pub struct OnPageApiTaskPost {Show 43 fields
pub target: String,
pub max_crawl_pages: i32,
pub start_url: Option<String>,
pub force_sitewide_checks: Option<bool>,
pub priority_urls: Option<Vec<String>>,
pub max_crawl_depth: Option<i32>,
pub crawl_delay: Option<i32>,
pub store_raw_html: Option<bool>,
pub enable_content_parsing: Option<bool>,
pub support_cookies: Option<bool>,
pub accept_language: Option<String>,
pub custom_robots_txt: Option<String>,
pub robots_txt_merge_mode: Option<String>,
pub custom_user_agent: Option<String>,
pub browser_preset: Option<String>,
pub browser_screen_width: Option<i32>,
pub browser_screen_height: Option<i32>,
pub browser_screen_scale_factor: Option<f64>,
pub respect_sitemap: Option<bool>,
pub custom_sitemap: Option<String>,
pub crawl_sitemap_only: Option<bool>,
pub load_resources: Option<bool>,
pub enable_www_redirect_check: Option<bool>,
pub enable_javascript: Option<bool>,
pub enable_xhr: Option<bool>,
pub enable_browser_rendering: Option<bool>,
pub disable_cookie_popup: Option<bool>,
pub custom_js: Option<String>,
pub validate_micromarkup: Option<bool>,
pub allow_subdomains: Option<bool>,
pub allowed_subdomains: Option<Vec<String>>,
pub disallowed_subdomains: Option<Vec<String>>,
pub check_spell: Option<bool>,
pub check_spell_language: Option<String>,
pub check_spell_exceptions: Option<Vec<String>>,
pub calculate_keyword_density: Option<bool>,
pub checks_threshold: Option<Value>,
pub disable_sitewide_checks: Option<Vec<String>>,
pub disable_page_checks: Option<Vec<String>>,
pub switch_pool: Option<bool>,
pub return_despite_timeout: Option<bool>,
pub tag: Option<String>,
pub pingback_url: Option<String>,
}Expand description
Request for OnPageApi::task_post.
See https://docs.dataforseo.com/v3/on_page/task_post/.
Fields§
§target: StringDomain to crawl, without protocol or www (e.g. “example.com”).
max_crawl_pages: i32Maximum number of pages to crawl.
start_url: Option<String>First URL to crawl; defaults to the domain’s home page.
force_sitewide_checks: Option<bool>Run sitewide checks even when only a single page is crawled.
priority_urls: Option<Vec<String>>URLs to crawl before the rest of the site (max 20).
max_crawl_depth: Option<i32>Maximum crawl depth, counted in clicks from the start page.
crawl_delay: Option<i32>Delay between page requests, in milliseconds.
store_raw_html: Option<bool>Store the raw HTML of crawled pages for later retrieval.
enable_content_parsing: Option<bool>Parse page content so it can be retrieved via the content endpoints.
Accept cookies while crawling.
accept_language: Option<String>Value of the Accept-Language header sent while crawling.
custom_robots_txt: Option<String>Custom robots.txt content to apply during the crawl.
robots_txt_merge_mode: Option<String>How custom robots.txt combines with the site’s: “merge” or “override”.
custom_user_agent: Option<String>Custom User-Agent header sent while crawling.
browser_preset: Option<String>Device preset for rendering: “desktop”, “mobile”, or “tablet”.
browser_screen_width: Option<i32>Viewport width used for rendering, in pixels.
browser_screen_height: Option<i32>Viewport height used for rendering, in pixels.
browser_screen_scale_factor: Option<f64>Device pixel ratio used for rendering.
respect_sitemap: Option<bool>Crawl following the site’s XML sitemap.
custom_sitemap: Option<String>URL of a custom sitemap to crawl.
crawl_sitemap_only: Option<bool>Restrict the crawl to URLs listed in the sitemap.
load_resources: Option<bool>Load page resources (images, scripts, stylesheets) while crawling.
enable_www_redirect_check: Option<bool>Check whether the www and non-www versions redirect consistently.
enable_javascript: Option<bool>Execute page JavaScript while crawling (incurs extra cost).
enable_xhr: Option<bool>Allow XMLHttpRequest calls while rendering the page.
enable_browser_rendering: Option<bool>Emulate full browser rendering to measure Core Web Vitals.
Hide cookie-consent popups before capturing the page.
custom_js: Option<String>Custom JavaScript to execute on each crawled page.
validate_micromarkup: Option<bool>Validate structured microdata markup on crawled pages.
allow_subdomains: Option<bool>Crawl subdomains of the target domain.
allowed_subdomains: Option<Vec<String>>Subdomains to crawl (used when subdomains are otherwise excluded).
disallowed_subdomains: Option<Vec<String>>Subdomains to exclude from the crawl.
check_spell: Option<bool>Check spelling on crawled pages using the Hunspell library.
check_spell_language: Option<String>Hunspell language code used for spell checking.
check_spell_exceptions: Option<Vec<String>>Words to ignore during spell checking (max 1000).
calculate_keyword_density: Option<bool>Compute keyword density for crawled pages.
checks_threshold: Option<Value>Custom threshold values for the checks in OnPage responses.
disable_sitewide_checks: Option<Vec<String>>Sitewide checks to skip during the crawl.
disable_page_checks: Option<Vec<String>>Per-page checks to skip during the crawl.
switch_pool: Option<bool>Retry using a different proxy pool if the first attempt fails.
return_despite_timeout: Option<bool>Return partial results even if the crawl times out.
tag: Option<String>User-defined task identifier (max 255 characters).
pingback_url: Option<String>URL notified by GET when the task completes.