{"uid":"cap_c0WKPdh4zoogpqPy8JscD","slug":"agent-data-tools-web-page-text-extraction-66158d38","name":"Agent Data Tools – Web Page Text Extraction","description":"Pay-per-call tools for AI agents: web page text extraction and summaries, screenshots, image generation, speech-to-text, image description, domain and email-auth intelligence, and live Base token and wallet lookups. No account or API key; pay per request in USDC on Base via x402.","url":"https://agent-data-tools.revmesh2074.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","description":"Absolute http(s) URL of the page to fetch"},"maxChars":{"type":"integer","description":"Maximum characters of body text to return (500-100000, default 20000)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"url":"https://example.com/","lang":"en","text":"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,"finalUrl":"https://example.com/","headings":[],"truncated":false,"textLength":156,"description":null}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","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":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_jK822CbamgLAhXMBpD4ZF","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a web page and returns its cleaned body text, title, headings, links, language, and metadata for AI agent consumption.","exampleAgentPrompt":"Can you fetch the text content of https://openai.com/blog and give me the title, headings, and first 5000 characters of the body text?","exampleUseCases":[{"title":"Research article content from URL","prompt":"Pull the full readable text from this article URL https://techcrunch.com/2024/01/15/some-article and give me a summary of what it says."},{"title":"Competitor website content scan","prompt":"Fetch the text from https://www.competitor.com/pricing and tell me what pricing plans they mention — limit to the first 10000 characters."},{"title":"Agent fact-checking from source URL","prompt":"Go to https://en.wikipedia.org/wiki/Artificial_intelligence and extract the text so I can verify a claim I read — grab up to 20000 characters."}],"resultDescription":"Returns a JSON object containing: the resolved final URL, HTTP status code, page title, detected language, meta description, cleaned body text (up to maxChars), headings array, links array, total text length, and a truncated flag indicating whether the text was cut off.","failureModes":["Non-HTTP/HTTPS URL or malformed URL returns an error","Target page returns a non-200 HTTP status (e.g. 404, 403) — status is reported but text may be empty","JavaScript-heavy single-page apps may return little or no text if the page requires JS rendering","Payment failure or insufficient USDC balance results in 402 rejection before the request is processed","maxChars out of range (below 500 or above 100000) may be rejected or clamped"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read the human-readable text of any public web page without setting up API keys or accounts — paying only $0.002 USDC per call via x402 on Base. It is ideal for one-off page reads, fact-checking, content summarization, or competitive research where you need clean structured metadata (title, headings, links, language) alongside body text. Prefer this over full browser automation tools when you need lightweight text extraction rather than screenshots or JavaScript-rendered DOM interaction.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-11T12:30:08.657Z","isFirstParty":false,"canonicalSlug":"agent-data-tools-web-page-text-extraction-66158d38"}