{"uid":"cap_D1zRPC6N5LGGX3nCWMXqo","slug":"agentshelf-json-ld-article-extractor-c731b108","name":"AgentShelf JSON-LD Article Extractor","description":"Call when an agent needs JSON-LD @type Article, NewsArticle, or BlogPosting extracted from a public page or HTML (SSRF-safe). Exact $0.002 USDC. Prefer unpaid POST /v1/sandbox/profile-jsonld-article first.","url":"https://agentshelf.syntexa.ch/v1/profile-jsonld-article?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","maxLength":2048,"minLength":8,"description":"Public page to fetch. The selector or profile is fixed by the SKU. Provide url or html."},"html":{"type":"string","examples":["<!doctype html><html lang=\"en\"><head><title>Hello</title>\n<meta name=\"description\" content=\"Desc\"><meta property=\"og:title\" content=\"OG\">\n<link rel=\"canonical\" href=\"https://example.com/\"><link rel=\"icon\" href=\"/favicon.ico\">\n</head><body><h1>Hello</h1><a href=\"https://example.com/a\">A</a></body></html>"],"maxLength":200000,"minLength":1,"description":"HTML to extract from locally. Provide html or url. When both are set, html is used."}}},"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_hyXhZwwJmR92v0lIxh_u0","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":"Extracts JSON-LD structured data of type Article, NewsArticle, or BlogPosting from a public URL or raw HTML input, with SSRF protection.","exampleAgentPrompt":"Can you extract the JSON-LD Article structured data from this news page — https://www.bbc.com/news/world-us-canada-12345678 — and give me the headline, author, and publish date?","exampleUseCases":[{"title":"News article metadata extraction","prompt":"Grab the JSON-LD Article metadata from https://www.reuters.com/world/some-news-story — I need the headline, author name, and publication date."},{"title":"Blog post schema parsing","prompt":"I have the raw HTML of a blog post — can you pull out the JSON-LD BlogPosting structured data from it, including the article body description and author?"},{"title":"Bulk content pipeline enrichment","prompt":"For this news article at https://techcrunch.com/2024/01/15/some-startup-story, extract the JSON-LD NewsArticle data so I can store the structured metadata in my content database."}],"resultDescription":"Returns the parsed JSON-LD object(s) of @type Article, NewsArticle, or BlogPosting found on the page or in the provided HTML, including fields such as headline, author, datePublished, dateModified, description, publisher, and articleBody as available in the source markup.","failureModes":["URL is unreachable or returns non-200 status — extraction fails with an error","No JSON-LD of type Article/NewsArticle/BlogPosting present on the page — returns empty result","HTML input exceeds 200,000 character limit — request rejected","URL blocked by SSRF protection (private/internal IP ranges) — request rejected","Malformed or invalid URL input — validation error returned"],"whenToPreferThis":"Choose this endpoint when you need to extract schema.org-compliant Article, NewsArticle, or BlogPosting JSON-LD structured data from a web page or HTML fragment. It is SSRF-safe, making it suitable for agent pipelines processing arbitrary user-supplied URLs. Prefer the free sandbox endpoint (/v1/sandbox/profile-jsonld-article) for testing; use this paid endpoint ($0.002 USDC) for production workloads. It is more targeted than a general HTML scraper — use it specifically when you need schema.org article metadata, not arbitrary page content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-02T03:02:21.601Z","isFirstParty":false,"canonicalSlug":"agentshelf-json-ld-article-extractor-c731b108"}