{"uid":"cap_hAHU0XIVQPidV_88YO7B4","slug":"x402-deployer-x402-deployer-workers-dev-56f71c1a","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. Alias of scrape-website. For JS-heavy SPAs that need a real browser, see website-screenshot.","url":"https://x402-deployer.x402-deployer.workers.dev/scrape","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), 'html' (raw), or 'markdown' (clean — 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 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_MCvA_wHfgzNKfTl0bDhKm","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, links, and body content as text, HTML, or markdown using Cheerio (no headless browser).","exampleAgentPrompt":"Scrape https://example.com/blog/my-article for me and give me the title, meta description, OpenGraph tags, all headings, and the body content as clean markdown, plus any outbound links.","exampleUseCases":null,"resultDescription":"Returns structured data including page title, meta description, canonical URL, OpenGraph and Twitter card metadata, heading hierarchy, outbound links, and body content in the requested format (plain text, raw HTML, or clean markdown).","failureModes":["URL is unreachable or returns non-200 status — error response with HTTP status code","JavaScript-heavy SPA content not rendered — returns empty or partial content since no headless browser is used","Invalid or malformed URL input — validation error returned","Rate limiting or bot-blocking by target site — may return incomplete or blocked response","Timeout on slow-loading pages — partial or error response"],"whenToPreferThis":"Use this endpoint when you need fast, cheap extraction of metadata and content from static or SSR-rendered pages. Prefer this over a headless browser solution (like website-screenshot) when you don't need JavaScript execution — it's significantly faster and more cost-effective. Best for SEO metadata extraction, content summarization pipelines, link analysis, and markdown conversion of standard HTML pages.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":1,"lastUsedAt":"2026-05-21T16:06:21.796Z","lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T04:29:19.208Z","isFirstParty":false}