Firecrawl Extract

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).

价格

$0.01 / 次调用

统一支付

支持使用 Aident 美元余额

• urlsarray

  必填
  A 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…
• promptstring
  Natural 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.
• schemaobject
  JSON 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.
• showSourcesboolean
  When true, the sources used to extract the data will be included in the response as `sources` key.
• ignoreSitemapboolean
  Bypasses sitemap.xml during scanning.
• scrapeOptionsobject
  Advanced scraping configuration.
• enableWebSearchboolean
  If `True`, allows crawling links outside initial domains in `urls`; if `False`, restricts to same domains.
• ignoreInvalidURLsboolean
  Proceeds with valid URLs, returning invalid ones separately.
• includeSubdomainsboolean
  Extends scanning to subdomains.

• data

  必填
  Data from the action execution
• errorstring
  Error if any occurred during the execution of the action
• successfulboolean

  必填
  Whether or not the action execution was successful or not

• +2

  快速制作可复用的品牌营销素材包

  先用 Aident Brand Marketing Pack 形成证据、信息架构、文案和制作简报，再用 Aident Brand Visual Production 套用已审模板并返回经检查的媒体，最后在所选的飞书/Lark、Google 或 Notion 工作区组装并核验完整素材包。