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

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/_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
@@ -135,7 +138,7 @@ class BrowserPool:
             kwargs: Additional arguments for default constructor.
         """
         plugin_options: dict = defaultdict(dict)
-        plugin_options['browser_launch_options'] = browser_launch_options or {}
+        plugin_options['browser_launch_options'] = dict(browser_launch_options) if browser_launch_options else {}
         plugin_options['browser_new_context_options'] = browser_new_context_options or {}
 
         if headless is not None:

crawlee/browsers/_playwright_browser.py

@@ -78,7 +78,8 @@ class PlaywrightPersistentBrowser(Browser):
 
     async def _delete_temp_dir(self, _: BrowserContext | None) -> None:
         if self._temp_dir and self._temp_dir.exists():
-            await asyncio.to_thread(shutil.rmtree, self._temp_dir, ignore_errors=True)
+            temp_dir = self._temp_dir
+            await asyncio.to_thread(shutil.rmtree, temp_dir, ignore_errors=True)
 
     @override
     async def close(self, **kwargs: Any) -> None:

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/configuration.py

@@ -28,7 +28,9 @@ class Configuration(BaseSettings):
     Settings can also be configured via environment variables, prefixed with `CRAWLEE_`.
     """
 
-    model_config = SettingsConfigDict(validate_by_name=True, validate_by_alias=True)
+    # TODO: https://github.com/pydantic/pydantic-settings/issues/706
+    # Use `SettingsConfigDict(validate_by_name=True, validate_by_alias=True)` when issue is resolved.
+    model_config = SettingsConfigDict(populate_by_name=True)
 
     internal_timeout: Annotated[timedelta | None, Field(alias='crawlee_internal_timeout')] = None
     """Timeout for the internal asynchronous operations."""

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
 
@@ -23,12 +23,14 @@ with _try_import(
     'AdaptivePlaywrightCrawler',
     'AdaptivePlaywrightCrawlingContext',
     'AdaptivePlaywrightPreNavCrawlingContext',
+    'AdaptivePlaywrightCrawlerStatisticState',
     'RenderingType',
     'RenderingTypePrediction',
     'RenderingTypePredictor',
 ):
     from ._adaptive_playwright import (
         AdaptivePlaywrightCrawler,
+        AdaptivePlaywrightCrawlerStatisticState,
         AdaptivePlaywrightCrawlingContext,
         AdaptivePlaywrightPreNavCrawlingContext,
         RenderingType,
@@ -41,6 +43,7 @@ __all__ = [
     'AbstractHttpCrawler',
     'AbstractHttpParser',
     'AdaptivePlaywrightCrawler',
+    'AdaptivePlaywrightCrawlerStatisticState',
     'AdaptivePlaywrightCrawlingContext',
     'AdaptivePlaywrightPreNavCrawlingContext',
     'BasicCrawler',
@@ -51,6 +54,7 @@ __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._request import Request, RequestOptions, RequestState
 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(
@@ -82,9 +100,7 @@ class AbstractHttpCrawler(
         this method simplifies cases where `TParseResult` is used for both generic parameters.
         """
 
-        class _ParsedHttpCrawler(
-            AbstractHttpCrawler[ParsedHttpCrawlingContext[TParseResult], TParseResult, TSelectResult]
-        ):
+        class _ParsedHttpCrawler(AbstractHttpCrawler):
             def __init__(
                 self,
                 parser: AbstractHttpParser[TParseResult, TSelectResult] = static_parser,
@@ -112,9 +128,17 @@ 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
@@ -165,9 +189,18 @@ class AbstractHttpCrawler(
             robots_txt_file = await self._get_robots_txt_file_for_url(context.request.url)
 
             kwargs.setdefault('strategy', 'same-hostname')
+            strategy = kwargs.get('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)
+
+            # 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)
@@ -175,7 +208,9 @@ class AbstractHttpCrawler(
                 skipped = iter([])
 
             for url in self._enqueue_links_filter_iterator(links_iterator, context.request.url, **kwargs):
-                request_options = RequestOptions(url=url, user_data={**base_user_data}, label=label)
+                request_options = RequestOptions(
+                    url=url, user_data={**base_user_data}, label=label, enqueue_strategy=strategy
+                )
 
                 if transform_request_function:
                     transform_request_options = transform_request_function(request_options)
@@ -214,13 +249,16 @@ 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,
+            )
 
+        context.request.state = RequestState.AFTER_NAV
         yield HttpCrawlingContext.from_basic_crawling_context(context=context, http_response=result.http_response)
 
     async def _handle_status_code_response(

crawlee/crawlers/_adaptive_playwright/__init__.py

@@ -11,13 +11,16 @@ _install_import_hook(__name__)
 
 # The following imports are wrapped in try_import to handle optional dependencies,
 # ensuring the module can still function even if these dependencies are missing.
-with _try_import(__name__, 'BeautifulSoupCrawler'):
+with _try_import(__name__, 'RenderingType', 'RenderingTypePrediction', 'RenderingTypePredictor'):
     from ._rendering_type_predictor import RenderingType, RenderingTypePrediction, RenderingTypePredictor
-with _try_import(__name__, 'BeautifulSoupCrawlingContext'):
+with _try_import(__name__, 'AdaptivePlaywrightCrawler'):
     from ._adaptive_playwright_crawler import AdaptivePlaywrightCrawler
+with _try_import(__name__, 'AdaptivePlaywrightCrawlerStatisticState'):
+    from ._adaptive_playwright_crawler import AdaptivePlaywrightCrawlerStatisticState
 
 __all__ = [
     'AdaptivePlaywrightCrawler',
+    'AdaptivePlaywrightCrawlerStatisticState',
     'AdaptivePlaywrightCrawlingContext',
     'AdaptivePlaywrightPreNavCrawlingContext',
     'RenderingType',

crawlee/crawlers/_adaptive_playwright/_adaptive_playwright_crawler.py

@@ -27,23 +27,16 @@ from crawlee.crawlers import (
 )
 from crawlee.crawlers._beautifulsoup._beautifulsoup_parser import BeautifulSoupParser
 from crawlee.crawlers._parsel._parsel_parser import ParselParser
+from crawlee.crawlers._playwright._playwright_crawler import _PlaywrightCrawlerAdditionalOptions
 from crawlee.statistics import Statistics, StatisticsState
 
-from ._adaptive_playwright_crawler_statistics import (
-    AdaptivePlaywrightCrawlerStatisticState,
-)
+from ._adaptive_playwright_crawler_statistics import AdaptivePlaywrightCrawlerStatisticState
 from ._adaptive_playwright_crawling_context import (
     AdaptivePlaywrightCrawlingContext,
     AdaptivePlaywrightPreNavCrawlingContext,
 )
-from ._rendering_type_predictor import (
-    DefaultRenderingTypePredictor,
-    RenderingType,
-    RenderingTypePredictor,
-)
-from ._result_comparator import (
-    create_default_comparator,
-)
+from ._rendering_type_predictor import DefaultRenderingTypePredictor, RenderingType, RenderingTypePredictor
+from ._result_comparator import create_default_comparator
 
 if TYPE_CHECKING:
     from types import TracebackType
@@ -51,7 +44,6 @@ if TYPE_CHECKING:
     from typing_extensions import Unpack
 
     from crawlee.crawlers._basic._basic_crawler import _BasicCrawlerOptions
-    from crawlee.crawlers._playwright._playwright_crawler import _PlaywrightCrawlerAdditionalOptions
 
 
 TStaticParseResult = TypeVar('TStaticParseResult')
@@ -71,7 +63,6 @@ class _NonPersistentStatistics(Statistics):
     async def __aenter__(self) -> Self:
         self._active = True
         await self._state.initialize()
-        self._after_initialize()
         return self
 
     async def __aexit__(
@@ -149,10 +140,6 @@ 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)
@@ -162,19 +149,21 @@ class AdaptivePlaywrightCrawler(
         if 'concurrency_settings' not in kwargs or kwargs['concurrency_settings'] is None:
             kwargs['concurrency_settings'] = ConcurrencySettings(desired_concurrency=1)
 
-        super().__init__(statistics=statistics, **kwargs)
+        adaptive_statistics = statistics or Statistics(state_model=AdaptivePlaywrightCrawlerStatisticState)
+
+        super().__init__(statistics=adaptive_statistics, **kwargs)
 
         # Sub crawlers related.
-        playwright_crawler_specific_kwargs = playwright_crawler_specific_kwargs or {}
+        playwright_crawler_specific_kwargs = playwright_crawler_specific_kwargs or _PlaywrightCrawlerAdditionalOptions()
 
         # 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)
@@ -295,11 +284,14 @@ class AdaptivePlaywrightCrawler(
             use_state_function = context.use_state
 
         # New result is created and injected to newly created context. This is done to ensure isolation of sub crawlers.
-        result = RequestHandlerRunResult(key_value_store_getter=self.get_key_value_store)
+        result = RequestHandlerRunResult(
+            key_value_store_getter=self.get_key_value_store,
+            request=context.request,
+        )
         context_linked_to_result = BasicCrawlingContext(
-            request=deepcopy(context.request),
-            session=deepcopy(context.session),
-            proxy_info=deepcopy(context.proxy_info),
+            request=result.request,
+            session=context.session,
+            proxy_info=context.proxy_info,
             send_request=context.send_request,
             add_requests=result.add_requests,
             push_data=result.push_data,
@@ -337,7 +329,7 @@ class AdaptivePlaywrightCrawler(
                 )
                 await self.router(adaptive_crawling_context)
 
-            return self._static_context_pipeline(context_linked_to_result, from_static_pipeline_to_top_router)
+            return self._static_context_pipeline(context_linked_to_result, from_static_pipeline_to_top_router)  # ty: ignore[invalid-argument-type]
 
         if rendering_type == 'client only':
 
@@ -347,7 +339,7 @@ class AdaptivePlaywrightCrawler(
                 )
                 await self.router(adaptive_crawling_context)
 
-            return self._pw_context_pipeline(context_linked_to_result, from_pw_pipeline_to_top_router)
+            return self._pw_context_pipeline(context_linked_to_result, from_pw_pipeline_to_top_router)  # ty: ignore[invalid-argument-type]
 
         raise RuntimeError(
             f'Not a valid rendering type. Must be one of the following: {", ".join(get_args(RenderingType))}'
@@ -407,12 +399,9 @@ class AdaptivePlaywrightCrawler(
             raise pw_run.exception
 
         if pw_run.result:
-            self._context_result_map[context] = pw_run.result
-
             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 +410,8 @@ 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._context_result_map[context] = pw_run.result
+
     def pre_navigation_hook(
         self,
         hook: Callable[[AdaptivePlaywrightPreNavCrawlingContext], Awaitable[None]] | None = None,

crawlee/crawlers/_adaptive_playwright/_adaptive_playwright_crawling_context.py

@@ -17,7 +17,7 @@ if TYPE_CHECKING:
     from playwright.async_api import Page, Response
     from typing_extensions import Self
 
-    from crawlee.crawlers._playwright._types import BlockRequestsFunction
+    from crawlee.crawlers._playwright._types import BlockRequestsFunction, GotoOptions
 
 
 TStaticParseResult = TypeVar('TStaticParseResult')
@@ -190,8 +190,9 @@ class AdaptivePlaywrightCrawlingContext(
         http_response = await PlaywrightHttpResponse.from_playwright_response(
             response=context.response, protocol=protocol_guess or ''
         )
-        # block_requests is useful only on pre-navigation contexts. It is useless here.
+        # block_requests and goto_options are useful only on pre-navigation contexts. It is useless here.
         context_kwargs.pop('block_requests')
+        context_kwargs.pop('goto_options')
         return cls(
             parsed_content=await parser.parse(http_response),
             http_response=http_response,
@@ -212,6 +213,9 @@ class AdaptivePlaywrightPreNavCrawlingContext(BasicCrawlingContext):
     block_requests: BlockRequestsFunction | None = None
     """Blocks network requests matching specified URL patterns."""
 
+    goto_options: GotoOptions | None = None
+    """Additional options to pass to Playwright's `Page.goto()` method. The `timeout` option is not supported."""
+
     @property
     def page(self) -> Page:
         """The Playwright `Page` object for the current page.