{"uid":"cap_g1HaeEjZ1tgqq-nRbX3Sx","slug":"rooms-by-aurmada-web-page-extractor-4facb6a0","name":"Rooms by Aurmada – Web Page Extractor","description":"Rooms is one shared space for you, your people, and everyone's AI.","url":"https://rooms.aurmada.com/x402/v1/web/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":"Public http(s) URL of the page."}},"additionalProperties":false}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"url":"https://example.com/post","lang":"en","links":[{"href":"https://example.com/","text":"Home"}],"title":"Example post","byline":null,"method":"readability","status":200,"excerpt":"First lines…","markdown":"# Example post\n\nText…","final_url":"https://example.com/post","word_count":812}},"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_9xgxyr_A9-95K6_yAc7Rw","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 web page and returns its main content as clean Markdown, along with title, byline, excerpt, word count, language, and up to 100 absolute links — using Mozilla Readability, no AI.","exampleAgentPrompt":"Can you fetch the main article content from https://example.com/some-article and give it to me as clean readable text, along with the title and any links on the page?","exampleUseCases":[{"title":"Article summarization pipeline","prompt":"Go to https://techcrunch.com/2024/05/01/openai-gpt5-announcement/ and pull out the full article text as clean markdown so I can summarize it."},{"title":"Research link discovery","prompt":"Fetch the content of https://en.wikipedia.org/wiki/Large_language_model and give me the main text and all the links on the page."},{"title":"Competitor blog monitoring","prompt":"Extract the readable content from https://www.anthropic.com/news/claude-3 — I want the title, the body text in markdown, and the word count."}],"resultDescription":"Returns the page's main content as clean Markdown (boilerplate removed via Mozilla Readability), plus structured metadata: title, byline, excerpt, word count, detected language, and up to 100 absolute links found on the page. Responses are limited to 2 MB and 8 seconds; private/internal addresses are rejected.","failureModes":["Private or internal IP addresses are refused with an error","Pages exceeding 2 MB are rejected","Pages that time out beyond 8 seconds fail","Non-public or login-required pages return empty or partial content","Pages with heavy JavaScript rendering may yield incomplete content","Invalid or malformed URLs return an error"],"whenToPreferThis":"Choose this endpoint when you need fast, clean, boilerplate-free text from a public web page without running an AI model — ideal for deterministic content extraction, link harvesting, or feeding page text into a downstream LLM. Prefer it over AI-based scrapers when you want predictable, cost-effective extraction with no hallucination risk, and over raw HTML fetchers when you need human-readable Markdown rather than raw markup.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T12:36:00.539Z","isFirstParty":false,"canonicalSlug":"rooms-by-aurmada-web-page-extractor-4facb6a0"}