{"uid":"cap_2bv8XBtmsKvQeUBG2E6yr","slug":"oromi-web-extract-ab7e8973","name":"Oromi Web Extract","description":"Machine-payable APIs for AI agents, paid per call in USDC via the x402 protocol: UK business data (Companies House), UK property market data (HM Land Registry), website agent-readiness audits, and crypto market context.","url":"https://agents.oromi.co.uk/api/web/extract","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","description":"Page URL to extract"}}},"responseSchema":{"type":"json","example":{"text":"...","title":"Example article","word_count":843}},"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_LFFNu0x08HML0JMTzzUgf","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 and extracts clean text content from a given webpage URL, returning the page title, plain text, and word count","exampleAgentPrompt":"Can you extract the readable text content from this page for me: https://www.bbc.co.uk/news/technology-12345678 — I want the title and the full article text.","exampleUseCases":[{"title":"Article text extraction for summarization","prompt":"Pull the full text from this article at https://www.theguardian.com/technology/2024/ai-news and summarize the key points for me."},{"title":"Competitor webpage content analysis","prompt":"Grab the readable content from https://www.competitorsite.co.uk/about and tell me what services they're describing."},{"title":"Research content ingestion","prompt":"Extract all the text from this report page at https://www.gov.uk/government/publications/some-report so I can analyse what it says."}],"resultDescription":"Returns a JSON object containing the extracted plain text body of the page, the page title as a string, and a word count integer — suitable for downstream summarization, analysis, or storage tasks.","failureModes":["URL is inaccessible or returns a non-200 HTTP status, resulting in an extraction error","Page is behind a login wall or CAPTCHA, preventing content retrieval","URL points to a binary file (PDF, image) rather than an HTML page, causing unexpected output or failure","Malformed URL input causes a validation or request error","Page content is JavaScript-rendered only, so static extraction may return empty or minimal text"],"whenToPreferThis":"Choose this endpoint when you need to retrieve clean, readable plain text from a specific public webpage on a per-call, pay-as-you-go basis via USDC/x402, without setting up your own scraping infrastructure. It is particularly suited for agentic workflows that need to ingest web content programmatically for summarization, research, or analysis. Prefer it over general-purpose browser automation when you just need text and word count from a URL, not structured data or screenshots.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T18:38:21.717Z","isFirstParty":false}