commit

batch_insert_urls.py

@@ -0,0 +1,62 @@
+"""批量插入URL到数据库"""
+from data_manager import DataManager
+
+# 要插入的URL列表
+urls = [
+    "https://health.baidu.com/m/detail/ar_1763832104063502612",
+    "https://health.baidu.com/m/detail/ar_3234161746463547514",
+    "https://health.baidu.com/m/detail/ar_2979413891570169996",
+    "https://health.baidu.com/m/detail/ar_2956015846029041423",
+    "https://health.baidu.com/m/detail/ar_168792171069657865",
+    "https://health.baidu.com/m/detail/ar_6465728881863076989",
+    "https://health.baidu.com/m/detail/ar_5239302258777444788",
+    "https://health.baidu.com/m/detail/ar_4713935339392349406",
+    "https://health.baidu.com/m/detail/ar_5279303492380349045",
+    "https://health.baidu.com/m/detail/ar_3049436766450657685",
+    "https://health.baidu.com/m/detail/ar_2014490668952387433",
+]
+
+print("=" * 60)
+print("批量插入URL到数据库")
+print("=" * 60)
+
+# 创建数据管理器
+dm = DataManager()
+print(f"\n存储方式: {'SQLite数据库' if dm.use_database else 'JSON文件'}")
+print(f"总URL数: {len(urls)}\n")
+
+# 批量插入
+success_count = 0
+failed_count = 0
+
+for idx, url in enumerate(urls, 1):
+    print(f"[{idx}/{len(urls)}] 插入: {url}")
+    result = dm.add_url(url)
+    
+    if result:
+        success_count += 1
+        print(f"  ✓ 成功")
+    else:
+        failed_count += 1
+        print(f"  × 失败（可能已存在）")
+
+# 统计结果
+print("\n" + "=" * 60)
+print("插入完成")
+print("=" * 60)
+print(f"成功: {success_count} 个")
+print(f"失败: {failed_count} 个")
+
+# 显示当前数据库统计
+print("\n数据库统计:")
+stats = dm.get_statistics()
+for key, value in stats.items():
+    print(f"  {key}: {value}")
+
+# 显示所有活跃URL
+print("\n活跃URL列表:")
+active_urls = dm.get_active_urls()
+for idx, site in enumerate(active_urls[:15], 1):
+    site_url = site.get('site_url', site.get('url'))
+    click_count = site.get('click_count', 0)
+    print(f"  {idx}. {site_url} (点击: {click_count}次)")