crawlo 1.1.6__py3-none-any.whl → 1.1.9__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 (190) 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 +65 -40
  8. crawlo/commands/__init__.py +14 -13
  9. crawlo/commands/check.py +594 -594
  10. crawlo/commands/genspider.py +151 -151
  11. crawlo/commands/help.py +133 -0
  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 +345 -345
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +136 -136
  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 +32 -32
  50. crawlo/middleware/download_delay.py +28 -28
  51. crawlo/middleware/middleware_manager.py +135 -135
  52. crawlo/middleware/proxy.py +272 -272
  53. crawlo/middleware/request_ignore.py +30 -30
  54. crawlo/middleware/response_code.py +18 -18
  55. crawlo/middleware/response_filter.py +26 -26
  56. crawlo/middleware/retry.py +124 -124
  57. crawlo/mode_manager.py +211 -211
  58. crawlo/network/__init__.py +21 -21
  59. crawlo/network/request.py +338 -338
  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 +224 -224
  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 +316 -316
  70. crawlo/pipelines/pipeline_manager.py +61 -61
  71. crawlo/pipelines/redis_dedup_pipeline.py +167 -167
  72. crawlo/project.py +187 -187
  73. crawlo/queue/pqueue.py +37 -37
  74. crawlo/queue/queue_manager.py +334 -334
  75. crawlo/queue/redis_priority_queue.py +298 -298
  76. crawlo/settings/__init__.py +7 -7
  77. crawlo/settings/default_settings.py +219 -219
  78. crawlo/settings/setting_manager.py +122 -122
  79. crawlo/spider/__init__.py +639 -639
  80. crawlo/stats_collector.py +59 -59
  81. crawlo/subscriber.py +130 -130
  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 +109 -110
  87. crawlo/templates/project/pipelines.py.tmpl +96 -97
  88. crawlo/templates/project/run.py.tmpl +46 -252
  89. crawlo/templates/project/settings.py.tmpl +326 -326
  90. crawlo/templates/project/settings_distributed.py.tmpl +119 -119
  91. crawlo/templates/project/settings_gentle.py.tmpl +94 -94
  92. crawlo/templates/project/settings_high_performance.py.tmpl +151 -151
  93. crawlo/templates/project/settings_simple.py.tmpl +68 -68
  94. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  95. crawlo/templates/spider/spider.py.tmpl +141 -141
  96. crawlo/tools/__init__.py +182 -182
  97. crawlo/tools/anti_crawler.py +268 -268
  98. crawlo/tools/authenticated_proxy.py +240 -240
  99. crawlo/tools/data_validator.py +180 -180
  100. crawlo/tools/date_tools.py +35 -35
  101. crawlo/tools/distributed_coordinator.py +386 -386
  102. crawlo/tools/retry_mechanism.py +220 -220
  103. crawlo/tools/scenario_adapter.py +262 -262
  104. crawlo/utils/__init__.py +35 -35
  105. crawlo/utils/batch_processor.py +260 -260
  106. crawlo/utils/controlled_spider_mixin.py +439 -439
  107. crawlo/utils/date_tools.py +290 -290
  108. crawlo/utils/db_helper.py +343 -343
  109. crawlo/utils/enhanced_error_handler.py +359 -359
  110. crawlo/utils/env_config.py +105 -105
  111. crawlo/utils/error_handler.py +125 -125
  112. crawlo/utils/func_tools.py +82 -82
  113. crawlo/utils/large_scale_config.py +286 -286
  114. crawlo/utils/large_scale_helper.py +343 -343
  115. crawlo/utils/log.py +128 -128
  116. crawlo/utils/performance_monitor.py +284 -284
  117. crawlo/utils/queue_helper.py +175 -175
  118. crawlo/utils/redis_connection_pool.py +334 -334
  119. crawlo/utils/redis_key_validator.py +199 -199
  120. crawlo/utils/request.py +267 -267
  121. crawlo/utils/request_serializer.py +219 -219
  122. crawlo/utils/spider_loader.py +62 -62
  123. crawlo/utils/system.py +11 -11
  124. crawlo/utils/tools.py +4 -4
  125. crawlo/utils/url.py +39 -39
  126. {crawlo-1.1.6.dist-info → crawlo-1.1.9.dist-info}/METADATA +626 -401
  127. crawlo-1.1.9.dist-info/RECORD +190 -0
  128. examples/__init__.py +7 -7
  129. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  130. tests/__init__.py +7 -7
  131. tests/advanced_tools_example.py +275 -275
  132. tests/authenticated_proxy_example.py +236 -236
  133. tests/cleaners_example.py +160 -160
  134. tests/config_validation_demo.py +102 -102
  135. tests/controlled_spider_example.py +205 -205
  136. tests/date_tools_example.py +180 -180
  137. tests/dynamic_loading_example.py +523 -523
  138. tests/dynamic_loading_test.py +104 -104
  139. tests/env_config_example.py +133 -133
  140. tests/error_handling_example.py +171 -171
  141. tests/redis_key_validation_demo.py +130 -130
  142. tests/response_improvements_example.py +144 -144
  143. tests/test_advanced_tools.py +148 -148
  144. tests/test_all_redis_key_configs.py +145 -145
  145. tests/test_authenticated_proxy.py +141 -141
  146. tests/test_cleaners.py +54 -54
  147. tests/test_comprehensive.py +146 -146
  148. tests/test_config_validator.py +193 -193
  149. tests/test_date_tools.py +123 -123
  150. tests/test_double_crawlo_fix.py +207 -207
  151. tests/test_double_crawlo_fix_simple.py +124 -124
  152. tests/test_dynamic_downloaders_proxy.py +124 -124
  153. tests/test_dynamic_proxy.py +92 -92
  154. tests/test_dynamic_proxy_config.py +146 -146
  155. tests/test_dynamic_proxy_real.py +109 -109
  156. tests/test_edge_cases.py +303 -303
  157. tests/test_enhanced_error_handler.py +270 -270
  158. tests/test_env_config.py +121 -121
  159. tests/test_error_handler_compatibility.py +112 -112
  160. tests/test_final_validation.py +153 -153
  161. tests/test_framework_env_usage.py +103 -103
  162. tests/test_integration.py +356 -356
  163. tests/test_item_dedup_redis_key.py +122 -122
  164. tests/test_parsel.py +29 -29
  165. tests/test_performance.py +327 -327
  166. tests/test_proxy_health_check.py +32 -32
  167. tests/test_proxy_middleware_integration.py +136 -136
  168. tests/test_proxy_providers.py +56 -56
  169. tests/test_proxy_stats.py +19 -19
  170. tests/test_proxy_strategies.py +59 -59
  171. tests/test_queue_manager_double_crawlo.py +230 -230
  172. tests/test_queue_manager_redis_key.py +176 -176
  173. tests/test_redis_config.py +28 -28
  174. tests/test_redis_connection_pool.py +294 -294
  175. tests/test_redis_key_naming.py +181 -181
  176. tests/test_redis_key_validator.py +123 -123
  177. tests/test_redis_queue.py +224 -224
  178. tests/test_request_serialization.py +70 -70
  179. tests/test_response_improvements.py +152 -152
  180. tests/test_scheduler.py +241 -241
  181. tests/test_simple_response.py +61 -61
  182. tests/test_telecom_spider_redis_key.py +205 -205
  183. tests/test_template_content.py +87 -87
  184. tests/test_template_redis_key.py +134 -134
  185. tests/test_tools.py +153 -153
  186. tests/tools_example.py +257 -257
  187. crawlo-1.1.6.dist-info/RECORD +0 -189
  188. {crawlo-1.1.6.dist-info → crawlo-1.1.9.dist-info}/WHEEL +0 -0
  189. {crawlo-1.1.6.dist-info → crawlo-1.1.9.dist-info}/entry_points.txt +0 -0
  190. {crawlo-1.1.6.dist-info → crawlo-1.1.9.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 -*-