feat(getPageContentText): add flexible property value retrieval and support for more block types

- Add getPropertyValue helper function for flexible property retrieval
- Enhance getText function to accept custom keys for property lookup
- Add support for additional block types: image, bookmark, callout, header
- Improve documentation with JSDoc comments for better code understanding

lib/notion/getPageContentText.js

@@ -1,18 +1,34 @@
 import { getTextContent } from 'notion-utils'
 
+/**
+ * 获取属性值，优先从 overrides 中读取，否则按顺序从 properties 中读取，最后返回默认值
+ * @param {Object} properties 原始属性对象
+ * @param {Array} keys 优先级字段名列表
+ * @param {Object} overrides 自定义覆盖对象（可选）
+ * @param {string} defaultValue 默认值（可选）
+ */
+function getPropertyValue(properties, keys, overrides = {}, defaultValue = '') {
+  for (const key of keys) {
+    if (overrides[key]) return overrides[key]
+    if (properties[key]) return properties[key]
+  }
+  return defaultValue
+}
+
 export function getPageContentText(post, pageBlockMap) {
   /**
    * 将对象的指定字段拼接到字符串
    * @param block
+   * @param customKeys 优先级字段名列表
    * @returns string
    */
-  function getText(block) {
+  function getText(block, customKeys = ['title', 'caption']) {
     const result = []
     const properties = block.properties
     if (!properties) {
       return ''
     }
-    const textArray = properties['title'] || properties['caption']
+    const textArray = getPropertyValue(properties, customKeys)
     result.push(getTextArray(textArray))
     if (block.type !== 'page' && block['content']?.length > 0) {
       for (const blockContent of block.content) {
@@ -61,9 +77,20 @@ export function getPageContentText(post, pageBlockMap) {
         }
         return ''
       case 'breadcrumb':
+      case 'external_object_instance':
       case 'divider':
         return ''
+      case 'image':
+        return getText(block, ['alt_text', 'title'])
+      // 除title以外,还有额外的link和description可供索引，但认为不需要
+      case 'bookmark':
       case 'quote':
+      case 'callout':
+      case 'header':
+      case 'sub_header':
+      case 'code':
+      case 'equation':
+      case 'text':
       default:
         return getText(block)
     }