const titleMatch = html.match(/<title[^>]*>([\s\S]*?)<\/title>/i); if (titleMatch) { const title = decodeEntities(titleMatch[1].trim()); if (title) meta["Page Title"] = title; } // <meta name="description"> const descMatch = html.match( /<meta[^>]+name=["']description["'][^>]+content=["']([\s\S]*?)["'][^>]*\/?>/i, ) || html.match( /<meta[^>]+content=["']([\s\S]*?)["'][^>]+name=["']description["'][^>]*\/?>/i, ); if (descMatch) { const desc = decodeEntities(descMatch[1].trim()); if (desc) meta["Meta Description"] = desc; } // <meta name="robots"> const robotsMatch = html.match( /<meta[^>]+name=["']robots["'][^>]+content=["']([\s\S]*?)["'][^>]*\/?>/i, ) || html.match( /<meta[^>]+content=["']([\s\S]*?)["'][^>]+name=["']robots["'][^>]*\/?>/i, ); if (robotsMatch) { const robots = decodeEntities(robotsMatch[1].trim()); if (robots) meta["Meta Robots"] = robots; } // <link rel="canonical"> const canonicalMatch = html.match( /<link[^>]+rel=["']canonical["'][^>]+href=["']([\s\S]*?)["'][^>]*\/?>/i, ); if (canonicalMatch) { meta["Canonical URL"] = decodeEntities(canonicalMatch[1].trim()); } // OG tags const ogTags = [ ["og:title", "OG / og:title"], ["og:description", "OG / og:description"], ["og:image", "OG / og:image"], ["og:url", "OG / og:url"], ["og:type", "OG / og:type"], ["og:site_name", "OG / og:site_name"], ]; for (const [prop, key] of ogTags) { const m = html.match( new RegExp( `<meta[^>]+property=["']${prop}["'][^>]+content=["']([\\s\\S]*?)["'][^>]*/?>`, "i", ), ) || html.match( new RegExp( `<meta[^>]+content=["']([\\s\\S]*?)["'][^>]+property=["']${prop}["'][^>]*/?>`, "i", ), ); if (m) { const val = decodeEntities(m[1].trim()); if (val) meta[key] = val; } } // Twitter tags const twTags = [ ["twitter:card", "Twitter / twitter:card"], ["twitter:title", "Twitter / twitter:title"], ["twitter:description", "Twitter / twitter:description"], ["twitter:image", "Twitter / twitter:image"], ]; for (const [name, key] of twTags) { const m = html.match( new RegExp( `<meta[^>]+name=["']${name}["'][^>]+content=["']([\\s\\S]*?)["'][^>]*/?>`, "i", ), ) || html.match( new RegExp( `<meta[^>]+content=["']([\\s\\S]*?)["'][^>]+name=["']${name}["'][^>]*/?>`, "i", ), ); if (m) { const val = decodeEntities(m[1].trim()); if (val) meta[key] = val; } } return meta; } function decodeEntities(str) { return str .replace(/&/g, "&") .replace(/</g, "<") .replace(/>/g, ">") .replace(/"/g, '"') .replace(/'/g, "'") .replace(/'/g, "'") .replace(/–/g, "–") .replace(/’/g, "'"); } // ─── Parallel runner ───────────────────────────────────────────────────────── async function processInParallel(items, concurrency, fn) { const results = []; let idx = 0; async function worker() { while (idx < items.length) { const i = idx++; results[i] = await fn(items[i], i); } } const workers = Array.from( { length: Math.min(concurrency, items.length) }, () => worker(), ); await Promise.all(workers); return results; } // ─── Main ──────────────────────────────────────────────────────────────────── (async function main() { try { const urls = await getSitemapUrls(); console.log(`\n✅ Found ${urls.length} page URLs\n`); const result = {}; let done = 0; await processInParallel(urls, CONCURRENCY, async (url, i) => { const u = new URL(url); let urlPath = u.pathname; // Ensure trailing slash if (!urlPath.endsWith("/")) urlPath += "/"; try { const { status, body } = await fetchUrl(url); if (status >= 400) { console.log(` ⚠ [${status}] ${urlPath}`); return; } const meta = extractMeta(body); if (Object.keys(meta).length > 0) { result[urlPath] = meta; } done++; process.stdout.write(`\r ✔ ${done}/${urls.length} pages extracted …`); } catch (err) { console.log(`\n ❌ ${urlPath}: ${err.message}`); } }); console.log( `\n\n📦 Writing ${Object.keys(result).length} entries to ${OUT_PATH}`, ); fs.writeFileSync(OUT_PATH, JSON.stringify(result, null, 2), "utf-8"); console.log("✅ Done!\n"); } catch (err) { console.error("Fatal error:", err); process.exit(1); } })(); </article></body></html>

/** * extract_old_meta.js * * Fetches every page from the LIVE (old) site and extracts SEO metadata * (title, meta description, OG tags, Twitter tags, robots, canonical). * * Outputs lib/site-metadata-raw.json in the format expected by * patch_all_meta.js. * * Usage: * node scripts/extract_old_meta.js */ const https = require("https"); const http = require("http"); const { URL } = require("url"); const fs = require("fs"); const path = require("path"); // ─── Config ────────────────────────────────────────────────────────────────── const SITEMAP_INDEX_URL = "https://syncsignature.com/sitemap_index.xml"; const OLD_SITE = "https://syncsignature.com"; const OUT_PATH = path.resolve(__dirname, "..", "lib", "site-metadata-raw.json"); const CONCURRENCY = 4; const TIMEOUT_MS = 20000; // ─── HTTP helpers ──────────────────────────────────────────────────────────── function fetchUrl(url) { return new Promise((resolve, reject) => { const lib = url.startsWith("https") ? https : http; const req = lib.get( url, { headers: { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36", Accept: "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8", }, timeout: TIMEOUT_MS, }, (res) => { // Follow redirects if ( [301, 302, 307, 308].includes(res.statusCode) && res.headers.location ) { return fetchUrl(res.headers.location).then(resolve, reject); } const chunks = []; res.on("data", (chunk) => chunks.push(chunk)); res.on("end", () => resolve({ status: res.statusCode, body: Buffer.concat(chunks).toString("utf-8"), }), ); res.on("error", reject); }, ); req.on("timeout", () => { req.destroy(); reject(new Error("Timeout")); }); req.on("error", reject); }); } // ─── Sitemap parsing (simple regex, no XML lib needed) ─────────────────────── async function getSitemapUrls() { console.log("📡 Fetching sitemap index:", SITEMAP_INDEX_URL); const { body } = await fetchUrl(SITEMAP_INDEX_URL); // Extract child sitemap URLs const sitemapUrls = [...body.matchAll(/\s*(.*?)\s*<\/loc>/g)].map( (m) => m[1], ); console.log(` Found ${sitemapUrls.length} child sitemaps`); const allPageUrls = []; for (const smUrl of sitemapUrls) { console.log(` Fetching: ${smUrl}`); const { body: smBody } = await fetchUrl(smUrl); const locs = [...smBody.matchAll(/\s*(.*?)\s*<\/loc>/g)].map( (m) => m[1], ); // Only keep HTML page URLs (skip images, videos, etc.) for (const loc of locs) { const u = new URL(loc); const ext = path.extname(u.pathname); if (!ext || ext === ".html" || ext === ".htm") { allPageUrls.push(loc); } } } // Deduplicate return [...new Set(allPageUrls)]; } // ─── HTML metadata extraction (regex-based, no cheerio/jsdom needed) ───────── function extractMeta(html) { const meta = {}; // const titleMatch = html.match(/<title[^>]*>([\s\S]*?)<\/title>/i); if (titleMatch) { const title = decodeEntities(titleMatch[1].trim()); if (title) meta["Page Title"] = title; } // <meta name="description"> const descMatch = html.match( /<meta[^>]+name=["']description["'][^>]+content=["']([\s\S]*?)["'][^>]*\/?>/i, ) || html.match( /<meta[^>]+content=["']([\s\S]*?)["'][^>]+name=["']description["'][^>]*\/?>/i, ); if (descMatch) { const desc = decodeEntities(descMatch[1].trim()); if (desc) meta["Meta Description"] = desc; } // <meta name="robots"> const robotsMatch = html.match( /<meta[^>]+name=["']robots["'][^>]+content=["']([\s\S]*?)["'][^>]*\/?>/i, ) || html.match( /<meta[^>]+content=["']([\s\S]*?)["'][^>]+name=["']robots["'][^>]*\/?>/i, ); if (robotsMatch) { const robots = decodeEntities(robotsMatch[1].trim()); if (robots) meta["Meta Robots"] = robots; } // <link rel="canonical"> const canonicalMatch = html.match( /<link[^>]+rel=["']canonical["'][^>]+href=["']([\s\S]*?)["'][^>]*\/?>/i, ); if (canonicalMatch) { meta["Canonical URL"] = decodeEntities(canonicalMatch[1].trim()); } // OG tags const ogTags = [ ["og:title", "OG / og:title"], ["og:description", "OG / og:description"], ["og:image", "OG / og:image"], ["og:url", "OG / og:url"], ["og:type", "OG / og:type"], ["og:site_name", "OG / og:site_name"], ]; for (const [prop, key] of ogTags) { const m = html.match( new RegExp( `<meta[^>]+property=["']${prop}["'][^>]+content=["']([\\s\\S]*?)["'][^>]*/?>`, "i", ), ) || html.match( new RegExp( `<meta[^>]+content=["']([\\s\\S]*?)["'][^>]+property=["']${prop}["'][^>]*/?>`, "i", ), ); if (m) { const val = decodeEntities(m[1].trim()); if (val) meta[key] = val; } } // Twitter tags const twTags = [ ["twitter:card", "Twitter / twitter:card"], ["twitter:title", "Twitter / twitter:title"], ["twitter:description", "Twitter / twitter:description"], ["twitter:image", "Twitter / twitter:image"], ]; for (const [name, key] of twTags) { const m = html.match( new RegExp( `<meta[^>]+name=["']${name}["'][^>]+content=["']([\\s\\S]*?)["'][^>]*/?>`, "i", ), ) || html.match( new RegExp( `<meta[^>]+content=["']([\\s\\S]*?)["'][^>]+name=["']${name}["'][^>]*/?>`, "i", ), ); if (m) { const val = decodeEntities(m[1].trim()); if (val) meta[key] = val; } } return meta; } function decodeEntities(str) { return str .replace(/&/g, "&") .replace(/</g, "<") .replace(/>/g, ">") .replace(/"/g, '"') .replace(/'/g, "'") .replace(/'/g, "'") .replace(/–/g, "–") .replace(/’/g, "'"); } // ─── Parallel runner ───────────────────────────────────────────────────────── async function processInParallel(items, concurrency, fn) { const results = []; let idx = 0; async function worker() { while (idx < items.length) { const i = idx++; results[i] = await fn(items[i], i); } } const workers = Array.from( { length: Math.min(concurrency, items.length) }, () => worker(), ); await Promise.all(workers); return results; } // ─── Main ──────────────────────────────────────────────────────────────────── (async function main() { try { const urls = await getSitemapUrls(); console.log(`\n✅ Found ${urls.length} page URLs\n`); const result = {}; let done = 0; await processInParallel(urls, CONCURRENCY, async (url, i) => { const u = new URL(url); let urlPath = u.pathname; // Ensure trailing slash if (!urlPath.endsWith("/")) urlPath += "/"; try { const { status, body } = await fetchUrl(url); if (status >= 400) { console.log(` ⚠ [${status}] ${urlPath}`); return; } const meta = extractMeta(body); if (Object.keys(meta).length > 0) { result[urlPath] = meta; } done++; process.stdout.write(`\r ✔ ${done}/${urls.length} pages extracted …`); } catch (err) { console.log(`\n ❌ ${urlPath}: ${err.message}`); } }); console.log( `\n\n📦 Writing ${Object.keys(result).length} entries to ${OUT_PATH}`, ); fs.writeFileSync(OUT_PATH, JSON.stringify(result, null, 2), "utf-8"); console.log("✅ Done!\n"); } catch (err) { console.error("Fatal error:", err); process.exit(1); } })(); </article></body></html>