{"uid":"cap_3dVpFVIFFYMUU4LJ1QRBa","slug":"webtools-structured-web-page-parser-bc60cb84","name":"WebTools 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://webtools402.176-109-107-191.sslip.io/structured","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":null,"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_uGmkDqLd-s20QKc1YhOgx","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":"Fetches and parses a public URL into structured fields: main text, headings, links, tables, and rich metadata (Open Graph, Twitter cards, JSON-LD, canonical, lang).","exampleAgentPrompt":"Can you fetch and parse https://example.com/blog/post-1 and give me the main text, all the headings, and any JSON-LD structured data on the page?","exampleUseCases":[{"title":"SEO audit of competitor pages","prompt":"Can you pull the Open Graph tags, meta description, canonical URL, and JSON-LD structured data from our top three competitors' homepages? I want to see how they're set up for SEO compared to ours."},{"title":"Extract links from documentation","prompt":"Go through https://docs.example.com/getting-started and grab all the hyperlinks on the page — I need to build a map of where their docs link out to so I can check for broken or outdated references."},{"title":"Summarize article from URL","prompt":"I've got this article URL — can you fetch the main body text and headings from it and give me a quick summary of what it's about? I don't need any of the navigation or sidebar stuff, just the core content."}],"resultDescription":"Returns a structured object with separate fields for: main body text, headings list, hyperlinks, HTML tables, and rich metadata including page description, canonical URL, language, Open Graph tags, Twitter card tags, and JSON-LD blobs — only the sections requested if the include filter is specified.","failureModes":["URL is not publicly accessible or returns non-200 status — parse fails with error","URL blocked by robots.txt — request refused with robots disallowed error","URL points to non-HTML content (PDF, image) — limited or no text extraction","Network timeout reaching the target URL — timeout error returned","Malformed or missing URL query parameter — validation error"],"whenToPreferThis":"Choose this endpoint when you need structured, field-by-field decomposition of a web page — especially Open Graph, Twitter cards, or JSON-LD metadata — rather than raw HTML or plain text. Ideal for SEO analysis, link extraction, content summarization pipelines, or any agent task that needs specific sections of a page without a full browser. Respects robots.txt, so appropriate for ethical crawling workflows.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:57:35.722Z","isFirstParty":false}