{"uid":"cap_nbCOuhzbIzIQu8L1D00rN","slug":"manylives-me-web-page-metadata-extractor-878d365a","name":"manylives.me Web Page Metadata Extractor","description":"Turn a public web page into structured JSON for an agent: title, description, language, canonical URL, Open Graph and social tags, JSON-LD structured data, headings, link and image counts. Respects robots.txt.","url":"https://manylives.me/paid/web/extract?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":{"type":"string","const":"GET"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","examples":["https://example.com/"],"description":"https://... public page (required)"}}}}},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string","const":"json"},"example":{"type":"object","properties":{"url":{"type":"string"},"links":{"type":"object","properties":{"total":{"type":"number"},"external":{"type":"number"},"internal":{"type":"number"}}},"title":{"type":"string"},"status":{"type":"number"},"json_ld":{"type":"array","items":{}},"headings":{"type":"array","items":{"type":"object","properties":{"text":{"type":"string"},"level":{"type":"string"}}}},"open_graph":{"type":"object","properties":{}},"description":{"type":["null","string","number","object"]}}}}}}},"responseSchema":{"type":"json","example":{"url":"https://example.com/","links":{"total":1,"external":1,"internal":0},"title":"Example Domain","status":200,"json_ld":[],"headings":[{"text":"Example Domain","level":"h1"}],"open_graph":{},"description":null}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","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":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_TzbCk51--BtOU-md2TwyM","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a public web page and returns structured JSON metadata including title, description, language, canonical URL, Open Graph tags, JSON-LD structured data, headings, and link/image counts.","exampleAgentPrompt":"Can you pull the structured metadata from https://www.bbc.com/news/technology — I want the page title, description, any Open Graph tags, JSON-LD structured data, and a count of internal vs external links.","exampleUseCases":[{"title":"SEO audit of competitor landing page","prompt":"Extract all the SEO metadata from https://www.stripe.com/pricing — give me the title, meta description, canonical URL, headings, and any JSON-LD structured data on the page."},{"title":"Social preview tag inspection","prompt":"Check what Open Graph and social tags are set on https://vercel.com/blog/ai-sdk-3-1 so I can see how it will appear when shared on Twitter and LinkedIn."},{"title":"Content indexing for research agent","prompt":"Fetch the structured metadata for https://arxiv.org/abs/2304.01852 — I need the title, description, language, and any JSON-LD data to index this paper in my research database."}],"resultDescription":"A JSON object containing: the page URL, HTTP status code, title, description, language, canonical URL, Open Graph tags object, JSON-LD array, headings array (each with text and level), and a links object with total, internal, and external counts.","failureModes":["URL is not publicly accessible — returns non-200 status or connection error","robots.txt disallows crawling — request is refused in compliance with robots.txt","Malformed or missing URL parameter — returns validation error","Page returns no parseable HTML (e.g. binary file or redirect loop) — partial or empty metadata returned","Rate limit or payment failure — HTTP 402 or 429 response"],"whenToPreferThis":"Choose this endpoint when you need rich structured metadata about a web page — especially Open Graph tags, JSON-LD, canonical URLs, and heading structure — rather than the raw page text. Prefer this over a full-text reader when your agent needs machine-readable SEO or social metadata, or when you want structured data without the bulk of full page content. It's robots.txt-compliant, making it safe for production agent use.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-13T00:40:50.272Z","isFirstParty":false,"canonicalSlug":"manylives-me-web-page-metadata-extractor-878d365a"}