crawlo 1.2.8__py3-none-any.whl → 1.2.9__py3-none-any.whl

crawlo/templates/project/settings_high_performance.py.tmpl

@@ -1,135 +1,126 @@
-# -*- coding: UTF-8 -*-
-"""
-高性能模式配置模板
-针对大规模高并发优化
-"""
-
-# ============================== 项目基本信息 ==============================
-PROJECT_NAME = '{{project_name}}'
-
-# ============================== 高性能运行模式 ==============================
-# 运行模式：'standalone'(单机), 'distributed'(分布式), 'auto'(自动检测)
-RUN_MODE = 'standalone'  # 单机模式 - 适用于开发和小规模数据采集
-
-# 并发配置
-CONCURRENCY = 32  # 高并发数以充分利用系统资源
-DOWNLOAD_DELAY = 0.1  # 极小延迟以提高吞吐量
-RANDOMNESS = False  # 禁用随机延迟以保证性能
-
-# ============================== 队列配置 ==============================
-
-# 队列类型：'auto'（自动选择）, 'memory'（内存队列）, 'redis'（分布式队列）
-QUEUE_TYPE = 'auto'  # 自动检测，如果Redis可用则使用Redis队列
-SCHEDULER_MAX_QUEUE_SIZE = 5000
-SCHEDULER_QUEUE_NAME = f'crawlo:{{project_name}}:queue:requests'
-QUEUE_MAX_RETRIES = 3
-QUEUE_TIMEOUT = 300
-
-# ============================== 去重过滤配置 ==============================
-
-# 高性能模式下，如果Redis可用则使用Redis去重，否则使用内存去重
-DEFAULT_DEDUP_PIPELINE = 'crawlo.pipelines.redis_dedup_pipeline.RedisDedupPipeline'
-FILTER_CLASS = 'crawlo.filters.aioredis_filter.AioRedisFilter'
-
-# --- Redis 配置（用于分布式去重和队列） ---
-REDIS_HOST = '127.0.0.1'
-REDIS_PORT = 6379
-REDIS_PASSWORD = ''  # 如果有密码，请填写
-
-# 根据是否有密码生成 URL
-if REDIS_PASSWORD:
-    REDIS_URL = f'redis://:{REDIS_PASSWORD}@{REDIS_HOST}:{REDIS_PORT}/0'
-else:
-    REDIS_URL = f'redis://{REDIS_HOST}:{REDIS_PORT}/0'
-
-# Redis key配置已移至各组件中，使用统一的命名规范
-# crawlo:{project_name}:filter:fingerprint (请求去重)
-# crawlo:{project_name}:item:fingerprint (数据项去重)
-# crawlo:{project_name}:queue:requests (请求队列)
-# crawlo:{project_name}:queue:processing (处理中队列)
-# crawlo:{project_name}:queue:failed (失败队列)
-
-REDIS_TTL = 0
-CLEANUP_FP = 0
-FILTER_DEBUG = True
-DECODE_RESPONSES = True
-
-# ============================== 中间件配置 ==============================
-
-MIDDLEWARES = [
-    # === 请求预处理阶段 ===
-    'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
-    'crawlo.middleware.download_delay.DownloadDelayMiddleware',
-    'crawlo.middleware.default_header.DefaultHeaderMiddleware',
-    'crawlo.middleware.proxy.ProxyMiddleware',
-    'crawlo.middleware.offsite.OffsiteMiddleware', 
-    
-    # === 响应处理阶段 ===
-    'crawlo.middleware.retry.RetryMiddleware',
-    'crawlo.middleware.response_code.ResponseCodeMiddleware',
-    'crawlo.middleware.response_filter.ResponseFilterMiddleware',
-]
-
-# ============================== 数据管道配置 ==============================
-
-# 数据处理管道（启用的存储方式）
-PIPELINES = [
-    'crawlo.pipelines.console_pipeline.ConsolePipeline',
-    # '{{project_name}}.pipelines.DatabasePipeline',        # 自定义数据库管道
-    # 'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline',  # MySQL 存储
-    # 'crawlo.pipelines.mongo_pipeline.MongoPipeline',      # MongoDB 存储
-]
-
-# 明确添加默认去重管道到管道列表开头
-PIPELINES.insert(0, DEFAULT_DEDUP_PIPELINE)
-
-# ============================== 扩展组件 ==============================
-
-EXTENSIONS = [
-    'crawlo.extension.log_interval.LogIntervalExtension',
-    'crawlo.extension.log_stats.LogStats',
-    'crawlo.extension.logging_extension.CustomLoggerExtension',
-    # 'crawlo.extension.memory_monitor.MemoryMonitorExtension',  # 内存监控
-    # 'crawlo.extension.request_recorder.RequestRecorderExtension',  # 请求记录
-    # 'crawlo.extension.performance_profiler.PerformanceProfilerExtension',  # 性能分析
-    # 'crawlo.extension.health_check.HealthCheckExtension',  # 健康检查
-]
-
-# ============================== 日志配置 ==============================
-
-LOG_LEVEL = 'INFO'
-STATS_DUMP = True
-LOG_FILE = f'logs/{{project_name}}.log'
-LOG_FORMAT = '%(asctime)s - [%(name)s] - %(levelname)s： %(message)s'
-LOG_ENCODING = 'utf-8'
-
-# ============================== 性能优化配置 ==============================
-
-# 连接池配置
-CONNECTION_POOL_LIMIT = 100
-DOWNLOAD_MAXSIZE = 10 * 1024 * 1024    # 10MB
-DOWNLOAD_WARN_SIZE = 1024 * 1024       # 1MB
-
-# 下载器优化配置
-DOWNLOADER_HEALTH_CHECK = True
-HEALTH_CHECK_INTERVAL = 30
-
-# 请求统计配置
-REQUEST_STATS_ENABLED = True
-STATS_RESET_ON_START = False
-
-# HttpX 下载器专用配置
-HTTPX_HTTP2 = True
-HTTPX_FOLLOW_REDIRECTS = True
-
-# AioHttp 下载器专用配置
-AIOHTTP_AUTO_DECOMPRESS = True
-AIOHTTP_FORCE_CLOSE = False
-
-# 通用优化配置
-CONNECTION_TTL_DNS_CACHE = 300
-CONNECTION_KEEPALIVE_TIMEOUT = 15
-
-# 性能监控
-ENABLE_PERFORMANCE_MONITORING = True
+# -*- coding: UTF-8 -*-
+"""
+高性能模式配置模板
+针对大规模高并发优化
+"""
+
+# ============================== 项目基本信息 ==============================
+PROJECT_NAME = '{{project_name}}'
+
+# ============================== 高性能运行模式 ==============================
+# 运行模式：'standalone'(单机), 'distributed'(分布式), 'auto'(自动检测)
+RUN_MODE = 'standalone'  # 单机模式 - 适用于开发和小规模数据采集
+
+# 并发配置
+CONCURRENCY = 32  # 高并发数以充分利用系统资源
+DOWNLOAD_DELAY = 0.1  # 极小延迟以提高吞吐量
+RANDOMNESS = False  # 禁用随机延迟以保证性能
+
+# ============================== 队列配置 ==============================
+
+# 队列类型：'auto'（自动选择）, 'memory'（内存队列）, 'redis'（分布式队列）
+QUEUE_TYPE = 'auto'  # 自动检测，如果Redis可用则使用Redis队列
+SCHEDULER_MAX_QUEUE_SIZE = 5000
+SCHEDULER_QUEUE_NAME = f'crawlo:{{project_name}}:queue:requests'
+QUEUE_MAX_RETRIES = 3
+QUEUE_TIMEOUT = 300
+
+# ============================== 去重过滤配置 ==============================
+
+# 高性能模式下，如果Redis可用则使用Redis去重，否则使用内存去重
+DEFAULT_DEDUP_PIPELINE = 'crawlo.pipelines.redis_dedup_pipeline.RedisDedupPipeline'
+FILTER_CLASS = 'crawlo.filters.aioredis_filter.AioRedisFilter'
+
+# --- Redis 配置（用于分布式去重和队列） ---
+REDIS_HOST = '127.0.0.1'
+REDIS_PORT = 6379
+REDIS_PASSWORD = ''  # 如果有密码，请填写
+
+# 根据是否有密码生成 URL
+if REDIS_PASSWORD:
+    REDIS_URL = f'redis://:{REDIS_PASSWORD}@{REDIS_HOST}:{REDIS_PORT}/0'
+else:
+    REDIS_URL = f'redis://{REDIS_HOST}:{REDIS_PORT}/0'
+
+# Redis key配置已移至各组件中，使用统一的命名规范
+# crawlo:{project_name}:filter:fingerprint (请求去重)
+# crawlo:{project_name}:item:fingerprint (数据项去重)
+# crawlo:{project_name}:queue:requests (请求队列)
+# crawlo:{project_name}:queue:processing (处理中队列)
+# crawlo:{project_name}:queue:failed (失败队列)
+
+REDIS_TTL = 0
+CLEANUP_FP = 0
+FILTER_DEBUG = True
+DECODE_RESPONSES = True
+
+# ============================== 用户自定义中间件配置 ==============================
+# 注意：框架默认中间件已自动加载，此处可添加或覆盖默认中间件
+
+# 中间件列表（框架默认中间件 + 用户自定义中间件）
+# MIDDLEWARES = [
+    # '{{project_name}}.middlewares.CustomMiddleware',  # 示例自定义中间件
+# ]
+
+# ============================== 用户自定义数据管道配置 ==============================
+# 注意：框架默认管道已自动加载，此处可添加或覆盖默认管道
+
+# 数据处理管道列表（框架默认管道 + 用户自定义管道）
+# PIPELINES = [
+    # '{{project_name}}.pipelines.DatabasePipeline',        # 自定义数据库管道
+    # 'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline',  # MySQL 存储
+    # 'crawlo.pipelines.mongo_pipeline.MongoPipeline',      # MongoDB 存储
+# ]
+
+# 明确添加默认去重管道到管道列表开头
+# PIPELINES.insert(0, DEFAULT_DEDUP_PIPELINE)
+
+# ============================== 用户自定义扩展组件 ==============================
+# 注意：框架默认扩展已自动加载，此处可添加或覆盖默认扩展
+
+# 扩展组件列表（框架默认扩展 + 用户自定义扩展）
+# EXTENSIONS = [
+    # 'crawlo.extension.memory_monitor.MemoryMonitorExtension',  # 内存监控
+    # 'crawlo.extension.request_recorder.RequestRecorderExtension',  # 请求记录
+    # 'crawlo.extension.performance_profiler.PerformanceProfilerExtension',  # 性能分析
+    # 'crawlo.extension.health_check.HealthCheckExtension',  # 健康检查
+# ]
+
+# ============================== 日志配置 ==============================
+
+LOG_LEVEL = 'INFO'
+STATS_DUMP = True
+LOG_FILE = f'logs/{{project_name}}.log'
+LOG_FORMAT = '%(asctime)s - [%(name)s] - %(levelname)s: %(message)s'
+LOG_ENCODING = 'utf-8'
+
+# ============================== 性能优化配置 ==============================
+
+# 连接池配置
+CONNECTION_POOL_LIMIT = 100
+DOWNLOAD_MAXSIZE = 10 * 1024 * 1024    # 10MB
+DOWNLOAD_WARN_SIZE = 1024 * 1024       # 1MB
+
+# 下载器优化配置
+DOWNLOADER_HEALTH_CHECK = True
+HEALTH_CHECK_INTERVAL = 30
+
+# 请求统计配置
+REQUEST_STATS_ENABLED = True
+STATS_RESET_ON_START = False
+
+# HttpX 下载器专用配置
+HTTPX_HTTP2 = True
+HTTPX_FOLLOW_REDIRECTS = True
+
+# AioHttp 下载器专用配置
+AIOHTTP_AUTO_DECOMPRESS = True
+AIOHTTP_FORCE_CLOSE = False
+
+# 通用优化配置
+CONNECTION_TTL_DNS_CACHE = 300
+CONNECTION_KEEPALIVE_TIMEOUT = 15
+
+# 性能监控
+ENABLE_PERFORMANCE_MONITORING = True
 MEMORY_USAGE_WARNING_THRESHOLD = 800  # MB

crawlo/templates/project/settings_minimal.py.tmpl

@@ -0,0 +1,30 @@
+# -*- coding: UTF-8 -*-
+"""
+{{project_name}} 最小化配置文件
+=============================
+仅包含最基本和常用的配置项，适合快速开始和简单项目。
+"""
+
+# ============================== 项目基本信息 ==============================
+PROJECT_NAME = '{{project_name}}'
+
+# ============================== 核心配置 ==============================
+# 并发数
+CONCURRENCY = 4
+
+# 请求延迟（秒）
+DOWNLOAD_DELAY = 1.0
+
+# ============================== 数据存储 ==============================
+# JSON文件存储（默认启用）
+PIPELINES = [
+    'crawlo.pipelines.json_pipeline.JsonPipeline',
+]
+
+# ============================== 日志配置 ==============================
+LOG_LEVEL = 'INFO'
+LOG_FILE = f'logs/{{project_name}}.log'
+STATS_DUMP = True
+
+# ============================== 自定义配置 ==============================
+# 在此处添加项目特定的配置项

crawlo/templates/project/settings_simple.py.tmpl

@@ -1,99 +1,97 @@
-# -*- coding: UTF-8 -*-
-"""
-简化模式配置模板
-最小配置，适合快速开始和简单项目
-"""
-
-# ============================== 项目基本信息 ==============================
-PROJECT_NAME = '{{project_name}}'
-
-# ============================== 简化运行模式 ==============================
-# 运行模式：'standalone'(单机), 'distributed'(分布式), 'auto'(自动检测)
-RUN_MODE = 'standalone'  # 单机模式 - 适用于开发和小规模数据采集
-
-# 并发配置
-CONCURRENCY = 4  # 低并发数以减少资源占用
-DOWNLOAD_DELAY = 1.0  # 增加延迟以降低目标网站压力
-
-# ============================== 队列配置 ==============================
-
-# 队列类型：'auto'（自动选择）, 'memory'（内存队列）, 'redis'（分布式队列）
-QUEUE_TYPE = 'auto'  # 自动检测，如果Redis可用则使用Redis队列
-SCHEDULER_MAX_QUEUE_SIZE = 1000
-SCHEDULER_QUEUE_NAME = f'crawlo:{{project_name}}:queue:requests'
-QUEUE_MAX_RETRIES = 3
-QUEUE_TIMEOUT = 300
-
-# ============================== 去重过滤配置 ==============================
-
-# 简化模式下使用内存去重管道和过滤器
-DEFAULT_DEDUP_PIPELINE = 'crawlo.pipelines.memory_dedup_pipeline.MemoryDedupPipeline'
-FILTER_CLASS = 'crawlo.filters.memory_filter.MemoryFilter'
-
-# --- Redis 配置（用于分布式去重和队列） ---
-REDIS_HOST = '127.0.0.1'
-REDIS_PORT = 6379
-REDIS_PASSWORD = ''  # 如果有密码，请填写
-
-# 根据是否有密码生成 URL
-if REDIS_PASSWORD:
-    REDIS_URL = f'redis://:{REDIS_PASSWORD}@{REDIS_HOST}:{REDIS_PORT}/0'
-else:
-    REDIS_URL = f'redis://{REDIS_HOST}:{REDIS_PORT}/0'
-
-# Redis key配置已移至各组件中，使用统一的命名规范
-# crawlo:{project_name}:filter:fingerprint (请求去重)
-# crawlo:{project_name}:item:fingerprint (数据项去重)
-# crawlo:{project_name}:queue:requests (请求队列)
-# crawlo:{project_name}:queue:processing (处理中队列)
-# crawlo:{project_name}:queue:failed (失败队列)
-
-REDIS_TTL = 0
-CLEANUP_FP = 0
-FILTER_DEBUG = True
-DECODE_RESPONSES = True
-
-# ============================== 中间件配置 ==============================
-
-MIDDLEWARES = [
-    # === 请求预处理阶段 ===
-    'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
-    'crawlo.middleware.download_delay.DownloadDelayMiddleware',
-    'crawlo.middleware.default_header.DefaultHeaderMiddleware',
-    'crawlo.middleware.proxy.ProxyMiddleware',
-    'crawlo.middleware.offsite.OffsiteMiddleware', 
-    
-    # === 响应处理阶段 ===
-    'crawlo.middleware.retry.RetryMiddleware',
-    'crawlo.middleware.response_code.ResponseCodeMiddleware',
-    'crawlo.middleware.response_filter.ResponseFilterMiddleware',
-]
-
-# ============================== 数据管道配置 ==============================
-
-# 数据处理管道（启用的存储方式）
-PIPELINES = [
-    'crawlo.pipelines.console_pipeline.ConsolePipeline',
-    # '{{project_name}}.pipelines.DatabasePipeline',        # 自定义数据库管道
-    # 'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline',  # MySQL 存储
-    # 'crawlo.pipelines.mongo_pipeline.MongoPipeline',      # MongoDB 存储
-]
-
-# 明确添加默认去重管道到管道列表开头
-PIPELINES.insert(0, DEFAULT_DEDUP_PIPELINE)
-
-# ============================== 扩展组件 ==============================
-
-EXTENSIONS = [
-    'crawlo.extension.log_interval.LogIntervalExtension',
-    'crawlo.extension.log_stats.LogStats',
-    'crawlo.extension.logging_extension.CustomLoggerExtension',
-]
-
-# ============================== 日志配置 ==============================
-
-LOG_LEVEL = 'INFO'
-STATS_DUMP = True
-LOG_FILE = f'logs/{{project_name}}.log'
-LOG_FORMAT = '%(asctime)s - [%(name)s] - %(levelname)s： %(message)s'
+# -*- coding: UTF-8 -*-
+"""
+简化模式配置模板
+最小配置，适合快速开始和简单项目
+"""
+
+# ============================== 项目基本信息 ==============================
+PROJECT_NAME = '{{project_name}}'
+
+# ============================== 简化运行模式 ==============================
+# 运行模式：'standalone'(单机), 'distributed'(分布式), 'auto'(自动检测)
+RUN_MODE = 'standalone'  # 单机模式 - 适用于开发和小规模数据采集
+
+# 并发配置
+CONCURRENCY = 4  # 低并发数以减少资源占用
+DOWNLOAD_DELAY = 1.0  # 增加延迟以降低目标网站压力
+
+# ============================== 队列配置 ==============================
+
+# 注意：框架已提供默认的队列配置，以下配置项通常无需修改
+# 如需自定义，请取消注释并修改相应值
+
+# 队列类型：'auto'（自动选择）, 'memory'（内存队列）, 'redis'（分布式队列）
+# QUEUE_TYPE = 'auto'  # 自动检测，如果Redis可用则使用Redis队列
+# SCHEDULER_MAX_QUEUE_SIZE = 1000
+# SCHEDULER_QUEUE_NAME = f'crawlo:{{project_name}}:queue:requests'
+# QUEUE_MAX_RETRIES = 3
+# QUEUE_TIMEOUT = 300
+
+# ============================== 去重过滤配置 ==============================
+
+# 注意：框架已提供默认的去重配置，以下配置项通常无需修改
+# 如需自定义，请取消注释并修改相应值
+
+# 简化模式下使用内存去重管道和过滤器
+# DEFAULT_DEDUP_PIPELINE = 'crawlo.pipelines.memory_dedup_pipeline.MemoryDedupPipeline'
+# FILTER_CLASS = 'crawlo.filters.memory_filter.MemoryFilter'
+
+# --- Redis 配置（用于分布式去重和队列） ---
+# REDIS_HOST = '127.0.0.1'
+# REDIS_PORT = 6379
+# REDIS_PASSWORD = ''  # 如果有密码，请填写
+
+# 根据是否有密码生成 URL
+# if REDIS_PASSWORD:
+#     REDIS_URL = f'redis://:{REDIS_PASSWORD}@{REDIS_HOST}:{REDIS_PORT}/0'
+# else:
+#     REDIS_URL = f'redis://{REDIS_HOST}:{REDIS_PORT}/0'
+
+# Redis key配置已移至各组件中，使用统一的命名规范
+# crawlo:{project_name}:filter:fingerprint (请求去重)
+# crawlo:{project_name}:item:fingerprint (数据项去重)
+# crawlo:{project_name}:queue:requests (请求队列)
+# crawlo:{project_name}:queue:processing (处理中队列)
+# crawlo:{project_name}:queue:failed (失败队列)
+
+# REDIS_TTL = 0
+# CLEANUP_FP = 0
+# FILTER_DEBUG = True
+# DECODE_RESPONSES = True
+
+# ============================== 用户自定义中间件配置 ==============================
+# 注意：框架默认中间件已自动加载，此处可添加或覆盖默认中间件
+
+# 中间件列表（框架默认中间件 + 用户自定义中间件）
+# MIDDLEWARES = [
+    # '{{project_name}}.middlewares.CustomMiddleware',  # 示例自定义中间件
+# ]
+
+# ============================== 用户自定义数据管道配置 ==============================
+# 注意：框架默认管道已自动加载，此处可添加或覆盖默认管道
+
+# 数据处理管道列表（框架默认管道 + 用户自定义管道）
+# PIPELINES = [
+    # '{{project_name}}.pipelines.DatabasePipeline',        # 自定义数据库管道
+    # 'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline',  # MySQL 存储
+    # 'crawlo.pipelines.mongo_pipeline.MongoPipeline',      # MongoDB 存储
+# ]
+
+# ============================== 用户自定义扩展组件 ==============================
+# 注意：框架默认扩展已自动加载，此处可添加或覆盖默认扩展
+
+# 扩展组件列表（框架默认扩展 + 用户自定义扩展）
+# EXTENSIONS = [
+    # 'crawlo.extension.memory_monitor.MemoryMonitorExtension',  # 内存监控
+    # 'crawlo.extension.request_recorder.RequestRecorderExtension',  # 请求记录
+    # 'crawlo.extension.performance_profiler.PerformanceProfilerExtension',  # 性能分析
+    # 'crawlo.extension.health_check.HealthCheckExtension',  # 健康检查
+# ]
+
+# ============================== 日志配置 ==============================
+
+LOG_LEVEL = 'INFO'
+STATS_DUMP = True
+LOG_FILE = f'logs/{{project_name}}.log'
+LOG_FORMAT = '%(asctime)s - [%(name)s] - %(levelname)s: %(message)s'
 LOG_ENCODING = 'utf-8'

crawlo/templates/project/spiders/__init__.py.tmpl

@@ -1,6 +1,6 @@
-# -*- coding: UTF-8 -*-
-"""
-{{project_name}}.spiders
-========================
-存放所有的爬虫。
+# -*- coding: UTF-8 -*-
+"""
+{{project_name}}.spiders
+========================
+存放所有的爬虫。
 """

crawlo/templates/run.py.tmpl

@@ -1,48 +1,48 @@
-#!/usr/bin/env python
-# -*- coding: UTF-8 -*-
-"""
-{{project_name}} 项目运行脚本
-============================
-基于 Crawlo 框架的简化爬虫启动器。
-"""
-
-import sys
-import os
-import asyncio
-
-# 添加项目根目录到 Python 路径
-project_root = os.path.dirname(os.path.abspath(__file__))
-sys.path.insert(0, project_root)
-
-# 切换到项目根目录
-os.chdir(project_root)
-
-from crawlo.crawler import CrawlerProcess
-
-
-def main():
-    """主函数：运行固定的爬虫"""
-    print("🚀 启动 {{project_name}} 爬虫")
-    
-    # 创建爬虫进程（自动加载默认配置）
-    try:
-        # 确保 spider 模块被正确导入
-        spider_modules = ['{{project_name}}.spiders']
-        process = CrawlerProcess(spider_modules=spider_modules)
-        print("✅ 爬虫进程初始化成功")
-        
-        # 运行固定的爬虫
-        # TODO: 请将 'your_spider_name' 替换为实际的爬虫名称
-        asyncio.run(process.crawl('your_spider_name'))
-        
-        print("✅ 爬虫运行完成")
-        
-    except Exception as e:
-        print(f"❌ 运行失败: {e}")
-        import traceback
-        traceback.print_exc()
-        sys.exit(1)
-
-
-if __name__ == '__main__':
+#!/usr/bin/env python
+# -*- coding: UTF-8 -*-
+"""
+{{project_name}} 项目运行脚本
+============================
+基于 Crawlo 框架的简化爬虫启动器。
+"""
+
+import sys
+import os
+import asyncio
+
+# 添加项目根目录到 Python 路径
+project_root = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, project_root)
+
+# 切换到项目根目录
+os.chdir(project_root)
+
+from crawlo.crawler import CrawlerProcess
+
+
+def main():
+    """主函数：运行固定的爬虫"""
+    print("🚀 启动 {{project_name}} 爬虫")
+    
+    # 创建爬虫进程（自动加载默认配置）
+    try:
+        # 确保 spider 模块被正确导入
+        spider_modules = ['{{project_name}}.spiders']
+        process = CrawlerProcess(spider_modules=spider_modules)
+        print("✅ 爬虫进程初始化成功")
+        
+        # 运行固定的爬虫
+        # TODO: 请将 'your_spider_name' 替换为实际的爬虫名称
+        asyncio.run(process.crawl('your_spider_name'))
+        
+        print("✅ 爬虫运行完成")
+        
+    except Exception as e:
+        print(f"❌ 运行失败: {e}")
+        import traceback
+        traceback.print_exc()
+        sys.exit(1)
+
+
+if __name__ == '__main__':
     main()