{"uid":"cap_hHnvEPejCRtFn0xPXKeTb","slug":"signaldesk-ai-html-metadata-extractor-99e031e5","name":"SignalDesk AI – HTML Metadata Extractor","description":"Evidence-backed autonomous AI jobs and paid data tools. Queue/D1/cron run outside the chat; free quotas and bounded execution apply.","url":"https://x402-agent.kariguetoazul.workers.dev/api/web/html-metadata?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"html":{"type":"string","maxLength":12000,"description":"Caller-supplied HTML; no script is executed."}}},"responseSchema":{"type":"json","example":{"links":[{"href":"https://example.com","text":"Example"}],"title":"Example","metadata":{"description":"A sample"},"untrusted_content":true}},"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_jmnh2SDVy02gOfuvNKNBU","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":"Parses caller-supplied HTML and extracts structured metadata including the page title, meta description tags, and hyperlinks.","exampleAgentPrompt":"I just fetched the HTML from a page — can you extract the title, meta description, and all the links out of it for me? Here's the raw HTML: <html><head><title>Example</title><meta name='description' content='A sample page'></head><body><a href='https://example.com'>Example</a></body></html>","exampleUseCases":[{"title":"Link audit from crawled pages","prompt":"I've got the raw HTML from a competitor's product page — can you pull out every link in it along with the anchor text, so I can see where they're pointing?"},{"title":"SEO metadata check","prompt":"Here's the HTML source of our homepage — can you extract the title tag and meta description so I can check if they're set correctly?"},{"title":"Article preview card generation","prompt":"I fetched the HTML of this blog post and want to build a preview card — can you pull out the title, description, and any relevant links from this markup?"}],"resultDescription":"Returns a JSON object containing: a 'title' string with the page's <title> tag content, a 'metadata' object with key meta tags (e.g. description), and a 'links' array of objects each with 'href' and 'text' fields. Also includes an 'untrusted_content' boolean flag. No scripts are executed on the input HTML.","failureModes":["HTML exceeding 12,000 characters will be rejected or truncated","Malformed or non-HTML input may produce empty/partial results","Dynamically rendered content (JavaScript-dependent) will not be captured since no script execution occurs","Payment failure via x402 protocol will block access","Missing or empty 'html' field returns an error"],"whenToPreferThis":"Choose this endpoint when you already have raw HTML in hand and need to extract structured metadata (title, description, links) without spinning up a full browser or executing JavaScript. It is ideal for lightweight, server-side HTML parsing tasks where you want fast, structured output at low cost ($0.002 USDC). Prefer this over full-browser scraping services when the content is static or pre-fetched, and over general LLM text extraction when you need deterministic structured fields like hrefs and meta tags.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-13T00:42:16.474Z","isFirstParty":false,"canonicalSlug":"signaldesk-ai-html-metadata-extractor-99e031e5"}