crawlo 1.3.2__py3-none-any.whl → 1.3.3__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 (219) hide show
  1. crawlo/__init__.py +63 -63
  2. crawlo/__version__.py +1 -1
  3. crawlo/cli.py +75 -75
  4. crawlo/commands/__init__.py +14 -14
  5. crawlo/commands/check.py +594 -594
  6. crawlo/commands/genspider.py +151 -151
  7. crawlo/commands/help.py +138 -138
  8. crawlo/commands/list.py +155 -155
  9. crawlo/commands/run.py +322 -314
  10. crawlo/commands/startproject.py +436 -436
  11. crawlo/commands/stats.py +187 -187
  12. crawlo/commands/utils.py +196 -196
  13. crawlo/config.py +312 -312
  14. crawlo/config_validator.py +277 -277
  15. crawlo/core/__init__.py +2 -2
  16. crawlo/core/engine.py +365 -365
  17. crawlo/core/processor.py +40 -40
  18. crawlo/core/scheduler.py +256 -256
  19. crawlo/crawler.py +1166 -1168
  20. crawlo/data/__init__.py +5 -5
  21. crawlo/data/user_agents.py +194 -194
  22. crawlo/downloader/__init__.py +273 -273
  23. crawlo/downloader/aiohttp_downloader.py +226 -226
  24. crawlo/downloader/cffi_downloader.py +245 -245
  25. crawlo/downloader/httpx_downloader.py +259 -259
  26. crawlo/downloader/hybrid_downloader.py +212 -212
  27. crawlo/downloader/playwright_downloader.py +402 -402
  28. crawlo/downloader/selenium_downloader.py +472 -472
  29. crawlo/event.py +11 -11
  30. crawlo/exceptions.py +81 -81
  31. crawlo/extension/__init__.py +39 -39
  32. crawlo/extension/health_check.py +141 -141
  33. crawlo/extension/log_interval.py +57 -57
  34. crawlo/extension/log_stats.py +81 -81
  35. crawlo/extension/logging_extension.py +52 -45
  36. crawlo/extension/memory_monitor.py +104 -104
  37. crawlo/extension/performance_profiler.py +133 -133
  38. crawlo/extension/request_recorder.py +107 -107
  39. crawlo/filters/__init__.py +154 -154
  40. crawlo/filters/aioredis_filter.py +234 -234
  41. crawlo/filters/memory_filter.py +269 -269
  42. crawlo/items/__init__.py +23 -23
  43. crawlo/items/base.py +21 -21
  44. crawlo/items/fields.py +52 -52
  45. crawlo/items/items.py +104 -104
  46. crawlo/middleware/__init__.py +21 -21
  47. crawlo/middleware/default_header.py +132 -132
  48. crawlo/middleware/download_delay.py +104 -104
  49. crawlo/middleware/middleware_manager.py +135 -135
  50. crawlo/middleware/offsite.py +123 -123
  51. crawlo/middleware/proxy.py +386 -386
  52. crawlo/middleware/request_ignore.py +86 -86
  53. crawlo/middleware/response_code.py +163 -163
  54. crawlo/middleware/response_filter.py +136 -136
  55. crawlo/middleware/retry.py +124 -124
  56. crawlo/middleware/simple_proxy.py +65 -65
  57. crawlo/mode_manager.py +187 -187
  58. crawlo/network/__init__.py +21 -21
  59. crawlo/network/request.py +379 -379
  60. crawlo/network/response.py +359 -359
  61. crawlo/pipelines/__init__.py +21 -21
  62. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  63. crawlo/pipelines/console_pipeline.py +39 -39
  64. crawlo/pipelines/csv_pipeline.py +316 -316
  65. crawlo/pipelines/database_dedup_pipeline.py +222 -222
  66. crawlo/pipelines/json_pipeline.py +218 -218
  67. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  68. crawlo/pipelines/mongo_pipeline.py +131 -131
  69. crawlo/pipelines/mysql_pipeline.py +318 -318
  70. crawlo/pipelines/pipeline_manager.py +75 -75
  71. crawlo/pipelines/redis_dedup_pipeline.py +166 -166
  72. crawlo/project.py +325 -297
  73. crawlo/queue/pqueue.py +37 -37
  74. crawlo/queue/queue_manager.py +379 -379
  75. crawlo/queue/redis_priority_queue.py +306 -306
  76. crawlo/settings/__init__.py +7 -7
  77. crawlo/settings/default_settings.py +225 -225
  78. crawlo/settings/setting_manager.py +198 -198
  79. crawlo/spider/__init__.py +639 -639
  80. crawlo/stats_collector.py +59 -59
  81. crawlo/subscriber.py +129 -129
  82. crawlo/task_manager.py +30 -30
  83. crawlo/templates/crawlo.cfg.tmpl +10 -10
  84. crawlo/templates/project/__init__.py.tmpl +3 -3
  85. crawlo/templates/project/items.py.tmpl +17 -17
  86. crawlo/templates/project/middlewares.py.tmpl +118 -118
  87. crawlo/templates/project/pipelines.py.tmpl +96 -96
  88. crawlo/templates/project/settings.py.tmpl +266 -266
  89. crawlo/templates/project/settings_distributed.py.tmpl +179 -179
  90. crawlo/templates/project/settings_gentle.py.tmpl +60 -60
  91. crawlo/templates/project/settings_high_performance.py.tmpl +130 -130
  92. crawlo/templates/project/settings_minimal.py.tmpl +34 -34
  93. crawlo/templates/project/settings_simple.py.tmpl +101 -101
  94. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  95. crawlo/templates/run.py.tmpl +38 -38
  96. crawlo/templates/spider/spider.py.tmpl +143 -143
  97. crawlo/tools/__init__.py +200 -200
  98. crawlo/tools/anti_crawler.py +268 -268
  99. crawlo/tools/authenticated_proxy.py +240 -240
  100. crawlo/tools/data_formatter.py +225 -225
  101. crawlo/tools/data_validator.py +180 -180
  102. crawlo/tools/date_tools.py +289 -289
  103. crawlo/tools/distributed_coordinator.py +388 -388
  104. crawlo/tools/encoding_converter.py +127 -127
  105. crawlo/tools/request_tools.py +82 -82
  106. crawlo/tools/retry_mechanism.py +224 -224
  107. crawlo/tools/scenario_adapter.py +262 -262
  108. crawlo/tools/text_cleaner.py +232 -232
  109. crawlo/utils/__init__.py +34 -34
  110. crawlo/utils/batch_processor.py +259 -259
  111. crawlo/utils/controlled_spider_mixin.py +439 -439
  112. crawlo/utils/db_helper.py +343 -343
  113. crawlo/utils/enhanced_error_handler.py +356 -356
  114. crawlo/utils/env_config.py +142 -142
  115. crawlo/utils/error_handler.py +123 -123
  116. crawlo/utils/func_tools.py +82 -82
  117. crawlo/utils/large_scale_config.py +286 -286
  118. crawlo/utils/large_scale_helper.py +344 -344
  119. crawlo/utils/log.py +199 -146
  120. crawlo/utils/performance_monitor.py +285 -285
  121. crawlo/utils/queue_helper.py +175 -175
  122. crawlo/utils/redis_connection_pool.py +351 -351
  123. crawlo/utils/redis_key_validator.py +198 -198
  124. crawlo/utils/request.py +267 -267
  125. crawlo/utils/request_serializer.py +218 -218
  126. crawlo/utils/spider_loader.py +61 -61
  127. crawlo/utils/system.py +11 -11
  128. crawlo/utils/tools.py +4 -4
  129. crawlo/utils/url.py +39 -39
  130. {crawlo-1.3.2.dist-info → crawlo-1.3.3.dist-info}/METADATA +1020 -1020
  131. crawlo-1.3.3.dist-info/RECORD +219 -0
  132. examples/__init__.py +7 -7
  133. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  134. tests/__init__.py +7 -7
  135. tests/advanced_tools_example.py +275 -275
  136. tests/authenticated_proxy_example.py +107 -107
  137. tests/cleaners_example.py +160 -160
  138. tests/config_validation_demo.py +142 -142
  139. tests/controlled_spider_example.py +205 -205
  140. tests/date_tools_example.py +180 -180
  141. tests/debug_pipelines.py +66 -66
  142. tests/dynamic_loading_example.py +523 -523
  143. tests/dynamic_loading_test.py +104 -104
  144. tests/env_config_example.py +133 -133
  145. tests/error_handling_example.py +171 -171
  146. tests/redis_key_validation_demo.py +130 -130
  147. tests/request_params_example.py +150 -150
  148. tests/response_improvements_example.py +144 -144
  149. tests/test_advanced_tools.py +148 -148
  150. tests/test_all_redis_key_configs.py +145 -145
  151. tests/test_authenticated_proxy.py +141 -141
  152. tests/test_cleaners.py +54 -54
  153. tests/test_comprehensive.py +146 -146
  154. tests/test_config_consistency.py +80 -80
  155. tests/test_config_merge.py +152 -152
  156. tests/test_config_validator.py +182 -182
  157. tests/test_crawlo_proxy_integration.py +108 -108
  158. tests/test_date_tools.py +123 -123
  159. tests/test_default_header_middleware.py +158 -158
  160. tests/test_distributed.py +65 -65
  161. tests/test_double_crawlo_fix.py +207 -207
  162. tests/test_double_crawlo_fix_simple.py +124 -124
  163. tests/test_download_delay_middleware.py +221 -221
  164. tests/test_downloader_proxy_compatibility.py +268 -268
  165. tests/test_dynamic_downloaders_proxy.py +124 -124
  166. tests/test_dynamic_proxy.py +92 -92
  167. tests/test_dynamic_proxy_config.py +146 -146
  168. tests/test_dynamic_proxy_real.py +109 -109
  169. tests/test_edge_cases.py +303 -303
  170. tests/test_enhanced_error_handler.py +270 -270
  171. tests/test_env_config.py +121 -121
  172. tests/test_error_handler_compatibility.py +112 -112
  173. tests/test_final_validation.py +153 -153
  174. tests/test_framework_env_usage.py +103 -103
  175. tests/test_integration.py +169 -169
  176. tests/test_item_dedup_redis_key.py +122 -122
  177. tests/test_mode_consistency.py +51 -51
  178. tests/test_offsite_middleware.py +221 -221
  179. tests/test_parsel.py +29 -29
  180. tests/test_performance.py +327 -327
  181. tests/test_proxy_api.py +264 -264
  182. tests/test_proxy_health_check.py +32 -32
  183. tests/test_proxy_middleware.py +121 -121
  184. tests/test_proxy_middleware_enhanced.py +216 -216
  185. tests/test_proxy_middleware_integration.py +136 -136
  186. tests/test_proxy_middleware_refactored.py +184 -184
  187. tests/test_proxy_providers.py +56 -56
  188. tests/test_proxy_stats.py +19 -19
  189. tests/test_proxy_strategies.py +59 -59
  190. tests/test_queue_manager_double_crawlo.py +173 -173
  191. tests/test_queue_manager_redis_key.py +176 -176
  192. tests/test_random_user_agent.py +72 -72
  193. tests/test_real_scenario_proxy.py +195 -195
  194. tests/test_redis_config.py +28 -28
  195. tests/test_redis_connection_pool.py +294 -294
  196. tests/test_redis_key_naming.py +181 -181
  197. tests/test_redis_key_validator.py +123 -123
  198. tests/test_redis_queue.py +224 -224
  199. tests/test_request_ignore_middleware.py +182 -182
  200. tests/test_request_params.py +111 -111
  201. tests/test_request_serialization.py +70 -70
  202. tests/test_response_code_middleware.py +349 -349
  203. tests/test_response_filter_middleware.py +427 -427
  204. tests/test_response_improvements.py +152 -152
  205. tests/test_retry_middleware.py +241 -241
  206. tests/test_scheduler.py +252 -252
  207. tests/test_scheduler_config_update.py +133 -133
  208. tests/test_simple_response.py +61 -61
  209. tests/test_telecom_spider_redis_key.py +205 -205
  210. tests/test_template_content.py +87 -87
  211. tests/test_template_redis_key.py +134 -134
  212. tests/test_tools.py +159 -159
  213. tests/test_user_agents.py +96 -96
  214. tests/tools_example.py +260 -260
  215. tests/verify_distributed.py +117 -117
  216. crawlo-1.3.2.dist-info/RECORD +0 -219
  217. {crawlo-1.3.2.dist-info → crawlo-1.3.3.dist-info}/WHEEL +0 -0
  218. {crawlo-1.3.2.dist-info → crawlo-1.3.3.dist-info}/entry_points.txt +0 -0
  219. {crawlo-1.3.2.dist-info → crawlo-1.3.3.dist-info}/top_level.txt +0 -0
@@ -1,278 +1,278 @@
1
- #!/usr/bin/python
2
- # -*- coding: UTF-8 -*-
3
- """
4
- 配置验证器
5
- ==========
6
- 提供配置项的验证和默认值设置功能,确保配置的合理性和一致性。
7
- """
8
- from typing import Dict, Any, List, Tuple
9
-
10
- from crawlo.utils.log import get_logger
11
-
12
-
13
- class ConfigValidator:
14
- """配置验证器"""
15
-
16
- def __init__(self):
17
- self.logger = get_logger(self.__class__.__name__)
18
- self.errors = []
19
- self.warnings = []
20
-
21
- def validate(self, config: Dict[str, Any]) -> Tuple[bool, List[str], List[str]]:
22
- """
23
- 验证配置
24
-
25
- Args:
26
- config: 配置字典
27
-
28
- Returns:
29
- Tuple[bool, List[str], List[str]]: (是否有效, 错误列表, 警告列表)
30
- """
31
- self.errors = []
32
- self.warnings = []
33
-
34
- # 验证各个配置项
35
- self._validate_basic_settings(config)
36
- self._validate_network_settings(config)
37
- self._validate_concurrency_settings(config)
38
- self._validate_queue_settings(config)
39
- self._validate_storage_settings(config)
40
- self._validate_redis_settings(config)
41
- self._validate_middleware_settings(config)
42
- self._validate_pipeline_settings(config)
43
- self._validate_extension_settings(config)
44
- self._validate_logging_settings(config)
45
-
46
- is_valid = len(self.errors) == 0
47
- return is_valid, self.errors, self.warnings
48
-
49
- def _validate_basic_settings(self, config: Dict[str, Any]):
50
- """验证基本设置"""
51
- project_name = config.get('PROJECT_NAME', 'crawlo')
52
- if not isinstance(project_name, str) or not project_name.strip():
53
- self.errors.append("PROJECT_NAME 必须是非空字符串")
54
-
55
- version = config.get('VERSION', '1.0')
56
- if not isinstance(version, str):
57
- self.errors.append("VERSION 必须是字符串")
58
-
59
- def _validate_network_settings(self, config: Dict[str, Any]):
60
- """验证网络设置"""
61
- # 下载器验证
62
- downloader = config.get('DOWNLOADER', 'crawlo.downloader.aiohttp_downloader.AioHttpDownloader')
63
- if not isinstance(downloader, str):
64
- self.errors.append("DOWNLOADER 必须是字符串")
65
-
66
- # 超时设置验证
67
- timeout = config.get('DOWNLOAD_TIMEOUT', 30)
68
- if not isinstance(timeout, (int, float)) or timeout <= 0:
69
- self.errors.append("DOWNLOAD_TIMEOUT 必须是正数")
70
-
71
- # 延迟设置验证
72
- delay = config.get('DOWNLOAD_DELAY', 1.0)
73
- if not isinstance(delay, (int, float)) or delay < 0:
74
- self.errors.append("DOWNLOAD_DELAY 必须是非负数")
75
-
76
- # 重试次数验证
77
- max_retries = config.get('MAX_RETRY_TIMES', 3)
78
- if not isinstance(max_retries, int) or max_retries < 0:
79
- self.errors.append("MAX_RETRY_TIMES 必须是非负整数")
80
-
81
- # 连接池限制验证
82
- pool_limit = config.get('CONNECTION_POOL_LIMIT', 50)
83
- if not isinstance(pool_limit, int) or pool_limit <= 0:
84
- self.errors.append("CONNECTION_POOL_LIMIT 必须是正整数")
85
-
86
- def _validate_concurrency_settings(self, config: Dict[str, Any]):
87
- """验证并发设置"""
88
- concurrency = config.get('CONCURRENCY', 8)
89
- if not isinstance(concurrency, int) or concurrency <= 0:
90
- self.errors.append("CONCURRENCY 必须是正整数")
91
-
92
- max_running_spiders = config.get('MAX_RUNNING_SPIDERS', 3)
93
- if not isinstance(max_running_spiders, int) or max_running_spiders <= 0:
94
- self.errors.append("MAX_RUNNING_SPIDERS 必须是正整数")
95
-
96
- def _validate_queue_settings(self, config: Dict[str, Any]):
97
- """验证队列设置"""
98
- queue_type = config.get('QUEUE_TYPE', 'memory')
99
- valid_queue_types = ['memory', 'redis', 'auto']
100
- if queue_type not in valid_queue_types:
101
- self.errors.append(f"QUEUE_TYPE 必须是以下值之一: {valid_queue_types}")
102
-
103
- # 队列大小验证
104
- max_queue_size = config.get('SCHEDULER_MAX_QUEUE_SIZE', 2000)
105
- if not isinstance(max_queue_size, int) or max_queue_size <= 0:
106
- self.errors.append("SCHEDULER_MAX_QUEUE_SIZE 必须是正整数")
107
-
108
- # 队列名称验证(如果是Redis队列)
109
- if queue_type == 'redis':
110
- queue_name = config.get('SCHEDULER_QUEUE_NAME', '')
111
- if not queue_name:
112
- self.errors.append("使用Redis队列时,SCHEDULER_QUEUE_NAME 不能为空")
113
- elif not self._is_valid_redis_key(queue_name):
114
- self.warnings.append(f"Redis队列名称 '{queue_name}' 不符合命名规范,建议使用 'crawlo:{config.get('PROJECT_NAME', 'project')}:queue:requests' 格式")
115
-
116
- def _validate_storage_settings(self, config: Dict[str, Any]):
117
- """验证存储设置"""
118
- # MySQL设置验证
119
- mysql_host = config.get('MYSQL_HOST')
120
- if mysql_host is not None and not isinstance(mysql_host, str):
121
- self.errors.append("MYSQL_HOST 必须是字符串")
122
-
123
- mysql_port = config.get('MYSQL_PORT')
124
- if mysql_port is not None and (not isinstance(mysql_port, int) or mysql_port <= 0 or mysql_port > 65535):
125
- self.errors.append("MYSQL_PORT 必须是1-65535之间的整数")
126
-
127
- # MongoDB设置验证
128
- mongo_uri = config.get('MONGO_URI')
129
- if mongo_uri is not None and not isinstance(mongo_uri, str):
130
- self.errors.append("MONGO_URI 必须是字符串")
131
-
132
- def _validate_redis_settings(self, config: Dict[str, Any]):
133
- """验证Redis设置"""
134
- queue_type = config.get('QUEUE_TYPE', 'memory')
135
- if queue_type == 'redis':
136
- # Redis主机验证
137
- redis_host = config.get('REDIS_HOST', '127.0.0.1')
138
- if not isinstance(redis_host, str) or not redis_host.strip():
139
- self.errors.append("REDIS_HOST 必须是非空字符串")
140
-
141
- # Redis端口验证
142
- redis_port = config.get('REDIS_PORT', 6379)
143
- if not isinstance(redis_port, int) or redis_port <= 0 or redis_port > 65535:
144
- self.errors.append("REDIS_PORT 必须是1-65535之间的整数")
145
-
146
- # Redis URL验证
147
- redis_url = config.get('REDIS_URL')
148
- if redis_url is not None and not isinstance(redis_url, str):
149
- self.errors.append("REDIS_URL 必须是字符串")
150
-
151
- # Redis队列名称验证(提供默认值)
152
- scheduler_queue_name = config.get('SCHEDULER_QUEUE_NAME')
153
- project_name = config.get('PROJECT_NAME', 'crawlo')
154
- if scheduler_queue_name is None:
155
- # 如果没有设置,使用默认值
156
- scheduler_queue_name = f'crawlo:{project_name}:queue:requests'
157
-
158
- if not scheduler_queue_name:
159
- self.errors.append("使用Redis队列时,SCHEDULER_QUEUE_NAME 不能为空")
160
- elif not self._is_valid_redis_key(scheduler_queue_name):
161
- self.warnings.append(f"Redis队列名称 '{scheduler_queue_name}' 不符合命名规范,建议使用 'crawlo:{project_name}:queue:requests' 格式")
162
-
163
- def _validate_middleware_settings(self, config: Dict[str, Any]):
164
- """验证中间件设置"""
165
- # 验证 MIDDLEWARES
166
- middlewares = config.get('MIDDLEWARES', [])
167
- if not isinstance(middlewares, list):
168
- self.errors.append("MIDDLEWARES 必须是列表")
169
- else:
170
- for i, middleware in enumerate(middlewares):
171
- if not isinstance(middleware, str):
172
- self.errors.append(f"MIDDLEWARES[{i}] 必须是字符串")
173
-
174
- def _validate_pipeline_settings(self, config: Dict[str, Any]):
175
- """验证管道设置"""
176
- # 验证 PIPELINES
177
- pipelines = config.get('PIPELINES', [])
178
- if not isinstance(pipelines, list):
179
- self.errors.append("PIPELINES 必须是列表")
180
- else:
181
- for i, pipeline in enumerate(pipelines):
182
- if not isinstance(pipeline, str):
183
- self.errors.append(f"PIPELINES[{i}] 必须是字符串")
184
-
185
- def _validate_extension_settings(self, config: Dict[str, Any]):
186
- """验证扩展设置"""
187
- # 验证 EXTENSIONS
188
- extensions = config.get('EXTENSIONS', [])
189
- if not isinstance(extensions, list):
190
- self.errors.append("EXTENSIONS 必须是列表")
191
- else:
192
- for i, extension in enumerate(extensions):
193
- if not isinstance(extension, str):
194
- self.errors.append(f"EXTENSIONS[{i}] 必须是字符串")
195
-
196
- def _validate_logging_settings(self, config: Dict[str, Any]):
197
- """验证日志设置"""
198
- log_level = config.get('LOG_LEVEL', 'INFO')
199
- valid_log_levels = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']
200
- if log_level not in valid_log_levels:
201
- self.errors.append(f"LOG_LEVEL 必须是以下值之一: {valid_log_levels}")
202
-
203
- log_file = config.get('LOG_FILE')
204
- if log_file is not None and not isinstance(log_file, str):
205
- self.errors.append("LOG_FILE 必须是字符串")
206
-
207
- def _is_valid_redis_key(self, key: str) -> bool:
208
- """检查Redis key是否符合命名规范"""
209
- # 检查是否以 crawlo: 开头
210
- if not key.startswith('crawlo:'):
211
- return False
212
-
213
- # 检查是否包含必要的部分
214
- parts = key.split(':')
215
- if len(parts) < 3:
216
- return False
217
-
218
- # 检查是否包含 queue 部分
219
- return 'queue' in parts
220
-
221
- def get_validation_report(self, config: Dict[str, Any]) -> str:
222
- """
223
- 获取验证报告
224
-
225
- Args:
226
- config: 配置字典
227
-
228
- Returns:
229
- str: 验证报告
230
- """
231
- is_valid, errors, warnings = self.validate(config)
232
-
233
- report = []
234
- report.append("=" * 50)
235
- report.append("配置验证报告")
236
- report.append("=" * 50)
237
-
238
- if is_valid:
239
- report.append("配置验证通过")
240
- else:
241
- report.append("配置验证失败")
242
- report.append("错误:")
243
- for error in errors:
244
- report.append(f" - {error}")
245
-
246
- if warnings:
247
- report.append("警告:")
248
- for warning in warnings:
249
- report.append(f" - {warning}")
250
-
251
- report.append("=" * 50)
252
- return "\n".join(report)
253
-
254
-
255
- # 便利函数
256
- def validate_config(config: Dict[str, Any]) -> Tuple[bool, List[str], List[str]]:
257
- """
258
- 验证配置
259
-
260
- Args:
261
- config: 配置字典
262
-
263
- Returns:
264
- Tuple[bool, List[str], List[str]]: (是否有效, 错误列表, 警告列表)
265
- """
266
- validator = ConfigValidator()
267
- return validator.validate(config)
268
-
269
-
270
- def print_validation_report(config: Dict[str, Any]):
271
- """
272
- 打印验证报告
273
-
274
- Args:
275
- config: 配置字典
276
- """
277
- validator = ConfigValidator()
1
+ #!/usr/bin/python
2
+ # -*- coding: UTF-8 -*-
3
+ """
4
+ 配置验证器
5
+ ==========
6
+ 提供配置项的验证和默认值设置功能,确保配置的合理性和一致性。
7
+ """
8
+ from typing import Dict, Any, List, Tuple
9
+
10
+ from crawlo.utils.log import get_logger
11
+
12
+
13
+ class ConfigValidator:
14
+ """配置验证器"""
15
+
16
+ def __init__(self):
17
+ self.logger = get_logger(self.__class__.__name__)
18
+ self.errors = []
19
+ self.warnings = []
20
+
21
+ def validate(self, config: Dict[str, Any]) -> Tuple[bool, List[str], List[str]]:
22
+ """
23
+ 验证配置
24
+
25
+ Args:
26
+ config: 配置字典
27
+
28
+ Returns:
29
+ Tuple[bool, List[str], List[str]]: (是否有效, 错误列表, 警告列表)
30
+ """
31
+ self.errors = []
32
+ self.warnings = []
33
+
34
+ # 验证各个配置项
35
+ self._validate_basic_settings(config)
36
+ self._validate_network_settings(config)
37
+ self._validate_concurrency_settings(config)
38
+ self._validate_queue_settings(config)
39
+ self._validate_storage_settings(config)
40
+ self._validate_redis_settings(config)
41
+ self._validate_middleware_settings(config)
42
+ self._validate_pipeline_settings(config)
43
+ self._validate_extension_settings(config)
44
+ self._validate_logging_settings(config)
45
+
46
+ is_valid = len(self.errors) == 0
47
+ return is_valid, self.errors, self.warnings
48
+
49
+ def _validate_basic_settings(self, config: Dict[str, Any]):
50
+ """验证基本设置"""
51
+ project_name = config.get('PROJECT_NAME', 'crawlo')
52
+ if not isinstance(project_name, str) or not project_name.strip():
53
+ self.errors.append("PROJECT_NAME 必须是非空字符串")
54
+
55
+ version = config.get('VERSION', '1.0')
56
+ if not isinstance(version, str):
57
+ self.errors.append("VERSION 必须是字符串")
58
+
59
+ def _validate_network_settings(self, config: Dict[str, Any]):
60
+ """验证网络设置"""
61
+ # 下载器验证
62
+ downloader = config.get('DOWNLOADER', 'crawlo.downloader.aiohttp_downloader.AioHttpDownloader')
63
+ if not isinstance(downloader, str):
64
+ self.errors.append("DOWNLOADER 必须是字符串")
65
+
66
+ # 超时设置验证
67
+ timeout = config.get('DOWNLOAD_TIMEOUT', 30)
68
+ if not isinstance(timeout, (int, float)) or timeout <= 0:
69
+ self.errors.append("DOWNLOAD_TIMEOUT 必须是正数")
70
+
71
+ # 延迟设置验证
72
+ delay = config.get('DOWNLOAD_DELAY', 1.0)
73
+ if not isinstance(delay, (int, float)) or delay < 0:
74
+ self.errors.append("DOWNLOAD_DELAY 必须是非负数")
75
+
76
+ # 重试次数验证
77
+ max_retries = config.get('MAX_RETRY_TIMES', 3)
78
+ if not isinstance(max_retries, int) or max_retries < 0:
79
+ self.errors.append("MAX_RETRY_TIMES 必须是非负整数")
80
+
81
+ # 连接池限制验证
82
+ pool_limit = config.get('CONNECTION_POOL_LIMIT', 50)
83
+ if not isinstance(pool_limit, int) or pool_limit <= 0:
84
+ self.errors.append("CONNECTION_POOL_LIMIT 必须是正整数")
85
+
86
+ def _validate_concurrency_settings(self, config: Dict[str, Any]):
87
+ """验证并发设置"""
88
+ concurrency = config.get('CONCURRENCY', 8)
89
+ if not isinstance(concurrency, int) or concurrency <= 0:
90
+ self.errors.append("CONCURRENCY 必须是正整数")
91
+
92
+ max_running_spiders = config.get('MAX_RUNNING_SPIDERS', 3)
93
+ if not isinstance(max_running_spiders, int) or max_running_spiders <= 0:
94
+ self.errors.append("MAX_RUNNING_SPIDERS 必须是正整数")
95
+
96
+ def _validate_queue_settings(self, config: Dict[str, Any]):
97
+ """验证队列设置"""
98
+ queue_type = config.get('QUEUE_TYPE', 'memory')
99
+ valid_queue_types = ['memory', 'redis', 'auto']
100
+ if queue_type not in valid_queue_types:
101
+ self.errors.append(f"QUEUE_TYPE 必须是以下值之一: {valid_queue_types}")
102
+
103
+ # 队列大小验证
104
+ max_queue_size = config.get('SCHEDULER_MAX_QUEUE_SIZE', 2000)
105
+ if not isinstance(max_queue_size, int) or max_queue_size <= 0:
106
+ self.errors.append("SCHEDULER_MAX_QUEUE_SIZE 必须是正整数")
107
+
108
+ # 队列名称验证(如果是Redis队列)
109
+ if queue_type == 'redis':
110
+ queue_name = config.get('SCHEDULER_QUEUE_NAME', '')
111
+ if not queue_name:
112
+ self.errors.append("使用Redis队列时,SCHEDULER_QUEUE_NAME 不能为空")
113
+ elif not self._is_valid_redis_key(queue_name):
114
+ self.warnings.append(f"Redis队列名称 '{queue_name}' 不符合命名规范,建议使用 'crawlo:{config.get('PROJECT_NAME', 'project')}:queue:requests' 格式")
115
+
116
+ def _validate_storage_settings(self, config: Dict[str, Any]):
117
+ """验证存储设置"""
118
+ # MySQL设置验证
119
+ mysql_host = config.get('MYSQL_HOST')
120
+ if mysql_host is not None and not isinstance(mysql_host, str):
121
+ self.errors.append("MYSQL_HOST 必须是字符串")
122
+
123
+ mysql_port = config.get('MYSQL_PORT')
124
+ if mysql_port is not None and (not isinstance(mysql_port, int) or mysql_port <= 0 or mysql_port > 65535):
125
+ self.errors.append("MYSQL_PORT 必须是1-65535之间的整数")
126
+
127
+ # MongoDB设置验证
128
+ mongo_uri = config.get('MONGO_URI')
129
+ if mongo_uri is not None and not isinstance(mongo_uri, str):
130
+ self.errors.append("MONGO_URI 必须是字符串")
131
+
132
+ def _validate_redis_settings(self, config: Dict[str, Any]):
133
+ """验证Redis设置"""
134
+ queue_type = config.get('QUEUE_TYPE', 'memory')
135
+ if queue_type == 'redis':
136
+ # Redis主机验证
137
+ redis_host = config.get('REDIS_HOST', '127.0.0.1')
138
+ if not isinstance(redis_host, str) or not redis_host.strip():
139
+ self.errors.append("REDIS_HOST 必须是非空字符串")
140
+
141
+ # Redis端口验证
142
+ redis_port = config.get('REDIS_PORT', 6379)
143
+ if not isinstance(redis_port, int) or redis_port <= 0 or redis_port > 65535:
144
+ self.errors.append("REDIS_PORT 必须是1-65535之间的整数")
145
+
146
+ # Redis URL验证
147
+ redis_url = config.get('REDIS_URL')
148
+ if redis_url is not None and not isinstance(redis_url, str):
149
+ self.errors.append("REDIS_URL 必须是字符串")
150
+
151
+ # Redis队列名称验证(提供默认值)
152
+ scheduler_queue_name = config.get('SCHEDULER_QUEUE_NAME')
153
+ project_name = config.get('PROJECT_NAME', 'crawlo')
154
+ if scheduler_queue_name is None:
155
+ # 如果没有设置,使用默认值
156
+ scheduler_queue_name = f'crawlo:{project_name}:queue:requests'
157
+
158
+ if not scheduler_queue_name:
159
+ self.errors.append("使用Redis队列时,SCHEDULER_QUEUE_NAME 不能为空")
160
+ elif not self._is_valid_redis_key(scheduler_queue_name):
161
+ self.warnings.append(f"Redis队列名称 '{scheduler_queue_name}' 不符合命名规范,建议使用 'crawlo:{project_name}:queue:requests' 格式")
162
+
163
+ def _validate_middleware_settings(self, config: Dict[str, Any]):
164
+ """验证中间件设置"""
165
+ # 验证 MIDDLEWARES
166
+ middlewares = config.get('MIDDLEWARES', [])
167
+ if not isinstance(middlewares, list):
168
+ self.errors.append("MIDDLEWARES 必须是列表")
169
+ else:
170
+ for i, middleware in enumerate(middlewares):
171
+ if not isinstance(middleware, str):
172
+ self.errors.append(f"MIDDLEWARES[{i}] 必须是字符串")
173
+
174
+ def _validate_pipeline_settings(self, config: Dict[str, Any]):
175
+ """验证管道设置"""
176
+ # 验证 PIPELINES
177
+ pipelines = config.get('PIPELINES', [])
178
+ if not isinstance(pipelines, list):
179
+ self.errors.append("PIPELINES 必须是列表")
180
+ else:
181
+ for i, pipeline in enumerate(pipelines):
182
+ if not isinstance(pipeline, str):
183
+ self.errors.append(f"PIPELINES[{i}] 必须是字符串")
184
+
185
+ def _validate_extension_settings(self, config: Dict[str, Any]):
186
+ """验证扩展设置"""
187
+ # 验证 EXTENSIONS
188
+ extensions = config.get('EXTENSIONS', [])
189
+ if not isinstance(extensions, list):
190
+ self.errors.append("EXTENSIONS 必须是列表")
191
+ else:
192
+ for i, extension in enumerate(extensions):
193
+ if not isinstance(extension, str):
194
+ self.errors.append(f"EXTENSIONS[{i}] 必须是字符串")
195
+
196
+ def _validate_logging_settings(self, config: Dict[str, Any]):
197
+ """验证日志设置"""
198
+ log_level = config.get('LOG_LEVEL', 'INFO')
199
+ valid_log_levels = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']
200
+ if log_level not in valid_log_levels:
201
+ self.errors.append(f"LOG_LEVEL 必须是以下值之一: {valid_log_levels}")
202
+
203
+ log_file = config.get('LOG_FILE')
204
+ if log_file is not None and not isinstance(log_file, str):
205
+ self.errors.append("LOG_FILE 必须是字符串")
206
+
207
+ def _is_valid_redis_key(self, key: str) -> bool:
208
+ """检查Redis key是否符合命名规范"""
209
+ # 检查是否以 crawlo: 开头
210
+ if not key.startswith('crawlo:'):
211
+ return False
212
+
213
+ # 检查是否包含必要的部分
214
+ parts = key.split(':')
215
+ if len(parts) < 3:
216
+ return False
217
+
218
+ # 检查是否包含 queue 部分
219
+ return 'queue' in parts
220
+
221
+ def get_validation_report(self, config: Dict[str, Any]) -> str:
222
+ """
223
+ 获取验证报告
224
+
225
+ Args:
226
+ config: 配置字典
227
+
228
+ Returns:
229
+ str: 验证报告
230
+ """
231
+ is_valid, errors, warnings = self.validate(config)
232
+
233
+ report = []
234
+ report.append("=" * 50)
235
+ report.append("配置验证报告")
236
+ report.append("=" * 50)
237
+
238
+ if is_valid:
239
+ report.append("配置验证通过")
240
+ else:
241
+ report.append("配置验证失败")
242
+ report.append("错误:")
243
+ for error in errors:
244
+ report.append(f" - {error}")
245
+
246
+ if warnings:
247
+ report.append("警告:")
248
+ for warning in warnings:
249
+ report.append(f" - {warning}")
250
+
251
+ report.append("=" * 50)
252
+ return "\n".join(report)
253
+
254
+
255
+ # 便利函数
256
+ def validate_config(config: Dict[str, Any]) -> Tuple[bool, List[str], List[str]]:
257
+ """
258
+ 验证配置
259
+
260
+ Args:
261
+ config: 配置字典
262
+
263
+ Returns:
264
+ Tuple[bool, List[str], List[str]]: (是否有效, 错误列表, 警告列表)
265
+ """
266
+ validator = ConfigValidator()
267
+ return validator.validate(config)
268
+
269
+
270
+ def print_validation_report(config: Dict[str, Any]):
271
+ """
272
+ 打印验证报告
273
+
274
+ Args:
275
+ config: 配置字典
276
+ """
277
+ validator = ConfigValidator()
278
278
  print(validator.get_validation_report(config))
crawlo/core/__init__.py CHANGED
@@ -1,2 +1,2 @@
1
- #!/usr/bin/python
2
- # -*- coding:UTF-8 -*-
1
+ #!/usr/bin/python
2
+ # -*- coding:UTF-8 -*-