docs: add CloakBrowser stealth browser example (#1794)

Add CloakBrowser integration example, following the same pattern as the
existing Camoufox example.

[CloakBrowser](https://github.com/CloakHQ/CloakBrowser) is a patched
Chromium binary with source-level fingerprint modifications that passes
Cloudflare Turnstile, reCAPTCHA v3 (0.9 score), and common bot detection
checks where stock Chromium and playwright-stealth get blocked.

The integration uses a custom `PlaywrightBrowserPlugin` that swaps the
default Chromium for CloakBrowser's binary. Same plugin pattern as
Camoufox — override `new_browser()`, return a
`PlaywrightBrowserController`.

Author: Cloak-HQ

docs/guides/avoid_blocking.mdx

@@ -10,6 +10,7 @@ import RunnableCodeBlock from '@site/src/components/RunnableCodeBlock';
 
 import PlaywrightDefaultFingerprintGenerator from '!!raw-loader!roa-loader!./code_examples/avoid_blocking/playwright_with_fingerprint_generator.py';
 import PlaywrightWithCamoufox from '!!raw-loader!roa-loader!../examples/code_examples/playwright_crawler_with_camoufox.py';
+import PlaywrightWithCloakBrowser from '!!raw-loader!roa-loader!./code_examples/avoid_blocking/playwright_with_cloakbrowser.py';
 
 import PlaywrightDefaultFingerprintGeneratorWithArgs from '!!raw-loader!./code_examples/avoid_blocking/default_fingerprint_generator_with_args.py';
 
@@ -41,6 +42,14 @@ In some cases even <ApiLink to="class/PlaywrightCrawler">`PlaywrightCrawler`</Ap
     {PlaywrightWithCamoufox}
 </RunnableCodeBlock>
 
+## Using CloakBrowser
+
+For sites with aggressive anti-bot protection, [CloakBrowser](https://github.com/CloakHQ/CloakBrowser) takes a different approach. Instead of overriding fingerprints at the JavaScript level (which anti-bot scripts can detect as tampering), CloakBrowser ships a custom Chromium binary with fingerprints modified directly in the C++ source code. It is also Chromium-based, which can matter when a target site behaves differently with Firefox than with Chrome. Install it separately with `pip install cloakbrowser` — the plugin calls `ensure_binary()` which automatically downloads and caches the Chromium binary on first run.
+
+<RunnableCodeBlock className="language-python" language="python">
+    {PlaywrightWithCloakBrowser}
+</RunnableCodeBlock>
+
 **Related links**
 
 - [Fingerprint Suite Docs](https://github.com/apify/fingerprint-suite)

docs/guides/code_examples/avoid_blocking/playwright_with_cloakbrowser.py

@@ -0,0 +1,81 @@
+import asyncio
+
+# CloakBrowser is an external package. Install it separately.
+from cloakbrowser.config import IGNORE_DEFAULT_ARGS, get_default_stealth_args
+from cloakbrowser.download import ensure_binary
+from typing_extensions import override
+
+from crawlee.browsers import (
+    BrowserPool,
+    PlaywrightBrowserController,
+    PlaywrightBrowserPlugin,
+)
+from crawlee.crawlers import PlaywrightCrawler, PlaywrightCrawlingContext
+
+
+class CloakBrowserPlugin(PlaywrightBrowserPlugin):
+    """Example browser plugin that uses CloakBrowser's patched Chromium,
+    but otherwise keeps the functionality of PlaywrightBrowserPlugin.
+    """
+
+    @override
+    async def new_browser(self) -> PlaywrightBrowserController:
+        if not self._playwright:
+            raise RuntimeError('Playwright browser plugin is not initialized.')
+
+        binary_path = ensure_binary()
+        stealth_args = get_default_stealth_args()
+
+        # Merge CloakBrowser stealth args with any user-provided launch options.
+        launch_options = dict(self._browser_launch_options)
+        launch_options.pop('executable_path', None)
+        launch_options.pop('chromium_sandbox', None)
+        existing_args = list(launch_options.pop('args', []))
+        launch_options['args'] = [*existing_args, *stealth_args]
+
+        return PlaywrightBrowserController(
+            browser=await self._playwright.chromium.launch(
+                executable_path=binary_path,
+                ignore_default_args=IGNORE_DEFAULT_ARGS,
+                **launch_options,
+            ),
+            max_open_pages_per_browser=1,
+            # CloakBrowser handles fingerprints at the binary level.
+            header_generator=None,
+        )
+
+
+async def main() -> None:
+    crawler = PlaywrightCrawler(
+        # Limit the crawl to max requests. Remove or increase it for crawling all links.
+        max_requests_per_crawl=10,
+        # Custom browser pool. Gives users full control over browsers used by the crawler.
+        browser_pool=BrowserPool(plugins=[CloakBrowserPlugin()]),
+    )
+
+    # Define the default request handler, which will be called for every request.
+    @crawler.router.default_handler
+    async def request_handler(context: PlaywrightCrawlingContext) -> None:
+        context.log.info(f'Processing {context.request.url} ...')
+
+        # Extract some data from the page using Playwright's API.
+        posts = await context.page.query_selector_all('.athing')
+        for post in posts:
+            # Get the HTML elements for the title and rank within each post.
+            title_element = await post.query_selector('.title a')
+
+            # Extract the data we want from the elements.
+            title = await title_element.inner_text() if title_element else None
+
+        # Push the extracted data to the default dataset.
+        await context.push_data({'title': title})
+
+        # Find a link to the next page and enqueue it if it exists.
+        await context.enqueue_links(selector='.morelink')
+
+    # Run the crawler with the initial list of URLs.
+    await crawler.run(['https://news.ycombinator.com/'])
+
+
+if __name__ == '__main__':
+    asyncio.run(main())

website/versioned_docs/version-1.6/guides/avoid_blocking.mdx

@@ -10,6 +10,7 @@ import RunnableCodeBlock from '@site/src/components/RunnableCodeBlock';
 
 import PlaywrightDefaultFingerprintGenerator from '!!raw-loader!roa-loader!./code_examples/avoid_blocking/playwright_with_fingerprint_generator.py';
 import PlaywrightWithCamoufox from '!!raw-loader!roa-loader!../examples/code_examples/playwright_crawler_with_camoufox.py';
+import PlaywrightWithCloakBrowser from '!!raw-loader!roa-loader!./code_examples/avoid_blocking/playwright_with_cloakbrowser.py';
 
 import PlaywrightDefaultFingerprintGeneratorWithArgs from '!!raw-loader!./code_examples/avoid_blocking/default_fingerprint_generator_with_args.py';
 
@@ -41,6 +42,14 @@ In some cases even <ApiLink to="class/PlaywrightCrawler">`PlaywrightCrawler`</Ap
     {PlaywrightWithCamoufox}
 </RunnableCodeBlock>
 
+## Using CloakBrowser
+
+For sites with aggressive anti-bot protection, [CloakBrowser](https://github.com/CloakHQ/CloakBrowser) takes a different approach. Instead of overriding fingerprints at the JavaScript level (which anti-bot scripts can detect as tampering), CloakBrowser ships a custom Chromium binary with fingerprints modified directly in the C++ source code. It is also Chromium-based, which can matter when a target site behaves differently with Firefox than with Chrome. Install it separately with `pip install cloakbrowser` — the plugin calls `ensure_binary()` which automatically downloads and caches the Chromium binary on first run.
+
+<RunnableCodeBlock className="language-python" language="python">
+    {PlaywrightWithCloakBrowser}
+</RunnableCodeBlock>
+
 **Related links**
 
 - [Fingerprint Suite Docs](https://github.com/apify/fingerprint-suite)

website/versioned_docs/version-1.6/guides/code_examples/avoid_blocking/playwright_with_cloakbrowser.py

@@ -0,0 +1,81 @@
+import asyncio
+
+# CloakBrowser is an external package. Install it separately.
+from cloakbrowser.config import IGNORE_DEFAULT_ARGS, get_default_stealth_args
+from cloakbrowser.download import ensure_binary
+from typing_extensions import override
+
+from crawlee.browsers import (
+    BrowserPool,
+    PlaywrightBrowserController,
+    PlaywrightBrowserPlugin,
+)
+from crawlee.crawlers import PlaywrightCrawler, PlaywrightCrawlingContext
+
+
+class CloakBrowserPlugin(PlaywrightBrowserPlugin):
+    """Example browser plugin that uses CloakBrowser's patched Chromium,
+    but otherwise keeps the functionality of PlaywrightBrowserPlugin.
+    """
+
+    @override
+    async def new_browser(self) -> PlaywrightBrowserController:
+        if not self._playwright:
+            raise RuntimeError('Playwright browser plugin is not initialized.')
+
+        binary_path = ensure_binary()
+        stealth_args = get_default_stealth_args()
+
+        # Merge CloakBrowser stealth args with any user-provided launch options.
+        launch_options = dict(self._browser_launch_options)
+        launch_options.pop('executable_path', None)
+        launch_options.pop('chromium_sandbox', None)
+        existing_args = list(launch_options.pop('args', []))
+        launch_options['args'] = [*existing_args, *stealth_args]
+
+        return PlaywrightBrowserController(
+            browser=await self._playwright.chromium.launch(
+                executable_path=binary_path,
+                ignore_default_args=IGNORE_DEFAULT_ARGS,
+                **launch_options,
+            ),
+            max_open_pages_per_browser=1,
+            # CloakBrowser handles fingerprints at the binary level.
+            header_generator=None,
+        )
+
+
+async def main() -> None:
+    crawler = PlaywrightCrawler(
+        # Limit the crawl to max requests. Remove or increase it for crawling all links.
+        max_requests_per_crawl=10,
+        # Custom browser pool. Gives users full control over browsers used by the crawler.
+        browser_pool=BrowserPool(plugins=[CloakBrowserPlugin()]),
+    )
+
+    # Define the default request handler, which will be called for every request.
+    @crawler.router.default_handler
+    async def request_handler(context: PlaywrightCrawlingContext) -> None:
+        context.log.info(f'Processing {context.request.url} ...')
+
+        # Extract some data from the page using Playwright's API.
+        posts = await context.page.query_selector_all('.athing')
+        for post in posts:
+            # Get the HTML elements for the title and rank within each post.
+            title_element = await post.query_selector('.title a')
+
+            # Extract the data we want from the elements.
+            title = await title_element.inner_text() if title_element else None
+
+        # Push the extracted data to the default dataset.
+        await context.push_data({'title': title})
+
+        # Find a link to the next page and enqueue it if it exists.
+        await context.enqueue_links(selector='.morelink')
+
+    # Run the crawler with the initial list of URLs.
+    await crawler.run(['https://news.ycombinator.com/'])
+
+
+if __name__ == '__main__':
+    asyncio.run(main())