111

frontend/scripts/extract-page.mjs

@@ -0,0 +1,48 @@
+import fs from 'node:fs'
+import path from 'node:path'
+import { fileURLToPath } from 'node:url'
+
+const [, , sourceHtmlArg, outputPrefixArg] = process.argv
+if (!sourceHtmlArg || !outputPrefixArg) {
+  throw new Error(
+    'Usage: node scripts/extract-page.mjs <source-html-path> <output-prefix>\n' +
+      'Example: npm run extract:page -- ./snapshots/about.html about\n' +
+      'Writes src/generated/<prefix>-page-body.html, <prefix>-assets.json, <prefix>-inline-scripts.txt'
+  )
+}
+
+const currentFile = fileURLToPath(import.meta.url)
+const rootDir = path.resolve(path.dirname(currentFile), '..')
+const sourceHtmlPath = path.resolve(rootDir, sourceHtmlArg)
+const outDir = path.resolve(rootDir, 'src', 'generated')
+
+const html = fs.readFileSync(sourceHtmlPath, 'utf8')
+const bodyMatch = html.match(/<body[^>]*>([\s\S]*?)<\/body>/i)
+if (!bodyMatch) throw new Error(`Failed to extract <body> from ${sourceHtmlArg}`)
+
+let bodyHtml = bodyMatch[1]
+bodyHtml = bodyHtml.replace(/<script\b[^>]*>[\s\S]*?<\/script>/gi, '')
+
+const links = Array.from(html.matchAll(/<link[^>]+href="([^"]+)"[^>]*>/gi)).map((m) => m[1])
+const scripts = Array.from(html.matchAll(/<script[^>]+src="([^"]+)"[^>]*><\/script>/gi)).map(
+  (m) => m[1]
+)
+const inlineScripts = Array.from(
+  html.matchAll(/<script\b(?![^>]*\bsrc=)[^>]*>([\s\S]*?)<\/script>/gi)
+)
+  .map((m) => m[1].trim())
+  .filter(Boolean)
+
+fs.writeFileSync(path.join(outDir, `${outputPrefixArg}-page-body.html`), bodyHtml, 'utf8')
+fs.writeFileSync(
+  path.join(outDir, `${outputPrefixArg}-assets.json`),
+  JSON.stringify({ scripts, links }, null, 2),
+  'utf8'
+)
+fs.writeFileSync(
+  path.join(outDir, `${outputPrefixArg}-inline-scripts.txt`),
+  inlineScripts.join('\n/*__INLINE_SPLIT__*/\n'),
+  'utf8'
+)
+
+console.log(`Generated files for ${outputPrefixArg}`)