crawlo 1.2.0__py3-none-any.whl → 1.2.2__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 (220) 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 +81 -65
  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 +143 -133
  12. crawlo/commands/list.py +155 -155
  13. crawlo/commands/run.py +292 -292
  14. crawlo/commands/startproject.py +418 -418
  15. crawlo/commands/stats.py +188 -188
  16. crawlo/commands/utils.py +186 -186
  17. crawlo/config.py +312 -312
  18. crawlo/config_validator.py +252 -252
  19. crawlo/core/__init__.py +2 -2
  20. crawlo/core/engine.py +354 -354
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +143 -143
  23. crawlo/crawler.py +1027 -1027
  24. crawlo/downloader/__init__.py +266 -266
  25. crawlo/downloader/aiohttp_downloader.py +220 -220
  26. crawlo/downloader/cffi_downloader.py +256 -256
  27. crawlo/downloader/httpx_downloader.py +259 -259
  28. crawlo/downloader/hybrid_downloader.py +213 -213
  29. crawlo/downloader/playwright_downloader.py +402 -402
  30. crawlo/downloader/selenium_downloader.py +472 -472
  31. crawlo/event.py +11 -11
  32. crawlo/exceptions.py +81 -81
  33. crawlo/extension/__init__.py +37 -37
  34. crawlo/extension/health_check.py +141 -141
  35. crawlo/extension/log_interval.py +57 -57
  36. crawlo/extension/log_stats.py +81 -81
  37. crawlo/extension/logging_extension.py +43 -43
  38. crawlo/extension/memory_monitor.py +104 -104
  39. crawlo/extension/performance_profiler.py +133 -133
  40. crawlo/extension/request_recorder.py +107 -107
  41. crawlo/filters/__init__.py +154 -154
  42. crawlo/filters/aioredis_filter.py +280 -280
  43. crawlo/filters/memory_filter.py +269 -269
  44. crawlo/items/__init__.py +23 -23
  45. crawlo/items/base.py +21 -21
  46. crawlo/items/fields.py +53 -53
  47. crawlo/items/items.py +104 -104
  48. crawlo/middleware/__init__.py +21 -21
  49. crawlo/middleware/default_header.py +132 -32
  50. crawlo/middleware/download_delay.py +105 -28
  51. crawlo/middleware/middleware_manager.py +135 -135
  52. crawlo/middleware/offsite.py +116 -0
  53. crawlo/middleware/proxy.py +366 -272
  54. crawlo/middleware/request_ignore.py +88 -30
  55. crawlo/middleware/response_code.py +164 -18
  56. crawlo/middleware/response_filter.py +138 -26
  57. crawlo/middleware/retry.py +124 -124
  58. crawlo/mode_manager.py +211 -211
  59. crawlo/network/__init__.py +21 -21
  60. crawlo/network/request.py +338 -338
  61. crawlo/network/response.py +359 -359
  62. crawlo/pipelines/__init__.py +21 -21
  63. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  64. crawlo/pipelines/console_pipeline.py +39 -39
  65. crawlo/pipelines/csv_pipeline.py +316 -316
  66. crawlo/pipelines/database_dedup_pipeline.py +224 -224
  67. crawlo/pipelines/json_pipeline.py +218 -218
  68. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  69. crawlo/pipelines/mongo_pipeline.py +131 -131
  70. crawlo/pipelines/mysql_pipeline.py +316 -316
  71. crawlo/pipelines/pipeline_manager.py +61 -61
  72. crawlo/pipelines/redis_dedup_pipeline.py +167 -167
  73. crawlo/project.py +187 -187
  74. crawlo/queue/pqueue.py +37 -37
  75. crawlo/queue/queue_manager.py +337 -337
  76. crawlo/queue/redis_priority_queue.py +298 -298
  77. crawlo/settings/__init__.py +7 -7
  78. crawlo/settings/default_settings.py +226 -219
  79. crawlo/settings/setting_manager.py +122 -122
  80. crawlo/spider/__init__.py +639 -639
  81. crawlo/stats_collector.py +59 -59
  82. crawlo/subscriber.py +130 -130
  83. crawlo/task_manager.py +30 -30
  84. crawlo/templates/crawlo.cfg.tmpl +10 -10
  85. crawlo/templates/project/__init__.py.tmpl +3 -3
  86. crawlo/templates/project/items.py.tmpl +17 -17
  87. crawlo/templates/project/middlewares.py.tmpl +118 -109
  88. crawlo/templates/project/pipelines.py.tmpl +96 -96
  89. crawlo/templates/project/run.py.tmpl +45 -45
  90. crawlo/templates/project/settings.py.tmpl +327 -326
  91. crawlo/templates/project/settings_distributed.py.tmpl +119 -119
  92. crawlo/templates/project/settings_gentle.py.tmpl +94 -94
  93. crawlo/templates/project/settings_high_performance.py.tmpl +151 -151
  94. crawlo/templates/project/settings_simple.py.tmpl +68 -68
  95. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  96. crawlo/templates/spider/spider.py.tmpl +143 -141
  97. crawlo/tools/__init__.py +182 -182
  98. crawlo/tools/anti_crawler.py +268 -268
  99. crawlo/tools/authenticated_proxy.py +240 -240
  100. crawlo/tools/data_validator.py +180 -180
  101. crawlo/tools/date_tools.py +35 -35
  102. crawlo/tools/distributed_coordinator.py +386 -386
  103. crawlo/tools/retry_mechanism.py +220 -220
  104. crawlo/tools/scenario_adapter.py +262 -262
  105. crawlo/utils/__init__.py +35 -35
  106. crawlo/utils/batch_processor.py +260 -260
  107. crawlo/utils/controlled_spider_mixin.py +439 -439
  108. crawlo/utils/date_tools.py +290 -290
  109. crawlo/utils/db_helper.py +343 -343
  110. crawlo/utils/enhanced_error_handler.py +359 -359
  111. crawlo/utils/env_config.py +105 -105
  112. crawlo/utils/error_handler.py +125 -125
  113. crawlo/utils/func_tools.py +82 -82
  114. crawlo/utils/large_scale_config.py +286 -286
  115. crawlo/utils/large_scale_helper.py +343 -343
  116. crawlo/utils/log.py +128 -128
  117. crawlo/utils/performance_monitor.py +284 -284
  118. crawlo/utils/queue_helper.py +175 -175
  119. crawlo/utils/redis_connection_pool.py +334 -334
  120. crawlo/utils/redis_key_validator.py +199 -199
  121. crawlo/utils/request.py +267 -267
  122. crawlo/utils/request_serializer.py +219 -219
  123. crawlo/utils/spider_loader.py +62 -62
  124. crawlo/utils/system.py +11 -11
  125. crawlo/utils/tools.py +4 -4
  126. crawlo/utils/url.py +39 -39
  127. {crawlo-1.2.0.dist-info → crawlo-1.2.2.dist-info}/METADATA +692 -697
  128. crawlo-1.2.2.dist-info/RECORD +220 -0
  129. examples/__init__.py +7 -7
  130. examples/aiohttp_settings.py +42 -0
  131. examples/curl_cffi_settings.py +41 -0
  132. examples/default_header_middleware_example.py +107 -0
  133. examples/default_header_spider_example.py +129 -0
  134. examples/download_delay_middleware_example.py +160 -0
  135. examples/httpx_settings.py +42 -0
  136. examples/multi_downloader_proxy_example.py +81 -0
  137. examples/offsite_middleware_example.py +55 -0
  138. examples/offsite_spider_example.py +107 -0
  139. examples/proxy_spider_example.py +166 -0
  140. examples/request_ignore_middleware_example.py +51 -0
  141. examples/request_ignore_spider_example.py +99 -0
  142. examples/response_code_middleware_example.py +52 -0
  143. examples/response_filter_middleware_example.py +67 -0
  144. examples/tong_hua_shun_settings.py +62 -0
  145. examples/tong_hua_shun_spider.py +170 -0
  146. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  147. tests/__init__.py +7 -7
  148. tests/advanced_tools_example.py +275 -275
  149. tests/authenticated_proxy_example.py +236 -236
  150. tests/cleaners_example.py +160 -160
  151. tests/config_validation_demo.py +102 -102
  152. tests/controlled_spider_example.py +205 -205
  153. tests/date_tools_example.py +180 -180
  154. tests/dynamic_loading_example.py +523 -523
  155. tests/dynamic_loading_test.py +104 -104
  156. tests/env_config_example.py +133 -133
  157. tests/error_handling_example.py +171 -171
  158. tests/redis_key_validation_demo.py +130 -130
  159. tests/response_improvements_example.py +144 -144
  160. tests/test_advanced_tools.py +148 -148
  161. tests/test_all_redis_key_configs.py +145 -145
  162. tests/test_authenticated_proxy.py +141 -141
  163. tests/test_cleaners.py +54 -54
  164. tests/test_comprehensive.py +146 -146
  165. tests/test_config_validator.py +193 -193
  166. tests/test_crawlo_proxy_integration.py +173 -0
  167. tests/test_date_tools.py +123 -123
  168. tests/test_default_header_middleware.py +159 -0
  169. tests/test_double_crawlo_fix.py +207 -207
  170. tests/test_double_crawlo_fix_simple.py +124 -124
  171. tests/test_download_delay_middleware.py +222 -0
  172. tests/test_downloader_proxy_compatibility.py +269 -0
  173. tests/test_dynamic_downloaders_proxy.py +124 -124
  174. tests/test_dynamic_proxy.py +92 -92
  175. tests/test_dynamic_proxy_config.py +146 -146
  176. tests/test_dynamic_proxy_real.py +109 -109
  177. tests/test_edge_cases.py +303 -303
  178. tests/test_enhanced_error_handler.py +270 -270
  179. tests/test_env_config.py +121 -121
  180. tests/test_error_handler_compatibility.py +112 -112
  181. tests/test_final_validation.py +153 -153
  182. tests/test_framework_env_usage.py +103 -103
  183. tests/test_integration.py +356 -356
  184. tests/test_item_dedup_redis_key.py +122 -122
  185. tests/test_offsite_middleware.py +222 -0
  186. tests/test_parsel.py +29 -29
  187. tests/test_performance.py +327 -327
  188. tests/test_proxy_api.py +265 -0
  189. tests/test_proxy_health_check.py +32 -32
  190. tests/test_proxy_middleware.py +122 -0
  191. tests/test_proxy_middleware_enhanced.py +217 -0
  192. tests/test_proxy_middleware_integration.py +136 -136
  193. tests/test_proxy_providers.py +56 -56
  194. tests/test_proxy_stats.py +19 -19
  195. tests/test_proxy_strategies.py +59 -59
  196. tests/test_queue_manager_double_crawlo.py +173 -173
  197. tests/test_queue_manager_redis_key.py +176 -176
  198. tests/test_real_scenario_proxy.py +196 -0
  199. tests/test_redis_config.py +28 -28
  200. tests/test_redis_connection_pool.py +294 -294
  201. tests/test_redis_key_naming.py +181 -181
  202. tests/test_redis_key_validator.py +123 -123
  203. tests/test_redis_queue.py +224 -224
  204. tests/test_request_ignore_middleware.py +183 -0
  205. tests/test_request_serialization.py +70 -70
  206. tests/test_response_code_middleware.py +350 -0
  207. tests/test_response_filter_middleware.py +428 -0
  208. tests/test_response_improvements.py +152 -152
  209. tests/test_retry_middleware.py +242 -0
  210. tests/test_scheduler.py +241 -241
  211. tests/test_simple_response.py +61 -61
  212. tests/test_telecom_spider_redis_key.py +205 -205
  213. tests/test_template_content.py +87 -87
  214. tests/test_template_redis_key.py +134 -134
  215. tests/test_tools.py +153 -153
  216. tests/tools_example.py +257 -257
  217. crawlo-1.2.0.dist-info/RECORD +0 -190
  218. {crawlo-1.2.0.dist-info → crawlo-1.2.2.dist-info}/WHEEL +0 -0
  219. {crawlo-1.2.0.dist-info → crawlo-1.2.2.dist-info}/entry_points.txt +0 -0
  220. {crawlo-1.2.0.dist-info → crawlo-1.2.2.dist-info}/top_level.txt +0 -0
@@ -1,253 +1,253 @@
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
-
9
- from typing import Dict, Any, List, Tuple, Optional
10
- import re
11
- from crawlo.utils.log import get_logger
12
-
13
-
14
- class ConfigValidator:
15
- """配置验证器"""
16
-
17
- def __init__(self):
18
- self.logger = get_logger(self.__class__.__name__)
19
- self.errors = []
20
- self.warnings = []
21
-
22
- def validate(self, config: Dict[str, Any]) -> Tuple[bool, List[str], List[str]]:
23
- """
24
- 验证配置
25
-
26
- Args:
27
- config: 配置字典
28
-
29
- Returns:
30
- Tuple[bool, List[str], List[str]]: (是否有效, 错误列表, 警告列表)
31
- """
32
- self.errors = []
33
- self.warnings = []
34
-
35
- # 验证各个配置项
36
- self._validate_basic_settings(config)
37
- self._validate_network_settings(config)
38
- self._validate_concurrency_settings(config)
39
- self._validate_queue_settings(config)
40
- self._validate_storage_settings(config)
41
- self._validate_redis_settings(config)
42
- self._validate_middleware_settings(config)
43
- self._validate_pipeline_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
- def _validate_middleware_settings(self, config: Dict[str, Any]):
152
- """验证中间件设置"""
153
- middlewares = config.get('MIDDLEWARES', [])
154
- if not isinstance(middlewares, list):
155
- self.errors.append("MIDDLEWARES 必须是列表")
156
- else:
157
- for i, middleware in enumerate(middlewares):
158
- if not isinstance(middleware, str):
159
- self.errors.append(f"MIDDLEWARES[{i}] 必须是字符串")
160
-
161
- def _validate_pipeline_settings(self, config: Dict[str, Any]):
162
- """验证管道设置"""
163
- pipelines = config.get('PIPELINES', [])
164
- if not isinstance(pipelines, list):
165
- self.errors.append("PIPELINES 必须是列表")
166
- else:
167
- for i, pipeline in enumerate(pipelines):
168
- if not isinstance(pipeline, str):
169
- self.errors.append(f"PIPELINES[{i}] 必须是字符串")
170
-
171
- def _validate_logging_settings(self, config: Dict[str, Any]):
172
- """验证日志设置"""
173
- log_level = config.get('LOG_LEVEL', 'INFO')
174
- valid_log_levels = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']
175
- if log_level not in valid_log_levels:
176
- self.errors.append(f"LOG_LEVEL 必须是以下值之一: {valid_log_levels}")
177
-
178
- log_file = config.get('LOG_FILE')
179
- if log_file is not None and not isinstance(log_file, str):
180
- self.errors.append("LOG_FILE 必须是字符串")
181
-
182
- def _is_valid_redis_key(self, key: str) -> bool:
183
- """检查Redis key是否符合命名规范"""
184
- # 检查是否以 crawlo: 开头
185
- if not key.startswith('crawlo:'):
186
- return False
187
-
188
- # 检查是否包含必要的部分
189
- parts = key.split(':')
190
- if len(parts) < 3:
191
- return False
192
-
193
- # 检查是否包含 queue 部分
194
- return 'queue' in parts
195
-
196
- def get_validation_report(self, config: Dict[str, Any]) -> str:
197
- """
198
- 获取验证报告
199
-
200
- Args:
201
- config: 配置字典
202
-
203
- Returns:
204
- str: 验证报告
205
- """
206
- is_valid, errors, warnings = self.validate(config)
207
-
208
- report = []
209
- report.append("=" * 50)
210
- report.append("配置验证报告")
211
- report.append("=" * 50)
212
-
213
- if is_valid:
214
- report.append("✅ 配置验证通过")
215
- else:
216
- report.append("❌ 配置验证失败")
217
- report.append("错误:")
218
- for error in errors:
219
- report.append(f" - {error}")
220
-
221
- if warnings:
222
- report.append("警告:")
223
- for warning in warnings:
224
- report.append(f" - {warning}")
225
-
226
- report.append("=" * 50)
227
- return "\n".join(report)
228
-
229
-
230
- # 便利函数
231
- def validate_config(config: Dict[str, Any]) -> Tuple[bool, List[str], List[str]]:
232
- """
233
- 验证配置
234
-
235
- Args:
236
- config: 配置字典
237
-
238
- Returns:
239
- Tuple[bool, List[str], List[str]]: (是否有效, 错误列表, 警告列表)
240
- """
241
- validator = ConfigValidator()
242
- return validator.validate(config)
243
-
244
-
245
- def print_validation_report(config: Dict[str, Any]):
246
- """
247
- 打印验证报告
248
-
249
- Args:
250
- config: 配置字典
251
- """
252
- 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
+
9
+ from typing import Dict, Any, List, Tuple, Optional
10
+ import re
11
+ from crawlo.utils.log import get_logger
12
+
13
+
14
+ class ConfigValidator:
15
+ """配置验证器"""
16
+
17
+ def __init__(self):
18
+ self.logger = get_logger(self.__class__.__name__)
19
+ self.errors = []
20
+ self.warnings = []
21
+
22
+ def validate(self, config: Dict[str, Any]) -> Tuple[bool, List[str], List[str]]:
23
+ """
24
+ 验证配置
25
+
26
+ Args:
27
+ config: 配置字典
28
+
29
+ Returns:
30
+ Tuple[bool, List[str], List[str]]: (是否有效, 错误列表, 警告列表)
31
+ """
32
+ self.errors = []
33
+ self.warnings = []
34
+
35
+ # 验证各个配置项
36
+ self._validate_basic_settings(config)
37
+ self._validate_network_settings(config)
38
+ self._validate_concurrency_settings(config)
39
+ self._validate_queue_settings(config)
40
+ self._validate_storage_settings(config)
41
+ self._validate_redis_settings(config)
42
+ self._validate_middleware_settings(config)
43
+ self._validate_pipeline_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
+ def _validate_middleware_settings(self, config: Dict[str, Any]):
152
+ """验证中间件设置"""
153
+ middlewares = config.get('MIDDLEWARES', [])
154
+ if not isinstance(middlewares, list):
155
+ self.errors.append("MIDDLEWARES 必须是列表")
156
+ else:
157
+ for i, middleware in enumerate(middlewares):
158
+ if not isinstance(middleware, str):
159
+ self.errors.append(f"MIDDLEWARES[{i}] 必须是字符串")
160
+
161
+ def _validate_pipeline_settings(self, config: Dict[str, Any]):
162
+ """验证管道设置"""
163
+ pipelines = config.get('PIPELINES', [])
164
+ if not isinstance(pipelines, list):
165
+ self.errors.append("PIPELINES 必须是列表")
166
+ else:
167
+ for i, pipeline in enumerate(pipelines):
168
+ if not isinstance(pipeline, str):
169
+ self.errors.append(f"PIPELINES[{i}] 必须是字符串")
170
+
171
+ def _validate_logging_settings(self, config: Dict[str, Any]):
172
+ """验证日志设置"""
173
+ log_level = config.get('LOG_LEVEL', 'INFO')
174
+ valid_log_levels = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']
175
+ if log_level not in valid_log_levels:
176
+ self.errors.append(f"LOG_LEVEL 必须是以下值之一: {valid_log_levels}")
177
+
178
+ log_file = config.get('LOG_FILE')
179
+ if log_file is not None and not isinstance(log_file, str):
180
+ self.errors.append("LOG_FILE 必须是字符串")
181
+
182
+ def _is_valid_redis_key(self, key: str) -> bool:
183
+ """检查Redis key是否符合命名规范"""
184
+ # 检查是否以 crawlo: 开头
185
+ if not key.startswith('crawlo:'):
186
+ return False
187
+
188
+ # 检查是否包含必要的部分
189
+ parts = key.split(':')
190
+ if len(parts) < 3:
191
+ return False
192
+
193
+ # 检查是否包含 queue 部分
194
+ return 'queue' in parts
195
+
196
+ def get_validation_report(self, config: Dict[str, Any]) -> str:
197
+ """
198
+ 获取验证报告
199
+
200
+ Args:
201
+ config: 配置字典
202
+
203
+ Returns:
204
+ str: 验证报告
205
+ """
206
+ is_valid, errors, warnings = self.validate(config)
207
+
208
+ report = []
209
+ report.append("=" * 50)
210
+ report.append("配置验证报告")
211
+ report.append("=" * 50)
212
+
213
+ if is_valid:
214
+ report.append("✅ 配置验证通过")
215
+ else:
216
+ report.append("❌ 配置验证失败")
217
+ report.append("错误:")
218
+ for error in errors:
219
+ report.append(f" - {error}")
220
+
221
+ if warnings:
222
+ report.append("警告:")
223
+ for warning in warnings:
224
+ report.append(f" - {warning}")
225
+
226
+ report.append("=" * 50)
227
+ return "\n".join(report)
228
+
229
+
230
+ # 便利函数
231
+ def validate_config(config: Dict[str, Any]) -> Tuple[bool, List[str], List[str]]:
232
+ """
233
+ 验证配置
234
+
235
+ Args:
236
+ config: 配置字典
237
+
238
+ Returns:
239
+ Tuple[bool, List[str], List[str]]: (是否有效, 错误列表, 警告列表)
240
+ """
241
+ validator = ConfigValidator()
242
+ return validator.validate(config)
243
+
244
+
245
+ def print_validation_report(config: Dict[str, Any]):
246
+ """
247
+ 打印验证报告
248
+
249
+ Args:
250
+ config: 配置字典
251
+ """
252
+ validator = ConfigValidator()
253
253
  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 -*-