{"uid":"cap_Ttg3kwo8JVcWhAMSiLoPE","slug":"sitecheck-web-intel-article-extractor-fc4fe12f","name":"SiteCheck Web Intel Article Extractor","description":"Extracts one article from a public news or blog page: headline (og:title or h1), author, published and modified times, description and the article body as Markdown. Reads the page you name only; paywalled text is not returned and body text depends on the page using <article> or <main>.","url":"https://api.webintel-api.workers.dev/api/search/article-extractor?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":"Full http or https address of an article page"},"maxChars":{"type":"string","description":"Longest body returned, 500 to 40000 characters (default 8000)"}}}},"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_syfHiRoGJUuFcYzYQYwa4","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 news or blog article URL and returns its headline, author, publication times, description, and full body text as Markdown","exampleAgentPrompt":"Can you pull the full article text and author from this news page — https://www.bbc.com/news/technology-12345678 — and give it to me as Markdown, up to 12000 characters?","exampleUseCases":[{"title":"Summarize a breaking news article","prompt":"Grab the full article text from https://www.reuters.com/technology/ai-regulation-2025/ and summarize the key points for me — extract up to 10000 characters of the body."},{"title":"Research a blog post for a report","prompt":"Pull the headline, author, publish date, and full body text from https://martinfowler.com/articles/micro-frontends.html so I can cite it in my report."},{"title":"Monitor competitor content","prompt":"Extract the article content from https://techcrunch.com/2025/05/01/openai-new-model/ — I want the title, description, and as much of the article body as possible, up to 20000 characters."}],"resultDescription":"A structured object containing: og:title or h1 headline, author name, published datetime, last-modified datetime, meta description, and the article body rendered as Markdown. Paywalled content and pages lacking <article> or <main> tags may return incomplete or empty body text.","failureModes":["Paywalled content returns empty or truncated body","Pages without <article> or <main> semantic tags return little or no body text","Invalid or unreachable URL returns an error","maxChars outside 500–40000 range may be rejected or clamped","Dynamic JavaScript-rendered pages may not be parsed correctly","og:title and h1 absent results in missing headline"],"whenToPreferThis":"Use this endpoint when you need to extract readable article content (headline, author, dates, body as Markdown) from a single known public URL. Prefer it over general-purpose web search APIs when you already have the URL and need structured article metadata and body text. Not suitable for paywalled content, full-site crawls, or pages without semantic HTML structure.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-24T12:44:52.359Z","isFirstParty":false,"canonicalSlug":"sitecheck-web-intel-article-extractor-fc4fe12f"}