feat: support custom profile in playwright

if user_data_dir option is found in browser_option,
then the launch function used is launch_persistent_context
instead of launch and the user_data_dir option is passed to playwright

src/crawlee/browsers/playwright_browser_plugin.py

@@ -92,14 +92,19 @@ async def new_browser(self) -> PlaywrightBrowserController:
         if not self._playwright:
             raise RuntimeError('Playwright browser plugin is not initialized.')
 
-        if self._browser_type == 'chromium':
-            browser = await self._playwright.chromium.launch(**self._browser_options)
-        elif self._browser_type == 'firefox':
-            browser = await self._playwright.firefox.launch(**self._browser_options)
-        elif self._browser_type == 'webkit':
-            browser = await self._playwright.webkit.launch(**self._browser_options)
-        else:
-            raise ValueError(f'Invalid browser type: {self._browser_type}')
+        if self._browser_type not in ('chromium', 'firefox', 'webkit'):
+            raise ValueError(f'Invalid browser type: {self._browser_type}.')
+
+        module = getattr(self._playwright, self._browser_type, None)
+        if module is None:
+            raise ValueError(f'Invalid browser type: {self._browser_type}.')
+
+        # Determine whether to launch browser with persistent context or not
+        launch_fn = 'launch_persistent_context' if 'user_data_dir' in self._browser_options else 'launch'
+        launch = getattr(module, launch_fn, None)
+        if launch is None:
+            raise RuntimeError(f'Playwright {self._browser_type} browser module does not implement {launch_fn}.')
+        browser = await launch(**self._browser_options)
 
         return PlaywrightBrowserController(
             browser,

tests/unit/browsers/test_playwright_browser_plugin_with_profile.py

@@ -0,0 +1,31 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import AsyncGenerator
+
+import pytest
+
+from crawlee.browsers import PlaywrightBrowserPlugin
+
+
+@pytest.fixture()
+async def plugin(tmp_path_factory) -> AsyncGenerator[PlaywrightBrowserPlugin, None]:
+    browser_options = {'user_data_dir': tmp_path_factory.mktemp('data') / 'profile'}
+    async with PlaywrightBrowserPlugin(browser_options=browser_options) as plugin:
+        yield plugin
+
+
+async def test_new_browser(plugin: PlaywrightBrowserPlugin, httpbin: str) -> None:
+    browser_controller = await plugin.new_browser()
+
+    # assert browser_controller.is_browser_connected
+
+    page = await browser_controller.new_page()
+    await page.goto(f'{httpbin}')
+
+    await page.close()
+    await browser_controller.close()
+
+    # assert not browser_controller.is_browser_connected
+    # check if profile directory does contain some files
+    assert any(Path(plugin.browser_options.get('user_data_dir')).iterdir())