{"uid":"cap_sDDKy3kDAlf6Dy3YiLWES","slug":"mat-web-data-toolkit-web-page-extractor-2671ffd0","name":"Mat Web & Data Toolkit – Web Page Extractor","description":"Fetches a public web page and returns its title, meta description, outbound links and readable plain text as JSON.","url":"https://automatom.matt-d59.workers.dev/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"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"url":"https://example.com/","text":"Example Domain This domain is for use in documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes.","links":[],"title":"Example Domain","status":200,"description":""}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_OreRKS869-1BGef7RFgN6","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a public web page by URL and returns its title, meta description, outbound links, and readable plain text as structured JSON.","exampleAgentPrompt":"Can you fetch the webpage at https://blog.example.com/ai-trends and pull out the title, meta description, all outbound links, and the readable text so I can read through it?","exampleUseCases":[{"title":"Research article content extraction","prompt":"Grab the full readable text and title from this news article at https://techcrunch.com/2024/01/15/openai-update/ so I can summarize what it covers."},{"title":"SEO metadata audit for a page","prompt":"Pull the title and meta description from https://mycompany.com/landing-page so I can check whether our SEO tags are set correctly."},{"title":"Link discovery from a resource page","prompt":"Fetch https://awesome-lists.github.io/resources and give me all the outbound links listed on that page so I can follow up on the references."}],"resultDescription":"A JSON object containing: the original URL, HTTP status code, page title, meta description string, an array of outbound link URLs found on the page, and the full readable plain-text content stripped of HTML markup.","failureModes":["Non-public or paywalled pages may return incomplete or empty text content","Pages with JavaScript-rendered content may not be fully extracted since the fetcher likely doesn't execute JS","Invalid or malformed URLs will result in an error response","Pages that block bots via robots.txt or rate limiting may return a non-200 status","Very large pages may be truncated or time out"],"whenToPreferThis":"Choose this endpoint when you need a quick, structured extraction of public web page content including title, meta description, links, and plain text in a single JSON response. It is ideal for lightweight web research, SEO checks, and link discovery tasks without needing a full headless browser. Prefer alternatives if you need JavaScript-rendered content, authenticated pages, or bulk crawling of entire sites.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-18T12:49:21.953Z","isFirstParty":false,"canonicalSlug":"mat-web-data-toolkit-web-page-extractor-2671ffd0"}