{"uid":"cap_S3jCtyINVABeAQQyyqdvL","slug":"readclean-clean-readable-webpage-text-extractor-600f942b","name":"Readclean - Clean Readable Webpage Text Extractor","description":"Pay-per-call x402 APIs for AI agents: OpenAI-compatible LLM chat, perp funding and arbitrage spreads, crypto prices, gas, FX, Solana SPL mint audit, token price by contract, x402 delivery-receipt verification, web search, clean page extraction, batch tools and deterministic code-security scanning. USDC on Base or Solana, no signup, no API key, from $0.0001 a call.","url":"https://scanpay-edge.alextaghiashvili.workers.dev/api/v1/readclean?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$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","format":"uri","pattern":"^https://","maxLength":2048,"minLength":8,"description":"Public HTTPS webpage or article URL to extract; no JavaScript rendering"},"format":{"enum":["markdown","text"],"type":"string","default":"markdown","description":"Format of the content field inside the JSON response"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"url":"https://example.com/article","chars":312,"title":"Example","words":51,"format":"markdown","sha256":"9f86d0…","content":"# Example\n\nClean main text...","http_status":200}},"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_GB7Opdjg8zy4rjoUkSqh0","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 URL and returns clean, readable markdown or plain text by stripping boilerplate, navigation, and ads using readability extraction — no LLM, no storage.","exampleAgentPrompt":"Can you grab the main article text from https://www.theverge.com/2024/5/1/example-article and return it as clean markdown, stripping out all the navigation and ads?","exampleUseCases":[{"title":"Research article summarization pipeline","prompt":"Pull the readable content from https://www.wired.com/story/ai-agents-future-work/ and give it to me as clean markdown so I can summarize it — strip out all the nav menus and ads."},{"title":"Podcast show notes from blog post","prompt":"Fetch the main text from this blog post URL https://simonwillison.net/2024/Mar/8/gpt4/ and convert it to clean readable markdown — I want just the article body, no sidebars or footers."},{"title":"Automated newsletter content digest","prompt":"Extract the clean article text from https://techcrunch.com/2024/05/01/openai-gpt5-announcement/ so I can include the key content in our weekly digest — remove all the boilerplate and just give me the readable part."}],"resultDescription":"A JSON object containing: the original URL, extracted clean content as markdown or plain text, article title, word count, character count, content format label, SHA-256 hash of the content, and the HTTP status code of the fetched page.","failureModes":["Page behind a login wall or paywall returns empty or partial content","Dynamic JavaScript-rendered pages may not yield full content since extraction is server-side","Invalid or unreachable URL returns a non-200 HTTP status","Pages with aggressive bot-blocking (e.g. Cloudflare challenges) may fail to fetch","Very large pages may timeout or return truncated content"],"whenToPreferThis":"Choose this endpoint when you need fast, deterministic, non-LLM article extraction from a single URL and want clean markdown output with metadata (title, word count, hash) without storing the page. Prefer it over LLM-based summarization pipelines when you want raw extracted text as input to your own downstream processing, and over full browser automation when you only need the readable text content, not rendered layout or screenshots.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-01T06:56:33.478Z","isFirstParty":false,"canonicalSlug":"readclean-clean-readable-webpage-text-extractor-600f942b"}