crawlee 1.1.1b1__py3-none-any.whl → 1.1.2b4__py3-none-any.whl

crawlee/_types.py

@@ -15,7 +15,7 @@ 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
@@ -643,6 +643,25 @@ 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."""
+        original_fields = {field.name: getattr(self, field.name) for field in dataclasses.fields(self)}
+        modified_fields = {
+            key: value
+            for key, value in {
+                'push_data': push_data,
+                'add_requests': add_requests,
+                'get_key_value_store': get_key_value_store,
+            }.items()
+            if value
+        }
+        return self.__class__(**{**original_fields, **modified_fields})
+
 
 class GetDataKwargs(TypedDict):
     """Keyword arguments for dataset's `get_data` method."""

crawlee/_utils/file.py

@@ -163,6 +163,13 @@ async def export_csv_to_stream(
     dst: TextIO,
     **kwargs: Unpack[ExportDataCsvKwargs],
 ) -> None:
+    # 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)  # type: ignore[arg-type]
     write_header = True
 

crawlee/_utils/time.py

@@ -3,11 +3,14 @@ from __future__ import annotations
 import time
 from contextlib import contextmanager
 from dataclasses import dataclass
+from datetime import timedelta
 from typing import TYPE_CHECKING
 
+from async_timeout import Timeout, timeout
+
 if TYPE_CHECKING:
     from collections.abc import Iterator
-    from datetime import timedelta
+    from types import TracebackType
 
 _SECONDS_PER_MINUTE = 60
 _SECONDS_PER_HOUR = 3600
@@ -35,6 +38,43 @@ def measure_time() -> Iterator[TimerResult]:
         result.cpu = after_cpu - before_cpu
 
 
+class SharedTimeout:
+    """Keeps track of a time budget shared by multiple independent async operations.
+
+    Provides a reusable, non-reentrant context manager interface.
+    """
+
+    def __init__(self, timeout: timedelta) -> None:
+        self._remaining_timeout = timeout
+        self._active_timeout: Timeout | None = None
+        self._activation_timestamp: float | None = None
+
+    async def __aenter__(self) -> timedelta:
+        if self._active_timeout is not None or self._activation_timestamp is not None:
+            raise RuntimeError('A shared timeout context cannot be entered twice at the same time')
+
+        self._activation_timestamp = time.monotonic()
+        self._active_timeout = new_timeout = timeout(self._remaining_timeout.total_seconds())
+        await new_timeout.__aenter__()
+        return self._remaining_timeout
+
+    async def __aexit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc_value: BaseException | None,
+        exc_traceback: TracebackType | None,
+    ) -> None:
+        if self._active_timeout is None or self._activation_timestamp is None:
+            raise RuntimeError('Logic error')
+
+        await self._active_timeout.__aexit__(exc_type, exc_value, exc_traceback)
+        elapsed = time.monotonic() - self._activation_timestamp
+        self._remaining_timeout = self._remaining_timeout - timedelta(seconds=elapsed)
+
+        self._active_timeout = None
+        self._activation_timestamp = None
+
+
 def format_duration(duration: timedelta | None) -> str:
     """Format a timedelta into a human-readable string with appropriate units."""
     if duration is None:

crawlee/crawlers/__init__.py

@@ -1,7 +1,7 @@
 from crawlee._utils.try_import import install_import_hook as _install_import_hook
 from crawlee._utils.try_import import try_import as _try_import
 
-from ._abstract_http import AbstractHttpCrawler, AbstractHttpParser, ParsedHttpCrawlingContext
+from ._abstract_http import AbstractHttpCrawler, AbstractHttpParser, HttpCrawlerOptions, ParsedHttpCrawlingContext
 from ._basic import BasicCrawler, BasicCrawlerOptions, BasicCrawlingContext, ContextPipeline
 from ._http import HttpCrawler, HttpCrawlingContext, HttpCrawlingResult
 
@@ -51,6 +51,7 @@ __all__ = [
     'BeautifulSoupParserType',
     'ContextPipeline',
     'HttpCrawler',
+    'HttpCrawlerOptions',
     'HttpCrawlingContext',
     'HttpCrawlingResult',
     'ParsedHttpCrawlingContext',

crawlee/crawlers/_abstract_http/__init__.py

@@ -1,9 +1,10 @@
-from ._abstract_http_crawler import AbstractHttpCrawler
+from ._abstract_http_crawler import AbstractHttpCrawler, HttpCrawlerOptions
 from ._abstract_http_parser import AbstractHttpParser
 from ._http_crawling_context import ParsedHttpCrawlingContext
 
 __all__ = [
     'AbstractHttpCrawler',
     'AbstractHttpParser',
+    'HttpCrawlerOptions',
     'ParsedHttpCrawlingContext',
 ]

crawlee/crawlers/_abstract_http/_abstract_http_crawler.py

@@ -3,14 +3,16 @@ from __future__ import annotations
 import asyncio
 import logging
 from abc import ABC
+from datetime import timedelta
 from typing import TYPE_CHECKING, Any, Generic
 
 from more_itertools import partition
 from pydantic import ValidationError
-from typing_extensions import TypeVar
+from typing_extensions import NotRequired, TypeVar
 
 from crawlee._request import Request, RequestOptions
 from crawlee._utils.docs import docs_group
+from crawlee._utils.time import SharedTimeout
 from crawlee._utils.urls import to_absolute_url_iterator
 from crawlee.crawlers._basic import BasicCrawler, BasicCrawlerOptions, ContextPipeline
 from crawlee.errors import SessionError
@@ -32,6 +34,19 @@ TCrawlingContext = TypeVar('TCrawlingContext', bound=ParsedHttpCrawlingContext)
 TStatisticsState = TypeVar('TStatisticsState', bound=StatisticsState, default=StatisticsState)
 
 
+class HttpCrawlerOptions(
+    BasicCrawlerOptions[TCrawlingContext, TStatisticsState],
+    Generic[TCrawlingContext, TStatisticsState],
+):
+    """Arguments for the `AbstractHttpCrawler` constructor.
+
+    It is intended for typing forwarded `__init__` arguments in the subclasses.
+    """
+
+    navigation_timeout: NotRequired[timedelta | None]
+    """Timeout for the HTTP request."""
+
+
 @docs_group('Crawlers')
 class AbstractHttpCrawler(
     BasicCrawler[TCrawlingContext, StatisticsState],
@@ -56,10 +71,13 @@ class AbstractHttpCrawler(
         self,
         *,
         parser: AbstractHttpParser[TParseResult, TSelectResult],
+        navigation_timeout: timedelta | None = None,
         **kwargs: Unpack[BasicCrawlerOptions[TCrawlingContext, StatisticsState]],
     ) -> None:
         self._parser = parser
+        self._navigation_timeout = navigation_timeout or timedelta(minutes=1)
         self._pre_navigation_hooks: list[Callable[[BasicCrawlingContext], Awaitable[None]]] = []
+        self._shared_navigation_timeouts: dict[int, SharedTimeout] = {}
 
         if '_context_pipeline' not in kwargs:
             raise ValueError(
@@ -112,9 +130,17 @@ class AbstractHttpCrawler(
     async def _execute_pre_navigation_hooks(
         self, context: BasicCrawlingContext
     ) -> AsyncGenerator[BasicCrawlingContext, None]:
-        for hook in self._pre_navigation_hooks:
-            await hook(context)
-        yield context
+        context_id = id(context)
+        self._shared_navigation_timeouts[context_id] = SharedTimeout(self._navigation_timeout)
+
+        try:
+            for hook in self._pre_navigation_hooks:
+                async with self._shared_navigation_timeouts[context_id]:
+                    await hook(context)
+
+            yield context
+        finally:
+            self._shared_navigation_timeouts.pop(context_id, None)
 
     async def _parse_http_response(
         self, context: HttpCrawlingContext
@@ -167,9 +193,15 @@ class AbstractHttpCrawler(
             kwargs.setdefault('strategy', 'same-hostname')
 
             links_iterator: Iterator[str] = iter(self._parser.find_links(parsed_content, selector=selector))
-            links_iterator = to_absolute_url_iterator(
-                context.request.loaded_url or context.request.url, links_iterator, logger=context.log
+
+            # Get base URL from <base> tag if present
+            extracted_base_urls = list(self._parser.find_links(parsed_content, 'base[href]'))
+            base_url: str = (
+                str(extracted_base_urls[0])
+                if extracted_base_urls
+                else context.request.loaded_url or context.request.url
             )
+            links_iterator = to_absolute_url_iterator(base_url, links_iterator, logger=context.log)
 
             if robots_txt_file:
                 skipped, links_iterator = partition(lambda url: robots_txt_file.is_allowed(url), links_iterator)
@@ -216,12 +248,14 @@ class AbstractHttpCrawler(
         Yields:
             The original crawling context enhanced by HTTP response.
         """
-        result = await self._http_client.crawl(
-            request=context.request,
-            session=context.session,
-            proxy_info=context.proxy_info,
-            statistics=self._statistics,
-        )
+        async with self._shared_navigation_timeouts[id(context)] as remaining_timeout:
+            result = await self._http_client.crawl(
+                request=context.request,
+                session=context.session,
+                proxy_info=context.proxy_info,
+                statistics=self._statistics,
+                timeout=remaining_timeout,
+            )
 
         yield HttpCrawlingContext.from_basic_crawling_context(context=context, http_response=result.http_response)
 

crawlee/crawlers/_basic/_basic_crawler.py

@@ -2,6 +2,7 @@
 from __future__ import annotations
 
 import asyncio
+import functools
 import logging
 import signal
 import sys
@@ -13,8 +14,9 @@ from collections.abc import AsyncGenerator, Awaitable, Callable, Iterable, Seque
 from contextlib import AsyncExitStack, suppress
 from datetime import timedelta
 from functools import partial
+from io import StringIO
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Generic, Literal, cast
+from typing import TYPE_CHECKING, Any, Generic, Literal, ParamSpec, cast
 from urllib.parse import ParseResult, urlparse
 from weakref import WeakKeyDictionary
 
@@ -31,6 +33,8 @@ from crawlee._service_locator import ServiceLocator
 from crawlee._types import (
     BasicCrawlingContext,
     EnqueueLinksKwargs,
+    ExportDataCsvKwargs,
+    ExportDataJsonKwargs,
     GetKeyValueStoreFromRequestHandlerFunction,
     HttpHeaders,
     HttpPayload,
@@ -40,7 +44,7 @@ from crawlee._types import (
     SkippedReason,
 )
 from crawlee._utils.docs import docs_group
-from crawlee._utils.file import export_csv_to_stream, export_json_to_stream
+from crawlee._utils.file import atomic_write, export_csv_to_stream, export_json_to_stream
 from crawlee._utils.recurring_task import RecurringTask
 from crawlee._utils.robots import RobotsTxtFile
 from crawlee._utils.urls import convert_to_absolute_url, is_url_absolute
@@ -96,6 +100,9 @@ if TYPE_CHECKING:
 TCrawlingContext = TypeVar('TCrawlingContext', bound=BasicCrawlingContext, default=BasicCrawlingContext)
 TStatisticsState = TypeVar('TStatisticsState', bound=StatisticsState, default=StatisticsState)
 TRequestIterator = TypeVar('TRequestIterator', str, Request)
+TParams = ParamSpec('TParams')
+T = TypeVar('T')
+
 ErrorHandler = Callable[[TCrawlingContext, Exception], Awaitable[Request | None]]
 FailedRequestHandler = Callable[[TCrawlingContext, Exception], Awaitable[None]]
 SkippedRequestCallback = Callable[[str, SkippedReason], Awaitable[None]]
@@ -520,6 +527,24 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
         self._logger.info(f'Crawler.stop() was called with following reason: {reason}.')
         self._unexpected_stop = True
 
+    def _wrap_handler_with_error_context(
+        self, handler: Callable[[TCrawlingContext | BasicCrawlingContext, Exception], Awaitable[T]]
+    ) -> Callable[[TCrawlingContext | BasicCrawlingContext, Exception], Awaitable[T]]:
+        """Decorate error handlers to make their context helpers usable."""
+
+        @functools.wraps(handler)
+        async def wrapped_handler(context: TCrawlingContext | BasicCrawlingContext, exception: Exception) -> T:
+            # Original context helpers that are from `RequestHandlerRunResult` will not be commited as the request
+            # failed. Modified context provides context helpers with direct access to the storages.
+            error_context = context.create_modified_copy(
+                push_data=self._push_data,
+                get_key_value_store=self.get_key_value_store,
+                add_requests=functools.partial(self._add_requests, context),
+            )
+            return await handler(error_context, exception)
+
+        return wrapped_handler
+
     def _stop_if_max_requests_count_exceeded(self) -> None:
         """Call `stop` when the maximum number of requests to crawl has been reached."""
         if self._max_requests_per_crawl is None:
@@ -618,7 +643,7 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
 
         The error handler is invoked after a request handler error occurs and before a retry attempt.
         """
-        self._error_handler = handler
+        self._error_handler = self._wrap_handler_with_error_context(handler)
         return handler
 
     def failed_request_handler(
@@ -628,7 +653,7 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
 
         The failed request handler is invoked when a request has failed all retry attempts.
         """
-        self._failed_request_handler = handler
+        self._failed_request_handler = self._wrap_handler_with_error_context(handler)
         return handler
 
     def on_skipped_request(self, callback: SkippedRequestCallback) -> SkippedRequestCallback:
@@ -846,6 +871,7 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
         dataset_id: str | None = None,
         dataset_name: str | None = None,
         dataset_alias: str | None = None,
+        **additional_kwargs: Unpack[ExportDataJsonKwargs | ExportDataCsvKwargs],  # type: ignore[misc]
     ) -> None:
         """Export all items from a Dataset to a JSON or CSV file.
 
@@ -858,6 +884,7 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
             dataset_id: The ID of the Dataset to export from.
             dataset_name: The name of the Dataset to export from (global scope, named storage).
             dataset_alias: The alias of the Dataset to export from (run scope, unnamed storage).
+            additional_kwargs: Extra keyword arguments forwarded to the JSON/CSV exporter depending on the file format.
         """
         dataset = await Dataset.open(
             id=dataset_id,
@@ -867,13 +894,18 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
             configuration=self._service_locator.get_configuration(),
         )
 
-        path = path if isinstance(path, Path) else Path(path)
-        dst = path.open('w', newline='')
+        path = Path(path)
 
         if path.suffix == '.csv':
-            await export_csv_to_stream(dataset.iterate_items(), dst)
+            dst = StringIO()
+            csv_kwargs = cast('ExportDataCsvKwargs', additional_kwargs)
+            await export_csv_to_stream(dataset.iterate_items(), dst, **csv_kwargs)
+            await atomic_write(path, dst.getvalue())
         elif path.suffix == '.json':
-            await export_json_to_stream(dataset.iterate_items(), dst)
+            dst = StringIO()
+            json_kwargs = cast('ExportDataJsonKwargs', additional_kwargs)
+            await export_json_to_stream(dataset.iterate_items(), dst, **json_kwargs)
+            await atomic_write(path, dst.getvalue())
         else:
             raise ValueError(f'Unsupported file extension: {path.suffix}')
 
@@ -1043,8 +1075,8 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
             return target_url.hostname == origin_url.hostname
 
         if strategy == 'same-domain':
-            origin_domain = self._tld_extractor.extract_str(origin_url.hostname).domain
-            target_domain = self._tld_extractor.extract_str(target_url.hostname).domain
+            origin_domain = self._tld_extractor.extract_str(origin_url.hostname).top_domain_under_public_suffix
+            target_domain = self._tld_extractor.extract_str(target_url.hostname).top_domain_under_public_suffix
             return origin_domain == target_domain
 
         if strategy == 'same-origin':
@@ -1113,19 +1145,14 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
                 except Exception as e:
                     raise UserDefinedErrorHandlerError('Exception thrown in user-defined request error handler') from e
                 else:
-                    if new_request is not None:
-                        request = new_request
+                    if new_request is not None and new_request != request:
+                        await request_manager.add_request(new_request)
+                        await self._mark_request_as_handled(request)
+                        return
 
             await request_manager.reclaim_request(request)
         else:
-            await wait_for(
-                lambda: request_manager.mark_request_as_handled(context.request),
-                timeout=self._internal_timeout,
-                timeout_message='Marking request as handled timed out after '
-                f'{self._internal_timeout.total_seconds()} seconds',
-                logger=self._logger,
-                max_retries=3,
-            )
+            await self._mark_request_as_handled(request)
             await self._handle_failed_request(context, error)
             self._statistics.record_request_processing_failure(request.unique_key)
 
@@ -1174,16 +1201,7 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
         self, request: Request | str, reason: SkippedReason, *, need_mark: bool = False
     ) -> None:
         if need_mark and isinstance(request, Request):
-            request_manager = await self.get_request_manager()
-
-            await wait_for(
-                lambda: request_manager.mark_request_as_handled(request),
-                timeout=self._internal_timeout,
-                timeout_message='Marking request as handled timed out after '
-                f'{self._internal_timeout.total_seconds()} seconds',
-                logger=self._logger,
-                max_retries=3,
-            )
+            await self._mark_request_as_handled(request)
             request.state = RequestState.SKIPPED
 
         url = request.url if isinstance(request, Request) else request
@@ -1256,52 +1274,46 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
             else:
                 yield Request.from_url(url)
 
-    async def _commit_request_handler_result(self, context: BasicCrawlingContext) -> None:
-        """Commit request handler result for the input `context`. Result is taken from `_context_result_map`."""
-        result = self._context_result_map[context]
-
-        base_request_manager = await self.get_request_manager()
-
-        origin = context.request.loaded_url or context.request.url
-
-        for add_requests_call in result.add_requests_calls:
-            rq_id = add_requests_call.get('rq_id')
-            rq_name = add_requests_call.get('rq_name')
-            rq_alias = add_requests_call.get('rq_alias')
-            specified_params = sum(1 for param in [rq_id, rq_name, rq_alias] if param is not None)
-            if specified_params > 1:
-                raise ValueError('You can only provide one of `rq_id`, `rq_name` or `rq_alias` arguments.')
-            if rq_id or rq_name or rq_alias:
-                request_manager: RequestManager | RequestQueue = await RequestQueue.open(
-                    id=rq_id,
-                    name=rq_name,
-                    alias=rq_alias,
-                    storage_client=self._service_locator.get_storage_client(),
-                    configuration=self._service_locator.get_configuration(),
-                )
-            else:
-                request_manager = base_request_manager
-
-            requests = list[Request]()
-
-            base_url = url if (url := add_requests_call.get('base_url')) else origin
-
-            requests_iterator = self._convert_url_to_request_iterator(add_requests_call['requests'], base_url)
+    async def _add_requests(
+        self,
+        context: BasicCrawlingContext,
+        requests: Sequence[str | Request],
+        rq_id: str | None = None,
+        rq_name: str | None = None,
+        rq_alias: str | None = None,
+        **kwargs: Unpack[EnqueueLinksKwargs],
+    ) -> None:
+        """Add requests method aware of the crawling context."""
+        if rq_id or rq_name or rq_alias:
+            request_manager: RequestManager = await RequestQueue.open(
+                id=rq_id,
+                name=rq_name,
+                alias=rq_alias,
+                storage_client=self._service_locator.get_storage_client(),
+                configuration=self._service_locator.get_configuration(),
+            )
+        else:
+            request_manager = await self.get_request_manager()
 
-            enqueue_links_kwargs: EnqueueLinksKwargs = {k: v for k, v in add_requests_call.items() if k != 'requests'}  # type: ignore[assignment]
+        context_aware_requests = list[Request]()
+        base_url = kwargs.get('base_url') or context.request.loaded_url or context.request.url
+        requests_iterator = self._convert_url_to_request_iterator(requests, base_url)
+        filter_requests_iterator = self._enqueue_links_filter_iterator(requests_iterator, context.request.url, **kwargs)
+        for dst_request in filter_requests_iterator:
+            # Update the crawl depth of the request.
+            dst_request.crawl_depth = context.request.crawl_depth + 1
 
-            filter_requests_iterator = self._enqueue_links_filter_iterator(
-                requests_iterator, context.request.url, **enqueue_links_kwargs
-            )
+            if self._max_crawl_depth is None or dst_request.crawl_depth <= self._max_crawl_depth:
+                context_aware_requests.append(dst_request)
 
-            for dst_request in filter_requests_iterator:
-                # Update the crawl depth of the request.
-                dst_request.crawl_depth = context.request.crawl_depth + 1
+        return await request_manager.add_requests(context_aware_requests)
 
-                if self._max_crawl_depth is None or dst_request.crawl_depth <= self._max_crawl_depth:
-                    requests.append(dst_request)
+    async def _commit_request_handler_result(self, context: BasicCrawlingContext) -> None:
+        """Commit request handler result for the input `context`. Result is taken from `_context_result_map`."""
+        result = self._context_result_map[context]
 
-            await request_manager.add_requests(requests)
+        for add_requests_call in result.add_requests_calls:
+            await self._add_requests(context, **add_requests_call)
 
         for push_data_call in result.push_data_calls:
             await self._push_data(**push_data_call)
@@ -1401,14 +1413,8 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
                 raise RequestHandlerError(e, context) from e
 
             await self._commit_request_handler_result(context)
-            await wait_for(
-                lambda: request_manager.mark_request_as_handled(context.request),
-                timeout=self._internal_timeout,
-                timeout_message='Marking request as handled timed out after '
-                f'{self._internal_timeout.total_seconds()} seconds',
-                logger=self._logger,
-                max_retries=3,
-            )
+
+            await self._mark_request_as_handled(request)
 
             request.state = RequestState.DONE
 
@@ -1451,14 +1457,7 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
                 await request_manager.reclaim_request(request)
                 await self._statistics.error_tracker_retry.add(error=session_error, context=context)
             else:
-                await wait_for(
-                    lambda: request_manager.mark_request_as_handled(context.request),
-                    timeout=self._internal_timeout,
-                    timeout_message='Marking request as handled timed out after '
-                    f'{self._internal_timeout.total_seconds()} seconds',
-                    logger=self._logger,
-                    max_retries=3,
-                )
+                await self._mark_request_as_handled(request)
 
                 await self._handle_failed_request(context, session_error)
                 self._statistics.record_request_processing_failure(request.unique_key)
@@ -1466,14 +1465,7 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
         except ContextPipelineInterruptedError as interrupted_error:
             self._logger.debug('The context pipeline was interrupted', exc_info=interrupted_error)
 
-            await wait_for(
-                lambda: request_manager.mark_request_as_handled(context.request),
-                timeout=self._internal_timeout,
-                timeout_message='Marking request as handled timed out after '
-                f'{self._internal_timeout.total_seconds()} seconds',
-                logger=self._logger,
-                max_retries=3,
-            )
+            await self._mark_request_as_handled(request)
 
         except ContextPipelineInitializationError as initialization_error:
             self._logger.debug(
@@ -1491,12 +1483,15 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
             raise
 
     async def _run_request_handler(self, context: BasicCrawlingContext) -> None:
-        await wait_for(
-            lambda: self._context_pipeline(context, self.router),
-            timeout=self._request_handler_timeout,
-            timeout_message=f'{self._request_handler_timeout_text}'
-            f' {self._request_handler_timeout.total_seconds()} seconds',
-            logger=self._logger,
+        await self._context_pipeline(
+            context,
+            lambda final_context: wait_for(
+                lambda: self.router(final_context),
+                timeout=self._request_handler_timeout,
+                timeout_message=f'{self._request_handler_timeout_text}'
+                f' {self._request_handler_timeout.total_seconds()} seconds',
+                logger=self._logger,
+            ),
         )
 
     def _raise_for_error_status_code(self, status_code: int) -> None:
@@ -1644,3 +1639,14 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
         )
 
         self._previous_crawler_state = current_state
+
+    async def _mark_request_as_handled(self, request: Request) -> None:
+        request_manager = await self.get_request_manager()
+        await wait_for(
+            lambda: request_manager.mark_request_as_handled(request),
+            timeout=self._internal_timeout,
+            timeout_message='Marking request as handled timed out after '
+            f'{self._internal_timeout.total_seconds()} seconds',
+            logger=self._logger,
+            max_retries=3,
+        )

crawlee/crawlers/_beautifulsoup/_beautifulsoup_crawler.py

@@ -5,7 +5,7 @@ from typing import TYPE_CHECKING
 from bs4 import BeautifulSoup, Tag
 
 from crawlee._utils.docs import docs_group
-from crawlee.crawlers import AbstractHttpCrawler, BasicCrawlerOptions
+from crawlee.crawlers import AbstractHttpCrawler, HttpCrawlerOptions
 
 from ._beautifulsoup_crawling_context import BeautifulSoupCrawlingContext
 from ._beautifulsoup_parser import BeautifulSoupParser, BeautifulSoupParserType
@@ -58,7 +58,7 @@ class BeautifulSoupCrawler(AbstractHttpCrawler[BeautifulSoupCrawlingContext, Bea
         self,
         *,
         parser: BeautifulSoupParserType = 'lxml',
-        **kwargs: Unpack[BasicCrawlerOptions[BeautifulSoupCrawlingContext]],
+        **kwargs: Unpack[HttpCrawlerOptions[BeautifulSoupCrawlingContext]],
     ) -> None:
         """Initialize a new instance.
 

crawlee/crawlers/_parsel/_parsel_crawler.py

@@ -5,7 +5,7 @@ from typing import TYPE_CHECKING
 from parsel import Selector
 
 from crawlee._utils.docs import docs_group
-from crawlee.crawlers import AbstractHttpCrawler, BasicCrawlerOptions
+from crawlee.crawlers import AbstractHttpCrawler, HttpCrawlerOptions
 
 from ._parsel_crawling_context import ParselCrawlingContext
 from ._parsel_parser import ParselParser
@@ -56,7 +56,7 @@ class ParselCrawler(AbstractHttpCrawler[ParselCrawlingContext, Selector, Selecto
 
     def __init__(
         self,
-        **kwargs: Unpack[BasicCrawlerOptions[ParselCrawlingContext]],
+        **kwargs: Unpack[HttpCrawlerOptions[ParselCrawlingContext]],
     ) -> None:
         """Initialize a new instance.