{"uid":"cap_Hd0EN4ct1pdMdL-kM37ft","slug":"web-page-content-extractor-x402atlas-d92d6cd7","name":"Web Page Content Extractor (x402atlas)","description":"Read any web page or article: fetch up to 5 URLs in one batch call and extract the main content as clean, LLM-ready markdown or plain text. Convert webpages to markdown, scrape page text, pull article content for RAG ingestion and AI agent context.","url":"https://websearch.use.x402atlas.com/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"],"type":"string"},"queryParams":{"type":"object","required":["urls"],"properties":{"urls":{"oneOf":[{"type":"string"},{"type":"array","items":{"type":"string"},"maxItems":5,"minItems":1}],"description":"One URL or an array of up to 5 absolute http(s) URLs to extract content from"},"query":{"type":"string","maxLength":1000,"description":"Optional intent — extracted chunks are reranked by relevance to it"},"format":{"enum":["markdown","text"],"type":"string","default":"markdown","description":"Output content format"},"chunks_per_source":{"type":"integer","maximum":5,"minimum":1,"description":"Relevant snippets per URL, 1..5 (requires query)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","required":["queried_at","results"],"properties":{"results":{"type":"array","items":{"type":"object","required":["url","content"],"properties":{"url":{"type":"string"},"content":{"type":"string","description":"Extracted page content as markdown or text"}}}},"queried_at":{"type":"string","format":"date-time","description":"Time the extraction was executed (UTC)"},"failed_urls":{"type":"array","items":{"type":"string"},"description":"URLs that could not be extracted"}}}}}}},"responseSchema":{"type":"json","example":{"results":[{"url":"https://en.wikipedia.org/wiki/Artificial_intelligence","content":"# Artificial intelligence\n\nArtificial intelligence (AI) is intelligence exhibited by machines..."}],"queried_at":"2026-07-01T12:00:00Z"}},"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_QHl0ykmZYEo2V2W0OTIoX","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 up to 5 URLs in one call and returns the main content of each page as clean markdown or plain text, optionally reranked by a query.","exampleAgentPrompt":"Fetch the main content from these three articles — https://example.com/article1, https://example.com/article2, and https://example.com/article3 — and return each one as clean markdown so I can use them in my research pipeline.","exampleUseCases":null,"resultDescription":"A JSON object containing a results array where each entry has the URL and its extracted content as markdown or plain text, plus a failed_urls list for any URLs that could not be fetched, and a queried_at timestamp in UTC.","failureModes":["URL is paywalled or bot-blocked — URL appears in failed_urls with no content","URL is malformed or unreachable — included in failed_urls array","More than 5 URLs provided — request rejected due to maxItems constraint","chunks_per_source requested without a query param — may be ignored or return error","Network timeout fetching a URL — that URL listed in failed_urls"],"whenToPreferThis":"Use this endpoint when you need to extract clean, LLM-ready content from specific known URLs (up to 5 at once), especially for RAG ingestion, article reading, or AI agent context building. Prefer it over a search endpoint when you already have the URLs and just need their textual content. It is particularly useful when you want markdown output that strips HTML boilerplate.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T18:36:21.216Z","isFirstParty":false}