feat: 开发采集插件

extension/src/collector/text.ts

@@ -0,0 +1,75 @@
+/**
+ * 文本提取 - 标题、价格、参数表、描述
+ * 从 docs/extension/plan.md §6.6 移植（简化版）
+ */
+import type { SiteProfile, TextRule } from '../profiles/types';
+
+export interface TextMaterial {
+  kind: TextRule['kind'];
+  content: string;
+  pairs?: Array<{ key: string; value: string }>;  // table 模式的结构化结果
+}
+
+function clean(s: string): string {
+  return s.replace(/\s+/g, ' ').trim();
+}
+
+function extractOne(rule: TextRule): TextMaterial | null {
+  for (const sel of rule.selectors) {
+    let nodes: NodeListOf<Element>;
+    try {
+      nodes = document.querySelectorAll(sel);
+    } catch {
+      continue;
+    }
+    if (!nodes.length) continue;
+
+    // table 模式：参数表
+    if (rule.extract === 'table') {
+      const pairs: Array<{ key: string; value: string }> = [];
+      nodes.forEach(row => {
+        const k = clean(row.querySelector(rule.tableKeySelector ?? '')?.textContent ?? '');
+        const v = clean(row.querySelector(rule.tableValueSelector ?? '')?.textContent ?? '');
+        if (k && v) pairs.push({ key: k.replace(/[:：]$/, ''), value: v });
+      });
+      if (pairs.length) {
+        return {
+          kind: rule.kind,
+          content: pairs.map(p => `${p.key}: ${p.value}`).join('\n'),
+          pairs
+        };
+      }
+      continue;
+    }
+
+    // join 模式：标题被拆成多个 span
+    if (rule.extract === 'join') {
+      let text = '';
+      nodes.forEach(n => { text += n.textContent ?? ''; });
+      text = clean(text);
+      if (text) return { kind: rule.kind, content: text };
+      continue;
+    }
+
+    // first 模式：只取第一个
+    const first = clean(nodes[0].textContent ?? '');
+    if (first) return { kind: rule.kind, content: first };
+  }
+  return null;
+}
+
+export function collectTexts(profile: SiteProfile): {
+  materials: TextMaterial[];
+  missingRequired: string[];
+} {
+  const materials: TextMaterial[] = [];
+  const missingRequired: string[] = [];
+
+  for (const rule of profile.textRules) {
+    const m = extractOne(rule);
+    if (m) materials.push(m);
+    else if (rule.required) missingRequired.push(rule.kind);
+  }
+
+  return { materials, missingRequired };
+}