{"uid":"cap_mToxFvGJv-UInNhv5f_GQ","slug":"agentstools-dev-structured-web-page-parser-dd22b7f3","name":"agentstools.dev Structured Web Page Parser","description":"Structured parse of a public web page: main text, headings, links, tables and rich metadata (description, canonical, lang, Open Graph, Twitter cards, JSON-LD) as separate fields. Browserless, robots.txt-respecting.","url":"https://api.agentstools.dev/structured?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","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"Public http(s) URL to parse"},"include":{"type":"array","items":{"enum":["text","headings","links","tables","metadata"],"type":"string"},"description":"Which sections to return (default: all)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","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":{"p10Cents":"0.3000","medianCents":"0.3000","p90Cents":"0.3000","minCents":"0.3000","maxCents":"0.3000","p95Cents":"0.3000","sampleCount":1,"varies":false,"failureChargeRate":1},"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_qXoHCpESAqXSUq910oVz9","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Parses a public URL into structured fields: main text, headings, links, tables, and rich metadata (Open Graph, Twitter cards, JSON-LD, canonical, lang) without a browser.","exampleAgentPrompt":"Can you parse https://techcrunch.com/2024/01/15/openai-sora/ and give me the main text, headings, and all the Open Graph and JSON-LD metadata from that page?","exampleUseCases":[{"title":"Extract product page structured data","prompt":"Can you pull the JSON-LD structured data, Open Graph tags, and main description from https://www.amazon.com/dp/B09X7CRKRX? I want to use it to enrich our product catalog."},{"title":"Summarize news article headings","prompt":"Go to https://www.bbc.com/news/technology-68240885 and give me the main text, all the headings, and the canonical URL so I can summarize what the article is about."},{"title":"Audit competitor landing page links","prompt":"Can you parse https://www.notion.so/product and extract all the outbound links and tables from the page? I'm trying to audit what resources and integrations they're promoting."}],"resultDescription":"A structured object with separate fields for: main page text, headings array, de-duplicated links, tables, and rich metadata including description, canonical URL, language, Open Graph tags, Twitter card tags, and JSON-LD — only the sections requested via the optional 'include' filter.","failureModes":["URL is not publicly accessible (private/paywalled) — returns error or empty content","robots.txt disallows crawling — request is refused with a robots-blocked error","Malformed or non-HTTP URL — validation error on the 'url' query parameter","Page returns non-200 status — upstream HTTP error propagated","Page has no structured metadata — metadata fields returned empty or null","Timeout on slow-loading upstream page — timeout error"],"whenToPreferThis":"Choose this endpoint when you need a structured breakdown of a public web page's content into typed fields (text, headings, links, tables, metadata) rather than raw HTML. It is ideal for agents that need to reason over page content, extract Open Graph/JSON-LD/Twitter card metadata for enrichment, or feed structured content into downstream processing — all without spinning up a browser. Prefer it over raw HTML fetch endpoints when clean field separation matters, and over full crawlers when you only need a single page.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-13T12:45:30.787Z","isFirstParty":false,"canonicalSlug":"agentstools-dev-structured-web-page-parser-dd22b7f3"}