crawlee 1.0.5b1__tar.gz → 1.0.5b2__tar.gz

{crawlee-1.0.5b1 → crawlee-1.0.5b2}/.gitignore

@@ -30,6 +30,7 @@ htmlcov
 # IDE, editors
 .vscode
 .idea
+*~
 .DS_Store
 .nvim.lua
 Session.vim

{crawlee-1.0.5b1 → crawlee-1.0.5b2}/CHANGELOG.md

@@ -5,6 +5,10 @@ All notable changes to this project will be documented in this file.
 <!-- git-cliff-unreleased-start -->
 ## 1.0.5 - **not yet released**
 
+### 🚀 Features
+
+- Add `chrome` `BrowserType` for `PlaywrightCrawler` to use the Chrome browser ([#1487](https://github.com/apify/crawlee-python/pull/1487)) ([b06937b](https://github.com/apify/crawlee-python/commit/b06937bbc3afe3c936b554bfc503365c1b2c526b)) by [@Mantisus](https://github.com/Mantisus), closes [#1071](https://github.com/apify/crawlee-python/issues/1071)
+
 
 <!-- git-cliff-unreleased-end -->
 ## [1.0.4](https://github.com/apify/crawlee-python/releases/tag/v1.0.4) (2025-10-24)

{crawlee-1.0.5b1 → crawlee-1.0.5b2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: crawlee
-Version: 1.0.5b1
+Version: 1.0.5b2
 Summary: Crawlee for Python
 Project-URL: Apify Homepage, https://apify.com
 Project-URL: Changelog, https://crawlee.dev/python/docs/changelog

{crawlee-1.0.5b1 → crawlee-1.0.5b2}/docs/examples/code_examples/using_browser_profiles_chrome.py

@@ -27,15 +27,13 @@ async def main() -> None:
 
         crawler = PlaywrightCrawler(
             headless=False,
-            # Use chromium for Chrome compatibility
-            browser_type='chromium',
+            # Use the installed Chrome browser
+            browser_type='chrome',
             # Disable fingerprints to preserve profile identity
             fingerprint_generator=None,
             # Set user data directory to temp folder
             user_data_dir=tmp_profile_dir,
             browser_launch_options={
-                # Use installed Chrome browser
-                'channel': 'chrome',
                 # Slow down actions to mimic human behavior
                 'slow_mo': 200,
                 'args': [

{crawlee-1.0.5b1 → crawlee-1.0.5b2}/docs/examples/using_browser_profile.mdx

@@ -18,8 +18,6 @@ Using browser profiles allows you to leverage existing login sessions, saved pas
 
 To run <ApiLink to="class/PlaywrightCrawler">`PlaywrightCrawler`</ApiLink> with your Chrome profile, you need to know the path to your profile files. You can find this information by entering `chrome://version/` as a URL in your Chrome browser. If you have multiple profiles, pay attention to the profile name - if you only have one profile, it's always `Default`.
 
-You also need to use the [`channel`](https://playwright.dev/python/docs/api/class-browsertype#browser-type-launch-option-channel) parameter in `browser_launch_options` to use the Chrome browser installed on your system instead of Playwright's Chromium.
-
 :::warning Profile access limitation
 Due to [Chrome's security policies](https://developer.chrome.com/blog/remote-debugging-port), automation cannot use your main browsing profile directly. The example copies your profile to a temporary location as a workaround.
 :::

{crawlee-1.0.5b1 → crawlee-1.0.5b2}/docs/guides/avoid_blocking.mdx

@@ -25,7 +25,7 @@ Changing browser fingerprints can be a tedious job. Luckily, Crawlee provides th
     {PlaywrightDefaultFingerprintGenerator}
 </RunnableCodeBlock>
 
-In certain cases we want to narrow down the fingerprints used - e.g. specify a certain operating system, locale or browser. This is also possible with Crawlee - the crawler can have the generation algorithm customized to reflect the particular browser version and many more. For description of fingerprint generation options please see <ApiLink to="class/HeaderGeneratorOptions">`HeaderGeneratorOptions`</ApiLink>, <ApiLink to="class/ScreenOptions">`ScreenOptions`</ApiLink> and <ApiLink to="class/BrowserforgeFingerprintGenerator#__init__">`DefaultFingerprintGenerator.__init__`</ApiLink>  See the example bellow:
+In certain cases we want to narrow down the fingerprints used - e.g. specify a certain operating system, locale or browser. This is also possible with Crawlee - the crawler can have the generation algorithm customized to reflect the particular browser version and many more. For description of fingerprint generation options please see <ApiLink to="class/HeaderGeneratorOptions">`HeaderGeneratorOptions`</ApiLink>, <ApiLink to="class/ScreenOptions">`ScreenOptions`</ApiLink> and <ApiLink to="class/BrowserforgeFingerprintGenerator#__init__">`DefaultFingerprintGenerator.__init__`</ApiLink>  See the example below:
 
 <CodeBlock className="language-python">
     {PlaywrightDefaultFingerprintGeneratorWithArgs}

{crawlee-1.0.5b1 → crawlee-1.0.5b2}/docs/introduction/09_running_in_cloud.mdx

@@ -50,7 +50,7 @@ apify login
 
 Now that you have your account set up, you will need to adjust the code a tiny bit. We will use the [Apify SDK](https://docs.apify.com/sdk/python/), which will help us to wire the Crawlee storages (like the [`RequestQueue`](https://docs.apify.com/sdk/python/reference/class/RequestQueue)) to their Apify platform counterparts - otherwise Crawlee would keep things only in memory.
 
-Open your `src/main.py` file, and wrap everyting in your `main` function with the [`Actor`](https://docs.apify.com/sdk/python/reference/class/Actor) context manager. Your code should look like this:
+Open your `src/main.py` file, and wrap everything in your `main` function with the [`Actor`](https://docs.apify.com/sdk/python/reference/class/Actor) context manager. Your code should look like this:
 
 <CodeBlock className="language-python" title="src/main.py">
     {MainExample}

{crawlee-1.0.5b1 → crawlee-1.0.5b2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "crawlee"
-version = "1.0.5b1"
+version = "1.0.5b2"
 description = "Crawlee for Python"
 authors = [{ name = "Apify Technologies s.r.o.", email = "support@apify.com" }]
 license = { file = "LICENSE" }

{crawlee-1.0.5b1 → crawlee-1.0.5b2}/src/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

{crawlee-1.0.5b1 → crawlee-1.0.5b2}/src/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-1.0.5b1 → crawlee-1.0.5b2}/src/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-1.0.5b1 → crawlee-1.0.5b2}/src/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-1.0.5b1 → crawlee-1.0.5b2}/src/crawlee/crawlers/_playwright/_playwright_crawler.py

@@ -114,7 +114,10 @@ class PlaywrightCrawler(BasicCrawler[PlaywrightCrawlingContext, StatisticsState]
             browser_pool: A `BrowserPool` instance to be used for launching the browsers and getting pages.
             user_data_dir: Path to a user data directory, which stores browser session data like cookies
                 and local storage.
-            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.
                 This option should not be used if `browser_pool` is provided.
             browser_launch_options: Keyword arguments to pass to the browser launch method. These options are provided
                 directly to Playwright's `browser_type.launch` method. For more details, refer to the
@@ -153,7 +156,7 @@ class PlaywrightCrawler(BasicCrawler[PlaywrightCrawlingContext, StatisticsState]
             ):
                 raise ValueError(
                     'You cannot provide `headless`, `browser_type`, `browser_launch_options`, '
-                    '`browser_new_context_options`, `use_incognito_pages`, `user_data_dir`  or'
+                    '`browser_new_context_options`, `use_incognito_pages`, `user_data_dir` or '
                     '`fingerprint_generator` arguments when `browser_pool` is provided.'
                 )
 
@@ -496,7 +499,9 @@ class _PlaywrightCrawlerAdditionalOptions(TypedDict):
     """A `BrowserPool` instance to be used for launching the browsers and getting pages."""
 
     browser_type: NotRequired[BrowserType]
-    """The type of browser to launch ('chromium', 'firefox', or 'webkit').
+    """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.
     This option should not be used if `browser_pool` is provided."""
 
     browser_launch_options: NotRequired[Mapping[str, Any]]

{crawlee-1.0.5b1 → crawlee-1.0.5b2}/src/crawlee/fingerprint_suite/_header_generator.py

@@ -11,9 +11,9 @@ if TYPE_CHECKING:
 
 
 def fingerprint_browser_type_from_playwright_browser_type(
-    playwright_browser_type: Literal['chromium', 'firefox', 'webkit'],
+    playwright_browser_type: Literal['chromium', 'firefox', 'webkit', 'chrome'],
 ) -> SupportedBrowserType:
-    if playwright_browser_type == 'chromium':
+    if playwright_browser_type in {'chromium', 'chrome'}:
         return 'chrome'
     if playwright_browser_type == 'firefox':
         return 'firefox'

{crawlee-1.0.5b1 → crawlee-1.0.5b2}/tests/unit/browsers/test_playwright_browser_plugin.py

@@ -69,3 +69,13 @@ async def test_methods_raise_error_when_not_active() -> None:
 
     async with plugin:
         assert plugin.active is True
+
+
+async def raise_error_if_chrome_and_executable_path() -> None:
+    with pytest.raises(
+        ValueError, match=r'Cannot use `use_chrome` with `Configuration.default_browser_path` or `executable_path` set.'
+    ):
+        PlaywrightBrowserPlugin(
+            browser_type='chrome',
+            browser_launch_options={'executable_path': '/path/to/chrome'},
+        )

{crawlee-1.0.5b1 → crawlee-1.0.5b2}/uv.lock

@@ -705,7 +705,7 @@ toml = [
 
 [[package]]
 name = "crawlee"
-version = "1.0.5b1"
+version = "1.0.5b2"
 source = { editable = "." }
 dependencies = [
     { name = "cachetools" },