{"uid":"cap_O9FR7TgYoeGyBx9NkxgoB","slug":"x402-deployer-x402-deployer-workers-dev-fc17f02d","name":"x402-deployer Web Scraper","description":"Scrape any webpage. 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 / clean markdown. Optional link extraction. Cheerio-based, no headless browser — fast and cheap, ideal for static pages and SSR sites. For JS-heavy SPAs that need a real browser, see website-screenshot.","url":"https://x402-deployer.x402-deployer.workers.dev/scrape-website","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"required":["url"],"properties":{"url":{"type":"string","description":"Public URL to fetch and parse. Must include scheme (http/https). Follows redirects."},"format":{"enum":["text","html","markdown"],"type":"string","description":"Body output format. 'text' (default, plain text), 'html' (raw HTML body), or 'markdown' (clean markdown — best for LLM ingestion)."},"user_agent":{"type":"string","description":"Custom User-Agent header. Defaults to a modern desktop Chrome UA."},"include_links":{"type":"boolean","description":"If true, also returns an array of all <a href> links found on the page. Default false."}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"h1":{"type":"string"},"og":{"type":"object","properties":{}},"url":{"type":"string"},"lang":{"type":"string"},"text":{"type":"string"},"title":{"type":"string"},"format":{"type":"string"},"twitter":{"type":"object","properties":{}},"canonical":{"type":"null"},"final_url":{"type":"string"},"body_chars":{"type":"integer"},"description":{"type":"string"},"status_code":{"type":"integer"}}}}}}},"responseSchema":null,"example":{"request":{"input":{"body":{"url":"https://example.com","format":"markdown","include_links":true},"type":"http","method":"POST","bodyType":"json"}},"response":{"h1":"Example Domain","og":{},"url":"https://example.com","lang":"en","links":[{"href":"https://iana.org/domains/example","text":"Learn more"}],"title":"Example Domain","format":"markdown","twitter":{},"markdown":"# Example Domain\n\nThis domain is for use in documentation examples without needing permission. Avoid use in operations.\n\nLearn more","canonical":null,"final_url":"https://example.com/","body_chars":131,"description":"","status_code":200}},"exampleRequest":{"url":"https://example.com","format":"markdown","include_links":true},"tags":["x402"],"displayCostAmount":"0.04","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","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":"$0.04/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.04","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.04","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_ws-dL2u8534NQhRwnS6mY","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.04","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Scrapes a webpage and returns its title, description, metadata, headings, body content, and outbound links using Cheerio (no headless browser)","exampleAgentPrompt":"Scrape https://example.com/blog/post-1 for me and return the page title, meta description, OpenGraph tags, all headings, and the body content as clean markdown, with outbound links included.","exampleUseCases":null,"resultDescription":"Returns structured data including the page title, meta description, canonical URL, OpenGraph and Twitter card metadata, an array of headings, the body rendered as text/HTML/markdown (depending on requested format), and a list of outbound links found on the page.","failureModes":["URL is unreachable or returns non-200 status — error response with HTTP status code","JS-heavy SPA with client-side rendering — content may be empty or incomplete since no headless browser is used","Malformed or non-HTTP URL — validation error","Rate limiting or bot protection on target site — may return partial or blocked content","Very large pages may time out on the Cloudflare Worker execution limit"],"whenToPreferThis":"Use this endpoint for static pages, server-side rendered sites, and any page where content is present in the raw HTML response. It is fast and cost-effective at $0.04/call. Avoid it for JavaScript-heavy single-page applications that require a real browser to render content — use a headless browser screenshot service instead.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T06:52:17.877Z","isFirstParty":false}