{"uid":"cap_uQxK6bqGQ1XrdoSwMyRIn","slug":"agentstools-dev-web-page-extractor-95147e02","name":"agentstools.dev Web Page Extractor","description":"Fetch any public web page and return its main readable content as clean Markdown or plain text plus metadata (title), stripping nav/ads/boilerplate (trafilatura). Optional JS rendering via headless browser for SPAs; markdown or text output. Robots-respecting, public content only — the reader/scraper building block for RAG and agent pipelines.","url":"https://api.agentstools.dev/extract","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","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"Public http(s) URL to extract"},"format":{"enum":["markdown","text"],"type":"string"},"render":{"type":"boolean","description":"Render JS via headless browser"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":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_ktz9XhQZ_K0HhI7dwBOG9","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 public URL and returns the main content as clean markdown or plain text, plus page metadata, using trafilatura.","exampleAgentPrompt":"Fetch https://www.bbc.com/news/science-environment-68887560 and give me the main article text as clean markdown — also render the JavaScript so nothing is missed.","exampleUseCases":null,"resultDescription":"Returns the main readable content of the page as clean markdown or plain text (with boilerplate and navigation stripped), plus page metadata such as title and author, extracted using trafilatura.","failureModes":["URL is not publicly accessible or requires authentication — extraction fails","Page is heavily JavaScript-rendered and render flag not set — content may be incomplete or empty","Invalid or malformed URL provided — returns error","Paywalled content cannot be extracted beyond the preview","trafilatura finds no main content block — returns empty or minimal result","Network timeout if the target URL is slow to respond"],"whenToPreferThis":"Use this endpoint when you need to extract the human-readable main content from a public webpage and want it returned as clean markdown or plain text with metadata, especially when you want JS rendering support. Prefer this over raw HTTP fetchers when you need boilerplate removed and content normalized for downstream LLM consumption.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T01:13:41.674Z","isFirstParty":false}