crawlo 1.2.5__py3-none-any.whl → 1.2.7__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 -354
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +251 -143
  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 -281
  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 -337
  78. crawlo/queue/redis_priority_queue.py +306 -299
  79. crawlo/settings/__init__.py +7 -7
  80. crawlo/settings/default_settings.py +219 -217
  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 -324
  92. crawlo/templates/project/settings_distributed.py.tmpl +157 -154
  93. crawlo/templates/project/settings_gentle.py.tmpl +101 -128
  94. crawlo/templates/project/settings_high_performance.py.tmpl +135 -150
  95. crawlo/templates/project/settings_simple.py.tmpl +99 -103
  96. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  97. crawlo/templates/run.py.tmpl +45 -47
  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 -334
  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-1.2.5.dist-info → crawlo-1.2.7.dist-info}/METADATA +764 -764
  130. crawlo-1.2.7.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-1.2.5.dist-info/RECORD +0 -206
  207. {crawlo-1.2.5.dist-info → crawlo-1.2.7.dist-info}/WHEEL +0 -0
  208. {crawlo-1.2.5.dist-info → crawlo-1.2.7.dist-info}/entry_points.txt +0 -0
  209. {crawlo-1.2.5.dist-info → crawlo-1.2.7.dist-info}/top_level.txt +0 -0
@@ -1,252 +1,252 @@
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_logging_settings(config)
44
-
45
- is_valid = len(self.errors) == 0
46
- return is_valid, self.errors, self.warnings
47
-
48
- def _validate_basic_settings(self, config: Dict[str, Any]):
49
- """验证基本设置"""
50
- project_name = config.get('PROJECT_NAME', 'crawlo')
51
- if not isinstance(project_name, str) or not project_name.strip():
52
- self.errors.append("PROJECT_NAME 必须是非空字符串")
53
-
54
- version = config.get('VERSION', '1.0')
55
- if not isinstance(version, str):
56
- self.errors.append("VERSION 必须是字符串")
57
-
58
- def _validate_network_settings(self, config: Dict[str, Any]):
59
- """验证网络设置"""
60
- # 下载器验证
61
- downloader = config.get('DOWNLOADER', 'crawlo.downloader.aiohttp_downloader.AioHttpDownloader')
62
- if not isinstance(downloader, str):
63
- self.errors.append("DOWNLOADER 必须是字符串")
64
-
65
- # 超时设置验证
66
- timeout = config.get('DOWNLOAD_TIMEOUT', 30)
67
- if not isinstance(timeout, (int, float)) or timeout <= 0:
68
- self.errors.append("DOWNLOAD_TIMEOUT 必须是正数")
69
-
70
- # 延迟设置验证
71
- delay = config.get('DOWNLOAD_DELAY', 1.0)
72
- if not isinstance(delay, (int, float)) or delay < 0:
73
- self.errors.append("DOWNLOAD_DELAY 必须是非负数")
74
-
75
- # 重试次数验证
76
- max_retries = config.get('MAX_RETRY_TIMES', 3)
77
- if not isinstance(max_retries, int) or max_retries < 0:
78
- self.errors.append("MAX_RETRY_TIMES 必须是非负整数")
79
-
80
- # 连接池限制验证
81
- pool_limit = config.get('CONNECTION_POOL_LIMIT', 50)
82
- if not isinstance(pool_limit, int) or pool_limit <= 0:
83
- self.errors.append("CONNECTION_POOL_LIMIT 必须是正整数")
84
-
85
- def _validate_concurrency_settings(self, config: Dict[str, Any]):
86
- """验证并发设置"""
87
- concurrency = config.get('CONCURRENCY', 8)
88
- if not isinstance(concurrency, int) or concurrency <= 0:
89
- self.errors.append("CONCURRENCY 必须是正整数")
90
-
91
- max_running_spiders = config.get('MAX_RUNNING_SPIDERS', 3)
92
- if not isinstance(max_running_spiders, int) or max_running_spiders <= 0:
93
- self.errors.append("MAX_RUNNING_SPIDERS 必须是正整数")
94
-
95
- def _validate_queue_settings(self, config: Dict[str, Any]):
96
- """验证队列设置"""
97
- queue_type = config.get('QUEUE_TYPE', 'memory')
98
- valid_queue_types = ['memory', 'redis', 'auto']
99
- if queue_type not in valid_queue_types:
100
- self.errors.append(f"QUEUE_TYPE 必须是以下值之一: {valid_queue_types}")
101
-
102
- # 队列大小验证
103
- max_queue_size = config.get('SCHEDULER_MAX_QUEUE_SIZE', 2000)
104
- if not isinstance(max_queue_size, int) or max_queue_size <= 0:
105
- self.errors.append("SCHEDULER_MAX_QUEUE_SIZE 必须是正整数")
106
-
107
- # 队列名称验证(如果是Redis队列)
108
- if queue_type == 'redis':
109
- queue_name = config.get('SCHEDULER_QUEUE_NAME', '')
110
- if not queue_name:
111
- self.errors.append("使用Redis队列时,SCHEDULER_QUEUE_NAME 不能为空")
112
- elif not self._is_valid_redis_key(queue_name):
113
- 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")
114
-
115
- def _validate_storage_settings(self, config: Dict[str, Any]):
116
- """验证存储设置"""
117
- # MySQL设置验证
118
- mysql_host = config.get('MYSQL_HOST')
119
- if mysql_host is not None and not isinstance(mysql_host, str):
120
- self.errors.append("MYSQL_HOST 必须是字符串")
121
-
122
- mysql_port = config.get('MYSQL_PORT')
123
- if mysql_port is not None and (not isinstance(mysql_port, int) or mysql_port <= 0 or mysql_port > 65535):
124
- self.errors.append("MYSQL_PORT 必须是1-65535之间的整数")
125
-
126
- # MongoDB设置验证
127
- mongo_uri = config.get('MONGO_URI')
128
- if mongo_uri is not None and not isinstance(mongo_uri, str):
129
- self.errors.append("MONGO_URI 必须是字符串")
130
-
131
- def _validate_redis_settings(self, config: Dict[str, Any]):
132
- """验证Redis设置"""
133
- queue_type = config.get('QUEUE_TYPE', 'memory')
134
- if queue_type == 'redis':
135
- # Redis主机验证
136
- redis_host = config.get('REDIS_HOST', '127.0.0.1')
137
- if not isinstance(redis_host, str) or not redis_host.strip():
138
- self.errors.append("REDIS_HOST 必须是非空字符串")
139
-
140
- # Redis端口验证
141
- redis_port = config.get('REDIS_PORT', 6379)
142
- if not isinstance(redis_port, int) or redis_port <= 0 or redis_port > 65535:
143
- self.errors.append("REDIS_PORT 必须是1-65535之间的整数")
144
-
145
- # Redis URL验证
146
- redis_url = config.get('REDIS_URL')
147
- if redis_url is not None and not isinstance(redis_url, str):
148
- self.errors.append("REDIS_URL 必须是字符串")
149
-
150
- def _validate_middleware_settings(self, config: Dict[str, Any]):
151
- """验证中间件设置"""
152
- middlewares = config.get('MIDDLEWARES', [])
153
- if not isinstance(middlewares, list):
154
- self.errors.append("MIDDLEWARES 必须是列表")
155
- else:
156
- for i, middleware in enumerate(middlewares):
157
- if not isinstance(middleware, str):
158
- self.errors.append(f"MIDDLEWARES[{i}] 必须是字符串")
159
-
160
- def _validate_pipeline_settings(self, config: Dict[str, Any]):
161
- """验证管道设置"""
162
- pipelines = config.get('PIPELINES', [])
163
- if not isinstance(pipelines, list):
164
- self.errors.append("PIPELINES 必须是列表")
165
- else:
166
- for i, pipeline in enumerate(pipelines):
167
- if not isinstance(pipeline, str):
168
- self.errors.append(f"PIPELINES[{i}] 必须是字符串")
169
-
170
- def _validate_logging_settings(self, config: Dict[str, Any]):
171
- """验证日志设置"""
172
- log_level = config.get('LOG_LEVEL', 'INFO')
173
- valid_log_levels = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']
174
- if log_level not in valid_log_levels:
175
- self.errors.append(f"LOG_LEVEL 必须是以下值之一: {valid_log_levels}")
176
-
177
- log_file = config.get('LOG_FILE')
178
- if log_file is not None and not isinstance(log_file, str):
179
- self.errors.append("LOG_FILE 必须是字符串")
180
-
181
- def _is_valid_redis_key(self, key: str) -> bool:
182
- """检查Redis key是否符合命名规范"""
183
- # 检查是否以 crawlo: 开头
184
- if not key.startswith('crawlo:'):
185
- return False
186
-
187
- # 检查是否包含必要的部分
188
- parts = key.split(':')
189
- if len(parts) < 3:
190
- return False
191
-
192
- # 检查是否包含 queue 部分
193
- return 'queue' in parts
194
-
195
- def get_validation_report(self, config: Dict[str, Any]) -> str:
196
- """
197
- 获取验证报告
198
-
199
- Args:
200
- config: 配置字典
201
-
202
- Returns:
203
- str: 验证报告
204
- """
205
- is_valid, errors, warnings = self.validate(config)
206
-
207
- report = []
208
- report.append("=" * 50)
209
- report.append("配置验证报告")
210
- report.append("=" * 50)
211
-
212
- if is_valid:
213
- report.append("✅ 配置验证通过")
214
- else:
215
- report.append("❌ 配置验证失败")
216
- report.append("错误:")
217
- for error in errors:
218
- report.append(f" - {error}")
219
-
220
- if warnings:
221
- report.append("警告:")
222
- for warning in warnings:
223
- report.append(f" - {warning}")
224
-
225
- report.append("=" * 50)
226
- return "\n".join(report)
227
-
228
-
229
- # 便利函数
230
- def validate_config(config: Dict[str, Any]) -> Tuple[bool, List[str], List[str]]:
231
- """
232
- 验证配置
233
-
234
- Args:
235
- config: 配置字典
236
-
237
- Returns:
238
- Tuple[bool, List[str], List[str]]: (是否有效, 错误列表, 警告列表)
239
- """
240
- validator = ConfigValidator()
241
- return validator.validate(config)
242
-
243
-
244
- def print_validation_report(config: Dict[str, Any]):
245
- """
246
- 打印验证报告
247
-
248
- Args:
249
- config: 配置字典
250
- """
251
- 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_logging_settings(config)
44
+
45
+ is_valid = len(self.errors) == 0
46
+ return is_valid, self.errors, self.warnings
47
+
48
+ def _validate_basic_settings(self, config: Dict[str, Any]):
49
+ """验证基本设置"""
50
+ project_name = config.get('PROJECT_NAME', 'crawlo')
51
+ if not isinstance(project_name, str) or not project_name.strip():
52
+ self.errors.append("PROJECT_NAME 必须是非空字符串")
53
+
54
+ version = config.get('VERSION', '1.0')
55
+ if not isinstance(version, str):
56
+ self.errors.append("VERSION 必须是字符串")
57
+
58
+ def _validate_network_settings(self, config: Dict[str, Any]):
59
+ """验证网络设置"""
60
+ # 下载器验证
61
+ downloader = config.get('DOWNLOADER', 'crawlo.downloader.aiohttp_downloader.AioHttpDownloader')
62
+ if not isinstance(downloader, str):
63
+ self.errors.append("DOWNLOADER 必须是字符串")
64
+
65
+ # 超时设置验证
66
+ timeout = config.get('DOWNLOAD_TIMEOUT', 30)
67
+ if not isinstance(timeout, (int, float)) or timeout <= 0:
68
+ self.errors.append("DOWNLOAD_TIMEOUT 必须是正数")
69
+
70
+ # 延迟设置验证
71
+ delay = config.get('DOWNLOAD_DELAY', 1.0)
72
+ if not isinstance(delay, (int, float)) or delay < 0:
73
+ self.errors.append("DOWNLOAD_DELAY 必须是非负数")
74
+
75
+ # 重试次数验证
76
+ max_retries = config.get('MAX_RETRY_TIMES', 3)
77
+ if not isinstance(max_retries, int) or max_retries < 0:
78
+ self.errors.append("MAX_RETRY_TIMES 必须是非负整数")
79
+
80
+ # 连接池限制验证
81
+ pool_limit = config.get('CONNECTION_POOL_LIMIT', 50)
82
+ if not isinstance(pool_limit, int) or pool_limit <= 0:
83
+ self.errors.append("CONNECTION_POOL_LIMIT 必须是正整数")
84
+
85
+ def _validate_concurrency_settings(self, config: Dict[str, Any]):
86
+ """验证并发设置"""
87
+ concurrency = config.get('CONCURRENCY', 8)
88
+ if not isinstance(concurrency, int) or concurrency <= 0:
89
+ self.errors.append("CONCURRENCY 必须是正整数")
90
+
91
+ max_running_spiders = config.get('MAX_RUNNING_SPIDERS', 3)
92
+ if not isinstance(max_running_spiders, int) or max_running_spiders <= 0:
93
+ self.errors.append("MAX_RUNNING_SPIDERS 必须是正整数")
94
+
95
+ def _validate_queue_settings(self, config: Dict[str, Any]):
96
+ """验证队列设置"""
97
+ queue_type = config.get('QUEUE_TYPE', 'memory')
98
+ valid_queue_types = ['memory', 'redis', 'auto']
99
+ if queue_type not in valid_queue_types:
100
+ self.errors.append(f"QUEUE_TYPE 必须是以下值之一: {valid_queue_types}")
101
+
102
+ # 队列大小验证
103
+ max_queue_size = config.get('SCHEDULER_MAX_QUEUE_SIZE', 2000)
104
+ if not isinstance(max_queue_size, int) or max_queue_size <= 0:
105
+ self.errors.append("SCHEDULER_MAX_QUEUE_SIZE 必须是正整数")
106
+
107
+ # 队列名称验证(如果是Redis队列)
108
+ if queue_type == 'redis':
109
+ queue_name = config.get('SCHEDULER_QUEUE_NAME', '')
110
+ if not queue_name:
111
+ self.errors.append("使用Redis队列时,SCHEDULER_QUEUE_NAME 不能为空")
112
+ elif not self._is_valid_redis_key(queue_name):
113
+ 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")
114
+
115
+ def _validate_storage_settings(self, config: Dict[str, Any]):
116
+ """验证存储设置"""
117
+ # MySQL设置验证
118
+ mysql_host = config.get('MYSQL_HOST')
119
+ if mysql_host is not None and not isinstance(mysql_host, str):
120
+ self.errors.append("MYSQL_HOST 必须是字符串")
121
+
122
+ mysql_port = config.get('MYSQL_PORT')
123
+ if mysql_port is not None and (not isinstance(mysql_port, int) or mysql_port <= 0 or mysql_port > 65535):
124
+ self.errors.append("MYSQL_PORT 必须是1-65535之间的整数")
125
+
126
+ # MongoDB设置验证
127
+ mongo_uri = config.get('MONGO_URI')
128
+ if mongo_uri is not None and not isinstance(mongo_uri, str):
129
+ self.errors.append("MONGO_URI 必须是字符串")
130
+
131
+ def _validate_redis_settings(self, config: Dict[str, Any]):
132
+ """验证Redis设置"""
133
+ queue_type = config.get('QUEUE_TYPE', 'memory')
134
+ if queue_type == 'redis':
135
+ # Redis主机验证
136
+ redis_host = config.get('REDIS_HOST', '127.0.0.1')
137
+ if not isinstance(redis_host, str) or not redis_host.strip():
138
+ self.errors.append("REDIS_HOST 必须是非空字符串")
139
+
140
+ # Redis端口验证
141
+ redis_port = config.get('REDIS_PORT', 6379)
142
+ if not isinstance(redis_port, int) or redis_port <= 0 or redis_port > 65535:
143
+ self.errors.append("REDIS_PORT 必须是1-65535之间的整数")
144
+
145
+ # Redis URL验证
146
+ redis_url = config.get('REDIS_URL')
147
+ if redis_url is not None and not isinstance(redis_url, str):
148
+ self.errors.append("REDIS_URL 必须是字符串")
149
+
150
+ def _validate_middleware_settings(self, config: Dict[str, Any]):
151
+ """验证中间件设置"""
152
+ middlewares = config.get('MIDDLEWARES', [])
153
+ if not isinstance(middlewares, list):
154
+ self.errors.append("MIDDLEWARES 必须是列表")
155
+ else:
156
+ for i, middleware in enumerate(middlewares):
157
+ if not isinstance(middleware, str):
158
+ self.errors.append(f"MIDDLEWARES[{i}] 必须是字符串")
159
+
160
+ def _validate_pipeline_settings(self, config: Dict[str, Any]):
161
+ """验证管道设置"""
162
+ pipelines = config.get('PIPELINES', [])
163
+ if not isinstance(pipelines, list):
164
+ self.errors.append("PIPELINES 必须是列表")
165
+ else:
166
+ for i, pipeline in enumerate(pipelines):
167
+ if not isinstance(pipeline, str):
168
+ self.errors.append(f"PIPELINES[{i}] 必须是字符串")
169
+
170
+ def _validate_logging_settings(self, config: Dict[str, Any]):
171
+ """验证日志设置"""
172
+ log_level = config.get('LOG_LEVEL', 'INFO')
173
+ valid_log_levels = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']
174
+ if log_level not in valid_log_levels:
175
+ self.errors.append(f"LOG_LEVEL 必须是以下值之一: {valid_log_levels}")
176
+
177
+ log_file = config.get('LOG_FILE')
178
+ if log_file is not None and not isinstance(log_file, str):
179
+ self.errors.append("LOG_FILE 必须是字符串")
180
+
181
+ def _is_valid_redis_key(self, key: str) -> bool:
182
+ """检查Redis key是否符合命名规范"""
183
+ # 检查是否以 crawlo: 开头
184
+ if not key.startswith('crawlo:'):
185
+ return False
186
+
187
+ # 检查是否包含必要的部分
188
+ parts = key.split(':')
189
+ if len(parts) < 3:
190
+ return False
191
+
192
+ # 检查是否包含 queue 部分
193
+ return 'queue' in parts
194
+
195
+ def get_validation_report(self, config: Dict[str, Any]) -> str:
196
+ """
197
+ 获取验证报告
198
+
199
+ Args:
200
+ config: 配置字典
201
+
202
+ Returns:
203
+ str: 验证报告
204
+ """
205
+ is_valid, errors, warnings = self.validate(config)
206
+
207
+ report = []
208
+ report.append("=" * 50)
209
+ report.append("配置验证报告")
210
+ report.append("=" * 50)
211
+
212
+ if is_valid:
213
+ report.append("✅ 配置验证通过")
214
+ else:
215
+ report.append("❌ 配置验证失败")
216
+ report.append("错误:")
217
+ for error in errors:
218
+ report.append(f" - {error}")
219
+
220
+ if warnings:
221
+ report.append("警告:")
222
+ for warning in warnings:
223
+ report.append(f" - {warning}")
224
+
225
+ report.append("=" * 50)
226
+ return "\n".join(report)
227
+
228
+
229
+ # 便利函数
230
+ def validate_config(config: Dict[str, Any]) -> Tuple[bool, List[str], List[str]]:
231
+ """
232
+ 验证配置
233
+
234
+ Args:
235
+ config: 配置字典
236
+
237
+ Returns:
238
+ Tuple[bool, List[str], List[str]]: (是否有效, 错误列表, 警告列表)
239
+ """
240
+ validator = ConfigValidator()
241
+ return validator.validate(config)
242
+
243
+
244
+ def print_validation_report(config: Dict[str, Any]):
245
+ """
246
+ 打印验证报告
247
+
248
+ Args:
249
+ config: 配置字典
250
+ """
251
+ validator = ConfigValidator()
252
252
  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 -*-