crawlo 1.2.3__py3-none-any.whl → 1.2.5__py3-none-any.whl

crawlo/templates/project/settings_distributed.py.tmpl

@@ -1,122 +1,155 @@
-# -*- coding: UTF-8 -*-
-"""
-{{project_name}} 项目配置文件（分布式版）
-=============================
-基于 Crawlo 框架的分布式爬虫项目配置。
-适合大规模数据采集和多节点部署。
-"""
-
-import os
-from crawlo.config import CrawloConfig
-
-# ============================== 项目基本信息 ==============================
-PROJECT_NAME = '{{project_name}}'
-VERSION = '1.0.0'
-
-# ============================== 分布式配置 ==============================
-# 使用配置工厂创建分布式配置
-CONFIG = CrawloConfig.distributed(
-    redis_host=os.getenv('REDIS_HOST', '127.0.0.1'),
-    redis_port=int(os.getenv('REDIS_PORT', 6379)),
-    redis_password=os.getenv('REDIS_PASSWORD', ''),
-    project_name='{{project_name}}',
-    concurrency=16,
-    download_delay=1.0
-)
-
-# 获取配置
-locals().update(CONFIG.to_dict())
-
-# ============================== 网络请求配置 ==============================
-DOWNLOADER = "crawlo.downloader.httpx_downloader.HttpXDownloader"
-DOWNLOAD_TIMEOUT = 60
-VERIFY_SSL = True
-
-# ============================== 并发配置 ==============================
-CONCURRENCY = 16
-MAX_RUNNING_SPIDERS = 5
-DOWNLOAD_DELAY = 1.0
-
-# ============================== 队列配置 ==============================
-SCHEDULER_MAX_QUEUE_SIZE = 5000
-QUEUE_MAX_RETRIES = 5
-QUEUE_TIMEOUT = 300
-
-# ============================== Redis 配置 ==============================
-REDIS_HOST = os.getenv('REDIS_HOST', '127.0.0.1')
-REDIS_PORT = int(os.getenv('REDIS_PORT', 6379))
-REDIS_PASSWORD = os.getenv('REDIS_PASSWORD', '')
-REDIS_DB = int(os.getenv('REDIS_DB', 0))
-
-# 根据是否有密码生成 URL
-if REDIS_PASSWORD:
-    REDIS_URL = f'redis://:{REDIS_PASSWORD}@{REDIS_HOST}:{REDIS_PORT}/{REDIS_DB}'
-else:
-    REDIS_URL = f'redis://{REDIS_HOST}:{REDIS_PORT}/{REDIS_DB}'
-
-# ============================== 数据存储配置 ==============================
-# MySQL 配置
-MYSQL_HOST = os.getenv('MYSQL_HOST', '127.0.0.1')
-MYSQL_PORT = int(os.getenv('MYSQL_PORT', 3306))
-MYSQL_USER = os.getenv('MYSQL_USER', 'root')
-MYSQL_PASSWORD = os.getenv('MYSQL_PASSWORD', '123456')
-MYSQL_DB = os.getenv('MYSQL_DB', '{{project_name}}')
-MYSQL_TABLE = '{{project_name}}_data'
-MYSQL_BATCH_SIZE = 100
-MYSQL_USE_BATCH = True
-
-# MongoDB 配置
-MONGO_URI = os.getenv('MONGO_URI', 'mongodb://localhost:27017')
-MONGO_DATABASE = '{{project_name}}_db'
-MONGO_COLLECTION = '{{project_name}}_items'
-MONGO_BATCH_SIZE = 100
-MONGO_USE_BATCH = True
-
-# ============================== 去重配置 ==============================
-REDIS_TTL = 0
-CLEANUP_FP = 0
-FILTER_DEBUG = True
-
-# ============================== 中间件与管道 ==============================
-MIDDLEWARES = [
-    'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
-    'crawlo.middleware.download_delay.DownloadDelayMiddleware',
-    'crawlo.middleware.default_header.DefaultHeaderMiddleware',
-    'crawlo.middleware.proxy.ProxyMiddleware',
-    'crawlo.middleware.offsite.OffsiteMiddleware', 
-    
-    'crawlo.middleware.retry.RetryMiddleware',
-    'crawlo.middleware.response_code.ResponseCodeMiddleware',
-    'crawlo.middleware.response_filter.ResponseFilterMiddleware',
-]
-
-PIPELINES = [
-    'crawlo.pipelines.console_pipeline.ConsolePipeline',
-    # '{{project_name}}.pipelines.DatabasePipeline',
-    # 'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline',
-    # 'crawlo.pipelines.mongo_pipeline.MongoPipeline',
-]
-
-# ============================== 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',
-    # 'crawlo.extension.request_recorder.RequestRecorderExtension',
-]
-
-# ============================== 日志配置 ==============================
-LOG_LEVEL = 'INFO'
-LOG_FILE = f'logs/{{project_name}}.log'
-STATS_DUMP = True
-
-# ============================== 代理配置 ==============================
-PROXY_ENABLED = False
-PROXY_API_URL = ""
-PROXY_EXTRACTOR = "proxy"
-PROXY_REFRESH_INTERVAL = 60
-PROXY_API_TIMEOUT = 10
-
-# ============================== 自定义配置 ==============================
+# -*- coding: UTF-8 -*-
+"""
+{{project_name}} 项目配置文件（分布式版）
+=============================
+基于 Crawlo 框架的分布式爬虫项目配置。
+适合大规模数据采集和多节点部署。
+"""
+import os
+from crawlo.config import CrawloConfig
+
+# ============================== 项目基本信息 ==============================
+PROJECT_NAME = '{{project_name}}'
+
+# ============================== 分布式配置说明 ==============================
+# 
+# 本模板专为分布式部署设计，适用于以下场景：
+# - 大规模数据采集任务
+# - 需要多节点协同工作的项目
+# - 高并发、高吞吐量需求
+# 
+# 运行模式特点：
+# - RUN_MODE = 'distributed'（分布式模式）
+# - QUEUE_TYPE = 'redis'（使用Redis队列实现分布式协调）
+# - FILTER_CLASS = 'crawlo.filters.aioredis_filter.AioRedisFilter'（Redis过滤器）
+# - DEFAULT_DEDUP_PIPELINE = 'crawlo.pipelines.redis_dedup_pipeline.RedisDedupPipeline'（Redis去重）
+# 
+# 部署要求：
+# - 需要配置Redis服务器连接参数
+# - 建议使用独立的Redis数据库避免数据冲突
+# - 多节点部署时确保所有节点能访问同一Redis实例
+#
+# 🎯 最佳使用方式：
+# 推荐使用配置工厂方式创建分布式配置：
+# from crawlo.config import CrawloConfig
+# config = CrawloConfig.distributed(
+#     redis_host='your_redis_host',
+#     redis_port=6379,
+#     redis_password='your_password',
+#     project_name='{{project_name}}'
+# )
+# process = CrawlerProcess(settings=config.to_dict())
+
+# ============================== 分布式配置 ==============================
+# 使用配置工厂创建分布式配置
+CONFIG = CrawloConfig.distributed(
+    redis_host=os.getenv('REDIS_HOST', '127.0.0.1'),
+    redis_port=int(os.getenv('REDIS_PORT', 6379)),
+    redis_password=os.getenv('REDIS_PASSWORD', ''),
+    project_name='{{project_name}}',
+    concurrency=16,
+    download_delay=1.0
+)
+
+# 获取配置
+locals().update(CONFIG.to_dict())
+
+# ============================== 网络请求配置 ==============================
+DOWNLOADER = "crawlo.downloader.httpx_downloader.HttpXDownloader"
+DOWNLOAD_TIMEOUT = 60
+VERIFY_SSL = True
+
+# ============================== 并发配置 ==============================
+CONCURRENCY = 16
+MAX_RUNNING_SPIDERS = 5
+DOWNLOAD_DELAY = 1.0
+
+# ============================== 队列配置 ==============================
+SCHEDULER_MAX_QUEUE_SIZE = 5000
+QUEUE_MAX_RETRIES = 5
+QUEUE_TIMEOUT = 300
+
+# ============================== Redis 配置 ==============================
+REDIS_HOST = os.getenv('REDIS_HOST', '127.0.0.1')
+REDIS_PORT = int(os.getenv('REDIS_PORT', 6379))
+REDIS_PASSWORD = os.getenv('REDIS_PASSWORD', '')
+REDIS_DB = int(os.getenv('REDIS_DB', 0))
+
+# 根据是否有密码生成 URL
+if REDIS_PASSWORD:
+    REDIS_URL = f'redis://:{REDIS_PASSWORD}@{REDIS_HOST}:{REDIS_PORT}/{REDIS_DB}'
+else:
+    REDIS_URL = f'redis://{REDIS_HOST}:{REDIS_PORT}/{REDIS_DB}'
+
+# ============================== 数据存储配置 ==============================
+# MySQL 配置
+MYSQL_HOST = os.getenv('MYSQL_HOST', '127.0.0.1')
+MYSQL_PORT = int(os.getenv('MYSQL_PORT', 3306))
+MYSQL_USER = os.getenv('MYSQL_USER', 'root')
+MYSQL_PASSWORD = os.getenv('MYSQL_PASSWORD', '123456')
+MYSQL_DB = os.getenv('MYSQL_DB', '{{project_name}}')
+MYSQL_TABLE = '{{project_name}}_data'
+MYSQL_BATCH_SIZE = 100
+MYSQL_USE_BATCH = True
+
+# MongoDB 配置
+MONGO_URI = os.getenv('MONGO_URI', 'mongodb://localhost:27017')
+MONGO_DATABASE = '{{project_name}}_db'
+MONGO_COLLECTION = '{{project_name}}_items'
+MONGO_BATCH_SIZE = 100
+MONGO_USE_BATCH = True
+
+# ============================== 去重配置 ==============================
+# 明确指定分布式模式下使用Redis去重管道
+DEFAULT_DEDUP_PIPELINE = 'crawlo.pipelines.redis_dedup_pipeline.RedisDedupPipeline'
+FILTER_CLASS = 'crawlo.filters.aioredis_filter.AioRedisFilter'
+REDIS_TTL = 0
+CLEANUP_FP = 0
+FILTER_DEBUG = True
+
+# ============================== 中间件与管道 ==============================
+MIDDLEWARES = [
+    'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
+    'crawlo.middleware.download_delay.DownloadDelayMiddleware',
+    'crawlo.middleware.default_header.DefaultHeaderMiddleware',
+    'crawlo.middleware.proxy.ProxyMiddleware',
+    'crawlo.middleware.offsite.OffsiteMiddleware', 
+    
+    'crawlo.middleware.retry.RetryMiddleware',
+    'crawlo.middleware.response_code.ResponseCodeMiddleware',
+    'crawlo.middleware.response_filter.ResponseFilterMiddleware',
+]
+
+PIPELINES = [
+    'crawlo.pipelines.console_pipeline.ConsolePipeline',
+    # '{{project_name}}.pipelines.DatabasePipeline',
+    # 'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline',
+    # 'crawlo.pipelines.mongo_pipeline.MongoPipeline',
+]
+
+# 明确添加Redis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',
+    # 'crawlo.extension.request_recorder.RequestRecorderExtension',
+]
+
+# ============================== 日志配置 ==============================
+LOG_LEVEL = 'INFO'
+LOG_FILE = f'logs/{{project_name}}.log'
+STATS_DUMP = True
+
+# ============================== 代理配置 ==============================
+PROXY_ENABLED = False
+PROXY_API_URL = ""
+PROXY_EXTRACTOR = "proxy"
+PROXY_REFRESH_INTERVAL = 60
+PROXY_API_TIMEOUT = 10
+
+# ============================== 自定义配置 ==============================
 # 在此处添加项目特定的配置项

crawlo/templates/project/settings_gentle.py.tmpl

@@ -1,95 +1,128 @@
-# -*- coding: UTF-8 -*-
-"""
-{{project_name}} 项目配置文件（温和版）
-=============================
-基于 Crawlo 框架的温和爬虫项目配置。
-适合对目标网站友好的低负载爬取。
-"""
-
-import os
-from crawlo.config import CrawloConfig
-
-# ============================== 项目基本信息 ==============================
-PROJECT_NAME = '{{project_name}}'
-VERSION = '1.0.0'
-
-# ============================== 温和模式配置 ==============================
-# 使用配置工厂创建温和模式配置
-CONFIG = CrawloConfig.presets().gentle()
-
-# 获取配置
-locals().update(CONFIG.to_dict())
-
-# ============================== 网络请求配置 ==============================
-DOWNLOADER = "crawlo.downloader.httpx_downloader.HttpXDownloader"
-DOWNLOAD_TIMEOUT = 60
-VERIFY_SSL = True
-
-# ============================== 低并发配置 ==============================
-CONCURRENCY = 2
-MAX_RUNNING_SPIDERS = 1
-DOWNLOAD_DELAY = 3.0
-RANDOMNESS = True
-RANDOM_RANGE = (2.0, 5.0)
-
-# ============================== 连接池配置 ==============================
-CONNECTION_POOL_LIMIT = 10
-CONNECTION_POOL_LIMIT_PER_HOST = 5
-
-# ============================== 重试配置 ==============================
-MAX_RETRY_TIMES = 3
-RETRY_HTTP_CODES = [408, 429, 500, 502, 503, 504, 522, 524]
-IGNORE_HTTP_CODES = [403, 404]
-
-# ============================== 队列配置 ==============================
-SCHEDULER_MAX_QUEUE_SIZE = 1000
-QUEUE_MAX_RETRIES = 3
-QUEUE_TIMEOUT = 300
-
-# ============================== 数据存储配置 ==============================
-# MySQL 配置
-MYSQL_HOST = os.getenv('MYSQL_HOST', '127.0.0.1')
-MYSQL_PORT = int(os.getenv('MYSQL_PORT', 3306))
-MYSQL_USER = os.getenv('MYSQL_USER', 'root')
-MYSQL_PASSWORD = os.getenv('MYSQL_PASSWORD', '123456')
-MYSQL_DB = os.getenv('MYSQL_DB', '{{project_name}}')
-MYSQL_TABLE = '{{project_name}}_data'
-
-# MongoDB 配置
-MONGO_URI = os.getenv('MONGO_URI', 'mongodb://localhost:27017')
-MONGO_DATABASE = '{{project_name}}_db'
-MONGO_COLLECTION = '{{project_name}}_items'
-
-# ============================== 去重配置 ==============================
-REDIS_TTL = 0
-CLEANUP_FP = 0
-FILTER_DEBUG = True
-
-# ============================== 中间件与管道 ==============================
-MIDDLEWARES = [
-    'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
-    'crawlo.middleware.download_delay.DownloadDelayMiddleware',
-    'crawlo.middleware.default_header.DefaultHeaderMiddleware',
-    'crawlo.middleware.retry.RetryMiddleware',
-    'crawlo.middleware.response_code.ResponseCodeMiddleware',
-]
-
-PIPELINES = [
-    'crawlo.pipelines.console_pipeline.ConsolePipeline',
-    # '{{project_name}}.pipelines.DatabasePipeline',
-]
-
-# ============================== 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'
-LOG_FILE = f'logs/{{project_name}}.log'
-STATS_DUMP = True
-
-# ============================== 自定义配置 ==============================
+# -*- coding: UTF-8 -*-
+"""
+{{project_name}} 项目配置文件（温和版）
+=============================
+基于 Crawlo 框架的温和爬虫项目配置。
+适合对目标网站友好的低负载爬取。
+"""
+import os
+from crawlo.config import CrawloConfig
+
+# ============================== 项目基本信息 ==============================
+PROJECT_NAME = '{{project_name}}'
+
+# ============================== 温和模式配置说明 ==============================
+# 
+# 本模板专为对目标网站友好的低负载爬取设计，适用于以下场景：
+# - 需要避免对目标网站造成过大压力
+# - 长时间运行的监控类爬虫
+# - 对目标网站有友好性要求的项目
+# 
+# 运行模式特点：
+# - RUN_MODE = 'standalone'（单机模式）
+# - QUEUE_TYPE = 'memory'（使用内存队列）
+# - FILTER_CLASS = 'crawlo.filters.memory_filter.MemoryFilter'（内存过滤器）
+# - DEFAULT_DEDUP_PIPELINE = 'crawlo.pipelines.memory_dedup_pipeline.MemoryDedupPipeline'（内存去重）
+# 
+# 配置特点：
+# - 低并发：CONCURRENCY = 2
+# - 高延迟：DOWNLOAD_DELAY = 3.0秒
+# - 随机化：启用RANDOMNESS增加随机性
+# - 连接池限制：减少连接数避免给服务器造成压力
+# 
+# 扩展建议：
+# - 如需跨会话去重，可将FILTER_CLASS和DEFAULT_DEDUP_PIPELINE改为Redis实现
+# - 可根据目标网站特性调整DOWNLOAD_DELAY和RANDOM_RANGE参数
+#
+# 🎯 最佳使用方式：
+# 推荐使用配置工厂方式创建温和模式配置：
+# from crawlo.config import CrawloConfig
+# config = CrawloConfig.presets().gentle()
+# process = CrawlerProcess(settings=config.to_dict())
+
+# ============================== 温和模式配置 ==============================
+# 使用配置工厂创建温和模式配置
+CONFIG = CrawloConfig.presets().gentle()
+
+# 获取配置
+locals().update(CONFIG.to_dict())
+
+# ============================== 网络请求配置 ==============================
+DOWNLOADER = "crawlo.downloader.httpx_downloader.HttpXDownloader"
+DOWNLOAD_TIMEOUT = 60
+VERIFY_SSL = True
+
+# ============================== 低并发配置 ==============================
+CONCURRENCY = 2
+MAX_RUNNING_SPIDERS = 1
+DOWNLOAD_DELAY = 3.0
+RANDOMNESS = True
+RANDOM_RANGE = (2.0, 5.0)
+
+# ============================== 连接池配置 ==============================
+CONNECTION_POOL_LIMIT = 10
+CONNECTION_POOL_LIMIT_PER_HOST = 5
+
+# ============================== 重试配置 ==============================
+MAX_RETRY_TIMES = 3
+RETRY_HTTP_CODES = [408, 429, 500, 502, 503, 504, 522, 524]
+IGNORE_HTTP_CODES = [403, 404]
+
+# ============================== 队列配置 ==============================
+SCHEDULER_MAX_QUEUE_SIZE = 1000
+QUEUE_MAX_RETRIES = 3
+QUEUE_TIMEOUT = 300
+
+# ============================== 数据存储配置 ==============================
+# MySQL 配置
+MYSQL_HOST = os.getenv('MYSQL_HOST', '127.0.0.1')
+MYSQL_PORT = int(os.getenv('MYSQL_PORT', 3306))
+MYSQL_USER = os.getenv('MYSQL_USER', 'root')
+MYSQL_PASSWORD = os.getenv('MYSQL_PASSWORD', '123456')
+MYSQL_DB = os.getenv('MYSQL_DB', '{{project_name}}')
+MYSQL_TABLE = '{{project_name}}_data'
+
+# MongoDB 配置
+MONGO_URI = os.getenv('MONGO_URI', 'mongodb://localhost:27017')
+MONGO_DATABASE = '{{project_name}}_db'
+MONGO_COLLECTION = '{{project_name}}_items'
+
+# ============================== 去重配置 ==============================
+# 明确指定温和模式下使用内存去重管道
+DEFAULT_DEDUP_PIPELINE = 'crawlo.pipelines.memory_dedup_pipeline.MemoryDedupPipeline'
+FILTER_CLASS = 'crawlo.filters.memory_filter.MemoryFilter'
+REDIS_TTL = 0
+CLEANUP_FP = 0
+FILTER_DEBUG = True
+
+# ============================== 中间件与管道 ==============================
+MIDDLEWARES = [
+    'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
+    'crawlo.middleware.download_delay.DownloadDelayMiddleware',
+    'crawlo.middleware.default_header.DefaultHeaderMiddleware',
+    'crawlo.middleware.retry.RetryMiddleware',
+    'crawlo.middleware.response_code.ResponseCodeMiddleware',
+]
+
+PIPELINES = [
+    'crawlo.pipelines.console_pipeline.ConsolePipeline',
+    # '{{project_name}}.pipelines.DatabasePipeline',
+]
+
+# 明确添加内存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'
+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