{"uid":"cap_LI3lp7Hb7RujL0rjYBiip","slug":"agentrxi-web-page-data-extractor-4adb5402","name":"AgentRXI Web Page Data Extractor","description":"Extract structured JSON from any web page. Give a URL plus a JSON schema or a plain-English prompt describing the fields you want; a headless browser renders the page and an LLM fills the schema. Also callable as GET with the same fields as query parameters.","url":"https://agentrxi.com/v1/extract?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string"},"prompt":{"type":"string","description":"Alternative to schema: describe what to extract"},"schema":{"type":"string","description":"JSON schema of the fields to extract; JSON"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.009","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.009/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.009","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.009","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Lq-VLOR3mijkb_QWaQ8bu","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.009","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Renders any public URL with a headless browser and uses an LLM to extract structured JSON fields defined by a schema or plain-English prompt.","exampleAgentPrompt":"Can you go to https://news.ycombinator.com and extract the top 10 story titles and their URLs as structured JSON? Use a schema with fields 'title' and 'url'.","exampleUseCases":[{"title":"Product price and detail extraction","prompt":"Go to https://www.bestbuy.com/site/apple-macbook-air/6578584.p and extract the product name, current price, availability status, and rating as structured JSON."},{"title":"Job listing scraper for recruiting","prompt":"Scrape this job listing page at https://jobs.lever.co/acme/senior-engineer and pull out the job title, location, salary range, required skills, and application deadline."},{"title":"News article metadata extraction","prompt":"Extract the headline, author name, publication date, and article summary from https://techcrunch.com/2024/05/01/openai-launches-new-model — return it as structured JSON."}],"resultDescription":"A structured JSON object whose keys match the provided schema or plain-English prompt fields, populated with values extracted from the rendered web page. If a field is not found, it may be null or absent. The response reflects the fully rendered DOM, including JavaScript-generated content.","failureModes":["URL is behind a login wall or CAPTCHA — returns empty or partial fields","Schema fields don't match any content on the page — returns nulls","Dynamic content that loads only after user interaction (infinite scroll, click events) may not be captured","Malformed or unparseable JSON schema input — returns an error","Rate-limiting or blocking by the target site — may return incomplete data","Invalid or unreachable URL — returns an HTTP error"],"whenToPreferThis":"Choose this endpoint when you need structured JSON from a real website, especially pages that use JavaScript rendering (SPAs, React, Vue) where simple HTTP fetch-and-parse fails. It is ideal when you have a clear schema of fields to extract or can describe them in plain English. Prefer it over raw HTML fetchers when you need LLM interpretation to map messy page content into clean structured data.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-15T06:39:06.757Z","isFirstParty":false,"canonicalSlug":"agentrxi-web-page-data-extractor-4adb5402"}