crawlo 1.2.6__py3-none-any.whl → 1.2.8__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of crawlo might be problematic. Click here for more details.

Files changed (209) hide show
  1. crawlo/__init__.py +61 -61
  2. crawlo/__version__.py +1 -1
  3. crawlo/cleaners/__init__.py +60 -60
  4. crawlo/cleaners/data_formatter.py +225 -225
  5. crawlo/cleaners/encoding_converter.py +125 -125
  6. crawlo/cleaners/text_cleaner.py +232 -232
  7. crawlo/cli.py +75 -88
  8. crawlo/commands/__init__.py +14 -14
  9. crawlo/commands/check.py +594 -594
  10. crawlo/commands/genspider.py +151 -151
  11. crawlo/commands/help.py +138 -144
  12. crawlo/commands/list.py +155 -155
  13. crawlo/commands/run.py +323 -323
  14. crawlo/commands/startproject.py +436 -436
  15. crawlo/commands/stats.py +187 -187
  16. crawlo/commands/utils.py +186 -186
  17. crawlo/config.py +312 -312
  18. crawlo/config_validator.py +251 -251
  19. crawlo/core/__init__.py +2 -2
  20. crawlo/core/engine.py +365 -356
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +251 -239
  23. crawlo/crawler.py +1099 -1110
  24. crawlo/data/__init__.py +5 -5
  25. crawlo/data/user_agents.py +107 -107
  26. crawlo/downloader/__init__.py +266 -266
  27. crawlo/downloader/aiohttp_downloader.py +228 -221
  28. crawlo/downloader/cffi_downloader.py +256 -256
  29. crawlo/downloader/httpx_downloader.py +259 -259
  30. crawlo/downloader/hybrid_downloader.py +212 -212
  31. crawlo/downloader/playwright_downloader.py +402 -402
  32. crawlo/downloader/selenium_downloader.py +472 -472
  33. crawlo/event.py +11 -11
  34. crawlo/exceptions.py +81 -81
  35. crawlo/extension/__init__.py +39 -38
  36. crawlo/extension/health_check.py +141 -141
  37. crawlo/extension/log_interval.py +57 -57
  38. crawlo/extension/log_stats.py +81 -81
  39. crawlo/extension/logging_extension.py +43 -43
  40. crawlo/extension/memory_monitor.py +104 -104
  41. crawlo/extension/performance_profiler.py +133 -133
  42. crawlo/extension/request_recorder.py +107 -107
  43. crawlo/filters/__init__.py +154 -154
  44. crawlo/filters/aioredis_filter.py +234 -234
  45. crawlo/filters/memory_filter.py +269 -269
  46. crawlo/items/__init__.py +23 -23
  47. crawlo/items/base.py +21 -21
  48. crawlo/items/fields.py +52 -52
  49. crawlo/items/items.py +104 -104
  50. crawlo/middleware/__init__.py +21 -21
  51. crawlo/middleware/default_header.py +131 -131
  52. crawlo/middleware/download_delay.py +104 -104
  53. crawlo/middleware/middleware_manager.py +136 -135
  54. crawlo/middleware/offsite.py +114 -114
  55. crawlo/middleware/proxy.py +367 -367
  56. crawlo/middleware/request_ignore.py +86 -86
  57. crawlo/middleware/response_code.py +163 -163
  58. crawlo/middleware/response_filter.py +136 -136
  59. crawlo/middleware/retry.py +124 -124
  60. crawlo/mode_manager.py +211 -211
  61. crawlo/network/__init__.py +21 -21
  62. crawlo/network/request.py +338 -338
  63. crawlo/network/response.py +359 -359
  64. crawlo/pipelines/__init__.py +21 -21
  65. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  66. crawlo/pipelines/console_pipeline.py +39 -39
  67. crawlo/pipelines/csv_pipeline.py +316 -316
  68. crawlo/pipelines/database_dedup_pipeline.py +222 -222
  69. crawlo/pipelines/json_pipeline.py +218 -218
  70. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  71. crawlo/pipelines/mongo_pipeline.py +131 -131
  72. crawlo/pipelines/mysql_pipeline.py +317 -317
  73. crawlo/pipelines/pipeline_manager.py +62 -61
  74. crawlo/pipelines/redis_dedup_pipeline.py +166 -165
  75. crawlo/project.py +314 -279
  76. crawlo/queue/pqueue.py +37 -37
  77. crawlo/queue/queue_manager.py +377 -376
  78. crawlo/queue/redis_priority_queue.py +306 -306
  79. crawlo/settings/__init__.py +7 -7
  80. crawlo/settings/default_settings.py +219 -215
  81. crawlo/settings/setting_manager.py +122 -122
  82. crawlo/spider/__init__.py +639 -639
  83. crawlo/stats_collector.py +59 -59
  84. crawlo/subscriber.py +129 -129
  85. crawlo/task_manager.py +30 -30
  86. crawlo/templates/crawlo.cfg.tmpl +10 -10
  87. crawlo/templates/project/__init__.py.tmpl +3 -3
  88. crawlo/templates/project/items.py.tmpl +17 -17
  89. crawlo/templates/project/middlewares.py.tmpl +118 -118
  90. crawlo/templates/project/pipelines.py.tmpl +96 -96
  91. crawlo/templates/project/settings.py.tmpl +288 -288
  92. crawlo/templates/project/settings_distributed.py.tmpl +157 -157
  93. crawlo/templates/project/settings_gentle.py.tmpl +100 -100
  94. crawlo/templates/project/settings_high_performance.py.tmpl +134 -134
  95. crawlo/templates/project/settings_simple.py.tmpl +98 -98
  96. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  97. crawlo/templates/run.py.tmpl +47 -45
  98. crawlo/templates/spider/spider.py.tmpl +143 -143
  99. crawlo/tools/__init__.py +182 -182
  100. crawlo/tools/anti_crawler.py +268 -268
  101. crawlo/tools/authenticated_proxy.py +240 -240
  102. crawlo/tools/data_validator.py +180 -180
  103. crawlo/tools/date_tools.py +35 -35
  104. crawlo/tools/distributed_coordinator.py +386 -386
  105. crawlo/tools/retry_mechanism.py +220 -220
  106. crawlo/tools/scenario_adapter.py +262 -262
  107. crawlo/utils/__init__.py +35 -35
  108. crawlo/utils/batch_processor.py +259 -259
  109. crawlo/utils/controlled_spider_mixin.py +439 -439
  110. crawlo/utils/date_tools.py +290 -290
  111. crawlo/utils/db_helper.py +343 -343
  112. crawlo/utils/enhanced_error_handler.py +356 -356
  113. crawlo/utils/env_config.py +143 -106
  114. crawlo/utils/error_handler.py +123 -123
  115. crawlo/utils/func_tools.py +82 -82
  116. crawlo/utils/large_scale_config.py +286 -286
  117. crawlo/utils/large_scale_helper.py +344 -344
  118. crawlo/utils/log.py +128 -128
  119. crawlo/utils/performance_monitor.py +285 -285
  120. crawlo/utils/queue_helper.py +175 -175
  121. crawlo/utils/redis_connection_pool.py +351 -351
  122. crawlo/utils/redis_key_validator.py +198 -198
  123. crawlo/utils/request.py +267 -267
  124. crawlo/utils/request_serializer.py +218 -218
  125. crawlo/utils/spider_loader.py +61 -61
  126. crawlo/utils/system.py +11 -11
  127. crawlo/utils/tools.py +4 -4
  128. crawlo/utils/url.py +39 -39
  129. {crawlo-1.2.6.dist-info → crawlo-1.2.8.dist-info}/METADATA +764 -764
  130. crawlo-1.2.8.dist-info/RECORD +209 -0
  131. examples/__init__.py +7 -7
  132. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  133. tests/__init__.py +7 -7
  134. tests/advanced_tools_example.py +275 -275
  135. tests/authenticated_proxy_example.py +236 -236
  136. tests/cleaners_example.py +160 -160
  137. tests/config_validation_demo.py +102 -102
  138. tests/controlled_spider_example.py +205 -205
  139. tests/date_tools_example.py +180 -180
  140. tests/dynamic_loading_example.py +523 -523
  141. tests/dynamic_loading_test.py +104 -104
  142. tests/env_config_example.py +133 -133
  143. tests/error_handling_example.py +171 -171
  144. tests/redis_key_validation_demo.py +130 -130
  145. tests/response_improvements_example.py +144 -144
  146. tests/test_advanced_tools.py +148 -148
  147. tests/test_all_redis_key_configs.py +145 -145
  148. tests/test_authenticated_proxy.py +141 -141
  149. tests/test_cleaners.py +54 -54
  150. tests/test_comprehensive.py +146 -146
  151. tests/test_config_consistency.py +81 -0
  152. tests/test_config_validator.py +193 -193
  153. tests/test_crawlo_proxy_integration.py +172 -172
  154. tests/test_date_tools.py +123 -123
  155. tests/test_default_header_middleware.py +158 -158
  156. tests/test_double_crawlo_fix.py +207 -207
  157. tests/test_double_crawlo_fix_simple.py +124 -124
  158. tests/test_download_delay_middleware.py +221 -221
  159. tests/test_downloader_proxy_compatibility.py +268 -268
  160. tests/test_dynamic_downloaders_proxy.py +124 -124
  161. tests/test_dynamic_proxy.py +92 -92
  162. tests/test_dynamic_proxy_config.py +146 -146
  163. tests/test_dynamic_proxy_real.py +109 -109
  164. tests/test_edge_cases.py +303 -303
  165. tests/test_enhanced_error_handler.py +270 -270
  166. tests/test_env_config.py +121 -121
  167. tests/test_error_handler_compatibility.py +112 -112
  168. tests/test_final_validation.py +153 -153
  169. tests/test_framework_env_usage.py +103 -103
  170. tests/test_integration.py +356 -356
  171. tests/test_item_dedup_redis_key.py +122 -122
  172. tests/test_mode_consistency.py +52 -0
  173. tests/test_offsite_middleware.py +221 -221
  174. tests/test_parsel.py +29 -29
  175. tests/test_performance.py +327 -327
  176. tests/test_proxy_api.py +264 -264
  177. tests/test_proxy_health_check.py +32 -32
  178. tests/test_proxy_middleware.py +121 -121
  179. tests/test_proxy_middleware_enhanced.py +216 -216
  180. tests/test_proxy_middleware_integration.py +136 -136
  181. tests/test_proxy_providers.py +56 -56
  182. tests/test_proxy_stats.py +19 -19
  183. tests/test_proxy_strategies.py +59 -59
  184. tests/test_queue_manager_double_crawlo.py +173 -173
  185. tests/test_queue_manager_redis_key.py +176 -176
  186. tests/test_real_scenario_proxy.py +195 -195
  187. tests/test_redis_config.py +28 -28
  188. tests/test_redis_connection_pool.py +294 -294
  189. tests/test_redis_key_naming.py +181 -181
  190. tests/test_redis_key_validator.py +123 -123
  191. tests/test_redis_queue.py +224 -224
  192. tests/test_request_ignore_middleware.py +182 -182
  193. tests/test_request_serialization.py +70 -70
  194. tests/test_response_code_middleware.py +349 -349
  195. tests/test_response_filter_middleware.py +427 -427
  196. tests/test_response_improvements.py +152 -152
  197. tests/test_retry_middleware.py +241 -241
  198. tests/test_scheduler.py +252 -241
  199. tests/test_scheduler_config_update.py +134 -0
  200. tests/test_simple_response.py +61 -61
  201. tests/test_telecom_spider_redis_key.py +205 -205
  202. tests/test_template_content.py +87 -87
  203. tests/test_template_redis_key.py +134 -134
  204. tests/test_tools.py +153 -153
  205. tests/tools_example.py +257 -257
  206. crawlo-1.2.6.dist-info/RECORD +0 -206
  207. {crawlo-1.2.6.dist-info → crawlo-1.2.8.dist-info}/WHEEL +0 -0
  208. {crawlo-1.2.6.dist-info → crawlo-1.2.8.dist-info}/entry_points.txt +0 -0
  209. {crawlo-1.2.6.dist-info → crawlo-1.2.8.dist-info}/top_level.txt +0 -0
@@ -1,135 +1,135 @@
1
- # -*- coding: UTF-8 -*-
2
- """
3
- 高性能模式配置模板
4
- 针对大规模高并发优化
5
- """
6
-
7
- # ============================== 项目基本信息 ==============================
8
- PROJECT_NAME = '{{project_name}}'
9
-
10
- # ============================== 高性能运行模式 ==============================
11
- # 运行模式:'standalone'(单机), 'distributed'(分布式), 'auto'(自动检测)
12
- RUN_MODE = 'standalone' # 单机模式 - 适用于开发和小规模数据采集
13
-
14
- # 并发配置
15
- CONCURRENCY = 32 # 高并发数以充分利用系统资源
16
- DOWNLOAD_DELAY = 0.1 # 极小延迟以提高吞吐量
17
- RANDOMNESS = False # 禁用随机延迟以保证性能
18
-
19
- # ============================== 队列配置 ==============================
20
-
21
- # 队列类型:'auto'(自动选择), 'memory'(内存队列), 'redis'(分布式队列)
22
- QUEUE_TYPE = 'auto' # 自动检测,如果Redis可用则使用Redis队列
23
- SCHEDULER_MAX_QUEUE_SIZE = 5000
24
- SCHEDULER_QUEUE_NAME = f'crawlo:{{project_name}}:queue:requests'
25
- QUEUE_MAX_RETRIES = 3
26
- QUEUE_TIMEOUT = 300
27
-
28
- # ============================== 去重过滤配置 ==============================
29
-
30
- # 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
31
- DEFAULT_DEDUP_PIPELINE = 'crawlo.pipelines.redis_dedup_pipeline.RedisDedupPipeline'
32
- FILTER_CLASS = 'crawlo.filters.aioredis_filter.AioRedisFilter'
33
-
34
- # --- Redis 配置(用于分布式去重和队列) ---
35
- REDIS_HOST = '127.0.0.1'
36
- REDIS_PORT = 6379
37
- REDIS_PASSWORD = '' # 如果有密码,请填写
38
-
39
- # 根据是否有密码生成 URL
40
- if REDIS_PASSWORD:
41
- REDIS_URL = f'redis://:{REDIS_PASSWORD}@{REDIS_HOST}:{REDIS_PORT}/0'
42
- else:
43
- REDIS_URL = f'redis://{REDIS_HOST}:{REDIS_PORT}/0'
44
-
45
- # Redis key配置已移至各组件中,使用统一的命名规范
46
- # crawlo:{project_name}:filter:fingerprint (请求去重)
47
- # crawlo:{project_name}:item:fingerprint (数据项去重)
48
- # crawlo:{project_name}:queue:requests (请求队列)
49
- # crawlo:{project_name}:queue:processing (处理中队列)
50
- # crawlo:{project_name}:queue:failed (失败队列)
51
-
52
- REDIS_TTL = 0
53
- CLEANUP_FP = 0
54
- FILTER_DEBUG = True
55
- DECODE_RESPONSES = True
56
-
57
- # ============================== 中间件配置 ==============================
58
-
59
- MIDDLEWARES = [
60
- # === 请求预处理阶段 ===
61
- 'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
62
- 'crawlo.middleware.download_delay.DownloadDelayMiddleware',
63
- 'crawlo.middleware.default_header.DefaultHeaderMiddleware',
64
- 'crawlo.middleware.proxy.ProxyMiddleware',
65
- 'crawlo.middleware.offsite.OffsiteMiddleware',
66
-
67
- # === 响应处理阶段 ===
68
- 'crawlo.middleware.retry.RetryMiddleware',
69
- 'crawlo.middleware.response_code.ResponseCodeMiddleware',
70
- 'crawlo.middleware.response_filter.ResponseFilterMiddleware',
71
- ]
72
-
73
- # ============================== 数据管道配置 ==============================
74
-
75
- # 数据处理管道(启用的存储方式)
76
- PIPELINES = [
77
- 'crawlo.pipelines.console_pipeline.ConsolePipeline',
78
- # '{{project_name}}.pipelines.DatabasePipeline', # 自定义数据库管道
79
- # 'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline', # MySQL 存储
80
- # 'crawlo.pipelines.mongo_pipeline.MongoPipeline', # MongoDB 存储
81
- ]
82
-
83
- # 明确添加默认去重管道到管道列表开头
84
- PIPELINES.insert(0, DEFAULT_DEDUP_PIPELINE)
85
-
86
- # ============================== 扩展组件 ==============================
87
-
88
- EXTENSIONS = [
89
- 'crawlo.extension.log_interval.LogIntervalExtension',
90
- 'crawlo.extension.log_stats.LogStats',
91
- 'crawlo.extension.logging_extension.CustomLoggerExtension',
92
- # 'crawlo.extension.memory_monitor.MemoryMonitorExtension', # 内存监控
93
- # 'crawlo.extension.request_recorder.RequestRecorderExtension', # 请求记录
94
- # 'crawlo.extension.performance_profiler.PerformanceProfilerExtension', # 性能分析
95
- # 'crawlo.extension.health_check.HealthCheckExtension', # 健康检查
96
- ]
97
-
98
- # ============================== 日志配置 ==============================
99
-
100
- LOG_LEVEL = 'INFO'
101
- STATS_DUMP = True
102
- LOG_FILE = f'logs/{{project_name}}.log'
103
- LOG_FORMAT = '%(asctime)s - [%(name)s] - %(levelname)s: %(message)s'
104
- LOG_ENCODING = 'utf-8'
105
-
106
- # ============================== 性能优化配置 ==============================
107
-
108
- # 连接池配置
109
- CONNECTION_POOL_LIMIT = 100
110
- DOWNLOAD_MAXSIZE = 10 * 1024 * 1024 # 10MB
111
- DOWNLOAD_WARN_SIZE = 1024 * 1024 # 1MB
112
-
113
- # 下载器优化配置
114
- DOWNLOADER_HEALTH_CHECK = True
115
- HEALTH_CHECK_INTERVAL = 30
116
-
117
- # 请求统计配置
118
- REQUEST_STATS_ENABLED = True
119
- STATS_RESET_ON_START = False
120
-
121
- # HttpX 下载器专用配置
122
- HTTPX_HTTP2 = True
123
- HTTPX_FOLLOW_REDIRECTS = True
124
-
125
- # AioHttp 下载器专用配置
126
- AIOHTTP_AUTO_DECOMPRESS = True
127
- AIOHTTP_FORCE_CLOSE = False
128
-
129
- # 通用优化配置
130
- CONNECTION_TTL_DNS_CACHE = 300
131
- CONNECTION_KEEPALIVE_TIMEOUT = 15
132
-
133
- # 性能监控
134
- ENABLE_PERFORMANCE_MONITORING = True
1
+ # -*- coding: UTF-8 -*-
2
+ """
3
+ 高性能模式配置模板
4
+ 针对大规模高并发优化
5
+ """
6
+
7
+ # ============================== 项目基本信息 ==============================
8
+ PROJECT_NAME = '{{project_name}}'
9
+
10
+ # ============================== 高性能运行模式 ==============================
11
+ # 运行模式:'standalone'(单机), 'distributed'(分布式), 'auto'(自动检测)
12
+ RUN_MODE = 'standalone' # 单机模式 - 适用于开发和小规模数据采集
13
+
14
+ # 并发配置
15
+ CONCURRENCY = 32 # 高并发数以充分利用系统资源
16
+ DOWNLOAD_DELAY = 0.1 # 极小延迟以提高吞吐量
17
+ RANDOMNESS = False # 禁用随机延迟以保证性能
18
+
19
+ # ============================== 队列配置 ==============================
20
+
21
+ # 队列类型:'auto'(自动选择), 'memory'(内存队列), 'redis'(分布式队列)
22
+ QUEUE_TYPE = 'auto' # 自动检测,如果Redis可用则使用Redis队列
23
+ SCHEDULER_MAX_QUEUE_SIZE = 5000
24
+ SCHEDULER_QUEUE_NAME = f'crawlo:{{project_name}}:queue:requests'
25
+ QUEUE_MAX_RETRIES = 3
26
+ QUEUE_TIMEOUT = 300
27
+
28
+ # ============================== 去重过滤配置 ==============================
29
+
30
+ # 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
31
+ DEFAULT_DEDUP_PIPELINE = 'crawlo.pipelines.redis_dedup_pipeline.RedisDedupPipeline'
32
+ FILTER_CLASS = 'crawlo.filters.aioredis_filter.AioRedisFilter'
33
+
34
+ # --- Redis 配置(用于分布式去重和队列) ---
35
+ REDIS_HOST = '127.0.0.1'
36
+ REDIS_PORT = 6379
37
+ REDIS_PASSWORD = '' # 如果有密码,请填写
38
+
39
+ # 根据是否有密码生成 URL
40
+ if REDIS_PASSWORD:
41
+ REDIS_URL = f'redis://:{REDIS_PASSWORD}@{REDIS_HOST}:{REDIS_PORT}/0'
42
+ else:
43
+ REDIS_URL = f'redis://{REDIS_HOST}:{REDIS_PORT}/0'
44
+
45
+ # Redis key配置已移至各组件中,使用统一的命名规范
46
+ # crawlo:{project_name}:filter:fingerprint (请求去重)
47
+ # crawlo:{project_name}:item:fingerprint (数据项去重)
48
+ # crawlo:{project_name}:queue:requests (请求队列)
49
+ # crawlo:{project_name}:queue:processing (处理中队列)
50
+ # crawlo:{project_name}:queue:failed (失败队列)
51
+
52
+ REDIS_TTL = 0
53
+ CLEANUP_FP = 0
54
+ FILTER_DEBUG = True
55
+ DECODE_RESPONSES = True
56
+
57
+ # ============================== 中间件配置 ==============================
58
+
59
+ MIDDLEWARES = [
60
+ # === 请求预处理阶段 ===
61
+ 'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
62
+ 'crawlo.middleware.download_delay.DownloadDelayMiddleware',
63
+ 'crawlo.middleware.default_header.DefaultHeaderMiddleware',
64
+ 'crawlo.middleware.proxy.ProxyMiddleware',
65
+ 'crawlo.middleware.offsite.OffsiteMiddleware',
66
+
67
+ # === 响应处理阶段 ===
68
+ 'crawlo.middleware.retry.RetryMiddleware',
69
+ 'crawlo.middleware.response_code.ResponseCodeMiddleware',
70
+ 'crawlo.middleware.response_filter.ResponseFilterMiddleware',
71
+ ]
72
+
73
+ # ============================== 数据管道配置 ==============================
74
+
75
+ # 数据处理管道(启用的存储方式)
76
+ PIPELINES = [
77
+ 'crawlo.pipelines.console_pipeline.ConsolePipeline',
78
+ # '{{project_name}}.pipelines.DatabasePipeline', # 自定义数据库管道
79
+ # 'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline', # MySQL 存储
80
+ # 'crawlo.pipelines.mongo_pipeline.MongoPipeline', # MongoDB 存储
81
+ ]
82
+
83
+ # 明确添加默认去重管道到管道列表开头
84
+ PIPELINES.insert(0, DEFAULT_DEDUP_PIPELINE)
85
+
86
+ # ============================== 扩展组件 ==============================
87
+
88
+ EXTENSIONS = [
89
+ 'crawlo.extension.log_interval.LogIntervalExtension',
90
+ 'crawlo.extension.log_stats.LogStats',
91
+ 'crawlo.extension.logging_extension.CustomLoggerExtension',
92
+ # 'crawlo.extension.memory_monitor.MemoryMonitorExtension', # 内存监控
93
+ # 'crawlo.extension.request_recorder.RequestRecorderExtension', # 请求记录
94
+ # 'crawlo.extension.performance_profiler.PerformanceProfilerExtension', # 性能分析
95
+ # 'crawlo.extension.health_check.HealthCheckExtension', # 健康检查
96
+ ]
97
+
98
+ # ============================== 日志配置 ==============================
99
+
100
+ LOG_LEVEL = 'INFO'
101
+ STATS_DUMP = True
102
+ LOG_FILE = f'logs/{{project_name}}.log'
103
+ LOG_FORMAT = '%(asctime)s - [%(name)s] - %(levelname)s: %(message)s'
104
+ LOG_ENCODING = 'utf-8'
105
+
106
+ # ============================== 性能优化配置 ==============================
107
+
108
+ # 连接池配置
109
+ CONNECTION_POOL_LIMIT = 100
110
+ DOWNLOAD_MAXSIZE = 10 * 1024 * 1024 # 10MB
111
+ DOWNLOAD_WARN_SIZE = 1024 * 1024 # 1MB
112
+
113
+ # 下载器优化配置
114
+ DOWNLOADER_HEALTH_CHECK = True
115
+ HEALTH_CHECK_INTERVAL = 30
116
+
117
+ # 请求统计配置
118
+ REQUEST_STATS_ENABLED = True
119
+ STATS_RESET_ON_START = False
120
+
121
+ # HttpX 下载器专用配置
122
+ HTTPX_HTTP2 = True
123
+ HTTPX_FOLLOW_REDIRECTS = True
124
+
125
+ # AioHttp 下载器专用配置
126
+ AIOHTTP_AUTO_DECOMPRESS = True
127
+ AIOHTTP_FORCE_CLOSE = False
128
+
129
+ # 通用优化配置
130
+ CONNECTION_TTL_DNS_CACHE = 300
131
+ CONNECTION_KEEPALIVE_TIMEOUT = 15
132
+
133
+ # 性能监控
134
+ ENABLE_PERFORMANCE_MONITORING = True
135
135
  MEMORY_USAGE_WARNING_THRESHOLD = 800 # MB
@@ -1,99 +1,99 @@
1
- # -*- coding: UTF-8 -*-
2
- """
3
- 简化模式配置模板
4
- 最小配置,适合快速开始和简单项目
5
- """
6
-
7
- # ============================== 项目基本信息 ==============================
8
- PROJECT_NAME = '{{project_name}}'
9
-
10
- # ============================== 简化运行模式 ==============================
11
- # 运行模式:'standalone'(单机), 'distributed'(分布式), 'auto'(自动检测)
12
- RUN_MODE = 'standalone' # 单机模式 - 适用于开发和小规模数据采集
13
-
14
- # 并发配置
15
- CONCURRENCY = 4 # 低并发数以减少资源占用
16
- DOWNLOAD_DELAY = 1.0 # 增加延迟以降低目标网站压力
17
-
18
- # ============================== 队列配置 ==============================
19
-
20
- # 队列类型:'auto'(自动选择), 'memory'(内存队列), 'redis'(分布式队列)
21
- QUEUE_TYPE = 'auto' # 自动检测,如果Redis可用则使用Redis队列
22
- SCHEDULER_MAX_QUEUE_SIZE = 1000
23
- SCHEDULER_QUEUE_NAME = f'crawlo:{{project_name}}:queue:requests'
24
- QUEUE_MAX_RETRIES = 3
25
- QUEUE_TIMEOUT = 300
26
-
27
- # ============================== 去重过滤配置 ==============================
28
-
29
- # 简化模式下使用内存去重管道和过滤器
30
- DEFAULT_DEDUP_PIPELINE = 'crawlo.pipelines.memory_dedup_pipeline.MemoryDedupPipeline'
31
- FILTER_CLASS = 'crawlo.filters.memory_filter.MemoryFilter'
32
-
33
- # --- Redis 配置(用于分布式去重和队列) ---
34
- REDIS_HOST = '127.0.0.1'
35
- REDIS_PORT = 6379
36
- REDIS_PASSWORD = '' # 如果有密码,请填写
37
-
38
- # 根据是否有密码生成 URL
39
- if REDIS_PASSWORD:
40
- REDIS_URL = f'redis://:{REDIS_PASSWORD}@{REDIS_HOST}:{REDIS_PORT}/0'
41
- else:
42
- REDIS_URL = f'redis://{REDIS_HOST}:{REDIS_PORT}/0'
43
-
44
- # Redis key配置已移至各组件中,使用统一的命名规范
45
- # crawlo:{project_name}:filter:fingerprint (请求去重)
46
- # crawlo:{project_name}:item:fingerprint (数据项去重)
47
- # crawlo:{project_name}:queue:requests (请求队列)
48
- # crawlo:{project_name}:queue:processing (处理中队列)
49
- # crawlo:{project_name}:queue:failed (失败队列)
50
-
51
- REDIS_TTL = 0
52
- CLEANUP_FP = 0
53
- FILTER_DEBUG = True
54
- DECODE_RESPONSES = True
55
-
56
- # ============================== 中间件配置 ==============================
57
-
58
- MIDDLEWARES = [
59
- # === 请求预处理阶段 ===
60
- 'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
61
- 'crawlo.middleware.download_delay.DownloadDelayMiddleware',
62
- 'crawlo.middleware.default_header.DefaultHeaderMiddleware',
63
- 'crawlo.middleware.proxy.ProxyMiddleware',
64
- 'crawlo.middleware.offsite.OffsiteMiddleware',
65
-
66
- # === 响应处理阶段 ===
67
- 'crawlo.middleware.retry.RetryMiddleware',
68
- 'crawlo.middleware.response_code.ResponseCodeMiddleware',
69
- 'crawlo.middleware.response_filter.ResponseFilterMiddleware',
70
- ]
71
-
72
- # ============================== 数据管道配置 ==============================
73
-
74
- # 数据处理管道(启用的存储方式)
75
- PIPELINES = [
76
- 'crawlo.pipelines.console_pipeline.ConsolePipeline',
77
- # '{{project_name}}.pipelines.DatabasePipeline', # 自定义数据库管道
78
- # 'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline', # MySQL 存储
79
- # 'crawlo.pipelines.mongo_pipeline.MongoPipeline', # MongoDB 存储
80
- ]
81
-
82
- # 明确添加默认去重管道到管道列表开头
83
- PIPELINES.insert(0, DEFAULT_DEDUP_PIPELINE)
84
-
85
- # ============================== 扩展组件 ==============================
86
-
87
- EXTENSIONS = [
88
- 'crawlo.extension.log_interval.LogIntervalExtension',
89
- 'crawlo.extension.log_stats.LogStats',
90
- 'crawlo.extension.logging_extension.CustomLoggerExtension',
91
- ]
92
-
93
- # ============================== 日志配置 ==============================
94
-
95
- LOG_LEVEL = 'INFO'
96
- STATS_DUMP = True
97
- LOG_FILE = f'logs/{{project_name}}.log'
98
- LOG_FORMAT = '%(asctime)s - [%(name)s] - %(levelname)s: %(message)s'
1
+ # -*- coding: UTF-8 -*-
2
+ """
3
+ 简化模式配置模板
4
+ 最小配置,适合快速开始和简单项目
5
+ """
6
+
7
+ # ============================== 项目基本信息 ==============================
8
+ PROJECT_NAME = '{{project_name}}'
9
+
10
+ # ============================== 简化运行模式 ==============================
11
+ # 运行模式:'standalone'(单机), 'distributed'(分布式), 'auto'(自动检测)
12
+ RUN_MODE = 'standalone' # 单机模式 - 适用于开发和小规模数据采集
13
+
14
+ # 并发配置
15
+ CONCURRENCY = 4 # 低并发数以减少资源占用
16
+ DOWNLOAD_DELAY = 1.0 # 增加延迟以降低目标网站压力
17
+
18
+ # ============================== 队列配置 ==============================
19
+
20
+ # 队列类型:'auto'(自动选择), 'memory'(内存队列), 'redis'(分布式队列)
21
+ QUEUE_TYPE = 'auto' # 自动检测,如果Redis可用则使用Redis队列
22
+ SCHEDULER_MAX_QUEUE_SIZE = 1000
23
+ SCHEDULER_QUEUE_NAME = f'crawlo:{{project_name}}:queue:requests'
24
+ QUEUE_MAX_RETRIES = 3
25
+ QUEUE_TIMEOUT = 300
26
+
27
+ # ============================== 去重过滤配置 ==============================
28
+
29
+ # 简化模式下使用内存去重管道和过滤器
30
+ DEFAULT_DEDUP_PIPELINE = 'crawlo.pipelines.memory_dedup_pipeline.MemoryDedupPipeline'
31
+ FILTER_CLASS = 'crawlo.filters.memory_filter.MemoryFilter'
32
+
33
+ # --- Redis 配置(用于分布式去重和队列) ---
34
+ REDIS_HOST = '127.0.0.1'
35
+ REDIS_PORT = 6379
36
+ REDIS_PASSWORD = '' # 如果有密码,请填写
37
+
38
+ # 根据是否有密码生成 URL
39
+ if REDIS_PASSWORD:
40
+ REDIS_URL = f'redis://:{REDIS_PASSWORD}@{REDIS_HOST}:{REDIS_PORT}/0'
41
+ else:
42
+ REDIS_URL = f'redis://{REDIS_HOST}:{REDIS_PORT}/0'
43
+
44
+ # Redis key配置已移至各组件中,使用统一的命名规范
45
+ # crawlo:{project_name}:filter:fingerprint (请求去重)
46
+ # crawlo:{project_name}:item:fingerprint (数据项去重)
47
+ # crawlo:{project_name}:queue:requests (请求队列)
48
+ # crawlo:{project_name}:queue:processing (处理中队列)
49
+ # crawlo:{project_name}:queue:failed (失败队列)
50
+
51
+ REDIS_TTL = 0
52
+ CLEANUP_FP = 0
53
+ FILTER_DEBUG = True
54
+ DECODE_RESPONSES = True
55
+
56
+ # ============================== 中间件配置 ==============================
57
+
58
+ MIDDLEWARES = [
59
+ # === 请求预处理阶段 ===
60
+ 'crawlo.middleware.request_ignore.RequestIgnoreMiddleware',
61
+ 'crawlo.middleware.download_delay.DownloadDelayMiddleware',
62
+ 'crawlo.middleware.default_header.DefaultHeaderMiddleware',
63
+ 'crawlo.middleware.proxy.ProxyMiddleware',
64
+ 'crawlo.middleware.offsite.OffsiteMiddleware',
65
+
66
+ # === 响应处理阶段 ===
67
+ 'crawlo.middleware.retry.RetryMiddleware',
68
+ 'crawlo.middleware.response_code.ResponseCodeMiddleware',
69
+ 'crawlo.middleware.response_filter.ResponseFilterMiddleware',
70
+ ]
71
+
72
+ # ============================== 数据管道配置 ==============================
73
+
74
+ # 数据处理管道(启用的存储方式)
75
+ PIPELINES = [
76
+ 'crawlo.pipelines.console_pipeline.ConsolePipeline',
77
+ # '{{project_name}}.pipelines.DatabasePipeline', # 自定义数据库管道
78
+ # 'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline', # MySQL 存储
79
+ # 'crawlo.pipelines.mongo_pipeline.MongoPipeline', # MongoDB 存储
80
+ ]
81
+
82
+ # 明确添加默认去重管道到管道列表开头
83
+ PIPELINES.insert(0, DEFAULT_DEDUP_PIPELINE)
84
+
85
+ # ============================== 扩展组件 ==============================
86
+
87
+ EXTENSIONS = [
88
+ 'crawlo.extension.log_interval.LogIntervalExtension',
89
+ 'crawlo.extension.log_stats.LogStats',
90
+ 'crawlo.extension.logging_extension.CustomLoggerExtension',
91
+ ]
92
+
93
+ # ============================== 日志配置 ==============================
94
+
95
+ LOG_LEVEL = 'INFO'
96
+ STATS_DUMP = True
97
+ LOG_FILE = f'logs/{{project_name}}.log'
98
+ LOG_FORMAT = '%(asctime)s - [%(name)s] - %(levelname)s: %(message)s'
99
99
  LOG_ENCODING = 'utf-8'
@@ -1,6 +1,6 @@
1
- # -*- coding: UTF-8 -*-
2
- """
3
- {{project_name}}.spiders
4
- ========================
5
- 存放所有的爬虫。
1
+ # -*- coding: UTF-8 -*-
2
+ """
3
+ {{project_name}}.spiders
4
+ ========================
5
+ 存放所有的爬虫。
6
6
  """
@@ -1,46 +1,48 @@
1
- #!/usr/bin/env python
2
- # -*- coding: UTF-8 -*-
3
- """
4
- {{project_name}} 项目运行脚本
5
- ============================
6
- 基于 Crawlo 框架的简化爬虫启动器。
7
- """
8
-
9
- import sys
10
- import os
11
- import asyncio
12
-
13
- # 添加项目根目录到 Python 路径
14
- project_root = os.path.dirname(os.path.abspath(__file__))
15
- sys.path.insert(0, project_root)
16
-
17
- # 切换到项目根目录
18
- os.chdir(project_root)
19
-
20
- from crawlo.crawler import CrawlerProcess
21
-
22
-
23
- def main():
24
- """主函数:运行固定的爬虫"""
25
- print("🚀 启动 {{project_name}} 爬虫")
26
-
27
- # 创建爬虫进程(自动加载默认配置)
28
- try:
29
- process = CrawlerProcess()
30
- print("✅ 爬虫进程初始化成功")
31
-
32
- # 运行固定的爬虫
33
- # TODO: 请将 'your_spider_name' 替换为实际的爬虫名称
34
- asyncio.run(process.crawl('your_spider_name'))
35
-
36
- print("✅ 爬虫运行完成")
37
-
38
- except Exception as e:
39
- print(f"❌ 运行失败: {e}")
40
- import traceback
41
- traceback.print_exc()
42
- sys.exit(1)
43
-
44
-
45
- if __name__ == '__main__':
1
+ #!/usr/bin/env python
2
+ # -*- coding: UTF-8 -*-
3
+ """
4
+ {{project_name}} 项目运行脚本
5
+ ============================
6
+ 基于 Crawlo 框架的简化爬虫启动器。
7
+ """
8
+
9
+ import sys
10
+ import os
11
+ import asyncio
12
+
13
+ # 添加项目根目录到 Python 路径
14
+ project_root = os.path.dirname(os.path.abspath(__file__))
15
+ sys.path.insert(0, project_root)
16
+
17
+ # 切换到项目根目录
18
+ os.chdir(project_root)
19
+
20
+ from crawlo.crawler import CrawlerProcess
21
+
22
+
23
+ def main():
24
+ """主函数:运行固定的爬虫"""
25
+ print("🚀 启动 {{project_name}} 爬虫")
26
+
27
+ # 创建爬虫进程(自动加载默认配置)
28
+ try:
29
+ # 确保 spider 模块被正确导入
30
+ spider_modules = ['{{project_name}}.spiders']
31
+ process = CrawlerProcess(spider_modules=spider_modules)
32
+ print("✅ 爬虫进程初始化成功")
33
+
34
+ # 运行固定的爬虫
35
+ # TODO: 请将 'your_spider_name' 替换为实际的爬虫名称
36
+ asyncio.run(process.crawl('your_spider_name'))
37
+
38
+ print("✅ 爬虫运行完成")
39
+
40
+ except Exception as e:
41
+ print(f"❌ 运行失败: {e}")
42
+ import traceback
43
+ traceback.print_exc()
44
+ sys.exit(1)
45
+
46
+
47
+ if __name__ == '__main__':
46
48
  main()