{"slug":"x402-agentutility-ai-scrape-website-83fc1f","title":"Scrapes any webpage and pulls title, description, canonical URL, OpenGraph + Twi","host":"x402.agentutility.ai","method":"POST","resource":"https://x402.agentutility.ai/scrape-website","category":"search","description":"Scrapes any webpage and pulls title, description, canonical URL, OpenGraph + Twitter card metadata, headings, and outbound links from a single URL. Server-side rendering; body content rendered as text, raw HTML, or clean markdown, with optional link extraction. Cheerio-based with no headless browser","price_listed":0.04,"price_asked":0.04,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":9391,"reported_calls_30d":8,"reported_payers_30d":1,"networks":["eip155:8453","solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"format":"text","url":"https://example.com"},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"format":{"description":"Body output format. 'text' (default, plain text), 'html' (raw HTML body), or 'markdown' (clean markdown — best for LLM ingestion).","enum":["text","html","markdown"],"type":"string"},"include_links":{"description":"If true, also returns an array of all <a href> links found on the page. Default false.","type":"boolean"},"url":{"description":"Public URL to fetch and parse. Must include scheme (http/https). Follows redirects.","type":"string"},"user_agent":{"description":"Custom User-Agent header. Defaults to a modern desktop Chrome UA.","type":"string"}},"required":["url"]},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"body_chars":{"type":"integer"},"canonical":{"type":"null"},"description":{"type":"string"},"final_url":{"type":"string"},"format":{"type":"string"},"h1":{"type":"string"},"lang":{"type":"string"},"og":{"properties":{},"type":"object"},"status_code":{"type":"integer"},"text":{"type":"string"},"title":{"type":"string"},"twitter":{"properties":{},"type":"object"},"url":{"type":"string"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-09-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.04,"price_match":true,"latency_ms":9391,"error":null}],"description_full":"Scrapes any webpage and pulls title, description, canonical URL, OpenGraph + Twitter card metadata, headings, and outbound links from a single URL. Server-side rendering; body content rendered as text, raw HTML, or clean markdown, with optional link extraction. Cheerio-based with no headless browser, so it is fast and cheap, ideal for static pages and SSR sites. For JS-heavy SPAs that need a real browser, see website-screenshot. Use it as a web scraping API or webpage metadata extractor.","last_updated":"2026-09-18T07:03:51.976Z","schemes":["exact"]}