scrapling 0.3.1__py3-none-any.whl → 0.3.2__py3-none-any.whl

scrapling/engines/_browsers/_controllers.py

@@ -1,10 +1,6 @@
-from time import time, sleep
-from asyncio import sleep as asyncio_sleep, Lock
-
 from playwright.sync_api import (
     Response as SyncPlaywrightResponse,
     sync_playwright,
-    BrowserContext,
     Playwright,
     Locator,
 )
@@ -21,9 +17,8 @@ from rebrowser_playwright.async_api import (
 )
 
 from scrapling.core.utils import log
-from ._page import PageInfo, PagePool
+from ._base import SyncSession, AsyncSession, DynamicSessionMixin
 from ._validators import validate, PlaywrightConfig
-from ._config_tools import _compiled_stealth_scripts, _launch_kwargs, _context_kwargs
 from scrapling.core._types import (
     Dict,
     List,
@@ -31,16 +26,16 @@ from scrapling.core._types import (
     Callable,
     SelectorWaitStates,
 )
-from scrapling.engines.toolbelt import (
+from scrapling.engines.toolbelt.convertor import (
     Response,
     ResponseFactory,
-    generate_convincing_referer,
-    intercept_route,
-    async_intercept_route,
 )
+from scrapling.engines.toolbelt.fingerprints import generate_convincing_referer
+
+_UNSET = object()
 
 
-class DynamicSession:
+class DynamicSession(DynamicSessionMixin, SyncSession):
     """A Browser session manager with page pooling."""
 
     __slots__ = (
@@ -59,6 +54,7 @@ class DynamicSession:
         "cookies",
         "disable_resources",
         "network_idle",
+        "load_dom",
         "wait_selector",
         "init_script",
         "wait_selector_state",
@@ -98,6 +94,7 @@ class DynamicSession:
         init_script: Optional[str] = None,
         cookies: Optional[List[Dict]] = None,
         network_idle: bool = False,
+        load_dom: bool = True,
         wait_selector_state: SelectorWaitStates = "attached",
         selector_config: Optional[Dict] = None,
     ):
@@ -112,7 +109,7 @@ class DynamicSession:
         :param network_idle: Wait for the page until there are no network connections for at least 500 ms.
         :param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
         :param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
-        :param page_action: Added for automation. A function that takes the `page` object, does the automation you need, then returns `page` again.
+        :param page_action: Added for automation. A function that takes the `page` object and does the automation you need.
         :param wait_selector: Wait for a specific CSS selector to be in a specific state.
         :param init_script: An absolute path to a JavaScript file to be executed on page creation for all pages in this session.
         :param locale: Set the locale for the browser if wanted. The default value is `en-US`.
@@ -121,114 +118,39 @@ class DynamicSession:
         :param real_chrome: If you have a Chrome browser installed on your device, enable this, and the Fetcher will launch an instance of your browser and use it.
         :param hide_canvas: Add random noise to canvas operations to prevent fingerprinting.
         :param disable_webgl: Disables WebGL and WebGL 2.0 support entirely.
+        :param load_dom: Enabled by default, wait for all JavaScript on page(s) to fully load and execute.
         :param cdp_url: Instead of launching a new browser instance, connect to this CDP URL to control real browsers/NSTBrowser through CDP.
         :param google_search: Enabled by default, Scrapling will set the referer header to be as if this request came from a Google search of this website's domain name.
         :param extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._
         :param proxy: The proxy to be used with requests, it can be a string or a dictionary with the keys 'server', 'username', and 'password' only.
         :param selector_config: The arguments that will be passed in the end while creating the final Selector's class.
         """
-
-        params = {
-            "max_pages": __max_pages,
-            "headless": headless,
-            "google_search": google_search,
-            "hide_canvas": hide_canvas,
-            "disable_webgl": disable_webgl,
-            "real_chrome": real_chrome,
-            "stealth": stealth,
-            "wait": wait,
-            "page_action": page_action,
-            "proxy": proxy,
-            "locale": locale,
-            "extra_headers": extra_headers,
-            "useragent": useragent,
-            "timeout": timeout,
-            "selector_config": selector_config,
-            "disable_resources": disable_resources,
-            "wait_selector": wait_selector,
-            "init_script": init_script,
-            "cookies": cookies,
-            "network_idle": network_idle,
-            "wait_selector_state": wait_selector_state,
-            "cdp_url": cdp_url,
-        }
-        config = validate(params, PlaywrightConfig)
-
-        self.max_pages = config.max_pages
-        self.headless = config.headless
-        self.hide_canvas = config.hide_canvas
-        self.disable_webgl = config.disable_webgl
-        self.real_chrome = config.real_chrome
-        self.stealth = config.stealth
-        self.google_search = config.google_search
-        self.wait = config.wait
-        self.proxy = config.proxy
-        self.locale = config.locale
-        self.extra_headers = config.extra_headers
-        self.useragent = config.useragent
-        self.timeout = config.timeout
-        self.cookies = config.cookies
-        self.disable_resources = config.disable_resources
-        self.cdp_url = config.cdp_url
-        self.network_idle = config.network_idle
-        self.wait_selector = config.wait_selector
-        self.init_script = config.init_script
-        self.wait_selector_state = config.wait_selector_state
-
-        self.playwright: Optional[Playwright] = None
-        self.context: Optional[BrowserContext] = None
-        self.page_pool = PagePool(self.max_pages)
-        self._closed = False
-        self.selector_config = config.selector_config
-        self.page_action = config.page_action
-        self._headers_keys = (
-            set(map(str.lower, self.extra_headers.keys()))
-            if self.extra_headers
-            else set()
+        self.__validate__(
+            wait=wait,
+            proxy=proxy,
+            locale=locale,
+            timeout=timeout,
+            stealth=stealth,
+            cdp_url=cdp_url,
+            cookies=cookies,
+            load_dom=load_dom,
+            headless=headless,
+            useragent=useragent,
+            max_pages=__max_pages,
+            real_chrome=real_chrome,
+            page_action=page_action,
+            hide_canvas=hide_canvas,
+            init_script=init_script,
+            network_idle=network_idle,
+            google_search=google_search,
+            extra_headers=extra_headers,
+            wait_selector=wait_selector,
+            disable_webgl=disable_webgl,
+            selector_config=selector_config,
+            disable_resources=disable_resources,
+            wait_selector_state=wait_selector_state,
         )
-        self.__initiate_browser_options__()
-
-    def __initiate_browser_options__(self):
-        if not self.cdp_url:
-            # `launch_options` is used with persistent context
-            self.launch_options = dict(
-                _launch_kwargs(
-                    self.headless,
-                    self.proxy,
-                    self.locale,
-                    tuple(self.extra_headers.items())
-                    if self.extra_headers
-                    else tuple(),
-                    self.useragent,
-                    self.real_chrome,
-                    self.stealth,
-                    self.hide_canvas,
-                    self.disable_webgl,
-                )
-            )
-            self.launch_options["extra_http_headers"] = dict(
-                self.launch_options["extra_http_headers"]
-            )
-            self.launch_options["proxy"] = dict(self.launch_options["proxy"]) or None
-            self.context_options = dict()
-        else:
-            # while `context_options` is left to be used when cdp mode is enabled
-            self.launch_options = dict()
-            self.context_options = dict(
-                _context_kwargs(
-                    self.proxy,
-                    self.locale,
-                    tuple(self.extra_headers.items())
-                    if self.extra_headers
-                    else tuple(),
-                    self.useragent,
-                    self.stealth,
-                )
-            )
-            self.context_options["extra_http_headers"] = dict(
-                self.context_options["extra_http_headers"]
-            )
-            self.context_options["proxy"] = dict(self.context_options["proxy"]) or None
+        super().__init__(max_pages=self.max_pages)
 
     def __create__(self):
         """Create a browser for this instance and context."""
@@ -237,16 +159,18 @@ class DynamicSession:
             # Because rebrowser_playwright doesn't play well with real browsers
             sync_context = sync_playwright
 
-        self.playwright = sync_context().start()
+        self.playwright: Playwright = sync_context().start()
 
         if self.cdp_url:  # pragma: no cover
-            self.context = self.playwright.chromium.connect_over_cdp(
-                endpoint_url=self.cdp_url
-            ).new_context(**self.context_options)
-        else:
-            self.context = self.playwright.chromium.launch_persistent_context(
-                user_data_dir="", **self.launch_options
+            self.context = self.playwright.chromium.connect_over_cdp(endpoint_url=self.cdp_url).new_context(
+                **self.context_options
             )
+        else:
+            self.context = self.playwright.chromium.launch_persistent_context(user_data_dir="", **self.launch_options)
+
+        # Get the default page and close it
+        default_page = self.context.pages[0]
+        default_page.close()
 
         if self.init_script:  # pragma: no cover
             self.context.add_init_script(path=self.init_script)
@@ -276,56 +200,63 @@ class DynamicSession:
 
         self._closed = True
 
-    def _get_or_create_page(self) -> PageInfo:  # pragma: no cover
-        """Get an available page or create a new one"""
-        # Try to get a ready page first
-        page_info = self.page_pool.get_ready_page()
-        if page_info:
-            return page_info
-
-        # Create a new page if under limit
-        if self.page_pool.pages_count < self.max_pages:
-            page = self.context.new_page()
-            page.set_default_navigation_timeout(self.timeout)
-            page.set_default_timeout(self.timeout)
-            if self.extra_headers:
-                page.set_extra_http_headers(self.extra_headers)
-
-            if self.disable_resources:
-                page.route("**/*", intercept_route)
-
-            if self.stealth:
-                for script in _compiled_stealth_scripts():
-                    page.add_init_script(script=script)
-
-            return self.page_pool.add_page(page)
-
-        # Wait for a page to become available
-        max_wait = 30
-        start_time = time()
-
-        while time() - start_time < max_wait:
-            page_info = self.page_pool.get_ready_page()
-            if page_info:
-                return page_info
-            sleep(0.05)
-
-        raise TimeoutError("No pages available within timeout period")
-
-    def fetch(self, url: str) -> Response:
+    def fetch(
+        self,
+        url: str,
+        google_search: bool = _UNSET,
+        timeout: int | float = _UNSET,
+        wait: int | float = _UNSET,
+        page_action: Optional[Callable] = _UNSET,
+        extra_headers: Optional[Dict[str, str]] = _UNSET,
+        disable_resources: bool = _UNSET,
+        wait_selector: Optional[str] = _UNSET,
+        wait_selector_state: SelectorWaitStates = _UNSET,
+        network_idle: bool = _UNSET,
+        load_dom: bool = _UNSET,
+        selector_config: Optional[Dict] = _UNSET,
+    ) -> Response:
         """Opens up the browser and do your request based on your chosen options.
 
         :param url: The Target url.
+        :param google_search: Enabled by default, Scrapling will set the referer header to be as if this request came from a Google search of this website's domain name.
+        :param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
+        :param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
+        :param page_action: Added for automation. A function that takes the `page` object and does the automation you need.
+        :param extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._
+        :param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites.
+            Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.
+            This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
+        :param wait_selector: Wait for a specific CSS selector to be in a specific state.
+        :param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
+        :param network_idle: Wait for the page until there are no network connections for at least 500 ms.
+        :param load_dom: Enabled by default, wait for all JavaScript on page(s) to fully load and execute.
+        :param selector_config: The arguments that will be passed in the end while creating the final Selector's class.
         :return: A `Response` object.
         """
+        # Validate all resolved parameters
+        params = validate(
+            dict(
+                google_search=self._get_with_precedence(google_search, self.google_search, _UNSET),
+                timeout=self._get_with_precedence(timeout, self.timeout, _UNSET),
+                wait=self._get_with_precedence(wait, self.wait, _UNSET),
+                page_action=self._get_with_precedence(page_action, self.page_action, _UNSET),
+                extra_headers=self._get_with_precedence(extra_headers, self.extra_headers, _UNSET),
+                disable_resources=self._get_with_precedence(disable_resources, self.disable_resources, _UNSET),
+                wait_selector=self._get_with_precedence(wait_selector, self.wait_selector, _UNSET),
+                wait_selector_state=self._get_with_precedence(wait_selector_state, self.wait_selector_state, _UNSET),
+                network_idle=self._get_with_precedence(network_idle, self.network_idle, _UNSET),
+                load_dom=self._get_with_precedence(load_dom, self.load_dom, _UNSET),
+                selector_config=self._get_with_precedence(selector_config, self.selector_config, _UNSET),
+            ),
+            PlaywrightConfig,
+        )
+
         if self._closed:  # pragma: no cover
             raise RuntimeError("Context manager has been closed")
 
         final_response = None
         referer = (
-            generate_convincing_referer(url)
-            if (self.google_search and "referer" not in self._headers_keys)
-            else None
+            generate_convincing_referer(url) if (params.google_search and "referer" not in self._headers_keys) else None
         )
 
         def handle_response(finished_response: SyncPlaywrightResponse):
@@ -336,48 +267,50 @@ class DynamicSession:
             ):
                 final_response = finished_response
 
-        page_info = self._get_or_create_page()
+        page_info = self._get_page(params.timeout, params.extra_headers, params.disable_resources)
         page_info.mark_busy(url=url)
 
         try:  # pragma: no cover
             # Navigate to URL and wait for a specified state
             page_info.page.on("response", handle_response)
             first_response = page_info.page.goto(url, referer=referer)
-            page_info.page.wait_for_load_state(state="domcontentloaded")
+            if params.load_dom:
+                page_info.page.wait_for_load_state(state="domcontentloaded")
 
-            if self.network_idle:
+            if params.network_idle:
                 page_info.page.wait_for_load_state("networkidle")
 
             if not first_response:
                 raise RuntimeError(f"Failed to get response for {url}")
 
-            if self.page_action is not None:
+            if params.page_action:
                 try:
-                    page_info.page = self.page_action(page_info.page)
+                    _ = params.page_action(page_info.page)
                 except Exception as e:  # pragma: no cover
                     log.error(f"Error executing page_action: {e}")
 
-            if self.wait_selector:
+            if params.wait_selector:
                 try:
-                    waiter: Locator = page_info.page.locator(self.wait_selector)
-                    waiter.first.wait_for(state=self.wait_selector_state)
+                    waiter: Locator = page_info.page.locator(params.wait_selector)
+                    waiter.first.wait_for(state=params.wait_selector_state)
                     # Wait again after waiting for the selector, helpful with protections like Cloudflare
                     page_info.page.wait_for_load_state(state="load")
-                    page_info.page.wait_for_load_state(state="domcontentloaded")
-                    if self.network_idle:
+                    if params.load_dom:
+                        page_info.page.wait_for_load_state(state="domcontentloaded")
+                    if params.network_idle:
                         page_info.page.wait_for_load_state("networkidle")
                 except Exception as e:  # pragma: no cover
-                    log.error(f"Error waiting for selector {self.wait_selector}: {e}")
+                    log.error(f"Error waiting for selector {params.wait_selector}: {e}")
 
-            page_info.page.wait_for_timeout(self.wait)
+            page_info.page.wait_for_timeout(params.wait)
 
             # Create response object
             response = ResponseFactory.from_playwright_response(
-                page_info.page, first_response, final_response, self.selector_config
+                page_info.page, first_response, final_response, params.selector_config
             )
 
-            # Mark the page as ready for next use
-            page_info.mark_ready()
+            # Mark the page as finished for next use
+            page_info.mark_finished()
 
             return response
 
@@ -385,17 +318,8 @@ class DynamicSession:
             page_info.mark_error()
             raise e
 
-    def get_pool_stats(self) -> Dict[str, int]:
-        """Get statistics about the current page pool"""
-        return {
-            "total_pages": self.page_pool.pages_count,
-            "ready_pages": self.page_pool.ready_count,
-            "busy_pages": self.page_pool.busy_count,
-            "max_pages": self.max_pages,
-        }
-
 
-class AsyncDynamicSession(DynamicSession):
+class AsyncDynamicSession(DynamicSessionMixin, AsyncSession):
     """An async Browser session manager with page pooling, it's using a persistent browser Context by default with a temporary user profile directory."""
 
     def __init__(
@@ -420,6 +344,7 @@ class AsyncDynamicSession(DynamicSession):
         init_script: Optional[str] = None,
         cookies: Optional[List[Dict]] = None,
         network_idle: bool = False,
+        load_dom: bool = True,
         wait_selector_state: SelectorWaitStates = "attached",
         selector_config: Optional[Dict] = None,
     ):
@@ -432,9 +357,10 @@ class AsyncDynamicSession(DynamicSession):
         :param useragent: Pass a useragent string to be used. Otherwise the fetcher will generate a real Useragent of the same browser and use it.
         :param cookies: Set cookies for the next request.
         :param network_idle: Wait for the page until there are no network connections for at least 500 ms.
+        :param load_dom: Enabled by default, wait for all JavaScript on page(s) to fully load and execute.
         :param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
         :param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
-        :param page_action: Added for automation. A function that takes the `page` object, does the automation you need, then returns `page` again.
+        :param page_action: Added for automation. A function that takes the `page` object and does the automation you need.
         :param wait_selector: Wait for a specific CSS selector to be in a specific state.
         :param init_script: An absolute path to a JavaScript file to be executed on page creation for all pages in this session.
         :param locale: Set the locale for the browser if wanted. The default value is `en-US`.
@@ -451,36 +377,32 @@ class AsyncDynamicSession(DynamicSession):
         :param selector_config: The arguments that will be passed in the end while creating the final Selector's class.
         """
 
-        super().__init__(
-            max_pages,
-            headless,
-            google_search,
-            hide_canvas,
-            disable_webgl,
-            real_chrome,
-            stealth,
-            wait,
-            page_action,
-            proxy,
-            locale,
-            extra_headers,
-            useragent,
-            cdp_url,
-            timeout,
-            disable_resources,
-            wait_selector,
-            init_script,
-            cookies,
-            network_idle,
-            wait_selector_state,
-            selector_config,
+        self.__validate__(
+            wait=wait,
+            proxy=proxy,
+            locale=locale,
+            timeout=timeout,
+            stealth=stealth,
+            cdp_url=cdp_url,
+            cookies=cookies,
+            load_dom=load_dom,
+            headless=headless,
+            useragent=useragent,
+            max_pages=max_pages,
+            real_chrome=real_chrome,
+            page_action=page_action,
+            hide_canvas=hide_canvas,
+            init_script=init_script,
+            network_idle=network_idle,
+            google_search=google_search,
+            extra_headers=extra_headers,
+            wait_selector=wait_selector,
+            disable_webgl=disable_webgl,
+            selector_config=selector_config,
+            disable_resources=disable_resources,
+            wait_selector_state=wait_selector_state,
         )
-
-        self.playwright: Optional[AsyncPlaywright] = None
-        self.context: Optional[AsyncBrowserContext] = None
-        self._lock = Lock()
-        self.__enter__ = None
-        self.__exit__ = None
+        super().__init__(max_pages=self.max_pages)
 
     async def __create__(self):
         """Create a browser for this instance and context."""
@@ -492,19 +414,17 @@ class AsyncDynamicSession(DynamicSession):
         self.playwright: AsyncPlaywright = await async_context().start()
 
         if self.cdp_url:
-            browser = await self.playwright.chromium.connect_over_cdp(
-                endpoint_url=self.cdp_url
-            )
-            self.context: AsyncBrowserContext = await browser.new_context(
-                **self.context_options
-            )
+            browser = await self.playwright.chromium.connect_over_cdp(endpoint_url=self.cdp_url)
+            self.context: AsyncBrowserContext = await browser.new_context(**self.context_options)
         else:
-            self.context: AsyncBrowserContext = (
-                await self.playwright.chromium.launch_persistent_context(
-                    user_data_dir="", **self.launch_options
-                )
+            self.context: AsyncBrowserContext = await self.playwright.chromium.launch_persistent_context(
+                user_data_dir="", **self.launch_options
             )
 
+        # Get the default page and close it
+        default_page = self.context.pages[0]
+        await default_page.close()
+
         if self.init_script:  # pragma: no cover
             await self.context.add_init_script(path=self.init_script)
 
@@ -533,57 +453,63 @@ class AsyncDynamicSession(DynamicSession):
 
         self._closed = True
 
-    async def _get_or_create_page(self) -> PageInfo:
-        """Get an available page or create a new one"""
-        async with self._lock:
-            # Try to get a ready page first
-            page_info = self.page_pool.get_ready_page()
-            if page_info:
-                return page_info
-
-            # Create a new page if under limit
-            if self.page_pool.pages_count < self.max_pages:
-                page = await self.context.new_page()
-                page.set_default_navigation_timeout(self.timeout)
-                page.set_default_timeout(self.timeout)
-                if self.extra_headers:
-                    await page.set_extra_http_headers(self.extra_headers)
-
-                if self.disable_resources:
-                    await page.route("**/*", async_intercept_route)
-
-                if self.stealth:
-                    for script in _compiled_stealth_scripts():
-                        await page.add_init_script(script=script)
-
-                return self.page_pool.add_page(page)
-
-        # Wait for a page to become available
-        max_wait = 30  # seconds
-        start_time = time()
-
-        while time() - start_time < max_wait:  # pragma: no cover
-            page_info = self.page_pool.get_ready_page()
-            if page_info:
-                return page_info
-            await asyncio_sleep(0.05)
-
-        raise TimeoutError("No pages available within timeout period")
-
-    async def fetch(self, url: str) -> Response:
+    async def fetch(
+        self,
+        url: str,
+        google_search: bool = _UNSET,
+        timeout: int | float = _UNSET,
+        wait: int | float = _UNSET,
+        page_action: Optional[Callable] = _UNSET,
+        extra_headers: Optional[Dict[str, str]] = _UNSET,
+        disable_resources: bool = _UNSET,
+        wait_selector: Optional[str] = _UNSET,
+        wait_selector_state: SelectorWaitStates = _UNSET,
+        network_idle: bool = _UNSET,
+        load_dom: bool = _UNSET,
+        selector_config: Optional[Dict] = _UNSET,
+    ) -> Response:
         """Opens up the browser and do your request based on your chosen options.
 
         :param url: The Target url.
+        :param google_search: Enabled by default, Scrapling will set the referer header to be as if this request came from a Google search of this website's domain name.
+        :param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30,000
+        :param wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object.
+        :param page_action: Added for automation. A function that takes the `page` object and does the automation you need.
+        :param extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._
+        :param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites.
+            Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`.
+            This can help save your proxy usage but be careful with this option as it makes some websites never finish loading.
+        :param wait_selector: Wait for a specific CSS selector to be in a specific state.
+        :param wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`.
+        :param network_idle: Wait for the page until there are no network connections for at least 500 ms.
+        :param load_dom: Enabled by default, wait for all JavaScript on page(s) to fully load and execute.
+        :param selector_config: The arguments that will be passed in the end while creating the final Selector's class.
         :return: A `Response` object.
         """
+        # Validate all resolved parameters
+        params = validate(
+            dict(
+                google_search=self._get_with_precedence(google_search, self.google_search, _UNSET),
+                timeout=self._get_with_precedence(timeout, self.timeout, _UNSET),
+                wait=self._get_with_precedence(wait, self.wait, _UNSET),
+                page_action=self._get_with_precedence(page_action, self.page_action, _UNSET),
+                extra_headers=self._get_with_precedence(extra_headers, self.extra_headers, _UNSET),
+                disable_resources=self._get_with_precedence(disable_resources, self.disable_resources, _UNSET),
+                wait_selector=self._get_with_precedence(wait_selector, self.wait_selector, _UNSET),
+                wait_selector_state=self._get_with_precedence(wait_selector_state, self.wait_selector_state, _UNSET),
+                network_idle=self._get_with_precedence(network_idle, self.network_idle, _UNSET),
+                load_dom=self._get_with_precedence(load_dom, self.load_dom, _UNSET),
+                selector_config=self._get_with_precedence(selector_config, self.selector_config, _UNSET),
+            ),
+            PlaywrightConfig,
+        )
+
         if self._closed:  # pragma: no cover
             raise RuntimeError("Context manager has been closed")
 
         final_response = None
         referer = (
-            generate_convincing_referer(url)
-            if (self.google_search and "referer" not in self._headers_keys)
-            else None
+            generate_convincing_referer(url) if (params.google_search and "referer" not in self._headers_keys) else None
         )
 
         async def handle_response(finished_response: AsyncPlaywrightResponse):
@@ -594,48 +520,50 @@ class AsyncDynamicSession(DynamicSession):
             ):
                 final_response = finished_response
 
-        page_info = await self._get_or_create_page()
+        page_info = await self._get_page(params.timeout, params.extra_headers, params.disable_resources)
         page_info.mark_busy(url=url)
 
         try:
             # Navigate to URL and wait for a specified state
             page_info.page.on("response", handle_response)
             first_response = await page_info.page.goto(url, referer=referer)
-            await page_info.page.wait_for_load_state(state="domcontentloaded")
+            if self.load_dom:
+                await page_info.page.wait_for_load_state(state="domcontentloaded")
 
-            if self.network_idle:
+            if params.network_idle:
                 await page_info.page.wait_for_load_state("networkidle")
 
             if not first_response:
                 raise RuntimeError(f"Failed to get response for {url}")
 
-            if self.page_action is not None:
+            if params.page_action:
                 try:
-                    page_info.page = await self.page_action(page_info.page)
+                    _ = await params.page_action(page_info.page)
                 except Exception as e:
                     log.error(f"Error executing page_action: {e}")
 
-            if self.wait_selector:
+            if params.wait_selector:
                 try:
-                    waiter: AsyncLocator = page_info.page.locator(self.wait_selector)
-                    await waiter.first.wait_for(state=self.wait_selector_state)
+                    waiter: AsyncLocator = page_info.page.locator(params.wait_selector)
+                    await waiter.first.wait_for(state=params.wait_selector_state)
                     # Wait again after waiting for the selector, helpful with protections like Cloudflare
                     await page_info.page.wait_for_load_state(state="load")
-                    await page_info.page.wait_for_load_state(state="domcontentloaded")
-                    if self.network_idle:
+                    if self.load_dom:
+                        await page_info.page.wait_for_load_state(state="domcontentloaded")
+                    if params.network_idle:
                         await page_info.page.wait_for_load_state("networkidle")
                 except Exception as e:
-                    log.error(f"Error waiting for selector {self.wait_selector}: {e}")
+                    log.error(f"Error waiting for selector {params.wait_selector}: {e}")
 
-            await page_info.page.wait_for_timeout(self.wait)
+            await page_info.page.wait_for_timeout(params.wait)
 
             # Create response object
             response = await ResponseFactory.from_async_playwright_response(
-                page_info.page, first_response, final_response, self.selector_config
+                page_info.page, first_response, final_response, params.selector_config
             )
 
-            # Mark the page as ready for next use
-            page_info.mark_ready()
+            # Mark the page as finished for next use
+            page_info.mark_finished()
 
             return response