{"uid":"cap_Bj1usfx9jHtyGP41pzP3O","slug":"agent-hub-web-page-structured-data-extractor-2982bf8f","name":"Agent Hub Web Page Structured 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://agents.torbrooknews.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":"0.03","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":"$0.03/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_MI6UZDS-izyrRHuE4UKVp","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.03","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Renders any web page in 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 5 story titles, their URLs, and point counts as structured JSON?","exampleUseCases":[{"title":"E-commerce product data extraction","prompt":"Go to https://www.amazon.com/dp/B09X7CRKRX and extract the product name, current price, star rating, and number of reviews as structured JSON."},{"title":"News article metadata scraping","prompt":"Extract the headline, author name, publication date, and article summary from this page: https://www.theguardian.com/technology/2024/jan/15/ai-regulation — return it as structured JSON."},{"title":"Job listing field extraction","prompt":"Scrape this job posting at https://jobs.lever.co/openai/software-engineer and pull out the job title, location, salary range, and required skills as a JSON object."}],"resultDescription":"A structured JSON object whose fields correspond to the schema or prompt provided. Each requested field is populated with the value found on the rendered web page, or null if not found. The response reflects the LLM's best extraction from the fully rendered DOM.","failureModes":["URL is inaccessible, behind a login wall, or returns non-200 — extraction may fail or return empty fields","Page uses heavy anti-bot measures (Cloudflare, CAPTCHA) — headless browser may be blocked","Schema or prompt is ambiguous — LLM may misinterpret field intent and return incorrect values","Dynamic content loaded after initial render may not be captured depending on render timing","Malformed JSON schema input causes a parsing error and the call fails","Rate limiting or network timeout on the target page leads to empty or partial results"],"whenToPreferThis":"Choose this endpoint when you need to extract structured, typed data from a live web page rather than raw HTML or plain text. It is particularly valuable when the page is JavaScript-rendered (React, Vue, etc.) since it uses a headless browser, and when you want LLM-assisted field mapping rather than writing CSS selectors manually. Prefer it over a CSS-selector scraper when you don't know the exact DOM structure in advance, or when a plain-English description of the fields is more practical than a hand-crafted selector list.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-13T12:46:04.708Z","isFirstParty":false,"canonicalSlug":"agent-hub-web-page-structured-data-extractor-2982bf8f"}