scrapling 0.3.3__tar.gz → 0.3.5__tar.gz

{scrapling-0.3.3/scrapling.egg-info → scrapling-0.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scrapling
-Version: 0.3.3
+Version: 0.3.5
 Summary: Scrapling is an undetectable, powerful, flexible, high-performance Python library that makes Web Scraping easy and effortless as it should be!
 Home-page: https://github.com/D4Vinci/Scrapling
 Author: Karim Shoair
@@ -69,15 +69,15 @@ Requires-Dist: cssselect>=1.3.0
 Requires-Dist: orjson>=3.11.3
 Requires-Dist: tldextract>=5.3.0
 Provides-Extra: fetchers
-Requires-Dist: click>=8.2.1; extra == "fetchers"
+Requires-Dist: click>=8.3.0; extra == "fetchers"
 Requires-Dist: curl_cffi>=0.13.0; extra == "fetchers"
-Requires-Dist: playwright>=1.52.0; extra == "fetchers"
-Requires-Dist: rebrowser-playwright>=1.52.0; extra == "fetchers"
+Requires-Dist: playwright>=1.55.0; extra == "fetchers"
+Requires-Dist: patchright>=1.55.2; extra == "fetchers"
 Requires-Dist: camoufox>=0.4.11; extra == "fetchers"
 Requires-Dist: geoip2>=5.1.0; extra == "fetchers"
 Requires-Dist: msgspec>=0.19.0; extra == "fetchers"
 Provides-Extra: ai
-Requires-Dist: mcp>=1.14.0; extra == "ai"
+Requires-Dist: mcp>=1.14.1; extra == "ai"
 Requires-Dist: markdownify>=1.2.0; extra == "ai"
 Requires-Dist: scrapling[fetchers]; extra == "ai"
 Provides-Extra: shell
@@ -114,14 +114,6 @@ Dynamic: license-file
 </p>
 
 <p align="center">
-    <a href="https://scrapling.readthedocs.io/en/latest/#installation">
-        Installation
-    </a>
-    ·
-    <a href="https://scrapling.readthedocs.io/en/latest/overview/">
-        Overview
-    </a>
-    ·
     <a href="https://scrapling.readthedocs.io/en/latest/parsing/selection/">
         Selection methods
     </a>
@@ -130,6 +122,14 @@ Dynamic: license-file
         Choosing a fetcher
     </a>
     ·
+    <a href="https://scrapling.readthedocs.io/en/latest/cli/overview/">
+        CLI
+    </a>
+    ·
+    <a href="https://scrapling.readthedocs.io/en/latest/ai/mcp-server/">
+        MCP mode
+    </a>
+    ·
     <a href="https://scrapling.readthedocs.io/en/latest/tutorials/migrating_from_beautifulsoup/">
         Migrating from Beautifulsoup
     </a>
@@ -157,11 +157,13 @@ Built for the modern Web, Scrapling has its own rapid parsing engine and its fet
 
 <!-- sponsors -->
 
+<a href="https://www.thordata.com/?ls=github&lk=D4Vinci" target="_blank" title="A global network of over 60M+ residential proxies with 99.7% availability, ensuring stable and reliable web data scraping to support AI, BI, and workflows."><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/thordata.jpg"></a>
 <a href="https://evomi.com?utm_source=github&utm_medium=banner&utm_campaign=d4vinci-scrapling" target="_blank" title="Evomi is your Swiss Quality Proxy Provider, starting at $0.49/GB"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/evomi.png"></a>
+<a href="https://visit.decodo.com/Dy6W0b" target="_blank" title="Try the Most Efficient Residential Proxies for Free"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/decodo.png"></a>
 <a href="https://petrosky.io/d4vinci" target="_blank" title="PetroSky delivers cutting-edge VPS hosting."><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/petrosky.png"></a>
 <a href="https://www.swiftproxy.net/" target="_blank" title="Unlock Reliable Proxy Services with Swiftproxy!"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/swiftproxy.png"></a>
-<a href="https://serpapi.com/?utm_source=scrapling" target="_blank" title="Scrape Google and other search engines with SerpApi"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/SerpApi.png"></a>
 <a href="https://www.nstproxy.com/?type=flow&utm_source=scrapling" target="_blank" title="One Proxy Service, Infinite Solutions at Unbeatable Prices!"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/NSTproxy.png"></a>
+<a href="https://serpapi.com/?utm_source=scrapling" target="_blank" title="Scrape Google and other search engines with SerpApi"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/SerpApi.png"></a>
 
 <!-- /sponsors -->
 
@@ -410,10 +412,9 @@ This project includes code adapted from:
 ## Thanks and References
 
 - [Daijro](https://github.com/daijro)'s brilliant work on [BrowserForge](https://github.com/daijro/browserforge) and [Camoufox](https://github.com/daijro/camoufox)
-- [Vinyzu](https://github.com/Vinyzu)'s work on [Botright](https://github.com/Vinyzu/Botright)
+- [Vinyzu](https://github.com/Vinyzu)'s brilliant work on [Botright](https://github.com/Vinyzu/Botright) and [PatchRight](https://github.com/Kaliiiiiiiiii-Vinyzu/patchright)
 - [brotector](https://github.com/kaliiiiiiiiii/brotector) for browser detection bypass techniques
-- [fakebrowser](https://github.com/kkoooqq/fakebrowser) for fingerprinting research
-- [rebrowser-patches](https://github.com/rebrowser/rebrowser-patches) for stealth improvements
+- [fakebrowser](https://github.com/kkoooqq/fakebrowser) and [BotBrowser](https://github.com/botswin/BotBrowser) for fingerprinting research
 
 ---
 <div align="center"><small>Designed & crafted with ❤️ by Karim Shoair.</small></div><br>

{scrapling-0.3.3 → scrapling-0.3.5}/README.md

@@ -24,14 +24,6 @@
 </p>
 
 <p align="center">
-    <a href="https://scrapling.readthedocs.io/en/latest/#installation">
-        Installation
-    </a>
-    ·
-    <a href="https://scrapling.readthedocs.io/en/latest/overview/">
-        Overview
-    </a>
-    ·
     <a href="https://scrapling.readthedocs.io/en/latest/parsing/selection/">
         Selection methods
     </a>
@@ -40,6 +32,14 @@
         Choosing a fetcher
     </a>
     ·
+    <a href="https://scrapling.readthedocs.io/en/latest/cli/overview/">
+        CLI
+    </a>
+    ·
+    <a href="https://scrapling.readthedocs.io/en/latest/ai/mcp-server/">
+        MCP mode
+    </a>
+    ·
     <a href="https://scrapling.readthedocs.io/en/latest/tutorials/migrating_from_beautifulsoup/">
         Migrating from Beautifulsoup
     </a>
@@ -67,11 +67,13 @@ Built for the modern Web, Scrapling has its own rapid parsing engine and its fet
 
 <!-- sponsors -->
 
+<a href="https://www.thordata.com/?ls=github&lk=D4Vinci" target="_blank" title="A global network of over 60M+ residential proxies with 99.7% availability, ensuring stable and reliable web data scraping to support AI, BI, and workflows."><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/thordata.jpg"></a>
 <a href="https://evomi.com?utm_source=github&utm_medium=banner&utm_campaign=d4vinci-scrapling" target="_blank" title="Evomi is your Swiss Quality Proxy Provider, starting at $0.49/GB"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/evomi.png"></a>
+<a href="https://visit.decodo.com/Dy6W0b" target="_blank" title="Try the Most Efficient Residential Proxies for Free"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/decodo.png"></a>
 <a href="https://petrosky.io/d4vinci" target="_blank" title="PetroSky delivers cutting-edge VPS hosting."><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/petrosky.png"></a>
 <a href="https://www.swiftproxy.net/" target="_blank" title="Unlock Reliable Proxy Services with Swiftproxy!"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/swiftproxy.png"></a>
-<a href="https://serpapi.com/?utm_source=scrapling" target="_blank" title="Scrape Google and other search engines with SerpApi"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/SerpApi.png"></a>
 <a href="https://www.nstproxy.com/?type=flow&utm_source=scrapling" target="_blank" title="One Proxy Service, Infinite Solutions at Unbeatable Prices!"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/NSTproxy.png"></a>
+<a href="https://serpapi.com/?utm_source=scrapling" target="_blank" title="Scrape Google and other search engines with SerpApi"><img src="https://raw.githubusercontent.com/D4Vinci/Scrapling/main/images/SerpApi.png"></a>
 
 <!-- /sponsors -->
 
@@ -320,10 +322,9 @@ This project includes code adapted from:
 ## Thanks and References
 
 - [Daijro](https://github.com/daijro)'s brilliant work on [BrowserForge](https://github.com/daijro/browserforge) and [Camoufox](https://github.com/daijro/camoufox)
-- [Vinyzu](https://github.com/Vinyzu)'s work on [Botright](https://github.com/Vinyzu/Botright)
+- [Vinyzu](https://github.com/Vinyzu)'s brilliant work on [Botright](https://github.com/Vinyzu/Botright) and [PatchRight](https://github.com/Kaliiiiiiiiii-Vinyzu/patchright)
 - [brotector](https://github.com/kaliiiiiiiiii/brotector) for browser detection bypass techniques
-- [fakebrowser](https://github.com/kkoooqq/fakebrowser) for fingerprinting research
-- [rebrowser-patches](https://github.com/rebrowser/rebrowser-patches) for stealth improvements
+- [fakebrowser](https://github.com/kkoooqq/fakebrowser) and [BotBrowser](https://github.com/botswin/BotBrowser) for fingerprinting research
 
 ---
 <div align="center"><small>Designed & crafted with ❤️ by Karim Shoair.</small></div><br>

{scrapling-0.3.3 → scrapling-0.3.5}/pyproject.toml

@@ -64,16 +64,16 @@ dependencies = [
 
 [project.optional-dependencies]
 fetchers = [
-    "click>=8.2.1",
+    "click>=8.3.0",
     "curl_cffi>=0.13.0",
-    "playwright>=1.52.0",
-    "rebrowser-playwright>=1.52.0",
+    "playwright>=1.55.0",
+    "patchright>=1.55.2",
     "camoufox>=0.4.11",
     "geoip2>=5.1.0",
     "msgspec>=0.19.0",
 ]
 ai = [
-    "mcp>=1.14.0",
+    "mcp>=1.14.1",
     "markdownify>=1.2.0",
     "scrapling[fetchers]",
 ]

{scrapling-0.3.3 → scrapling-0.3.5}/scrapling/__init__.py

@@ -1,5 +1,5 @@
 __author__ = "Karim Shoair (karim.shoair@pm.me)"
-__version__ = "0.3.3"
+__version__ = "0.3.5"
 __copyright__ = "Copyright (c) 2024 Karim Shoair"
 
 

{scrapling-0.3.3 → scrapling-0.3.5}/scrapling/cli.py

@@ -32,8 +32,8 @@ def __ParseJSONData(json_string: Optional[str] = None) -> Optional[Dict[str, Any
 
     try:
         return json_loads(json_string)
-    except JSONDecodeError as e:  # pragma: no cover
-        raise ValueError(f"Invalid JSON data '{json_string}': {e}")
+    except JSONDecodeError as err:  # pragma: no cover
+        raise ValueError(f"Invalid JSON data '{json_string}': {err}")
 
 
 def __Request_and_Save(
@@ -65,8 +65,8 @@ def __ParseExtractArguments(
         for key, value in _CookieParser(cookies):
             try:
                 parsed_cookies[key] = value
-            except Exception as e:
-                raise ValueError(f"Could not parse cookies '{cookies}': {e}")
+            except Exception as err:
+                raise ValueError(f"Could not parse cookies '{cookies}': {err}")
 
     parsed_json = __ParseJSONData(json)
     parsed_params = {}

{scrapling-0.3.3 → scrapling-0.3.5}/scrapling/core/custom_types.py

@@ -145,7 +145,7 @@ class TextHandler(str):
         clean_match: bool = False,
         case_sensitive: bool = True,
         check_match: Literal[False] = False,
-    ) -> "TextHandlers[TextHandler]": ...
+    ) -> "TextHandlers": ...
 
     def re(
         self,
@@ -241,7 +241,7 @@ class TextHandlers(List[TextHandler]):
         replace_entities: bool = True,
         clean_match: bool = False,
         case_sensitive: bool = True,
-    ) -> "TextHandlers[TextHandler]":
+    ) -> "TextHandlers":
         """Call the ``.re()`` method for each element in this list and return
         their results flattened as TextHandlers.
 

{scrapling-0.3.3 → scrapling-0.3.5}/scrapling/core/shell.py

@@ -201,7 +201,7 @@ class CurlParser:
                 data_payload = parsed_args.data_binary  # Fallback to string
 
         elif parsed_args.data_raw is not None:
-            data_payload = parsed_args.data_raw
+            data_payload = parsed_args.data_raw.lstrip("$")
 
         elif parsed_args.data is not None:
             data_payload = parsed_args.data
@@ -318,7 +318,7 @@ def show_page_in_browser(page: Selector):  # pragma: no cover
     try:
         fd, fname = make_temp_file(prefix="scrapling_view_", suffix=".html")
         with open(fd, "w", encoding=page.encoding) as f:
-            f.write(page.body)
+            f.write(page.html_content)
 
         open_in_browser(f"file://{fname}")
     except IOError as e:
@@ -335,15 +335,25 @@ class CustomShell:
         from scrapling.fetchers import (
             Fetcher as __Fetcher,
             AsyncFetcher as __AsyncFetcher,
+            FetcherSession as __FetcherSession,
             DynamicFetcher as __DynamicFetcher,
+            DynamicSession as __DynamicSession,
+            AsyncDynamicSession as __AsyncDynamicSession,
             StealthyFetcher as __StealthyFetcher,
+            StealthySession as __StealthySession,
+            AsyncStealthySession as __AsyncStealthySession,
         )
 
         self.__InteractiveShellEmbed = __InteractiveShellEmbed
         self.__Fetcher = __Fetcher
         self.__AsyncFetcher = __AsyncFetcher
+        self.__FetcherSession = __FetcherSession
         self.__DynamicFetcher = __DynamicFetcher
+        self.__DynamicSession = __DynamicSession
+        self.__AsyncDynamicSession = __AsyncDynamicSession
         self.__StealthyFetcher = __StealthyFetcher
+        self.__StealthySession = __StealthySession
+        self.__AsyncStealthySession = __AsyncStealthySession
         self.code = code
         self.page = None
         self.pages = Selectors([])
@@ -379,9 +389,9 @@ class CustomShell:
         """Create a custom banner for the shell"""
         return f"""
 -> Available Scrapling objects:
-   - Fetcher/AsyncFetcher
-   - DynamicFetcher
-   - StealthyFetcher
+   - Fetcher/AsyncFetcher/FetcherSession
+   - DynamicFetcher/DynamicSession/AsyncDynamicSession
+   - StealthyFetcher/StealthySession/AsyncStealthySession
    - Selector
 
 -> Useful shortcuts:
@@ -449,6 +459,11 @@ Type 'exit' or press Ctrl+D to exit.
             "delete": delete,
             "Fetcher": self.__Fetcher,
             "AsyncFetcher": self.__AsyncFetcher,
+            "FetcherSession": self.__FetcherSession,
+            "DynamicSession": self.__DynamicSession,
+            "AsyncDynamicSession": self.__AsyncDynamicSession,
+            "StealthySession": self.__StealthySession,
+            "AsyncStealthySession": self.__AsyncStealthySession,
             "fetch": dynamic_fetch,
             "DynamicFetcher": self.__DynamicFetcher,
             "stealthy_fetch": stealthy_fetch,
@@ -530,7 +545,7 @@ class Convertor:
             for page in pages:
                 match extraction_type:
                     case "markdown":
-                        yield cls._convert_to_markdown(page.body)
+                        yield cls._convert_to_markdown(page.html_content)
                     case "html":
                         yield page.body
                     case "text":

{scrapling-0.3.3 → scrapling-0.3.5}/scrapling/engines/_browsers/_base.py

@@ -1,4 +1,4 @@
-from time import time, sleep
+from time import time
 from asyncio import sleep as asyncio_sleep, Lock
 
 from camoufox import DefaultAddons
@@ -31,7 +31,7 @@ class SyncSession:
     def __init__(self, max_pages: int = 1):
         self.max_pages = max_pages
         self.page_pool = PagePool(max_pages)
-        self.__max_wait_for_page = 60
+        self._max_wait_for_page = 60
         self.playwright: Optional[Playwright] = None
         self.context: Optional[BrowserContext] = None
         self._closed = False
@@ -44,23 +44,7 @@ class SyncSession:
     ) -> PageInfo:  # pragma: no cover
         """Get a new page to use"""
 
-        # Close all finished pages to ensure clean state
-        self.page_pool.close_all_finished_pages()
-
-        # If we're at max capacity after cleanup, wait for busy pages to finish
-        if self.page_pool.pages_count >= self.max_pages:
-            start_time = time()
-            while time() - start_time < self.__max_wait_for_page:
-                # Wait for any pages to finish, then clean them up
-                sleep(0.05)
-                self.page_pool.close_all_finished_pages()
-                if self.page_pool.pages_count < self.max_pages:
-                    break
-            else:
-                raise TimeoutError(
-                    f"No pages finished to clear place in the pool within the {self.__max_wait_for_page}s timeout period"
-                )
-
+        # No need to check if a page is available or not in sync code because the code blocked before reaching here till the page closed, ofc.
         page = self.context.new_page()
         page.set_default_navigation_timeout(timeout)
         page.set_default_timeout(timeout)
@@ -76,11 +60,6 @@ class SyncSession:
 
         return self.page_pool.add_page(page)
 
-    @staticmethod
-    def _get_with_precedence(request_value: Any, session_value: Any, sentinel_value: object) -> Any:
-        """Get value with request-level priority over session-level"""
-        return request_value if request_value is not sentinel_value else session_value
-
     def get_pool_stats(self) -> Dict[str, int]:
         """Get statistics about the current page pool"""
         return {
@@ -105,21 +84,16 @@ class AsyncSession(SyncSession):
     ) -> PageInfo:  # pragma: no cover
         """Get a new page to use"""
         async with self._lock:
-            # Close all finished pages to ensure clean state
-            await self.page_pool.aclose_all_finished_pages()
-
             # If we're at max capacity after cleanup, wait for busy pages to finish
             if self.page_pool.pages_count >= self.max_pages:
                 start_time = time()
-                while time() - start_time < self.__max_wait_for_page:
-                    # Wait for any pages to finish, then clean them up
+                while time() - start_time < self._max_wait_for_page:
                     await asyncio_sleep(0.05)
-                    await self.page_pool.aclose_all_finished_pages()
                     if self.page_pool.pages_count < self.max_pages:
                         break
                 else:
                     raise TimeoutError(
-                        f"No pages finished to clear place in the pool within the {self.__max_wait_for_page}s timeout period"
+                        f"No pages finished to clear place in the pool within the {self._max_wait_for_page}s timeout period"
                     )
 
             page = await self.context.new_page()

{scrapling-0.3.3 → scrapling-0.3.5}/scrapling/engines/_browsers/_camoufox.py

@@ -14,8 +14,9 @@ from playwright.async_api import (
     Locator as AsyncLocator,
     Page as async_Page,
 )
+from playwright._impl._errors import Error as PlaywrightError
 
-from ._validators import validate, CamoufoxConfig
+from ._validators import validate_fetch as _validate
 from ._base import SyncSession, AsyncSession, StealthySessionMixin
 from scrapling.core.utils import log
 from scrapling.core._types import (
@@ -201,20 +202,34 @@ class StealthySession(StealthySessionMixin, SyncSession):
 
         self._closed = True
 
+    @staticmethod
+    def _get_page_content(page: Page) -> str | None:
+        """
+        A workaround for Playwright issue with `page.content()` on Windows. Ref.: https://github.com/microsoft/playwright/issues/16108
+        :param page: The page to extract content from.
+        :return:
+        """
+        while True:
+            try:
+                return page.content() or ""
+            except PlaywrightError:
+                page.wait_for_timeout(1000)
+                continue
+
     def _solve_cloudflare(self, page: Page) -> None:  # pragma: no cover
         """Solve the cloudflare challenge displayed on the playwright page passed
 
         :param page: The targeted page
         :return:
         """
-        challenge_type = self._detect_cloudflare(page.content())
+        challenge_type = self._detect_cloudflare(self._get_page_content(page))
         if not challenge_type:
             log.error("No Cloudflare challenge found.")
             return
         else:
             log.info(f'The turnstile version discovered is "{challenge_type}"')
             if challenge_type == "non-interactive":
-                while "<title>Just a moment...</title>" in (page.content()):
+                while "<title>Just a moment...</title>" in (self._get_page_content(page)):
                     log.info("Waiting for Cloudflare wait page to disappear.")
                     page.wait_for_timeout(1000)
                     page.wait_for_load_state()
@@ -222,7 +237,7 @@ class StealthySession(StealthySessionMixin, SyncSession):
                 return
 
             else:
-                while "Verifying you are human." in page.content():
+                while "Verifying you are human." in self._get_page_content(page):
                     # Waiting for the verify spinner to disappear, checking every 1s if it disappeared
                     page.wait_for_timeout(500)
 
@@ -282,23 +297,22 @@ class StealthySession(StealthySessionMixin, SyncSession):
         :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),
-                solve_cloudflare=self._get_with_precedence(solve_cloudflare, self.solve_cloudflare, _UNSET),
-                selector_config=self._get_with_precedence(selector_config, self.selector_config, _UNSET),
-            ),
-            CamoufoxConfig,
+        params = _validate(
+            [
+                ("google_search", google_search, self.google_search),
+                ("timeout", timeout, self.timeout),
+                ("wait", wait, self.wait),
+                ("page_action", page_action, self.page_action),
+                ("extra_headers", extra_headers, self.extra_headers),
+                ("disable_resources", disable_resources, self.disable_resources),
+                ("wait_selector", wait_selector, self.wait_selector),
+                ("wait_selector_state", wait_selector_state, self.wait_selector_state),
+                ("network_idle", network_idle, self.network_idle),
+                ("load_dom", load_dom, self.load_dom),
+                ("solve_cloudflare", solve_cloudflare, self.solve_cloudflare),
+                ("selector_config", selector_config, self.selector_config),
+            ],
+            _UNSET,
         )
 
         if self._closed:  # pragma: no cover
@@ -366,8 +380,9 @@ class StealthySession(StealthySessionMixin, SyncSession):
                 page_info.page, first_response, final_response, params.selector_config
             )
 
-            # Mark the page as finished for next use
-            page_info.mark_finished()
+            # Close the page, to free up resources
+            page_info.page.close()
+            self.page_pool.pages.remove(page_info)
 
             return response
 
@@ -506,20 +521,34 @@ class AsyncStealthySession(StealthySessionMixin, AsyncSession):
 
         self._closed = True
 
+    @staticmethod
+    async def _get_page_content(page: async_Page) -> str | None:
+        """
+        A workaround for Playwright issue with `page.content()` on Windows. Ref.: https://github.com/microsoft/playwright/issues/16108
+        :param page: The page to extract content from.
+        :return:
+        """
+        while True:
+            try:
+                return (await page.content()) or ""
+            except PlaywrightError:
+                await page.wait_for_timeout(1000)
+                continue
+
     async def _solve_cloudflare(self, page: async_Page):
         """Solve the cloudflare challenge displayed on the playwright page passed. The async version
 
         :param page: The async targeted page
         :return:
         """
-        challenge_type = self._detect_cloudflare(await page.content())
+        challenge_type = self._detect_cloudflare(await self._get_page_content(page))
         if not challenge_type:
             log.error("No Cloudflare challenge found.")
             return
         else:
             log.info(f'The turnstile version discovered is "{challenge_type}"')
             if challenge_type == "non-interactive":  # pragma: no cover
-                while "<title>Just a moment...</title>" in (await page.content()):
+                while "<title>Just a moment...</title>" in (await self._get_page_content(page)):
                     log.info("Waiting for Cloudflare wait page to disappear.")
                     await page.wait_for_timeout(1000)
                     await page.wait_for_load_state()
@@ -527,7 +556,7 @@ class AsyncStealthySession(StealthySessionMixin, AsyncSession):
                 return
 
             else:
-                while "Verifying you are human." in (await page.content()):
+                while "Verifying you are human." in (await self._get_page_content(page)):
                     # Waiting for the verify spinner to disappear, checking every 1s if it disappeared
                     await page.wait_for_timeout(500)
 
@@ -587,22 +616,22 @@ class AsyncStealthySession(StealthySessionMixin, AsyncSession):
         :param selector_config: The arguments that will be passed in the end while creating the final Selector's class.
         :return: A `Response` object.
         """
-        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),
-                solve_cloudflare=self._get_with_precedence(solve_cloudflare, self.solve_cloudflare, _UNSET),
-                selector_config=self._get_with_precedence(selector_config, self.selector_config, _UNSET),
-            ),
-            CamoufoxConfig,
+        params = _validate(
+            [
+                ("google_search", google_search, self.google_search),
+                ("timeout", timeout, self.timeout),
+                ("wait", wait, self.wait),
+                ("page_action", page_action, self.page_action),
+                ("extra_headers", extra_headers, self.extra_headers),
+                ("disable_resources", disable_resources, self.disable_resources),
+                ("wait_selector", wait_selector, self.wait_selector),
+                ("wait_selector_state", wait_selector_state, self.wait_selector_state),
+                ("network_idle", network_idle, self.network_idle),
+                ("load_dom", load_dom, self.load_dom),
+                ("solve_cloudflare", solve_cloudflare, self.solve_cloudflare),
+                ("selector_config", selector_config, self.selector_config),
+            ],
+            _UNSET,
         )
 
         if self._closed:  # pragma: no cover
@@ -672,8 +701,9 @@ class AsyncStealthySession(StealthySessionMixin, AsyncSession):
                 page_info.page, first_response, final_response, params.selector_config
             )
 
-            # Mark the page as finished for next use
-            page_info.mark_finished()
+            # Close the page, to free up resources
+            await page_info.page.close()
+            self.page_pool.pages.remove(page_info)
 
             return response