#!/usr/bin/env python # -*- coding: utf-8 -*- import os import sqlite3 import csv import sys import argparse from datetime import datetime # 数据库路径 db_path = '/root/autodl-tmp/TravelContentCreator/distribution.db' def query_products(product_name=None, object_name=None, output_file=None, show_undistributed_only=False): """查询产品信息 Args: product_name: 产品名称（可选） object_name: 景点名称（可选） output_file: 输出CSV文件路径（可选） show_undistributed_only: 是否只显示未分发的内容 Returns: 查询结果列表 """ # 连接数据库 try: conn = sqlite3.connect(db_path) conn.row_factory = sqlite3.Row # 设置结果为字典格式 cursor = conn.cursor() print(f"已连接到数据库: {db_path}") except sqlite3.Error as e: print(f"数据库连接错误: {e}") return [] try: # 构建查询条件 conditions = [] params = [] if product_name: conditions.append("product LIKE ?") params.append(f"%{product_name}%") if object_name: conditions.append("object LIKE ?") params.append(f"%{object_name}%") if show_undistributed_only: conditions.append("is_distributed = 0") # 构建WHERE子句 where_clause = " AND ".join(conditions) if conditions else "1=1" # 执行查询 query = f""" SELECT id, entry_id, product, object, date, logic, judge_status, output_txt_path, poster_path, article_json_path, created_at, is_distributed FROM contents WHERE {where_clause} ORDER BY product, object, entry_id """ cursor.execute(query, params) results = [dict(row) for row in cursor.fetchall()] # 获取分布统计信息 statistics = {} if results: # 按产品分组统计 cursor.execute(f""" SELECT product, COUNT(*) as count, COUNT(CASE WHEN judge_status = 1 THEN 1 END) as approved_count, COUNT(CASE WHEN is_distributed = 1 THEN 1 END) as distributed_count FROM contents WHERE product IS NOT NULL AND product != '' AND {where_clause} GROUP BY product ORDER BY count DESC """, params) statistics['products'] = [dict(row) for row in cursor.fetchall()] # 按景点分组统计 cursor.execute(f""" SELECT object, COUNT(*) as count, COUNT(CASE WHEN judge_status = 1 THEN 1 END) as approved_count, COUNT(CASE WHEN is_distributed = 1 THEN 1 END) as distributed_count FROM contents WHERE object IS NOT NULL AND object != '' AND {where_clause} GROUP BY object ORDER BY count DESC LIMIT 20 """, params) statistics['objects'] = [dict(row) for row in cursor.fetchall()] # 输出结果 if results: print(f"\n查询到 {len(results)} 条产品记录") # 输出前10条记录 print("\n===== 查询结果 (前10条) =====") for i, row in enumerate(results[:10], 1): judge_status = '已通过' if row['judge_status'] == 1 else '未通过' if row['judge_status'] == 0 else '未知' distributed = '已分发' if row['is_distributed'] == 1 else '未分发' print(f"{i}. ID: {row['entry_id']}, 产品: {row['product']}, 景点: {row['object']}, 审核: {judge_status}, 分发状态: {distributed}") if len(results) > 10: print(f"... 还有 {len(results) - 10} 条记录未显示") # 输出统计信息 if 'products' in statistics and statistics['products']: print("\n===== 产品统计 =====") for prod in statistics['products']: dist_percent = (prod['distributed_count'] / prod['count'] * 100) if prod['count'] > 0 else 0 approved_percent = (prod['approved_count'] / prod['count'] * 100) if prod['count'] > 0 else 0 print(f"产品: {prod['product']}") print(f" - 内容总数: {prod['count']}") print(f" - 已审核通过: {prod['approved_count']} ({approved_percent:.1f}%)") print(f" - 已分发: {prod['distributed_count']} ({dist_percent:.1f}%)") print(f" - 未分发: {prod['count'] - prod['distributed_count']} ({100 - dist_percent:.1f}%)") if 'objects' in statistics and statistics['objects'] and len(statistics['objects']) <= 10: print("\n===== 景点统计 =====") for obj in statistics['objects']: dist_percent = (obj['distributed_count'] / obj['count'] * 100) if obj['count'] > 0 else 0 approved_percent = (obj['approved_count'] / obj['count'] * 100) if obj['count'] > 0 else 0 print(f"景点: {obj['object']}") print(f" - 内容总数: {obj['count']}") print(f" - 已审核通过: {obj['approved_count']} ({approved_percent:.1f}%)") print(f" - 已分发: {obj['distributed_count']} ({dist_percent:.1f}%)") print(f" - 未分发: {obj['count'] - obj['distributed_count']} ({100 - dist_percent:.1f}%)") # 未分发内容和已分发内容的汇总 total_count = len(results) distributed_count = sum(1 for r in results if r['is_distributed'] == 1) undistributed_count = total_count - distributed_count print("\n===== 分发状态汇总 =====") print(f"总内容数: {total_count}") print(f"已分发: {distributed_count} ({distributed_count/total_count*100:.1f}% 如果为0)" if total_count > 0 else "已分发: 0 (0%)") print(f"未分发: {undistributed_count} ({undistributed_count/total_count*100:.1f}% 如果为100%)" if total_count > 0 else "未分发: 0 (0%)") # 如果指定了输出文件，保存结果到CSV if output_file: # 确保目录存在 os.makedirs(os.path.dirname(os.path.abspath(output_file)), exist_ok=True) with open(output_file, 'w', newline='', encoding='utf-8-sig') as f: if results: # 确定CSV列 fieldnames = list(results[0].keys()) writer = csv.DictWriter(f, fieldnames=fieldnames) writer.writeheader() writer.writerows(results) print(f"\n查询结果已保存到: {output_file}") else: print("\n未查询到相关产品记录") # 检查数据库是否有任何内容记录 cursor.execute("SELECT COUNT(*) as count FROM contents") count = cursor.fetchone()['count'] if count == 0: print("\n提示: 数据库中没有任何内容记录，请先导入数据") else: print(f"\n提示: 数据库中有 {count} 条内容记录，但没有符合条件的产品") return results except Exception as e: print(f"查询产品时出错: {e}") import traceback traceback.print_exc() return [] finally: conn.close() def main(): parser = argparse.ArgumentParser(description="查询数据库中的产品信息") parser.add_argument("--product", type=str, help="按产品名称查询") parser.add_argument("--object", type=str, help="按景点名称查询") parser.add_argument("--output", type=str, help="输出CSV文件路径") parser.add_argument("--all", action="store_true", help="查询所有产品") parser.add_argument("--export-csv", action="store_true", help="导出结果到CSV文件") parser.add_argument("--undistributed", action="store_true", help="只显示未分发的内容") args = parser.parse_args() # 默认输出文件 output_file = None if args.output: output_file = args.output elif args.export_csv or args.all: timestamp = datetime.now().strftime('%Y%m%d_%H%M%S') suffix = "_undistributed" if args.undistributed else "" output_file = f"/root/autodl-tmp/TravelContentCreator/output/product_query{suffix}_{timestamp}.csv" # 执行查询 if args.product or args.object or args.all or args.undistributed: results = query_products(args.product, args.object, output_file, args.undistributed) return len(results) > 0 else: print("请提供查询条件: --product, --object, --all 或 --undistributed") parser.print_help() return False if __name__ == "__main__": success = main() sys.exit(0 if success else 1)