Merge pull request #173 from alibaba/feat/tolerant-html-cleaning

feat: support wildcard in `includeAttributes`

packages/page-controller/src/dom/index.ts

@@ -74,6 +74,43 @@ export function getFlatTree(config: DomConfig): FlatDomTree {
 	return elements
 }
 
+const globRegexCache = new Map<string, RegExp>()
+
+function globToRegex(pattern: string): RegExp {
+	let regex = globRegexCache.get(pattern)
+	if (!regex) {
+		const escaped = pattern.replace(/[.+^${}()|[\]\\]/g, '\\$&')
+		regex = new RegExp(`^${escaped.replace(/\*/g, '.*')}$`)
+		globRegexCache.set(pattern, regex)
+	}
+	return regex
+}
+
+function matchAttributes(
+	attrs: Record<string, string>,
+	patterns: string[]
+): Record<string, string> {
+	const result: Record<string, string> = {}
+
+	for (const pattern of patterns) {
+		if (pattern.includes('*')) {
+			const regex = globToRegex(pattern)
+			for (const key of Object.keys(attrs)) {
+				if (regex.test(key) && attrs[key].trim()) {
+					result[key] = attrs[key].trim()
+				}
+			}
+		} else {
+			const value = attrs[pattern]
+			if (value && value.trim()) {
+				result[pattern] = value.trim()
+			}
+		}
+	}
+
+	return result
+}
+
 /**
  * elementsToString 内部使用的类型
  */
@@ -248,23 +285,15 @@ export function flatTreeToString(flatTree: FlatDomTree, includeAttributes?: stri
 				let attributesHtmlStr = ''
 
 				if (includeAttrs.length > 0 && node.attributes) {
-					const attributesToInclude: Record<string, string> = {}
-
-					// Filter attributes
-					for (const key of includeAttrs) {
-						const value = node.attributes[key]
-						if (value && value.trim() !== '') {
-							attributesToInclude[key] = value.trim()
-						}
-					}
+					const attributesToInclude = matchAttributes(node.attributes, includeAttrs)
 
 					// Remove duplicate values (for attributes longer than 5 chars)
-					const orderedKeys = includeAttrs.filter((key) => key in attributesToInclude)
-					if (orderedKeys.length > 1) {
+					const keys = Object.keys(attributesToInclude)
+					if (keys.length > 1) {
 						const keysToRemove = new Set<string>()
 						const seenValues: Record<string, string> = {}
 
-						for (const key of orderedKeys) {
+						for (const key of keys) {
 							const value = attributesToInclude[key]
 							if (value.length > 5) {
 								if (value in seenValues) {

packages/website/src/pages/docs/advanced/page-controller/page.tsx

@@ -105,8 +105,8 @@ const agent = new PageAgentCore({
 							name: 'includeAttributes',
 							type: 'string[]',
 							description: isZh
-								? '在 DOM 提取中包含的额外 HTML 属性（如 data-testid）。默认已包含常见属性如 role, aria-label 等。'
-								: 'Additional HTML attributes to include in DOM extraction (e.g. data-testid). Common attributes like role, aria-label are included by default.',
+								? '在 DOM 提取中包含的额外 HTML 属性。支持通配符 *（如 data-* 匹配所有 data- 开头的属性）。默认已包含常见属性如 role, aria-label 等。'
+								: 'Additional HTML attributes to include in DOM extraction. Supports wildcard * (e.g. data-* matches all data- prefixed attributes). Common attributes like role, aria-label are included by default.',
 						},
 					]}
 				/>