crawlee 1.0.3b6__py3-none-any.whl → 1.0.5b6__py3-none-any.whl

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/_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

@@ -7,6 +7,9 @@ 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__)
 
@@ -26,6 +29,18 @@ class RecurringTask:
         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.
 

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)

crawlee/_utils/urls.py

@@ -7,6 +7,7 @@ from yarl import URL
 
 if TYPE_CHECKING:
     from collections.abc import Iterator
+    from logging import Logger
 
 
 def is_url_absolute(url: str) -> bool:
@@ -22,13 +23,19 @@ def convert_to_absolute_url(base_url: str, relative_url: str) -> str:
     return str(URL(base_url).join(URL(relative_url)))
 
 
-def to_absolute_url_iterator(base_url: str, urls: Iterator[str]) -> Iterator[str]:
+def to_absolute_url_iterator(base_url: str, urls: Iterator[str], logger: Logger | None = None) -> Iterator[str]:
     """Convert an iterator of relative URLs to absolute URLs using a base URL."""
     for url in urls:
         if is_url_absolute(url):
             yield url
         else:
-            yield convert_to_absolute_url(base_url, url)
+            converted_url = convert_to_absolute_url(base_url, url)
+            # Skip the URL if conversion fails, probably due to an incorrect format, such as 'mailto:'.
+            if not is_url_absolute(converted_url):
+                if logger:
+                    logger.debug(f'Could not convert URL "{url}" to absolute using base URL "{base_url}". Skipping it.')
+                continue
+            yield converted_url
 
 
 _http_url_adapter = TypeAdapter(AnyHttpUrl)

crawlee/browsers/_browser_pool.py

@@ -118,7 +118,10 @@ class BrowserPool:
         """Initialize a new instance with a single `PlaywrightBrowserPlugin` configured with the provided options.
 
         Args:
-            browser_type: The type of browser to launch ('chromium', 'firefox', or 'webkit').
+            browser_type: The type of browser to launch:
+                - 'chromium', 'firefox', 'webkit': Use Playwright-managed browsers
+                - 'chrome': Use your locally installed Google Chrome browser. Requires Google Chrome to be installed on
+                    the system.
             user_data_dir: Path to a user data directory, which stores browser session data like cookies
                 and local storage.
             browser_launch_options: Keyword arguments to pass to the browser launch method. These options are provided

crawlee/browsers/_playwright_browser_controller.py

@@ -216,7 +216,7 @@ class PlaywrightBrowserController(BrowserController):
         browser_new_context_options = dict(browser_new_context_options) if browser_new_context_options else {}
         if proxy_info:
             if browser_new_context_options.get('proxy'):
-                logger.warning("browser_new_context_options['proxy'] overriden by explicit `proxy_info` argument.")
+                logger.warning("browser_new_context_options['proxy'] overridden by explicit `proxy_info` argument.")
 
             browser_new_context_options['proxy'] = ProxySettings(
                 server=f'{proxy_info.scheme}://{proxy_info.hostname}:{proxy_info.port}',

crawlee/browsers/_playwright_browser_plugin.py

@@ -34,8 +34,8 @@ class PlaywrightBrowserPlugin(BrowserPlugin):
 
     It is a plugin designed to manage browser instances using the Playwright automation library. It acts as a factory
     for creating new browser instances and provides a unified interface for interacting with different browser types
-    (chromium, firefox, and webkit). This class integrates configuration options for browser launches (headless mode,
-    executable paths, sandboxing, ...). It also manages browser contexts and the number of pages open within each
+    (chromium, firefox, webkit and chrome). This class integrates configuration options for browser launches (headless
+    mode, executable paths, sandboxing, ...). It also manages browser contexts and the number of pages open within each
     browser instance, ensuring that resource limits are respected.
     """
 
@@ -55,7 +55,10 @@ class PlaywrightBrowserPlugin(BrowserPlugin):
         """Initialize a new instance.
 
         Args:
-            browser_type: The type of browser to launch ('chromium', 'firefox', or 'webkit').
+            browser_type: The type of browser to launch:
+                - 'chromium', 'firefox', 'webkit': Use Playwright-managed browsers
+                - 'chrome': Use your locally installed Google Chrome browser. Requires Google Chrome to be installed on
+                    the system.
             user_data_dir: Path to a User Data Directory, which stores browser session data like cookies and local
                 storage.
             browser_launch_options: Keyword arguments to pass to the browser launch method. These options are provided
@@ -80,6 +83,17 @@ class PlaywrightBrowserPlugin(BrowserPlugin):
             'chromium_sandbox': not config.disable_browser_sandbox,
         }
 
+        if browser_type == 'chrome' and default_launch_browser_options['executable_path']:
+            raise ValueError(
+                'Cannot use browser_type `chrome` with `Configuration.default_browser_path` or `executable_path` set.'
+            )
+
+        # Map 'chrome' to 'chromium' with the 'chrome' channel.
+        if browser_type == 'chrome':
+            browser_type = 'chromium'
+            # Chromium parameter 'channel' set to 'chrome' enables using installed Google Chrome.
+            default_launch_browser_options['channel'] = 'chrome'
+
         self._browser_type: BrowserType = browser_type
         self._browser_launch_options: dict[str, Any] = default_launch_browser_options | (browser_launch_options or {})
         self._browser_new_context_options = browser_new_context_options or {}

crawlee/browsers/_types.py

@@ -6,7 +6,7 @@ from typing import TYPE_CHECKING, Literal
 if TYPE_CHECKING:
     from playwright.async_api import Page
 
-BrowserType = Literal['chromium', 'firefox', 'webkit']
+BrowserType = Literal['chromium', 'firefox', 'webkit', 'chrome']
 
 
 @dataclass

crawlee/crawlers/_abstract_http/_abstract_http_crawler.py

@@ -167,7 +167,9 @@ 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)
+            links_iterator = to_absolute_url_iterator(
+                context.request.loaded_url or context.request.url, links_iterator, logger=context.log
+            )
 
             if robots_txt_file:
                 skipped, links_iterator = partition(lambda url: robots_txt_file.is_allowed(url), links_iterator)

crawlee/crawlers/_adaptive_playwright/_adaptive_playwright_crawler.py

@@ -149,10 +149,6 @@ class AdaptivePlaywrightCrawler(
                 non-default configuration.
             kwargs: Additional keyword arguments to pass to the underlying `BasicCrawler`.
         """
-        # Some sub crawler kwargs are internally modified. Prepare copies.
-        basic_crawler_kwargs_for_static_crawler = deepcopy(kwargs)
-        basic_crawler_kwargs_for_pw_crawler = deepcopy(kwargs)
-
         # Adaptive crawling related.
         self.rendering_type_predictor = rendering_type_predictor or DefaultRenderingTypePredictor()
         self.result_checker = result_checker or (lambda _: True)
@@ -170,11 +166,11 @@ class AdaptivePlaywrightCrawler(
         # Each sub crawler will use custom logger .
         static_logger = getLogger('Subcrawler_static')
         static_logger.setLevel(logging.ERROR)
-        basic_crawler_kwargs_for_static_crawler['_logger'] = static_logger
+        basic_crawler_kwargs_for_static_crawler: _BasicCrawlerOptions = {'_logger': static_logger, **kwargs}
 
         pw_logger = getLogger('Subcrawler_playwright')
         pw_logger.setLevel(logging.ERROR)
-        basic_crawler_kwargs_for_pw_crawler['_logger'] = pw_logger
+        basic_crawler_kwargs_for_pw_crawler: _BasicCrawlerOptions = {'_logger': pw_logger, **kwargs}
 
         # Initialize sub crawlers to create their pipelines.
         static_crawler_class = AbstractHttpCrawler.create_parsed_http_crawler_class(static_parser=static_parser)
@@ -319,7 +315,7 @@ class AdaptivePlaywrightCrawler(
                 ),
                 logger=self._logger,
             )
-            return SubCrawlerRun(result=result)
+            return SubCrawlerRun(result=result, run_context=context_linked_to_result)
         except Exception as e:
             return SubCrawlerRun(exception=e)
 
@@ -375,7 +371,8 @@ class AdaptivePlaywrightCrawler(
                 self.track_http_only_request_handler_runs()
 
                 static_run = await self._crawl_one(rendering_type='static', context=context)
-                if static_run.result and self.result_checker(static_run.result):
+                if static_run.result and static_run.run_context and self.result_checker(static_run.result):
+                    self._update_context_from_copy(context, static_run.run_context)
                     self._context_result_map[context] = static_run.result
                     return
                 if static_run.exception:
@@ -406,13 +403,10 @@ class AdaptivePlaywrightCrawler(
         if pw_run.exception is not None:
             raise pw_run.exception
 
-        if pw_run.result:
-            self._context_result_map[context] = pw_run.result
-
+        if pw_run.result and pw_run.run_context:
             if should_detect_rendering_type:
                 detection_result: RenderingType
                 static_run = await self._crawl_one('static', context=context, state=old_state_copy)
-
                 if static_run.result and self.result_comparator(static_run.result, pw_run.result):
                     detection_result = 'static'
                 else:
@@ -421,6 +415,9 @@ class AdaptivePlaywrightCrawler(
                 context.log.debug(f'Detected rendering type {detection_result} for {context.request.url}')
                 self.rendering_type_predictor.store_result(context.request, detection_result)
 
+            self._update_context_from_copy(context, pw_run.run_context)
+            self._context_result_map[context] = pw_run.result
+
     def pre_navigation_hook(
         self,
         hook: Callable[[AdaptivePlaywrightPreNavCrawlingContext], Awaitable[None]] | None = None,
@@ -455,8 +452,32 @@ class AdaptivePlaywrightCrawler(
     def track_rendering_type_mispredictions(self) -> None:
         self.statistics.state.rendering_type_mispredictions += 1
 
+    def _update_context_from_copy(self, context: BasicCrawlingContext, context_copy: BasicCrawlingContext) -> None:
+        """Update mutable fields of `context` from `context_copy`.
+
+        Uses object.__setattr__ to bypass frozen dataclass restrictions,
+        allowing state synchronization after isolated crawler execution.
+        """
+        updating_attributes = {
+            'request': ('headers', 'user_data'),
+            'session': ('_user_data', '_usage_count', '_error_score', '_cookies'),
+        }
+
+        for attr, sub_attrs in updating_attributes.items():
+            original_sub_obj = getattr(context, attr)
+            copy_sub_obj = getattr(context_copy, attr)
+
+            # Check that both sub objects are not None
+            if original_sub_obj is None or copy_sub_obj is None:
+                continue
+
+            for sub_attr in sub_attrs:
+                new_value = getattr(copy_sub_obj, sub_attr)
+                object.__setattr__(original_sub_obj, sub_attr, new_value)
+
 
 @dataclass(frozen=True)
 class SubCrawlerRun:
     result: RequestHandlerRunResult | None = None
     exception: Exception | None = None
+    run_context: BasicCrawlingContext | None = None

crawlee/crawlers/_basic/_basic_crawler.py

@@ -56,7 +56,7 @@ from crawlee.errors import (
     SessionError,
     UserDefinedErrorHandlerError,
 )
-from crawlee.events._types import Event, EventCrawlerStatusData
+from crawlee.events._types import Event, EventCrawlerStatusData, EventPersistStateData
 from crawlee.http_clients import ImpitHttpClient
 from crawlee.router import Router
 from crawlee.sessions import SessionPool
@@ -437,14 +437,23 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
         self._statistics_log_format = statistics_log_format
 
         # Statistics
-        self._statistics = statistics or cast(
-            'Statistics[TStatisticsState]',
-            Statistics.with_default_state(
-                periodic_message_logger=self._logger,
-                statistics_log_format=self._statistics_log_format,
-                log_message='Current request statistics:',
-            ),
-        )
+        if statistics:
+            self._statistics = statistics
+        else:
+
+            async def persist_state_factory() -> KeyValueStore:
+                return await self.get_key_value_store()
+
+            self._statistics = cast(
+                'Statistics[TStatisticsState]',
+                Statistics.with_default_state(
+                    persistence_enabled=True,
+                    periodic_message_logger=self._logger,
+                    statistics_log_format=self._statistics_log_format,
+                    log_message='Current request statistics:',
+                    persist_state_kvs_factory=persist_state_factory,
+                ),
+            )
 
         # Additional context managers to enter and exit
         self._additional_context_managers = _additional_context_managers or []
@@ -689,7 +698,6 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
         except CancelledError:
             pass
         finally:
-            await self._crawler_state_rec_task.stop()
             if threading.current_thread() is threading.main_thread():
                 with suppress(NotImplementedError):
                     asyncio.get_running_loop().remove_signal_handler(signal.SIGINT)
@@ -721,8 +729,6 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
     async def _run_crawler(self) -> None:
         event_manager = self._service_locator.get_event_manager()
 
-        self._crawler_state_rec_task.start()
-
         # Collect the context managers to be entered. Context managers that are already active are excluded,
         # as they were likely entered by the caller, who will also be responsible for exiting them.
         contexts_to_enter = [
@@ -733,6 +739,7 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
                 self._statistics,
                 self._session_pool if self._use_session_pool else None,
                 self._http_client,
+                self._crawler_state_rec_task,
                 *self._additional_context_managers,
             )
             if cm and getattr(cm, 'active', False) is False
@@ -744,6 +751,9 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
 
             await self._autoscaled_pool.run()
 
+            # Emit PERSIST_STATE event when crawler is finishing to allow listeners to persist their state if needed
+            event_manager.emit(event=Event.PERSIST_STATE, event_data=EventPersistStateData(is_migrating=False))
+
     async def add_requests(
         self,
         requests: Sequence[str | Request],
@@ -972,6 +982,7 @@ class BasicCrawler(Generic[TCrawlingContext, TStatisticsState]):
                         label=label,
                         user_data=user_data,
                         transform_request_function=transform_request_function,
+                        **kwargs,
                     ),
                     rq_id=rq_id,
                     rq_name=rq_name,

crawlee/crawlers/_playwright/_playwright_crawler.py

@@ -114,7 +114,10 @@ class PlaywrightCrawler(BasicCrawler[PlaywrightCrawlingContext, StatisticsState]
             browser_pool: A `BrowserPool` instance to be used for launching the browsers and getting pages.
             user_data_dir: Path to a user data directory, which stores browser session data like cookies
                 and local storage.
-            browser_type: The type of browser to launch ('chromium', 'firefox', or 'webkit').
+            browser_type: The type of browser to launch:
+                - 'chromium', 'firefox', 'webkit': Use Playwright-managed browsers
+                - 'chrome': Use your locally installed Google Chrome browser. Requires Google Chrome to be installed on
+                    the system.
                 This option should not be used if `browser_pool` is provided.
             browser_launch_options: Keyword arguments to pass to the browser launch method. These options are provided
                 directly to Playwright's `browser_type.launch` method. For more details, refer to the
@@ -153,7 +156,7 @@ class PlaywrightCrawler(BasicCrawler[PlaywrightCrawlingContext, StatisticsState]
             ):
                 raise ValueError(
                     'You cannot provide `headless`, `browser_type`, `browser_launch_options`, '
-                    '`browser_new_context_options`, `use_incognito_pages`, `user_data_dir`  or'
+                    '`browser_new_context_options`, `use_incognito_pages`, `user_data_dir` or '
                     '`fingerprint_generator` arguments when `browser_pool` is provided.'
                 )
 
@@ -366,7 +369,9 @@ class PlaywrightCrawler(BasicCrawler[PlaywrightCrawlingContext, StatisticsState]
             links_iterator: Iterator[str] = iter(
                 [url for element in elements if (url := await element.get_attribute('href')) is not None]
             )
-            links_iterator = to_absolute_url_iterator(context.request.loaded_url or context.request.url, links_iterator)
+            links_iterator = to_absolute_url_iterator(
+                context.request.loaded_url or context.request.url, links_iterator, logger=context.log
+            )
 
             if robots_txt_file:
                 skipped, links_iterator = partition(lambda url: robots_txt_file.is_allowed(url), links_iterator)
@@ -494,7 +499,9 @@ class _PlaywrightCrawlerAdditionalOptions(TypedDict):
     """A `BrowserPool` instance to be used for launching the browsers and getting pages."""
 
     browser_type: NotRequired[BrowserType]
-    """The type of browser to launch ('chromium', 'firefox', or 'webkit').
+    """The type of browser to launch:
+    - 'chromium', 'firefox', 'webkit': Use Playwright-managed browsers
+    - 'chrome': Use your locally installed Google Chrome browser. Requires Google Chrome to be installed on the system.
     This option should not be used if `browser_pool` is provided."""
 
     browser_launch_options: NotRequired[Mapping[str, Any]]

crawlee/fingerprint_suite/_header_generator.py

@@ -11,9 +11,9 @@ if TYPE_CHECKING:
 
 
 def fingerprint_browser_type_from_playwright_browser_type(
-    playwright_browser_type: Literal['chromium', 'firefox', 'webkit'],
+    playwright_browser_type: Literal['chromium', 'firefox', 'webkit', 'chrome'],
 ) -> SupportedBrowserType:
-    if playwright_browser_type == 'chromium':
+    if playwright_browser_type in {'chromium', 'chrome'}:
         return 'chrome'
     if playwright_browser_type == 'firefox':
         return 'firefox'

crawlee/request_loaders/_sitemap_request_loader.py

@@ -90,6 +90,11 @@ class SitemapRequestLoaderState(BaseModel):
 class SitemapRequestLoader(RequestLoader):
     """A request loader that reads URLs from sitemap(s).
 
+    The loader is designed to handle sitemaps that follow the format described in the Sitemaps protocol
+    (https://www.sitemaps.org/protocol.html). It supports both XML and plain text sitemap formats.
+    Note that HTML pages containing links are not supported - those should be handled by regular crawlers
+    and the `enqueue_links` functionality.
+
     The loader fetches and parses sitemaps in the background, allowing crawling to start
     before all URLs are loaded. It supports filtering URLs using glob and regex patterns.
 

crawlee/statistics/_error_snapshotter.py

@@ -32,7 +32,7 @@ class ErrorSnapshotter:
         """Capture error snapshot and save it to key value store.
 
         It saves the error snapshot directly to a key value store. It can't use `context.get_key_value_store` because
-        it returns `KeyValueStoreChangeRecords` which is commited to the key value store only if the `RequestHandler`
+        it returns `KeyValueStoreChangeRecords` which is committed to the key value store only if the `RequestHandler`
         returned without an exception. ErrorSnapshotter is on the contrary active only when `RequestHandler` fails with
         an exception.
 

crawlee/statistics/_statistics.py

@@ -17,8 +17,11 @@ from crawlee.statistics import FinalStatistics, StatisticsState
 from crawlee.statistics._error_tracker import ErrorTracker
 
 if TYPE_CHECKING:
+    from collections.abc import Callable, Coroutine
     from types import TracebackType
 
+    from crawlee.storages import KeyValueStore
+
 TStatisticsState = TypeVar('TStatisticsState', bound=StatisticsState, default=StatisticsState)
 TNewStatisticsState = TypeVar('TNewStatisticsState', bound=StatisticsState, default=StatisticsState)
 logger = getLogger(__name__)
@@ -70,6 +73,7 @@ class Statistics(Generic[TStatisticsState]):
         persistence_enabled: bool | Literal['explicit_only'] = False,
         persist_state_kvs_name: str | None = None,
         persist_state_key: str | None = None,
+        persist_state_kvs_factory: Callable[[], Coroutine[None, None, KeyValueStore]] | None = None,
         log_message: str = 'Statistics',
         periodic_message_logger: Logger | None = None,
         log_interval: timedelta = timedelta(minutes=1),
@@ -92,9 +96,10 @@ class Statistics(Generic[TStatisticsState]):
 
         self._state = RecoverableState(
             default_state=state_model(stats_id=self._id),
-            persist_state_key=persist_state_key or f'SDK_CRAWLER_STATISTICS_{self._id}',
+            persist_state_key=persist_state_key or f'__CRAWLER_STATISTICS_{self._id}',
             persistence_enabled=persistence_enabled,
             persist_state_kvs_name=persist_state_kvs_name,
+            persist_state_kvs_factory=persist_state_kvs_factory,
             logger=logger,
         )
 
@@ -110,8 +115,8 @@ class Statistics(Generic[TStatisticsState]):
         """Create near copy of the `Statistics` with replaced `state_model`."""
         new_statistics: Statistics[TNewStatisticsState] = Statistics(
             persistence_enabled=self._state._persistence_enabled,  # noqa: SLF001
-            persist_state_kvs_name=self._state._persist_state_kvs_name,  # noqa: SLF001
             persist_state_key=self._state._persist_state_key,  # noqa: SLF001
+            persist_state_kvs_factory=self._state._persist_state_kvs_factory,  # noqa: SLF001
             log_message=self._log_message,
             periodic_message_logger=self._periodic_message_logger,
             state_model=state_model,
@@ -125,6 +130,7 @@ class Statistics(Generic[TStatisticsState]):
         persistence_enabled: bool = False,
         persist_state_kvs_name: str | None = None,
         persist_state_key: str | None = None,
+        persist_state_kvs_factory: Callable[[], Coroutine[None, None, KeyValueStore]] | None = None,
         log_message: str = 'Statistics',
         periodic_message_logger: Logger | None = None,
         log_interval: timedelta = timedelta(minutes=1),
@@ -136,6 +142,7 @@ class Statistics(Generic[TStatisticsState]):
             persistence_enabled=persistence_enabled,
             persist_state_kvs_name=persist_state_kvs_name,
             persist_state_key=persist_state_key,
+            persist_state_kvs_factory=persist_state_kvs_factory,
             log_message=log_message,
             periodic_message_logger=periodic_message_logger,
             log_interval=log_interval,
@@ -182,7 +189,10 @@ class Statistics(Generic[TStatisticsState]):
         if not self._active:
             raise RuntimeError(f'The {self.__class__.__name__} is not active.')
 
-        self._state.current_value.crawler_finished_at = datetime.now(timezone.utc)
+        if not self.state.crawler_last_started_at:
+            raise RuntimeError('Statistics.state.crawler_last_started_at not set.')
+        self.state.crawler_finished_at = datetime.now(timezone.utc)
+        self.state.crawler_runtime += self.state.crawler_finished_at - self.state.crawler_last_started_at
 
         await self._state.teardown()
 
@@ -250,8 +260,7 @@ class Statistics(Generic[TStatisticsState]):
         if self._instance_start is None:
             raise RuntimeError('The Statistics object is not initialized')
 
-        crawler_runtime = datetime.now(timezone.utc) - self._instance_start
-        total_minutes = crawler_runtime.total_seconds() / 60
+        total_minutes = self.state.crawler_runtime.total_seconds() / 60
         state = self._state.current_value
         serialized_state = state.model_dump(by_alias=False)
 
@@ -262,7 +271,7 @@ class Statistics(Generic[TStatisticsState]):
             requests_failed_per_minute=math.floor(state.requests_failed / total_minutes) if total_minutes else 0,
             request_total_duration=state.request_total_finished_duration + state.request_total_failed_duration,
             requests_total=state.requests_failed + state.requests_finished,
-            crawler_runtime=crawler_runtime,
+            crawler_runtime=state.crawler_runtime,
             requests_finished=state.requests_finished,
             requests_failed=state.requests_failed,
             retry_histogram=serialized_state['request_retry_histogram'],

crawlee/storage_clients/_file_system/_request_queue_client.py

@@ -31,6 +31,7 @@ if TYPE_CHECKING:
     from collections.abc import Sequence
 
     from crawlee.configuration import Configuration
+    from crawlee.storages import KeyValueStore
 
 logger = getLogger(__name__)
 
@@ -92,6 +93,7 @@ class FileSystemRequestQueueClient(RequestQueueClient):
         metadata: RequestQueueMetadata,
         path_to_rq: Path,
         lock: asyncio.Lock,
+        recoverable_state: RecoverableState[RequestQueueState],
     ) -> None:
         """Initialize a new instance.
 
@@ -114,12 +116,7 @@ class FileSystemRequestQueueClient(RequestQueueClient):
         self._is_empty_cache: bool | None = None
         """Cache for is_empty result: None means unknown, True/False is cached state."""
 
-        self._state = RecoverableState[RequestQueueState](
-            default_state=RequestQueueState(),
-            persist_state_key=f'__RQ_STATE_{self._metadata.id}',
-            persistence_enabled=True,
-            logger=logger,
-        )
+        self._state = recoverable_state
         """Recoverable state to maintain request ordering, in-progress status, and handled status."""
 
     @override
@@ -136,6 +133,22 @@ class FileSystemRequestQueueClient(RequestQueueClient):
         """The full path to the request queue metadata file."""
         return self.path_to_rq / METADATA_FILENAME
 
+    @classmethod
+    async def _create_recoverable_state(cls, id: str, configuration: Configuration) -> RecoverableState:
+        async def kvs_factory() -> KeyValueStore:
+            from crawlee.storage_clients import FileSystemStorageClient  # noqa: PLC0415 avoid circular import
+            from crawlee.storages import KeyValueStore  # noqa: PLC0415 avoid circular import
+
+            return await KeyValueStore.open(storage_client=FileSystemStorageClient(), configuration=configuration)
+
+        return RecoverableState[RequestQueueState](
+            default_state=RequestQueueState(),
+            persist_state_key=f'__RQ_STATE_{id}',
+            persist_state_kvs_factory=kvs_factory,
+            persistence_enabled=True,
+            logger=logger,
+        )
+
     @classmethod
     async def open(
         cls,
@@ -194,6 +207,9 @@ class FileSystemRequestQueueClient(RequestQueueClient):
                                 metadata=metadata,
                                 path_to_rq=rq_base_path / rq_dir,
                                 lock=asyncio.Lock(),
+                                recoverable_state=await cls._create_recoverable_state(
+                                    id=id, configuration=configuration
+                                ),
                             )
                             await client._state.initialize()
                             await client._discover_existing_requests()
@@ -230,6 +246,7 @@ class FileSystemRequestQueueClient(RequestQueueClient):
                     metadata=metadata,
                     path_to_rq=path_to_rq,
                     lock=asyncio.Lock(),
+                    recoverable_state=await cls._create_recoverable_state(id=metadata.id, configuration=configuration),
                 )
 
                 await client._state.initialize()
@@ -254,6 +271,7 @@ class FileSystemRequestQueueClient(RequestQueueClient):
                     metadata=metadata,
                     path_to_rq=path_to_rq,
                     lock=asyncio.Lock(),
+                    recoverable_state=await cls._create_recoverable_state(id=metadata.id, configuration=configuration),
                 )
                 await client._state.initialize()
                 await client._update_metadata()

crawlee/storage_clients/_sql/_db_models.py

@@ -205,9 +205,8 @@ class RequestDb(Base):
             'idx_fetch_available',
             'request_queue_id',
             'is_handled',
-            'time_blocked_until',
             'sequence_number',
-            postgresql_where=text('is_handled = false'),
+            postgresql_where=text('is_handled is false'),
         ),
     )
 

crawlee/storages/_key_value_store.py

@@ -281,11 +281,14 @@ class KeyValueStore(Storage):
             if key in cache:
                 return cache[key].current_value.root
 
+            async def kvs_factory() -> KeyValueStore:
+                return self
+
             cache[key] = recoverable_state = RecoverableState(
                 default_state=AutosavedValue(default_value),
-                persistence_enabled=True,
-                persist_state_kvs_id=self.id,
                 persist_state_key=key,
+                persistence_enabled=True,
+                persist_state_kvs_factory=kvs_factory,
                 logger=logger,
             )
 

{crawlee-1.0.3b6.dist-info → crawlee-1.0.5b6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: crawlee
-Version: 1.0.3b6
+Version: 1.0.5b6
 Summary: Crawlee for Python
 Project-URL: Apify Homepage, https://apify.com
 Project-URL: Changelog, https://crawlee.dev/python/docs/changelog

{crawlee-1.0.3b6.dist-info → crawlee-1.0.5b6.dist-info}/RECORD

@@ -4,7 +4,7 @@ crawlee/_cli.py,sha256=czuEsGD8QYEiq5gtMcBxrL08hQ5OJQQkMVhAr1pvDaQ,10353
 crawlee/_consts.py,sha256=RQ96gx7V-WPH91cVsMUz76X5UZUNDNhCudtlyGkxFVk,133
 crawlee/_log_config.py,sha256=VyxoEfWCq_9fyicmmJbjiZ5KC91onMcAtX2L4oKX4m4,5999
 crawlee/_request.py,sha256=XliqiaL5Gp3fIDqHVVw0GF35VydXOtg6wJIkeaLcAwk,16458
-crawlee/_service_locator.py,sha256=uO1eml4YeMs0xqlFN2d1LvOAroAdNJYbb2Mt15V-qzs,5066
+crawlee/_service_locator.py,sha256=SJ8ABYtclBl7rz8kfZ2jZkIgKq5oNIoGT7WmN8ApTzo,5058
 crawlee/_types.py,sha256=DAmfSv5W1dt3nJhJ8z-02gDaE06fdEizNKUlHpsd2_A,29129
 crawlee/configuration.py,sha256=KG_XDkPe1VaYfaIu41nICvMjfHbDKM0h4-YTi3DkyRY,7917
 crawlee/errors.py,sha256=RhFNA_uT615nVBHf9TylpX5YWwtDuHUUEV8LPT4CYa4,3878
@@ -29,43 +29,43 @@ crawlee/_utils/globs.py,sha256=SGX2J35Kqw7yZnSS5c4mLz9UD8c77PF0IoCgXQM5uiw,5310
 crawlee/_utils/html_to_text.py,sha256=1iykT-OXd2xXNy7isHVWHqPxe23X82CGQBHIfbZbZkY,902
 crawlee/_utils/models.py,sha256=EqM50Uc-xvxKlLCLA2lPpRduzfKvT0z_-Q-UWG8aTRQ,1955
 crawlee/_utils/raise_if_too_many_kwargs.py,sha256=J2gaUJmsmNwexohuehXw_mdYKv-eWiui6WUHFsQ3qTQ,597
-crawlee/_utils/recoverable_state.py,sha256=_88kOEDDRg1lr6RWs7NNDku6NNRlg7zuzUOoUxwMwGk,7734
-crawlee/_utils/recurring_task.py,sha256=sA0n4Cf9pYLQyBD9PZ7QbR6m6KphlbkACaT2GdbLfs4,1757
+crawlee/_utils/recoverable_state.py,sha256=c1D2ZecxEliGZzhqYz9_oU5CF2Hm0UKvpOHqO6CDJRE,9032
+crawlee/_utils/recurring_task.py,sha256=sQMiURuDXbwwfAcIXK8V4NXncSxIBxsqN1cZWX7DLyg,2128
 crawlee/_utils/requests.py,sha256=yOjai7bHR9_duPJ0ck-L76y9AnKZr49JBfSOQv9kvJc,5048
-crawlee/_utils/robots.py,sha256=k3Yi2OfKT0H04MPkP-OBGGV7fEePgOqb60awltjMYWY,4346
-crawlee/_utils/sitemap.py,sha256=9FtZRG87i5YZJhJa2m5CexSpm7RpvsSAgG60ih4BQc0,16636
+crawlee/_utils/robots.py,sha256=DBU5ni4Y-p7bIKMbLd_ws8wgHSFc4K8zPVF3JvH_pkw,4661
+crawlee/_utils/sitemap.py,sha256=UI9EJiFiyFvV5_flVUtdsEVz8ZsJeRERPtcx8ZsqjTU,16632
 crawlee/_utils/system.py,sha256=tA8AP__9vsJ9OTLTnAYAKkxc8U5-IEna0N_hqYBybUo,4294
 crawlee/_utils/time.py,sha256=WK17P939r65dLz2rWvL59OEJoxgzdinw-ND9WuG4DuU,2353
 crawlee/_utils/try_import.py,sha256=QI_58ifc2l0Rxehzu6xcofQrRAVeLzZuBTTTHttLl8s,1310
-crawlee/_utils/urls.py,sha256=NN27TA6KMU5V_j5TCZ4o33UIXw4pB9a-wGlmDQtYT8E,1294
+crawlee/_utils/urls.py,sha256=fEYXJxBT02f-DIYKF_h7PdaKAShfXBs99-dHDjDX03A,1725
 crawlee/_utils/wait.py,sha256=RfiXhp5VUBxOEtEMtru7_jNfKDr2BJCcFge5qGg2gxk,2848
 crawlee/_utils/web.py,sha256=nnKhg8pUSWz0RY64Qd-_GPNBX1fWI2hXS-gzcfQ-rig,364
 crawlee/browsers/__init__.py,sha256=TghkrNSbI_k87UgVBlgNNcEm8Ot05pSLEAPRSv6YsUs,1064
 crawlee/browsers/_browser_controller.py,sha256=-g0pB5Nx5q67eMZVka49x-HMfQqJYoI6kcV-g3AXE0I,3068
 crawlee/browsers/_browser_plugin.py,sha256=Wuojop___8ZO9eDoMs4JFmwMAFe5mZaTl0-Vz1PjkD8,3057
-crawlee/browsers/_browser_pool.py,sha256=2pT4m_g0DfopjTHYXb-piN6GqxvkayOeb4gmOtn1QNM,15634
+crawlee/browsers/_browser_pool.py,sha256=n1GTVS220yxo-aMaKDVfQO571_AqEV5pMawWbr0zUHk,15832
 crawlee/browsers/_playwright_browser.py,sha256=1yXD6cXuLefZZGUG1m0CT38xXYSwIC7n95bJBdMOxbo,3820
-crawlee/browsers/_playwright_browser_controller.py,sha256=YaY19slRj8gIKrZy0M8rzF_zy2Z1Ym6d0S_vXcMX108,10215
-crawlee/browsers/_playwright_browser_plugin.py,sha256=axZa_yZNCPHyM3Ijx9jW4CzzRXQTVzYAswcGAZHP3Hk,8106
-crawlee/browsers/_types.py,sha256=eWgpoLMWu103hMQQTObkA01sVc_7hdPESl-TCyDMMV0,426
+crawlee/browsers/_playwright_browser_controller.py,sha256=W6G5MjZpg9IcZoHts6lTML5VxSEpBTgzx5qeQ8XDigY,10216
+crawlee/browsers/_playwright_browser_plugin.py,sha256=A1qa1nJhTSKNP9uOiO-oGzR7VGlnOMo0A0YNedccb2A,8869
+crawlee/browsers/_types.py,sha256=ZnDgJHeQNSd_s_mXhgQnAf09c2smuiXC31VbawHHXUM,436
 crawlee/browsers/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 crawlee/crawlers/__init__.py,sha256=9VmFahav3rjE-2Bxa5PAhBgkYXP0k5SSAEpdG2xMZ7c,2340
 crawlee/crawlers/_types.py,sha256=xbGTJQirgz5wUbfr12afMR4q-_5AWP7ngF2e8K5P8l0,355
 crawlee/crawlers/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 crawlee/crawlers/_abstract_http/__init__.py,sha256=QCjn8x7jpo8FwEeSRw10TVj_0La2v9mLEiQWdk2RoTw,273
-crawlee/crawlers/_abstract_http/_abstract_http_crawler.py,sha256=ZG6A4DNGZYbOBXi0Th6K6CHDi2SqWO5VpxcnjypDO-A,11503
+crawlee/crawlers/_abstract_http/_abstract_http_crawler.py,sha256=DEiErZi7j2FHMgyVELPy09GyHo5Gx4UDpuiN6D3sGNk,11553
 crawlee/crawlers/_abstract_http/_abstract_http_parser.py,sha256=Y5o_hiW_0mQAte5GFqkUxscwKEFpWrBYRsLKP1cfBwE,3521
 crawlee/crawlers/_abstract_http/_http_crawling_context.py,sha256=Rno_uJ8ivmyRxFQv2MyY_z9B5WPHSEd5MAPz31_1ZIo,2179
 crawlee/crawlers/_abstract_http/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 crawlee/crawlers/_adaptive_playwright/__init__.py,sha256=LREq9WR9BKsE8S8lSsEhlCoNjQaLhlJ9yo8y_6a8o4c,1072
-crawlee/crawlers/_adaptive_playwright/_adaptive_playwright_crawler.py,sha256=j-7lm5vTI_14JrEQQDUFQ3iWnidTaca376UbSZ-uiTk,21731
+crawlee/crawlers/_adaptive_playwright/_adaptive_playwright_crawler.py,sha256=ME90JLkScWj_ynUymA59f832vEvvVpkP01cYfEc8m-Y,22895
 crawlee/crawlers/_adaptive_playwright/_adaptive_playwright_crawler_statistics.py,sha256=_At8T8S3JLGPA-1AeCFGrpE-FuCDW9sazrXt9U0tK6U,1048
 crawlee/crawlers/_adaptive_playwright/_adaptive_playwright_crawling_context.py,sha256=9FlHIUC05IzUhJsVldQvpnDnj1jk8GJpqC98mPLN_fw,10431
 crawlee/crawlers/_adaptive_playwright/_rendering_type_predictor.py,sha256=TM4mkbIN_059jUyCG8Z6XAb_FBLClIKw7z-aDvjon2I,10834
 crawlee/crawlers/_adaptive_playwright/_result_comparator.py,sha256=NAfw5VKzTnkvARtLr_zrZj6UGeMp05Voc6Oi8oPxU3w,1747
 crawlee/crawlers/_adaptive_playwright/_utils.py,sha256=EUYVz5i2YkLpL_gbVRp9BAD5u6w1xJ_AFzc_qB9bdDQ,1102
 crawlee/crawlers/_basic/__init__.py,sha256=LPln8SiBBXSMqrApiFUfpqz3hvqxN5HUa1cHQXMVKgU,280
-crawlee/crawlers/_basic/_basic_crawler.py,sha256=7qnDAO3t9qIn_RF2dCYgqTzr7rTg3namul3o3dsyES4,72690
+crawlee/crawlers/_basic/_basic_crawler.py,sha256=yZ_A_l9Dux9Y2eYa9XbN3c7h-3YO7MgGmJbzCMbCplg,73257
 crawlee/crawlers/_basic/_basic_crawling_context.py,sha256=fjxm2RQXMDkDlWu38dQ3xn5rrGUOhJXkXiqkgbFJFk4,155
 crawlee/crawlers/_basic/_context_pipeline.py,sha256=vM8EEvnCoguERjRV3oyrxUq2Ln2F9DzY7P5dAEiuMHo,5869
 crawlee/crawlers/_basic/_logging_utils.py,sha256=jp5mEwSq5a_BgzUhNPJ9WrIDcoIeYGbeHstcRqCcP0s,3093
@@ -85,7 +85,7 @@ crawlee/crawlers/_parsel/_parsel_crawling_context.py,sha256=sZB26RcRLjSoD15myEOM
 crawlee/crawlers/_parsel/_parsel_parser.py,sha256=yWBfuXUHMriK4DRnyrXTQoGeqX5WV9bOEkBp_g0YCvQ,1540
 crawlee/crawlers/_parsel/_utils.py,sha256=MbRwx-cdjlq1zLzFYf64M3spOGQ6yxum4FvP0sdqA_Q,2693
 crawlee/crawlers/_playwright/__init__.py,sha256=6Cahe6VEF82o8CYiP8Cmp58Cmb6Rb8uMeyy7wnwe5ms,837
-crawlee/crawlers/_playwright/_playwright_crawler.py,sha256=YI_EvJApfabuBY5TZq7OdBI-45ASiDE2GfsIC4qpd8A,23756
+crawlee/crawlers/_playwright/_playwright_crawler.py,sha256=53iytj5LZHw19QOYqYNlZL4ApPlhbWn9Ds-DPTKANhQ,24158
 crawlee/crawlers/_playwright/_playwright_crawling_context.py,sha256=Oi0tMBXHaEDlFjqG01DzgB7Ck52bjVjz-X__eMioxas,1249
 crawlee/crawlers/_playwright/_playwright_http_client.py,sha256=Nfm69dqX85k68jN1p3ljZWbn8egqDWPIPRykXyXsoQs,3977
 crawlee/crawlers/_playwright/_playwright_pre_nav_crawling_context.py,sha256=fEI2laWhmJdWiGoMF5JBLBsim9NtENfagZt6FFd2Rgo,1387
@@ -100,7 +100,7 @@ crawlee/fingerprint_suite/__init__.py,sha256=noY9qw80B0seZGj_B3bBvCDIDk2YWOSN-ll
 crawlee/fingerprint_suite/_browserforge_adapter.py,sha256=bsGebBjjHawM-FiINgqkZW5I9a9Fnv3SGwdKgaVWiRI,11934
 crawlee/fingerprint_suite/_consts.py,sha256=SgykWfxD-pYvOpRp_ooQ4ZTPS0sQ2b3wDyyCjwU_8-w,258
 crawlee/fingerprint_suite/_fingerprint_generator.py,sha256=Di4sDk1qioiFGx4ZcoVyHhtFHF8JXDhxQt8ZPug99k8,730
-crawlee/fingerprint_suite/_header_generator.py,sha256=GMveKjVRsfyt_iq0Cvif98D7pFiPryPD0-zQ7efE8j8,3491
+crawlee/fingerprint_suite/_header_generator.py,sha256=9X9FbStehXdw-FZc_D0y-nLk1BUHXVYFxs7fv4dl9zU,3513
 crawlee/fingerprint_suite/_types.py,sha256=7n2LJTiL2XvL-H4G-Y26Uoq5-ZXzH07Dq4o50uhMa-w,2423
 crawlee/fingerprint_suite/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 crawlee/http_clients/__init__.py,sha256=OQFhR9F8BrdlIaS5aRS7hvgQ0tKJPQ8FiyYPualyQcU,890
@@ -137,7 +137,7 @@ crawlee/request_loaders/_request_list.py,sha256=SIalHBMuFanE5GLnFocI0QCppWUiJQjr
 crawlee/request_loaders/_request_loader.py,sha256=2Bg-AWWkIV1W-Dwjqo91dPY8nmc7H3teQy7d6OSgliQ,3620
 crawlee/request_loaders/_request_manager.py,sha256=qFizyJuV2meIb9iiPfuii7ciuERMrp4SldAufiH46dc,3000
 crawlee/request_loaders/_request_manager_tandem.py,sha256=lv-s94KPsoQAqx1KaXFch96ejhO147uOflF3UK5ORTk,4058
-crawlee/request_loaders/_sitemap_request_loader.py,sha256=y5KQs5riT32WMdN3Awk2lKQNkYcXT3FYQ-mmbd31AJc,15201
+crawlee/request_loaders/_sitemap_request_loader.py,sha256=s65D_N0mZxeIrGJEjqUYfu1uYj2AXSOkmErSnfAHv2A,15554
 crawlee/sessions/__init__.py,sha256=dJdelbL-6MK5sW4SMU4QrjFbb9kRZ9uRnN-VS3R5-8Y,190
 crawlee/sessions/_cookies.py,sha256=ihYbmpXfCzClzXDT7M2wefB_3KVzcMUdIzTZo6uGk6Y,9356
 crawlee/sessions/_models.py,sha256=JMRQgDUP30XUdZ32isncHowOsXvK9jC_m9QYegbBI1E,2916
@@ -145,10 +145,10 @@ crawlee/sessions/_session.py,sha256=cMXVf6QjfGJDgdLUB4MhUP-zTm3pEDHRs-W5SBA4JFI,
 crawlee/sessions/_session_pool.py,sha256=-cMODmTRAXuoYa9DoW0cSTxbPuauF5qXY9QJcX6hXTg,9630
 crawlee/sessions/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 crawlee/statistics/__init__.py,sha256=lXAsHNkeRZQBffW1B7rERarivXIUJveNlcKTGOXQZY0,154
-crawlee/statistics/_error_snapshotter.py,sha256=ChBBG0gIMWcSeyEzs3jQf3mSnHLZUHcD284wEDan1Js,3278
+crawlee/statistics/_error_snapshotter.py,sha256=g-roZgkJ-glyStZL7gXrOhrpdZvZ686W9lR43uZjPao,3279
 crawlee/statistics/_error_tracker.py,sha256=x9Yw1TuyEptjwgPPJ4gIom-0oVjawcNReQDsHH2nZ3w,8553
 crawlee/statistics/_models.py,sha256=SFWYpT3r1c4XugU8nrm0epTpcM5_0fS1mXi9fnbhGJ8,5237
-crawlee/statistics/_statistics.py,sha256=fJr_du4CkVTz4_UgVToivAJKgA88PThE6IDBCW8RSTQ,12183
+crawlee/statistics/_statistics.py,sha256=d6z5XxXm-an4M_8TierOPpSB78vxqxwvUFCewIEmiK4,12786
 crawlee/storage_clients/__init__.py,sha256=RCnutWMOqs_kUQpzfLVT5jgpHGWakLv557c6UIYFQsA,754
 crawlee/storage_clients/models.py,sha256=gfW_kpSCOBuoTBIW0N7tb3FUv7BgD3keZADS7pyT4_I,6586
 crawlee/storage_clients/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -161,7 +161,7 @@ crawlee/storage_clients/_base/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJ
 crawlee/storage_clients/_file_system/__init__.py,sha256=w3twfwz5YeLYeu_70pNPBRINS2wXRvzOMvA1hUDYgf0,387
 crawlee/storage_clients/_file_system/_dataset_client.py,sha256=1Z8VCDx8ueh0FQQXUr8tJlOtKw8ggkaFjuz3-T_GJDY,17735
 crawlee/storage_clients/_file_system/_key_value_store_client.py,sha256=qNa3RRJQ8Omy2AteQvYh1Td04PsP5AhUFyTpL6KQbSg,18676
-crawlee/storage_clients/_file_system/_request_queue_client.py,sha256=0TM4BFcz2knQiWyF6dH62WTTj11wN9dNtpYOiBDqkpY,32862
+crawlee/storage_clients/_file_system/_request_queue_client.py,sha256=ETwy6eODf3dlBqy2RPM3nr2_oEm2ht37WpoTlFxn4A8,33970
 crawlee/storage_clients/_file_system/_storage_client.py,sha256=My63uc513kfUPe5X-PTYWBRe9xUGnkLqJN7IcsQd2yw,3293
 crawlee/storage_clients/_file_system/_utils.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 crawlee/storage_clients/_file_system/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -174,7 +174,7 @@ crawlee/storage_clients/_memory/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NM
 crawlee/storage_clients/_sql/__init__.py,sha256=X_fDMc6jn50gEBZ9QyUw54sjovYfFvE-dgXAdci6Y2M,312
 crawlee/storage_clients/_sql/_client_mixin.py,sha256=U9ThDUuRbT5JDtCFlBurhZIs1Ay5t9fTfPXXI_4dwHY,15988
 crawlee/storage_clients/_sql/_dataset_client.py,sha256=tiJVvOPZgc7cy4kGfWnun-g2TJMHMdaLnoqns5Sl6ek,10203
-crawlee/storage_clients/_sql/_db_models.py,sha256=Gs4MS1YL0gWaUfNReVKJUXsqbU_d5jxiyvZ0sFxAV2A,9845
+crawlee/storage_clients/_sql/_db_models.py,sha256=KzA-R_L6zv9gqQg7B27mF-fERNJuMUEnewV9iofmTnI,9812
 crawlee/storage_clients/_sql/_key_value_store_client.py,sha256=LnVLWhOjo4LdvtCac4fwuf__DgEQjlqSxz8KkjY3Qx4,11311
 crawlee/storage_clients/_sql/_request_queue_client.py,sha256=OlvAOwEoYY5f4NO7BdhLFRT_i_E3YzJDb_ptKKK2huY,29478
 crawlee/storage_clients/_sql/_storage_client.py,sha256=ITtMpwfotIW4SZjO4rycB5wfMKaqTAJgMvzcUZxckrk,10905
@@ -182,13 +182,13 @@ crawlee/storage_clients/_sql/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJW
 crawlee/storages/__init__.py,sha256=wc2eioyCKAAYrg4N7cshpjC-UbE23OzGar9nK_kteSY,186
 crawlee/storages/_base.py,sha256=zUOcMJTg8MAzq-m9X1NJcWncCfxzI5mb5MyY35WAkMk,2310
 crawlee/storages/_dataset.py,sha256=l3VJCaJnaAEhJFpfRUOLzIbW332R8gdEPSSGhLq65pg,14652
-crawlee/storages/_key_value_store.py,sha256=ik--ZPCzOiG5hmm6k5LNH_FO9P3MoW0UvTKiGVf1RIY,10206
+crawlee/storages/_key_value_store.py,sha256=xdkMJYdH3zXzwB3jtkijq-YkMlwBtfXxDFIUlpvpXAE,10298
 crawlee/storages/_request_queue.py,sha256=bjBOGbpMaGUsqJPVB-JD2VShziPAYMI-GvWKKpylzDE,13233
 crawlee/storages/_storage_instance_manager.py,sha256=72n0YlPwNpSQDJSPf4TxnI2GvIK6L-ZiTmHRbFcoVU0,8164
 crawlee/storages/_utils.py,sha256=Yz-5tEBYKYCFJemYT29--uGJqoJLApLDLgPcsnbifRw,439
 crawlee/storages/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-crawlee-1.0.3b6.dist-info/METADATA,sha256=7gVTyMLixer2yNVr26q903WFfW0rVXX-wPTqq97IVts,29314
-crawlee-1.0.3b6.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-crawlee-1.0.3b6.dist-info/entry_points.txt,sha256=1p65X3dA-cYvzjtlxLL6Kn1wpY-3uEDVqJLp53uNPeo,45
-crawlee-1.0.3b6.dist-info/licenses/LICENSE,sha256=AsFjHssKjj4LGd2ZCqXn6FBzMqcWdjQre1byPPSypVw,11355
-crawlee-1.0.3b6.dist-info/RECORD,,
+crawlee-1.0.5b6.dist-info/METADATA,sha256=VRTs6oXZKJWwfcqFD0n5jzVg9Y2K5kZnryeQWs0eXto,29314
+crawlee-1.0.5b6.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+crawlee-1.0.5b6.dist-info/entry_points.txt,sha256=1p65X3dA-cYvzjtlxLL6Kn1wpY-3uEDVqJLp53uNPeo,45
+crawlee-1.0.5b6.dist-info/licenses/LICENSE,sha256=AsFjHssKjj4LGd2ZCqXn6FBzMqcWdjQre1byPPSypVw,11355
+crawlee-1.0.5b6.dist-info/RECORD,,