{"name":"url-metadata","id":"sfoln/url-metadata","title":"URL Metadata & Open Graph Extractor","description":"Extract metadata from any list of URLs: title, meta description, canonical, language, favicon, Open Graph and Twitter Card tags, JSON-LD types, feeds, H1, word and link counts. One fast HTTP fetch per URL, no browser. $1 per 1,000 URLs; failed and missing pages are free.","version":"0.1","status":"ready","family":{"id":"ai-agent-web-toolkit","name":"Web toolkit for agents","description":"Web search for retrieval, pages and sites converted to Markdown, AI extraction to JSON, URL metadata and safety checks, sitemaps, feeds, change monitoring and academic paper search.","actors":11},"categories":["DEVELOPER_TOOLS","SEO_TOOLS","AUTOMATION"],"availability":"public","seoTitle":"URL Metadata & Open Graph API – $1 per 1,000 URLs","seoDescription":"Extract Open Graph, Twitter Card, title, description, canonical, favicon and JSON-LD from any URL as JSON for link previews and SEO. $1 per 1,000 URLs.","summary":"URL Metadata & Open Graph Extractor turns a list of URLs into clean, structured page metadata: title, meta description, canonical URL, language, favicon, Open Graph and Twitter Card tags, JSON-LD schema types, publish/modify dates, author, robots and generator tags, the first H1, a visible word count, internal/external link counts and RSS/Atom feed links. Built for link previews, SEO audits, content inventories, lead enrichment and AI agents that need to know what a page is about without rendering it.","pricing":{"model":"pay-per-event","currency":"USD","billedBy":"Apify","freePlanMaxItemsPerRun":10,"events":[{"name":"url-metadata","title":"URL metadata record","description":"Charged once per URL whose page was fetched and analysed (status ok). Missing pages (404/410), dead domains, blocked or invalid URLs and failed fetches are not charged.","priceUsd":0.001}]},"input":{"description":"Paste URLs (one per line). Each URL produces one dataset record with page metadata and a `status` field.","required":["urls"],"fields":[{"name":"urls","title":"URLs","type":"array","required":true,"description":"Pages to analyse, one per line. `https://` is added when the scheme is missing. Duplicates are removed. Objects with a `url` key are accepted too. Accounts on the Apify free plan can process up to 10 URLs per run.","prefill":["https://apify.com","https://blog.apify.com"],"editor":"stringList"},{"name":"maxUrls","title":"Max URLs","type":"integer","required":false,"description":"Safety cap on how many URLs are processed in this run.","default":1000,"minimum":1,"maximum":100000},{"name":"timeoutSecs","title":"Fetch timeout (seconds)","type":"integer","required":false,"description":"Maximum time to wait for one page (redirects included). Slow pages are retried once.","default":10,"minimum":3,"maximum":30},{"name":"concurrency","title":"Concurrency","type":"integer","required":false,"description":"How many pages are fetched in parallel.","default":5,"minimum":1,"maximum":10},{"name":"includeRaw","title":"Include fetch details","type":"boolean","required":false,"description":"Attach low-level fetch details (detected charset) under `raw`.","default":false}]},"exampleInput":{"urls":["https://apify.com","https://blog.apify.com"]},"outputFields":[{"name":"input","type":"string | object","title":"Input","description":"The URL as given in the input."},{"name":"url","type":"string","title":"URL","description":"Normalized requested URL.","example":"https://apify.com/"},{"name":"finalUrl","type":"string | null","title":"Final URL","description":"URL after redirects."},{"name":"redirected","type":"boolean | null","title":"Redirected","description":"True when the request was redirected."},{"name":"statusCode","type":"integer | null","title":"HTTP status","description":"Final HTTP status code.","example":200},{"name":"contentType","type":"string | null","title":"Content type","description":"Content-Type response header."},{"name":"title","type":"string | null","title":"Title","description":"<title> text."},{"name":"description","type":"string | null","title":"Meta description","description":"<meta name=description> content."},{"name":"canonical","type":"string | null","title":"Canonical URL","description":"Absolute <link rel=canonical> URL."},{"name":"language","type":"string | null","title":"Language","description":"<html lang>, Content-Language meta/header or og:locale."},{"name":"favicon","type":"string | null","title":"Favicon","description":"Absolute icon URL (falls back to /favicon.ico)."},{"name":"ogTitle","type":"string | null","title":"og:title"},{"name":"ogDescription","type":"string | null","title":"og:description"},{"name":"ogImage","type":"string | null","title":"og:image","description":"Absolute image URL."},{"name":"ogType","type":"string | null","title":"og:type"},{"name":"ogSiteName","type":"string | null","title":"og:site_name"},{"name":"ogUrl","type":"string | null","title":"og:url"},{"name":"ogLocale","type":"string | null","title":"og:locale"},{"name":"twitterCard","type":"string | null","title":"twitter:card"},{"name":"twitterTitle","type":"string | null","title":"twitter:title"},{"name":"twitterDescription","type":"string | null","title":"twitter:description"},{"name":"twitterImage","type":"string | null","title":"twitter:image"},{"name":"twitterSite","type":"string | null","title":"twitter:site"},{"name":"twitterCreator","type":"string | null","title":"twitter:creator"},{"name":"jsonLdTypes","type":"array","title":"JSON-LD types","description":"Distinct schema.org @type values found in JSON-LD blocks (incl. @graph)."},{"name":"publishedTime","type":"string | null","title":"Published","description":"article:published_time or equivalent (as written on the page)."},{"name":"modifiedTime","type":"string | null","title":"Modified","description":"article:modified_time / og:updated_time or equivalent."},{"name":"author","type":"string | null","title":"Author"},{"name":"robots","type":"string | null","title":"Robots meta"},{"name":"xRobotsTag","type":"string | null","title":"X-Robots-Tag header"},{"name":"generator","type":"string | null","title":"Generator","description":"CMS / site generator meta."},{"name":"keywords","type":"string | null","title":"Meta keywords"},{"name":"themeColor","type":"string | null","title":"Theme color"},{"name":"h1","type":"string | null","title":"First H1"},{"name":"h1Count","type":"integer","title":"H1 count"},{"name":"wordCount","type":"integer","title":"Word count","description":"Visible-text word estimate."},{"name":"linksInternal","type":"integer","title":"Internal links","description":"Distinct same-host link targets."},{"name":"linksExternal","type":"integer","title":"External links","description":"Distinct other-host link targets."},{"name":"feeds","type":"array","title":"Feeds","description":"RSS / Atom / JSON Feed links: { url, type, title }."},{"name":"pageBytes","type":"integer | null","title":"Bytes analysed"},{"name":"truncated","type":"boolean | null","title":"Truncated","description":"True when the page exceeded 1 MB."},{"name":"responseTimeMs","type":"integer | null","title":"Response time (ms)"},{"name":"status","type":"string","title":"Status","description":"ok | not_found | error | skipped_invalid | skipped_budget | skipped_free_plan","example":"ok"},{"name":"charged","type":"boolean","title":"Charged","description":"Whether this record incurred a pay-per-event charge."},{"name":"source","type":"string","title":"Source","description":"Data source (selfhosted = fetched by this Actor)."},{"name":"fetchedAt","type":"string","title":"Fetched at","description":"ISO timestamp."}],"outputExample":{"input":"https://apify.com","url":"https://apify.com/","finalUrl":"https://apify.com/","redirected":false,"statusCode":200,"contentType":"text/html; charset=utf-8","title":"Apify: Full-stack web scraping and data extraction platform","description":"Cloud platform for web scraping, browser automation, AI agents, and data for AI...","canonical":"https://apify.com/","language":"en","favicon":"https://apify.com/favicon.ico","ogTitle":"Apify: Full-stack web scraping and data extraction platform","ogDescription":"Cloud platform for web scraping...","ogImage":"https://apify.com/og-image.png","ogType":"website","ogSiteName":"Apify","twitterCard":"summary_large_image","twitterSite":"@apify","jsonLdTypes":["Organization","WebSite"],"publishedTime":null,"modifiedTime":null,"author":null,"robots":"index, follow","generator":null,"h1":"Build reliable web scrapers. Fast.","h1Count":1,"wordCount":1432,"linksInternal":118,"linksExternal":21,"feeds":[],"pageBytes":412339,"truncated":false,"responseTimeMs":312,"status":"ok","charged":true,"chargedEvent":"url-metadata","source":"selfhosted","fetchedAt":"2026-10-14T10:00:00.000Z"},"faq":[],"mcpExamplePrompt":"Get the title, description, Open Graph image and canonical URL of https://apify.com and https://blog.apify.com for a link preview.","related":["url-to-markdown-summary","website-to-markdown","ai-web-scraper","url-safety-check","domain-intelligence","website-change-monitor","onpage-seo-audit"],"urls":{"site":"https://www.sfoln.com/actors/url-metadata/","siteJson":"https://www.sfoln.com/actors/url-metadata.json","siteMarkdown":"https://www.sfoln.com/actors/url-metadata.md","store":"https://apify.com/sfoln/url-metadata","storeMarkdown":"https://apify.com/sfoln/url-metadata.md","runSync":"https://api.apify.com/v2/actors/sfoln~url-metadata/run-sync-get-dataset-items","runAsync":"https://api.apify.com/v2/actors/sfoln~url-metadata/runs","mcp":"https://mcp.apify.com?tools=sfoln/url-metadata"},"publisher":{"name":"SFOLN LLC","apifyUsername":"sfoln","url":"https://www.sfoln.com","apifyProfile":"https://apify.com/sfoln","email":"contact@sfoln.com"},"generatedAt":"2026-10-22T04:28:58.477Z"}