🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
Python aiai-scrapingautomationcrawlercrawlingcrawling-pythondatadata-extractionmcpmcp-serverplaywrightpythonscrapingselectorsstealthweb-scraperweb-scrapingweb-scraping-pythonwebscrapingxpath
PlaywrightFetcher - Add the option to set locale of the browser
Karim shoair60d551d83972
diff --git a/README.md b/README.mdindex 3669b3a..de324cb 100644--- a/README.md+++ b/README.md@@ -317,6 +317,7 @@ Add that to a lot of controlling/hiding options as you will see in the arguments| disable_webgl | Disables WebGL and WebGL 2.0 support entirely. | ✔️ || stealth | Enables stealth mode, always check the documentation to see what stealth mode does currently. | ✔️ || real_chrome | If you have chrome browser installed on your device, enable this and the Fetcher will launch an instance of your browser and use it. | ✔️ |+| locale | Set the locale for the browser if wanted. The default value is `en-US`. | ✔️ || cdp_url | Instead of launching a new browser instance, connect to this CDP URL to control real browsers/NSTBrowser through CDP. | ✔️ || nstbrowser_mode | Enables NSTBrowser mode, **it have to be used with `cdp_url` argument or it will get completely ignored.** | ✔️ || nstbrowser_config | The config you want to send with requests to the NSTBrowser. _If left empty, Scrapling defaults to an optimized NSTBrowser's docker browserless config._ | ✔️ |diff --git a/scrapling/engines/pw.py b/scrapling/engines/pw.pyindex 9330094..d4dc5ea 100644--- a/scrapling/engines/pw.py+++ b/scrapling/engines/pw.py@@ -26,6 +26,7 @@ class PlaywrightEngine:timeout: Optional[float] = 30000,page_action: Callable = do_nothing,wait_selector: Optional[str] = None,+ locale: Optional[str] = 'en-US',wait_selector_state: Optional[str] = 'attached',stealth: Optional[bool] = False,real_chrome: Optional[bool] = False,@@ -50,6 +51,7 @@ class PlaywrightEngine::param timeout: The timeout in milliseconds that is used in all operations and waits through the page. The default is 30000:param page_action: Added for automation. A function that takes the `page` object, does the automation you need, then returns `page` again.:param wait_selector: Wait for a specific css selector to be in a specific state.+ :param locale: Set the locale for the browser if wanted. The default value is `en-US`.:param wait_selector_state: The state to wait for the selector given with `wait_selector`. Default state is `attached`.:param stealth: Enables stealth mode, check the documentation to see what stealth mode does currently.:param real_chrome: If you have chrome browser installed on your device, enable this and the Fetcher will launch an instance of your browser and use it.@@ -64,6 +66,7 @@ class PlaywrightEngine::param adaptor_arguments: The arguments that will be passed in the end while creating the final Adaptor's class."""self.headless = headless+ self.locale = check_type_validity(locale, [str], 'en-US', param_name='locale')self.disable_resources = disable_resourcesself.network_idle = bool(network_idle)self.stealth = bool(stealth)@@ -159,7 +162,7 @@ class PlaywrightEngine:# Creating the contextif self.stealth:context = browser.new_context(- locale='en-US',+ locale=self.locale,is_mobile=False,has_touch=False,proxy=self.proxy,@@ -176,6 +179,7 @@ class PlaywrightEngine:)else:context = browser.new_context(+ locale=self.locale,proxy=self.proxy,color_scheme='dark',user_agent=useragent,diff --git a/scrapling/fetchers.py b/scrapling/fetchers.pyindex bc47c8e..1e81ffd 100644--- a/scrapling/fetchers.py+++ b/scrapling/fetchers.py@@ -148,7 +148,7 @@ class PlayWrightFetcher(BaseFetcher):useragent: Optional[str] = None, network_idle: Optional[bool] = False, timeout: Optional[float] = 30000,page_action: Optional[Callable] = do_nothing, wait_selector: Optional[str] = None, wait_selector_state: Optional[str] = 'attached',hide_canvas: Optional[bool] = False, disable_webgl: Optional[bool] = False, extra_headers: Optional[Dict[str, str]] = None, google_search: Optional[bool] = True,- proxy: Optional[Union[str, Dict[str, str]]] = None,+ proxy: Optional[Union[str, Dict[str, str]]] = None, locale: Optional[str] = 'en-US',stealth: Optional[bool] = False, real_chrome: Optional[bool] = False,cdp_url: Optional[str] = None,nstbrowser_mode: Optional[bool] = False, nstbrowser_config: Optional[Dict] = None,@@ -163,6 +163,7 @@ class PlayWrightFetcher(BaseFetcher)::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 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 30000+ :param locale: Set the locale for the browser if wanted. The default value is `en-US`.:param page_action: Added for automation. A function that takes the `page` object, does the automation you need, then returns `page` again.: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`. Default state is `attached`.@@ -180,6 +181,7 @@ class PlayWrightFetcher(BaseFetcher):"""engine = PlaywrightEngine(proxy=proxy,+ locale=locale,timeout=timeout,stealth=stealth,cdp_url=cdp_url,