""
         if self._configuration is None:
-            logger.warning('No configuration set, implicitly creating and using default Configuration.')
+            logger.debug('No configuration set, implicitly creating and using default Configuration.')
             self._configuration = Configuration()
 
         return self._configuration
@@ -63,9 +63,9 @@ class ServiceLocator:
     def get_event_manager(self) -> EventManager:
         """Get the event manager."""
         if self._event_manager is None:
-            logger.warning('No event manager set, implicitly creating and using default LocalEventManager.')
+            logger.debug('No event manager set, implicitly creating and using default LocalEventManager.')
             if self._configuration is None:
-                logger.warning(
+                logger.debug(
                     'Implicit creation of event manager will implicitly set configuration as side effect. '
                     'It is advised to explicitly first set the configuration instead.'
                 )
@@ -93,7 +93,7 @@ class ServiceLocator:
     def get_storage_client(self) -> StorageClient:
         """Get the storage client."""
         if self._storage_client is None:
-            logger.warning('No storage client set, implicitly creating and using default FileSystemStorageClient.')
+            logger.debug('No storage client set, implicitly creating and using default FileSystemStorageClient.')
             if self._configuration is None:
                 logger.warning(
                     'Implicit creation of storage client will implicitly set configuration as side effect. '

crawlee/_types.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import dataclasses
 from collections.abc import Callable, Iterator, Mapping
+from copy import deepcopy
 from dataclasses import dataclass
 from typing import TYPE_CHECKING, Annotated, Any, Literal, Protocol, TypedDict, TypeVar, cast, overload
 
@@ -15,7 +16,7 @@ if TYPE_CHECKING:
     import re
     from collections.abc import Callable, Coroutine, Sequence
 
-    from typing_extensions import NotRequired, Required, Unpack
+    from typing_extensions import NotRequired, Required, Self, Unpack
 
     from crawlee import Glob, Request
     from crawlee._request import RequestOptions
@@ -61,14 +62,14 @@ class HttpHeaders(RootModel, Mapping[str, str]):
 
     model_config = ConfigDict(validate_by_name=True, validate_by_alias=True)
 
-    # Workaround for pydantic 2.12 and mypy type checking issue for Annotated with default_factory
+    # Workaround for Pydantic and type checkers when using Annotated with default_factory
     if TYPE_CHECKING:
         root: dict[str, str] = {}
     else:
         root: Annotated[
             dict[str, str],
             PlainValidator(lambda value: _normalize_headers(value)),
-            Field(default_factory=dict),
+            Field(default_factory=lambda: dict[str, str]()),
         ]
 
     def __getitem__(self, key: str) -> str:
@@ -90,7 +91,7 @@ class HttpHeaders(RootModel, Mapping[str, str]):
         combined_headers = {**other, **self.root}
         return HttpHeaders(combined_headers)
 
-    def __iter__(self) -> Iterator[str]:  # type: ignore[override]
+    def __iter__(self) -> Iterator[str]:  # ty: ignore[invalid-method-override]
         yield from self.root
 
     def __len__(self) -> int:
@@ -260,12 +261,24 @@ class KeyValueStoreChangeRecords:
 class RequestHandlerRunResult:
     """Record of calls to storage-related context helpers."""
 
-    def __init__(self, *, key_value_store_getter: GetKeyValueStoreFunction) -> None:
+    def __init__(
+        self,
+        *,
+        key_value_store_getter: GetKeyValueStoreFunction,
+        request: Request,
+    ) -> None:
         self._key_value_store_getter = key_value_store_getter
         self.add_requests_calls = list[AddRequestsKwargs]()
         self.push_data_calls = list[PushDataFunctionCall]()
         self.key_value_store_changes = dict[tuple[str | None, str | None, str | None], KeyValueStoreChangeRecords]()
 
+        # Isolated copies for handler execution
+        self._request = deepcopy(request)
+
+    @property
+    def request(self) -> Request:
+        return self._request
+
     async def add_requests(
         self,
         requests: Sequence[str | Request],
@@ -315,6 +328,14 @@ class RequestHandlerRunResult:
 
         return self.key_value_store_changes[id, name, alias]
 
+    def apply_request_changes(self, target: Request) -> None:
+        """Apply tracked changes from handler copy to original request."""
+        if self.request.user_data != target.user_data:
+            target.user_data = self.request.user_data
+
+        if self.request.headers != target.headers:
+            target.headers = self.request.headers
+
 
 @docs_group('Functions')
 class AddRequestsFunction(Protocol):
@@ -643,6 +664,24 @@ class BasicCrawlingContext:
         """Return hash of the context. Each context is considered unique."""
         return id(self)
 
+    def create_modified_copy(
+        self,
+        push_data: PushDataFunction | None = None,
+        add_requests: AddRequestsFunction | None = None,
+        get_key_value_store: GetKeyValueStoreFromRequestHandlerFunction | None = None,
+    ) -> Self:
+        """Create a modified copy of the crawling context with specified changes."""
+        modifications = dict[str, Any]()
+
+        if push_data is not None:
+            modifications['push_data'] = push_data
+        if add_requests is not None:
+            modifications['add_requests'] = add_requests
+        if get_key_value_store is not None:
+            modifications['get_key_value_store'] = get_key_value_store
+
+        return dataclasses.replace(self, **modifications)
+
 
 class GetDataKwargs(TypedDict):
     """Keyword arguments for dataset's `get_data` method."""

crawlee/_utils/context.py

@@ -1,9 +1,9 @@
 from __future__ import annotations
 
-import asyncio
+import inspect
 from collections.abc import Callable
 from functools import wraps
-from typing import Any, TypeVar
+from typing import Any, TypeVar, cast
 
 T = TypeVar('T', bound=Callable[..., Any])
 
@@ -44,4 +44,4 @@ def ensure_context(method: T) -> T:
 
         return await method(self, *args, **kwargs)
 
-    return async_wrapper if asyncio.iscoroutinefunction(method) else sync_wrapper  # type: ignore[return-value]
+    return cast('T', async_wrapper if inspect.iscoroutinefunction(method) else sync_wrapper)

crawlee/_utils/file.py

@@ -163,7 +163,14 @@ async def export_csv_to_stream(
     dst: TextIO,
     **kwargs: Unpack[ExportDataCsvKwargs],
 ) -> None:
-    writer = csv.writer(dst, **kwargs)  # type: ignore[arg-type]
+    # Set lineterminator to '\n' if not explicitly provided. This prevents double line endings on Windows.
+    # The csv.writer default is '\r\n', which when written to a file in text mode on Windows gets converted
+    # to '\r\r\n' due to newline translation. By using '\n', we let the platform handle the line ending
+    # conversion: '\n' stays as '\n' on Unix, and becomes '\r\n' on Windows.
+    if 'lineterminator' not in kwargs:
+        kwargs['lineterminator'] = '\n'
+
+    writer = csv.writer(dst, **kwargs)
     write_header = True
 
     # Iterate over the dataset and write to CSV.

crawlee/_utils/globs.py

@@ -33,12 +33,12 @@ def _translate(
 
     HACK: This function is copied from CPython stdlib source. It will be released in Python 3.13 as `glob.translate`
     """
-    if not seps:
-        seps = (os.path.sep, os.path.altsep) if os.path.altsep else os.path.sep
+    _seps = ((os.path.sep, os.path.altsep) if os.path.altsep else (os.path.sep,)) if seps is None else seps
 
-    escaped_seps = ''.join(map(re.escape, seps))
-    any_sep = f'[{escaped_seps}]' if len(seps) > 1 else escaped_seps
+    escaped_seps = ''.join(map(re.escape, _seps))
+    any_sep = f'[{escaped_seps}]' if len(_seps) > 1 else escaped_seps
     not_sep = f'[^{escaped_seps}]'
+
     if include_hidden:
         one_last_segment = f'{not_sep}+'
         one_segment = f'{one_last_segment}{any_sep}'

crawlee/_utils/recoverable_state.py

@@ -4,12 +4,14 @@ from typing import TYPE_CHECKING, Generic, Literal, TypeVar
 
 from pydantic import BaseModel
 
+from crawlee._utils.raise_if_too_many_kwargs import raise_if_too_many_kwargs
 from crawlee.events._types import Event, EventPersistStateData
 
 if TYPE_CHECKING:
     import logging
+    from collections.abc import Callable, Coroutine
 
-    from crawlee.storages._key_value_store import KeyValueStore
+    from crawlee.storages import KeyValueStore
 
 TStateModel = TypeVar('TStateModel', bound=BaseModel)
 
@@ -37,6 +39,7 @@ class RecoverableState(Generic[TStateModel]):
         persistence_enabled: Literal[True, False, 'explicit_only'] = False,
         persist_state_kvs_name: str | None = None,
         persist_state_kvs_id: str | None = None,
+        persist_state_kvs_factory: Callable[[], Coroutine[None, None, KeyValueStore]] | None = None,
         logger: logging.Logger,
     ) -> None:
         """Initialize a new recoverable state object.
@@ -51,16 +54,40 @@ class RecoverableState(Generic[TStateModel]):
                 If neither a name nor and id are supplied, the default store will be used.
             persist_state_kvs_id: The identifier of the KeyValueStore to use for persistence.
                 If neither a name nor and id are supplied, the default store will be used.
+            persist_state_kvs_factory: Factory that can be awaited to create KeyValueStore to use for persistence. If
+                not provided, a system-wide KeyValueStore will be used, based on service locator configuration.
             logger: A logger instance for logging operations related to state persistence
         """
+        raise_if_too_many_kwargs(
+            persist_state_kvs_name=persist_state_kvs_name,
+            persist_state_kvs_id=persist_state_kvs_id,
+            persist_state_kvs_factory=persist_state_kvs_factory,
+        )
+        if not persist_state_kvs_factory:
+            logger.debug(
+                'No explicit key_value_store set for recoverable state. Recovery will use a system-wide KeyValueStore '
+                'based on service_locator configuration, potentially calling service_locator.set_storage_client in the '
+                'process. It is recommended to initialize RecoverableState with explicit key_value_store to avoid '
+                'global side effects.'
+            )
+
         self._default_state = default_state
         self._state_type: type[TStateModel] = self._default_state.__class__
         self._state: TStateModel | None = None
         self._persistence_enabled = persistence_enabled
         self._persist_state_key = persist_state_key
-        self._persist_state_kvs_name = persist_state_kvs_name
-        self._persist_state_kvs_id = persist_state_kvs_id
-        self._key_value_store: 'KeyValueStore | None' = None  # noqa: UP037
+        if persist_state_kvs_factory is None:
+
+            async def kvs_factory() -> KeyValueStore:
+                from crawlee.storages import KeyValueStore  # noqa: PLC0415 avoid circular import
+
+                return await KeyValueStore.open(name=persist_state_kvs_name, id=persist_state_kvs_id)
+
+            self._persist_state_kvs_factory = kvs_factory
+        else:
+            self._persist_state_kvs_factory = persist_state_kvs_factory
+
+        self._key_value_store: KeyValueStore | None = None
         self._log = logger
 
     async def initialize(self) -> TStateModel:
@@ -77,11 +104,8 @@ class RecoverableState(Generic[TStateModel]):
             return self.current_value
 
         # Import here to avoid circular imports.
-        from crawlee.storages._key_value_store import KeyValueStore  # noqa: PLC0415
 
-        self._key_value_store = await KeyValueStore.open(
-            name=self._persist_state_kvs_name, id=self._persist_state_kvs_id
-        )
+        self._key_value_store = await self._persist_state_kvs_factory()
 
         await self._load_saved_state()
 

crawlee/_utils/recurring_task.py

@@ -1,12 +1,16 @@
 from __future__ import annotations
 
 import asyncio
+import inspect
 from logging import getLogger
 from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
     from collections.abc import Callable
     from datetime import timedelta
+    from types import TracebackType
+
+    from typing_extensions import Self
 
 logger = getLogger(__name__)
 
@@ -21,11 +25,27 @@ class RecurringTask:
     """
 
     def __init__(self, func: Callable, delay: timedelta) -> None:
-        logger.debug(f'Calling RecurringTask.__init__(func={func.__name__}, delay={delay})...')
+        logger.debug(
+            'Calling RecurringTask.__init__(func={%s}, delay={%s})...',
+            func.__name__ if hasattr(func, '__name__') else func.__class__.__name__,
+            delay,
+        )
         self.func = func
         self.delay = delay
         self.task: asyncio.Task | None = None
 
+    async def __aenter__(self) -> Self:
+        self.start()
+        return self
+
+    async def __aexit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc_value: BaseException | None,
+        exc_traceback: TracebackType | None,
+    ) -> None:
+        await self.stop()
+
     async def _wrapper(self) -> None:
         """Continuously execute the provided function with the specified delay.
 
@@ -34,12 +54,16 @@ class RecurringTask:
         """
         sleep_time_secs = self.delay.total_seconds()
         while True:
-            await self.func() if asyncio.iscoroutinefunction(self.func) else self.func()
+            await self.func() if inspect.iscoroutinefunction(self.func) else self.func()
             await asyncio.sleep(sleep_time_secs)
 
     def start(self) -> None:
         """Start the recurring task execution."""
-        self.task = asyncio.create_task(self._wrapper(), name=f'Task-recurring-{self.func.__name__}')
+        name = self.func.__name__ if hasattr(self.func, '__name__') else self.func.__class__.__name__
+        self.task = asyncio.create_task(
+            self._wrapper(),
+            name=f'Task-recurring-{name}',
+        )
 
     async def stop(self) -> None:
         """Stop the recurring task execution."""

crawlee/_utils/robots.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+from logging import getLogger
 from typing import TYPE_CHECKING
 
 from protego import Protego
@@ -15,6 +16,9 @@ if TYPE_CHECKING:
     from crawlee.proxy_configuration import ProxyInfo
 
 
+logger = getLogger(__name__)
+
+
 class RobotsTxtFile:
     def __init__(
         self, url: str, robots: Protego, http_client: HttpClient | None = None, proxy_info: ProxyInfo | None = None
@@ -56,12 +60,20 @@ class RobotsTxtFile:
             http_client: The `HttpClient` instance used to perform the network request for fetching the robots.txt file.
             proxy_info: Optional `ProxyInfo` to be used when fetching the robots.txt file. If None, no proxy is used.
         """
-        response = await http_client.send_request(url, proxy_info=proxy_info)
-        body = (
-            b'User-agent: *\nAllow: /' if is_status_code_client_error(response.status_code) else await response.read()
-        )
+        try:
+            response = await http_client.send_request(url, proxy_info=proxy_info)
+
+            body = (
+                b'User-agent: *\nAllow: /'
+                if is_status_code_client_error(response.status_code)
+                else await response.read()
+            )
+            robots = Protego.parse(body.decode('utf-8'))
+
+        except Exception as e:
+            logger.warning(f'Failed to fetch from robots.txt from "{url}" with error: "{e}"')
 
-        robots = Protego.parse(body.decode('utf-8'))
+            robots = Protego.parse('User-agent: *\nAllow: /')
 
         return cls(url, robots, http_client=http_client, proxy_info=proxy_info)
 

crawlee/_utils/sitemap.py

@@ -335,7 +335,7 @@ async def _fetch_and_process_sitemap(
                         # Check if the first chunk is a valid gzip header
                         if first_chunk and raw_chunk.startswith(b'\x1f\x8b'):
                             decompressor = zlib.decompressobj(zlib.MAX_WBITS | 16)
-                            first_chunk = False
+                        first_chunk = False
 
                         chunk = decompressor.decompress(raw_chunk) if decompressor else raw_chunk
                         text_chunk = decoder.decode(chunk)
@@ -430,10 +430,17 @@ async def parse_sitemap(
     up to the specified maximum depth.
     """
     # Set default options
-    options = options or {}
-    emit_nested_sitemaps = options.get('emit_nested_sitemaps', False)
-    max_depth = options.get('max_depth', float('inf'))
-    sitemap_retries = options.get('sitemap_retries', 3)
+    default_timeout = timedelta(seconds=30)
+    if options:
+        emit_nested_sitemaps = options['emit_nested_sitemaps']
+        max_depth = options['max_depth']
+        sitemap_retries = options['sitemap_retries']
+        timeout = options.get('timeout', default_timeout)
+    else:
+        emit_nested_sitemaps = False
+        max_depth = float('inf')
+        sitemap_retries = 3
+        timeout = default_timeout
 
     # Setup working state
     sources = list(initial_sources)
@@ -472,7 +479,7 @@ async def parse_sitemap(
                 sitemap_retries,
                 emit_nested_sitemaps=emit_nested_sitemaps,
                 proxy_info=proxy_info,
-                timeout=options.get('timeout', timedelta(seconds=30)),
+                timeout=timeout,
             ):
                 yield result
         else:

crawlee/_utils/system.py

@@ -5,7 +5,7 @@ import sys
 from contextlib import suppress
 from datetime import datetime, timezone
 from logging import getLogger
-from typing import Annotated
+from typing import TYPE_CHECKING, Annotated
 
 import psutil
 from pydantic import BaseModel, ConfigDict, Field, PlainSerializer, PlainValidator
@@ -41,11 +41,19 @@ class CpuInfo(BaseModel):
     used_ratio: Annotated[float, Field(alias='usedRatio')]
     """The ratio of CPU currently in use, represented as a float between 0 and 1."""
 
-    created_at: datetime = Field(
-        alias='createdAt',
-        default_factory=lambda: datetime.now(timezone.utc),
-    )
-    """The time at which the measurement was taken."""
+    # Workaround for Pydantic and type checkers when using Annotated with default_factory
+    if TYPE_CHECKING:
+        created_at: datetime = datetime.now(timezone.utc)
+        """The time at which the measurement was taken."""
+    else:
+        created_at: Annotated[
+            datetime,
+            Field(
+                alias='createdAt',
+                default_factory=lambda: datetime.now(timezone.utc),
+            ),
+        ]
+        """The time at which the measurement was taken."""
 
 
 class MemoryUsageInfo(BaseModel):
@@ -61,11 +69,19 @@ class MemoryUsageInfo(BaseModel):
     ]
     """Memory usage of the current Python process and its children."""
 
-    created_at: datetime = Field(
-        alias='createdAt',
-        default_factory=lambda: datetime.now(timezone.utc),
-    )
-    """The time at which the measurement was taken."""
+    # Workaround for Pydantic and type checkers when using Annotated with default_factory
+    if TYPE_CHECKING:
+        created_at: datetime = datetime.now(timezone.utc)
+        """The time at which the measurement was taken."""
+    else:
+        created_at: Annotated[
+            datetime,
+            Field(
+                alias='createdAt',
+                default_factory=lambda: datetime.now(timezone.utc),
+            ),
+        ]
+        """The time at which the measurement was taken."""
 
 
 class MemoryInfo(MemoryUsageInfo):