{"uid":"cap_mqbxRpPQV-EKDc3lXEyER","slug":"html-metadata-extractor-bba2c84f","name":"HTML Metadata Extractor","description":"Machine-payable x402 utilities for hashing, Base64, UUID generation, unit and timezone conversion, realtime crypto market data, webpage/document extraction, URL-to-Markdown, metadata, RAG ingestion and deterministic website change detection.","url":"https://x402-gateway-production-1f21.up.railway.app/html/meta?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","required":["html"],"properties":{"html":{"type":"string","maxLength":500000},"base_url":{"type":"string","maxLength":8192}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"status":"ready"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","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":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_EWP1QQq7gJfDN9O2WKWlE","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts metadata (title, description, Open Graph tags, structured data, etc.) from a raw HTML string","exampleAgentPrompt":"Extract the metadata from this HTML I just fetched — I need the title, description, Open Graph tags, and any structured data you can find in it.","exampleUseCases":[{"title":"SEO audit of scraped pages","prompt":"I have the raw HTML from our product landing page — can you pull out all the metadata including the title, meta description, and Open Graph tags so I can check them for SEO?"},{"title":"Link preview card generation","prompt":"I fetched the HTML for this article and need you to extract the Open Graph title, description, and image URL so I can render a link preview card."},{"title":"Content indexing pipeline","prompt":"Here's the raw HTML from a document I want to index — extract all the metadata fields like title, author, description, and any schema.org structured data so I can store them for search."}],"resultDescription":"A JSON object containing extracted metadata fields from the HTML, such as page title, meta description, Open Graph properties (og:title, og:description, og:image, etc.), Twitter card tags, canonical URL, and any other structured metadata found in the HTML head section.","failureModes":["Missing or malformed HTML input returns an error","HTML exceeding 500,000 character limit is rejected","No metadata present in the HTML yields empty fields","Invalid base_url format causes URL resolution errors","Malformed HTML that cannot be parsed may return partial or empty results"],"whenToPreferThis":"Use this endpoint when you have already fetched raw HTML and need to extract its metadata fields efficiently without re-fetching the URL. Ideal for pipelines that scrape pages first and then process metadata separately, or when working with HTML from sources that require authentication or custom fetch logic. Prefer this over full-page fetch endpoints when you already hold the HTML content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T12:34:54.337Z","isFirstParty":false,"canonicalSlug":"html-metadata-extractor-bba2c84f"}