{"uid":"cap_Ph_9AX1WlguAAqa69k2zM","slug":"gateway-d402-xyz-extract-article-metadata-and-clean-markdown-d402-d41b080d","name":"Extract Article Metadata and Clean Markdown (d402)","description":"Paid d402 capability alias for web.extract_article@1. Workers return article metadata, body markdown, summary, outbound links, and evidence.","url":"https://gateway.d402.xyz/v1/web/extract-article","method":"POST","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","format":"uri","description":"Public article/news/blog page URL to extract."},"sync":{"type":"boolean","description":"Optional d402 sync flag. Defaults to gateway policy."},"timeoutMs":{"type":"number","maximum":45000,"minimum":1,"description":"Optional per-request timeout, capped by gateway policy."}},"additionalProperties":false},"responseSchema":{"type":"object","required":["taskId","status"],"properties":{"error":{"type":["string","null"]},"links":{"type":"object","properties":{"task":{"type":"string"},"result":{"type":"string"},"receipt":{"type":"string"}}},"result":{"type":"object","required":["url","bodyMarkdown","contentHash","snapshotCid","extractorVersion"],"properties":{"url":{"type":"string"},"site":{"type":["string","null"]},"title":{"type":["string","null"]},"author":{"type":["string","null"]},"summary":{"type":["string","null"]},"evidence":{"type":"array","items":{"type":"object"}},"fetchedAt":{"type":"string"},"published":{"type":["string","null"]},"wordCount":{"type":["number","null"]},"contentHash":{"type":"string"},"description":{"type":["string","null"]},"serviceName":{"type":"string"},"snapshotCid":{"type":"string"},"bodyMarkdown":{"type":"string"},"canonicalUrl":{"type":["string","null"]},"outboundLinks":{"type":"array","items":{"type":"object"}},"serviceVersion":{"type":"string"},"extractorVersion":{"type":"string"}}},"status":{"enum":["accepted","rejected","running","error"],"type":"string"},"taskId":{"type":"string"},"settlement":{"type":["object","null"],"additionalProperties":true},"x402Settlement":{"type":["object","null"],"additionalProperties":true},"validationReceipt":{"type":["object","null"],"additionalProperties":true}}},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"down","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_iv2Xsrk4eBgbUJmeZzx-Q","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":"gateway.d402.xyz","brandSlug":"gateway-d402-xyz-x402","brandBaseUrl":"https://gateway.d402.xyz","brandDocsUrl":null,"whatItDoes":"Fetches a public article, news, or blog URL and returns structured metadata (title, author, published date, summary) plus clean body markdown, outbound links, and evidence.","exampleAgentPrompt":"Can you extract the full article text, title, author, and publish date from this news page as clean markdown? https://www.theguardian.com/technology/2025/jan/10/ai-agents-future","exampleUseCases":[{"title":"Research digest from news links","prompt":"I have a list of news article URLs about renewable energy policy. Can you pull the title, author, publish date, and full body text from each one so I can compile a research digest?"},{"title":"Blog post metadata for CMS import","prompt":"I need to import a bunch of external blog posts into our CMS. Can you fetch the metadata — title, author, published date, and summary — plus the clean article body from this URL so I can prep it for import? https://blog.hubspot.com/marketing/content-marketing-strategy"},{"title":"Fact-check outbound links in article","prompt":"Can you grab all the outbound links from this news article along with its full body text so I can verify what sources the author is citing? https://www.bbc.com/news/technology-68178963"}],"resultDescription":"Returns a task result containing the article URL, site name, title, author, publish date, word count, a plain-text summary, the full article body as clean markdown, canonical URL, outbound links array, a content hash for integrity, a snapshot CID for provenance, and evidence objects. Also includes task ID, status, and settlement/receipt details.","failureModes":["URL is behind a paywall or requires login — extraction fails or returns partial content","URL points to a non-article page (homepage, search results) — metadata fields may be null","Request timeout exceeded (up to 45000ms) — returns error status","Invalid or malformed URL — rejected with validation error","Page is JavaScript-heavy and content cannot be fetched — bodyMarkdown may be empty","Insufficient USDC payment — transaction rejected before extraction begins"],"whenToPreferThis":"Choose this endpoint when you need structured article metadata (title, author, date, summary) alongside clean markdown body text from a public article, news, or blog URL. Prefer it over a generic page-to-markdown endpoint when you need the semantic metadata fields extracted and structured, not just raw markdown. Use it over web.render_snapshot when you need readable text rather than a visual render.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T15:26:47.468Z","isFirstParty":false}