diff --git a/scrapling/core/ai.py b/scrapling/core/ai.py index 794f9a7..4d5929b 100644 --- a/scrapling/core/ai.py +++ b/scrapling/core/ai.py @@ -242,9 +242,8 @@ class ScraplingMCPServer: :param css_selector: CSS selector to extract the content from the page. If main_content_only is True, then it will be executed on the main content of the page. Defaults to None. :param main_content_only: Whether to extract only the main content of the page. Defaults to True. The main content here is the data inside the `` tag. :param headless: Run the browser in headless/hidden (default), or headful/visible mode. - :param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. + :param disable_resources: Drop requests for unnecessary resources for a speed boost. Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. :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 cookies: Set cookies for the next request. It should be in a dictionary format that Playwright accepts. :param network_idle: Wait for the page until there are no network connections for at least 500 ms. @@ -325,9 +324,8 @@ class ScraplingMCPServer: :param css_selector: CSS selector to extract the content from the page. If main_content_only is True, then it will be executed on the main content of the page. Defaults to None. :param main_content_only: Whether to extract only the main content of the page. Defaults to True. The main content here is the data inside the `` tag. :param headless: Run the browser in headless/hidden (default), or headful/visible mode. - :param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. + :param disable_resources: Drop requests for unnecessary resources for a speed boost. Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. :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 cookies: Set cookies for the next request. It should be in a dictionary format that Playwright accepts. :param network_idle: Wait for the page until there are no network connections for at least 500 ms. @@ -418,9 +416,8 @@ class ScraplingMCPServer: :param css_selector: CSS selector to extract the content from the page. If main_content_only is True, then it will be executed on the main content of the page. Defaults to None. :param main_content_only: Whether to extract only the main content of the page. Defaults to True. The main content here is the data inside the `` tag. :param headless: Run the browser in headless/hidden (default), or headful/visible mode. - :param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. + :param disable_resources: Drop requests for unnecessary resources for a speed boost. Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. :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 cookies: Set cookies for the next request. :param solve_cloudflare: Solves all types of the Cloudflare's Turnstile/Interstitial challenges before returning the response to you. @@ -516,9 +513,8 @@ class ScraplingMCPServer: :param css_selector: CSS selector to extract the content from the page. If main_content_only is True, then it will be executed on the main content of the page. Defaults to None. :param main_content_only: Whether to extract only the main content of the page. Defaults to True. The main content here is the data inside the `` tag. :param headless: Run the browser in headless/hidden (default), or headful/visible mode. - :param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. + :param disable_resources: Drop requests for unnecessary resources for a speed boost. Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. :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 cookies: Set cookies for the next request. :param solve_cloudflare: Solves all types of the Cloudflare's Turnstile/Interstitial challenges before returning the response to you. diff --git a/scrapling/engines/_browsers/_controllers.py b/scrapling/engines/_browsers/_controllers.py index 4474a45..1682dcf 100644 --- a/scrapling/engines/_browsers/_controllers.py +++ b/scrapling/engines/_browsers/_controllers.py @@ -38,9 +38,8 @@ class DynamicSession(SyncSession, DynamicSessionMixin): """A Browser session manager with page pooling, it's using a persistent browser Context by default with a temporary user profile directory. :param headless: Run the browser in headless/hidden (default), or headful/visible mode. - :param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. + :param disable_resources: Drop requests for unnecessary resources for a speed boost. Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. :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 cookies: Set cookies for the next request. :param network_idle: Wait for the page until there are no network connections for at least 500 ms. @@ -99,9 +98,8 @@ class DynamicSession(SyncSession, DynamicSessionMixin): - wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object. - page_action: Added for automation. A function that takes the `page` object and does the automation you need. - extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._ - - disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. + - disable_resources: Drop requests for unnecessary resources for a speed boost. Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. - wait_selector: Wait for a specific CSS selector to be in a specific state. - wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`. - network_idle: Wait for the page until there are no network connections for at least 500 ms. @@ -170,9 +168,8 @@ class AsyncDynamicSession(AsyncSession, DynamicSessionMixin): """A Browser session manager with page pooling :param headless: Run the browser in headless/hidden (default), or headful/visible mode. - :param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. + :param disable_resources: Drop requests for unnecessary resources for a speed boost. Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. :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 cookies: Set cookies for the next request. :param network_idle: Wait for the page until there are no network connections for at least 500 ms. @@ -234,9 +231,8 @@ class AsyncDynamicSession(AsyncSession, DynamicSessionMixin): - wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object. - page_action: Added for automation. A function that takes the `page` object and does the automation you need. - extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._ - - disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. + - disable_resources: Drop requests for unnecessary resources for a speed boost. Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. - wait_selector: Wait for a specific CSS selector to be in a specific state. - wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`. - network_idle: Wait for the page until there are no network connections for at least 500 ms. diff --git a/scrapling/engines/_browsers/_stealth.py b/scrapling/engines/_browsers/_stealth.py index 482ae4c..0a4c912 100644 --- a/scrapling/engines/_browsers/_stealth.py +++ b/scrapling/engines/_browsers/_stealth.py @@ -46,9 +46,8 @@ class StealthySession(SyncSession, StealthySessionMixin): """A Browser session manager with page pooling, it's using a persistent browser Context by default with a temporary user profile directory. :param headless: Run the browser in headless/hidden (default), or headful/visible mode. - :param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. + :param disable_resources: Drop requests for unnecessary resources for a speed boost. Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. :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 cookies: Set cookies for the next request. :param network_idle: Wait for the page until there are no network connections for at least 500 ms. @@ -182,9 +181,8 @@ class StealthySession(SyncSession, StealthySessionMixin): - wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object. - page_action: Added for automation. A function that takes the `page` object and does the automation you need. - extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._ - - disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. + - disable_resources: Drop requests for unnecessary resources for a speed boost. Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. - wait_selector: Wait for a specific CSS selector to be in a specific state. - wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`. - network_idle: Wait for the page until there are no network connections for at least 500 ms. @@ -259,9 +257,8 @@ class AsyncStealthySession(AsyncSession, StealthySessionMixin): """A Browser session manager with page pooling, it's using a persistent browser Context by default with a temporary user profile directory. :param headless: Run the browser in headless/hidden (default), or headful/visible mode. - :param disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. + :param disable_resources: Drop requests for unnecessary resources for a speed boost. Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. :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 cookies: Set cookies for the next request. :param network_idle: Wait for the page until there are no network connections for at least 500 ms. @@ -397,9 +394,8 @@ class AsyncStealthySession(AsyncSession, StealthySessionMixin): - wait: The time (milliseconds) the fetcher will wait after everything finishes before closing the page and returning the ` Response ` object. - page_action: Added for automation. A function that takes the `page` object and does the automation you need. - extra_headers: A dictionary of extra headers to add to the request. _The referer set by the `google_search` argument takes priority over the referer set here if used together._ - - disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. + - disable_resources: Drop requests for unnecessary resources for a speed boost. Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. - wait_selector: Wait for a specific CSS selector to be in a specific state. - wait_selector_state: The state to wait for the selector given with `wait_selector`. The default state is `attached`. - network_idle: Wait for the page until there are no network connections for at least 500 ms. diff --git a/scrapling/fetchers/stealth_chrome.py b/scrapling/fetchers/stealth_chrome.py index 3567388..64511a2 100644 --- a/scrapling/fetchers/stealth_chrome.py +++ b/scrapling/fetchers/stealth_chrome.py @@ -18,9 +18,8 @@ class StealthyFetcher(BaseFetcher): :param url: Target url. :param kwargs: Browser session configuration options including: - headless: Run the browser in headless/hidden (default), or headful/visible mode. - - disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. + - disable_resources: Drop requests for unnecessary resources for a speed boost. Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. - useragent: Pass a useragent string to be used. Otherwise the fetcher will generate a real Useragent of the same browser and use it. - cookies: Set cookies for the next request. - network_idle: Wait for the page until there are no network connections for at least 500 ms. @@ -68,9 +67,8 @@ class StealthyFetcher(BaseFetcher): :param url: Target url. :param kwargs: Browser session configuration options including: - headless: Run the browser in headless/hidden (default), or headful/visible mode. - - disable_resources: Drop requests of unnecessary resources for a speed boost. It depends, but it made requests ~25% faster in my tests for some websites. + - disable_resources: Drop requests for unnecessary resources for a speed boost. Requests dropped are of type `font`, `image`, `media`, `beacon`, `object`, `imageset`, `texttrack`, `websocket`, `csp_report`, and `stylesheet`. - This can help save your proxy usage but be careful with this option as it makes some websites never finish loading. - useragent: Pass a useragent string to be used. Otherwise the fetcher will generate a real Useragent of the same browser and use it. - cookies: Set cookies for the next request. - network_idle: Wait for the page until there are no network connections for at least 500 ms.