Extracts structured data from web pages by initiating an extraction job and polling for completion; requires a natural language `prompt` or a JSON `schema` (one must be provided).
urlsRequiredarrayA list of URLs from which to extract data (maximum 10 URLs while in beta). Wildcards (e.g., `https://example.com/blog/*`) can be used for crawling multiple pages under a specific path. Note: You can also pass a single URL as 'url' (singular) which will be automatically converted…
promptstringNatural language query for information to extract from URL content. E.g., 'Extract the company mission, whether it supports SSO, etc.'. At least one of 'prompt' or 'schema' must be provided.
schemaobjectJSON object (dictionary) defining the desired structure for extracted data. Must be a valid JSON Schema object with properties and types. At least one of 'prompt' or 'schema' must be provided.
showSourcesbooleanWhen true, the sources used to extract the data will be included in the response as `sources` key.
ignoreSitemapbooleanBypasses sitemap.xml during scanning.
scrapeOptionsobjectAdvanced scraping configuration.
enableWebSearchbooleanIf `True`, allows crawling links outside initial domains in `urls`; if `False`, restricts to same domains.
ignoreInvalidURLsbooleanProceeds with valid URLs, returning invalid ones separately.
includeSubdomainsbooleanExtends scanning to subdomains.
dataRequiredData from the action execution
errorstringError if any occurred during the execution of the action
successfulRequiredbooleanWhether or not the action execution was successful or not
Aident-managed access. Risk level 2 of 5.
$0.01 / call
No published Skills explicitly reference this Action yet.