crawlo 1.2.3__py3-none-any.whl → 1.2.4__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 (222) 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 -81
  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 +144 -142
  12. crawlo/commands/list.py +155 -155
  13. crawlo/commands/run.py +323 -292
  14. crawlo/commands/startproject.py +420 -417
  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 +354 -354
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +143 -143
  23. crawlo/crawler.py +1110 -1027
  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 +220 -220
  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 +37 -37
  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 +280 -280
  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 +135 -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 +61 -61
  74. crawlo/pipelines/redis_dedup_pipeline.py +165 -165
  75. crawlo/project.py +279 -187
  76. crawlo/queue/pqueue.py +37 -37
  77. crawlo/queue/queue_manager.py +337 -337
  78. crawlo/queue/redis_priority_queue.py +298 -298
  79. crawlo/settings/__init__.py +7 -7
  80. crawlo/settings/default_settings.py +217 -226
  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/run.py.tmpl +47 -45
  92. crawlo/templates/project/settings.py.tmpl +350 -325
  93. crawlo/templates/project/settings_distributed.py.tmpl +160 -121
  94. crawlo/templates/project/settings_gentle.py.tmpl +133 -94
  95. crawlo/templates/project/settings_high_performance.py.tmpl +155 -151
  96. crawlo/templates/project/settings_simple.py.tmpl +108 -68
  97. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  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 +105 -105
  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 +334 -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-1.2.3.dist-info → crawlo-1.2.4.dist-info}/METADATA +764 -692
  130. crawlo-1.2.4.dist-info/RECORD +206 -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_validator.py +193 -193
  152. tests/test_crawlo_proxy_integration.py +172 -172
  153. tests/test_date_tools.py +123 -123
  154. tests/test_default_header_middleware.py +158 -158
  155. tests/test_double_crawlo_fix.py +207 -207
  156. tests/test_double_crawlo_fix_simple.py +124 -124
  157. tests/test_download_delay_middleware.py +221 -221
  158. tests/test_downloader_proxy_compatibility.py +268 -268
  159. tests/test_dynamic_downloaders_proxy.py +124 -124
  160. tests/test_dynamic_proxy.py +92 -92
  161. tests/test_dynamic_proxy_config.py +146 -146
  162. tests/test_dynamic_proxy_real.py +109 -109
  163. tests/test_edge_cases.py +303 -303
  164. tests/test_enhanced_error_handler.py +270 -270
  165. tests/test_env_config.py +121 -121
  166. tests/test_error_handler_compatibility.py +112 -112
  167. tests/test_final_validation.py +153 -153
  168. tests/test_framework_env_usage.py +103 -103
  169. tests/test_integration.py +356 -356
  170. tests/test_item_dedup_redis_key.py +122 -122
  171. tests/test_offsite_middleware.py +221 -221
  172. tests/test_parsel.py +29 -29
  173. tests/test_performance.py +327 -327
  174. tests/test_proxy_api.py +264 -264
  175. tests/test_proxy_health_check.py +32 -32
  176. tests/test_proxy_middleware.py +121 -121
  177. tests/test_proxy_middleware_enhanced.py +216 -216
  178. tests/test_proxy_middleware_integration.py +136 -136
  179. tests/test_proxy_providers.py +56 -56
  180. tests/test_proxy_stats.py +19 -19
  181. tests/test_proxy_strategies.py +59 -59
  182. tests/test_queue_manager_double_crawlo.py +173 -173
  183. tests/test_queue_manager_redis_key.py +176 -176
  184. tests/test_real_scenario_proxy.py +195 -195
  185. tests/test_redis_config.py +28 -28
  186. tests/test_redis_connection_pool.py +294 -294
  187. tests/test_redis_key_naming.py +181 -181
  188. tests/test_redis_key_validator.py +123 -123
  189. tests/test_redis_queue.py +224 -224
  190. tests/test_request_ignore_middleware.py +182 -182
  191. tests/test_request_serialization.py +70 -70
  192. tests/test_response_code_middleware.py +349 -349
  193. tests/test_response_filter_middleware.py +427 -427
  194. tests/test_response_improvements.py +152 -152
  195. tests/test_retry_middleware.py +241 -241
  196. tests/test_scheduler.py +241 -241
  197. tests/test_simple_response.py +61 -61
  198. tests/test_telecom_spider_redis_key.py +205 -205
  199. tests/test_template_content.py +87 -87
  200. tests/test_template_redis_key.py +134 -134
  201. tests/test_tools.py +153 -153
  202. tests/tools_example.py +257 -257
  203. crawlo-1.2.3.dist-info/RECORD +0 -222
  204. examples/aiohttp_settings.py +0 -42
  205. examples/curl_cffi_settings.py +0 -41
  206. examples/default_header_middleware_example.py +0 -107
  207. examples/default_header_spider_example.py +0 -129
  208. examples/download_delay_middleware_example.py +0 -160
  209. examples/httpx_settings.py +0 -42
  210. examples/multi_downloader_proxy_example.py +0 -81
  211. examples/offsite_middleware_example.py +0 -55
  212. examples/offsite_spider_example.py +0 -107
  213. examples/proxy_spider_example.py +0 -166
  214. examples/request_ignore_middleware_example.py +0 -51
  215. examples/request_ignore_spider_example.py +0 -99
  216. examples/response_code_middleware_example.py +0 -52
  217. examples/response_filter_middleware_example.py +0 -67
  218. examples/tong_hua_shun_settings.py +0 -62
  219. examples/tong_hua_shun_spider.py +0 -170
  220. {crawlo-1.2.3.dist-info → crawlo-1.2.4.dist-info}/WHEEL +0 -0
  221. {crawlo-1.2.3.dist-info → crawlo-1.2.4.dist-info}/entry_points.txt +0 -0
  222. {crawlo-1.2.3.dist-info → crawlo-1.2.4.dist-info}/top_level.txt +0 -0
@@ -1,357 +1,357 @@
1
- #!/usr/bin/python
2
- # -*- coding:UTF-8 -*-
3
- """
4
- 误处理工具
5
- 提供更详细、更一致的错误处理和日志记录机制
6
- """
7
- import traceback
8
- from datetime import datetime
9
- from functools import wraps
10
- from typing import Optional, Callable, Any, Dict, List
11
-
12
- from crawlo.utils.log import get_logger
13
-
14
-
15
- class ErrorContext:
16
- """错误上下文信息"""
17
-
18
- def __init__(self, context: str = "", module: str = "", function: str = ""):
19
- self.context = context
20
- self.module = module
21
- self.function = function
22
- self.timestamp = datetime.now()
23
-
24
- def __str__(self):
25
- parts = []
26
- if self.module:
27
- parts.append(f"Module: {self.module}")
28
- if self.function:
29
- parts.append(f"Function: {self.function}")
30
- if self.context:
31
- parts.append(f"Context: {self.context}")
32
- parts.append(f"Time: {self.timestamp.strftime('%Y-%m-%d %H:%M:%S')}")
33
- return " | ".join(parts)
34
-
35
-
36
- class DetailedException(Exception):
37
- """带有详细信息的异常基类"""
38
-
39
- def __init__(self, message: str, context: Optional[ErrorContext] = None,
40
- error_code: Optional[str] = None, **kwargs):
41
- super().__init__(message)
42
- self.context = context
43
- self.error_code = error_code
44
- self.details = kwargs
45
- self.timestamp = datetime.now()
46
-
47
- def __str__(self):
48
- base_msg = super().__str__()
49
- if self.context:
50
- return f"{base_msg} ({self.context})"
51
- return base_msg
52
-
53
- def get_full_details(self) -> Dict:
54
- """获取完整的错误详情"""
55
- return {
56
- "message": str(self),
57
- "error_code": self.error_code,
58
- "context": str(self.context) if self.context else None,
59
- "details": self.details,
60
- "timestamp": self.timestamp.isoformat(),
61
- "exception_type": self.__class__.__name__
62
- }
63
-
64
-
65
- class EnhancedErrorHandler:
66
- """增强版错误处理器"""
67
-
68
- def __init__(self, logger_name: str = __name__, log_level: str = 'ERROR'):
69
- self.logger = get_logger(logger_name, log_level)
70
- self.error_history: List[Dict] = [] # 错误历史记录
71
- self.max_history_size = 100 # 最大历史记录数
72
-
73
- def handle_error(self, exception: Exception, context: Optional[ErrorContext] = None,
74
- raise_error: bool = True, log_error: bool = True,
75
- extra_info: Optional[Dict] = None) -> Dict:
76
- """
77
- 增强版错误处理
78
-
79
- Args:
80
- exception: 异常对象
81
- context: 错误上下文信息
82
- raise_error: 是否重新抛出异常
83
- log_error: 是否记录错误日志
84
- extra_info: 额外的错误信息
85
-
86
- Returns:
87
- 包含错误详情的字典
88
- """
89
- # 构建错误详情
90
- error_details = {
91
- "exception": exception,
92
- "exception_type": type(exception).__name__,
93
- "message": str(exception),
94
- "context": str(context) if context else None,
95
- "timestamp": datetime.now().isoformat(),
96
- "traceback": traceback.format_exc() if log_error else None,
97
- "extra_info": extra_info or {}
98
- }
99
-
100
- # 记录到历史
101
- self._record_error(error_details)
102
-
103
- # 记录日志
104
- if log_error:
105
- self._log_error(error_details)
106
-
107
- # 重新抛出异常
108
- if raise_error:
109
- raise exception
110
-
111
- return error_details
112
-
113
- def _log_error(self, error_details: Dict):
114
- """记录错误日志"""
115
- # 基本错误信息
116
- context_info = error_details.get("context", "")
117
- message = error_details["message"]
118
- error_msg = f"{message} [{context_info}]" if context_info else message
119
-
120
- # 记录错误
121
- self.logger.error(error_msg)
122
-
123
- # 记录详细信息
124
- if error_details.get("traceback"):
125
- self.logger.debug(f"详细错误信息:\n{error_details['traceback']}")
126
-
127
- # 记录额外信息
128
- if error_details.get("extra_info"):
129
- self.logger.debug(f"额外信息: {error_details['extra_info']}")
130
-
131
- def _record_error(self, error_details: Dict):
132
- """记录错误到历史"""
133
- self.error_history.append(error_details)
134
- # 限制历史记录大小
135
- if len(self.error_history) > self.max_history_size:
136
- self.error_history.pop(0)
137
-
138
- def safe_call(self, func: Callable, *args, default_return=None,
139
- context: Optional[ErrorContext] = None, **kwargs) -> Any:
140
- """
141
- 安全调用函数,捕获并处理异常
142
-
143
- Args:
144
- func: 要调用的函数
145
- *args: 函数参数
146
- default_return: 默认返回值
147
- context: 错误上下文
148
- **kwargs: 函数关键字参数
149
-
150
- Returns:
151
- 函数返回值或默认值
152
- """
153
- try:
154
- return func(*args, **kwargs)
155
- except Exception as e:
156
- self.handle_error(e, context=context, raise_error=False)
157
- return default_return
158
-
159
- def retry_on_failure(self, max_retries: int = 3, delay: float = 1.0,
160
- exceptions: tuple = (Exception,), backoff_factor: float = 1.0,
161
- context: Optional[ErrorContext] = None):
162
- """
163
- 装饰器:失败时重试(增强版)
164
-
165
- Args:
166
- max_retries: 最大重试次数
167
- delay: 初始重试间隔(秒)
168
- exceptions: 需要重试的异常类型
169
- backoff_factor: 退避因子(每次重试间隔乘以此因子)
170
- context: 错误上下文
171
- """
172
- def decorator(func):
173
- @wraps(func)
174
- async def async_wrapper(*args, **kwargs):
175
- last_exception = None
176
- current_delay = delay
177
-
178
- for attempt in range(max_retries + 1):
179
- try:
180
- return await func(*args, **kwargs)
181
- except exceptions as e:
182
- last_exception = e
183
- if attempt < max_retries:
184
- # 记录重试信息
185
- retry_context = ErrorContext(
186
- context=f"函数 {func.__name__} 执行失败 (尝试 {attempt + 1}/{max_retries + 1})",
187
- module=context.module if context else "",
188
- function=func.__name__
189
- ) if context else None
190
-
191
- self.logger.warning(
192
- f"函数 {func.__name__} 执行失败 (尝试 {attempt + 1}/{max_retries + 1}): {e}"
193
- )
194
-
195
- import asyncio
196
- await asyncio.sleep(current_delay)
197
- current_delay *= backoff_factor # 指数退避
198
- else:
199
- # 最后一次尝试失败
200
- final_context = ErrorContext(
201
- context=f"函数 {func.__name__} 执行失败,已达到最大重试次数",
202
- module=context.module if context else "",
203
- function=func.__name__
204
- ) if context else None
205
-
206
- self.logger.error(
207
- f"函数 {func.__name__} 执行失败,已达到最大重试次数: {e}"
208
- )
209
- raise last_exception
210
-
211
- @wraps(func)
212
- def sync_wrapper(*args, **kwargs):
213
- last_exception = None
214
- current_delay = delay
215
-
216
- for attempt in range(max_retries + 1):
217
- try:
218
- return func(*args, **kwargs)
219
- except exceptions as e:
220
- last_exception = e
221
- if attempt < max_retries:
222
- # 记录重试信息
223
- retry_context = ErrorContext(
224
- context=f"函数 {func.__name__} 执行失败 (尝试 {attempt + 1}/{max_retries + 1})",
225
- module=context.module if context else "",
226
- function=func.__name__
227
- ) if context else None
228
-
229
- self.logger.warning(
230
- f"函数 {func.__name__} 执行失败 (尝试 {attempt + 1}/{max_retries + 1}): {e}"
231
- )
232
-
233
- import time
234
- time.sleep(current_delay)
235
- current_delay *= backoff_factor # 指数退避
236
- else:
237
- # 最后一次尝试失败
238
- final_context = ErrorContext(
239
- context=f"函数 {func.__name__} 执行失败,已达到最大重试次数",
240
- module=context.module if context else "",
241
- function=func.__name__
242
- ) if context else None
243
-
244
- self.logger.error(
245
- f"函数 {func.__name__} 执行失败,已达到最大重试次数: {e}"
246
- )
247
- raise last_exception
248
-
249
- # 根据函数是否为异步函数返回相应的包装器
250
- import inspect
251
- if inspect.iscoroutinefunction(func):
252
- return async_wrapper
253
- else:
254
- return sync_wrapper
255
-
256
- return decorator
257
-
258
- def get_error_history(self) -> List[Dict]:
259
- """获取错误历史记录"""
260
- return self.error_history.copy()
261
-
262
- def clear_error_history(self):
263
- """清空错误历史记录"""
264
- self.error_history.clear()
265
-
266
-
267
- # 全局增强错误处理器实例
268
- enhanced_error_handler = EnhancedErrorHandler()
269
-
270
-
271
- def handle_exception(context: str = "", module: str = "", function: str = "",
272
- raise_error: bool = True, log_error: bool = True,
273
- error_code: Optional[str] = None):
274
- """
275
- 装饰器:处理函数异常(增强版)
276
-
277
- Args:
278
- context: 错误上下文描述
279
- module: 模块名称
280
- function: 函数名称
281
- raise_error: 是否重新抛出异常
282
- log_error: 是否记录错误日志
283
- error_code: 错误代码
284
- """
285
- def decorator(func):
286
- @wraps(func)
287
- async def async_wrapper(*args, **kwargs):
288
- try:
289
- return await func(*args, **kwargs)
290
- except Exception as e:
291
- error_context = ErrorContext(
292
- context=f"{context} - {func.__name__}",
293
- module=module,
294
- function=func.__name__
295
- )
296
-
297
- # 如果是详细异常,保留原有信息
298
- if isinstance(e, DetailedException):
299
- # 确保上下文信息完整
300
- if not e.context:
301
- e.context = error_context
302
- enhanced_error_handler.handle_error(
303
- e, context=e.context,
304
- raise_error=raise_error, log_error=log_error
305
- )
306
- else:
307
- # 包装为详细异常
308
- detailed_e = DetailedException(
309
- str(e), context=error_context, error_code=error_code
310
- )
311
- enhanced_error_handler.handle_error(
312
- detailed_e, context=error_context,
313
- raise_error=raise_error, log_error=log_error
314
- )
315
- if not raise_error:
316
- return None
317
-
318
- @wraps(func)
319
- def sync_wrapper(*args, **kwargs):
320
- try:
321
- return func(*args, **kwargs)
322
- except Exception as e:
323
- error_context = ErrorContext(
324
- context=f"{context} - {func.__name__}",
325
- module=module,
326
- function=func.__name__
327
- )
328
-
329
- # 如果是详细异常,保留原有信息
330
- if isinstance(e, DetailedException):
331
- # 确保上下文信息完整
332
- if not e.context:
333
- e.context = error_context
334
- enhanced_error_handler.handle_error(
335
- e, context=e.context,
336
- raise_error=raise_error, log_error=log_error
337
- )
338
- else:
339
- # 包装为详细异常
340
- detailed_e = DetailedException(
341
- str(e), context=error_context, error_code=error_code
342
- )
343
- enhanced_error_handler.handle_error(
344
- detailed_e, context=error_context,
345
- raise_error=raise_error, log_error=log_error
346
- )
347
- if not raise_error:
348
- return None
349
-
350
- # 根据函数是否为异步函数返回相应的包装器
351
- import inspect
352
- if inspect.iscoroutinefunction(func):
353
- return async_wrapper
354
- else:
355
- return sync_wrapper
356
-
1
+ #!/usr/bin/python
2
+ # -*- coding:UTF-8 -*-
3
+ """
4
+ 误处理工具
5
+ 提供更详细、更一致的错误处理和日志记录机制
6
+ """
7
+ import traceback
8
+ from datetime import datetime
9
+ from functools import wraps
10
+ from typing import Optional, Callable, Any, Dict, List
11
+
12
+ from crawlo.utils.log import get_logger
13
+
14
+
15
+ class ErrorContext:
16
+ """错误上下文信息"""
17
+
18
+ def __init__(self, context: str = "", module: str = "", function: str = ""):
19
+ self.context = context
20
+ self.module = module
21
+ self.function = function
22
+ self.timestamp = datetime.now()
23
+
24
+ def __str__(self):
25
+ parts = []
26
+ if self.module:
27
+ parts.append(f"Module: {self.module}")
28
+ if self.function:
29
+ parts.append(f"Function: {self.function}")
30
+ if self.context:
31
+ parts.append(f"Context: {self.context}")
32
+ parts.append(f"Time: {self.timestamp.strftime('%Y-%m-%d %H:%M:%S')}")
33
+ return " | ".join(parts)
34
+
35
+
36
+ class DetailedException(Exception):
37
+ """带有详细信息的异常基类"""
38
+
39
+ def __init__(self, message: str, context: Optional[ErrorContext] = None,
40
+ error_code: Optional[str] = None, **kwargs):
41
+ super().__init__(message)
42
+ self.context = context
43
+ self.error_code = error_code
44
+ self.details = kwargs
45
+ self.timestamp = datetime.now()
46
+
47
+ def __str__(self):
48
+ base_msg = super().__str__()
49
+ if self.context:
50
+ return f"{base_msg} ({self.context})"
51
+ return base_msg
52
+
53
+ def get_full_details(self) -> Dict:
54
+ """获取完整的错误详情"""
55
+ return {
56
+ "message": str(self),
57
+ "error_code": self.error_code,
58
+ "context": str(self.context) if self.context else None,
59
+ "details": self.details,
60
+ "timestamp": self.timestamp.isoformat(),
61
+ "exception_type": self.__class__.__name__
62
+ }
63
+
64
+
65
+ class EnhancedErrorHandler:
66
+ """增强版错误处理器"""
67
+
68
+ def __init__(self, logger_name: str = __name__, log_level: str = 'ERROR'):
69
+ self.logger = get_logger(logger_name, log_level)
70
+ self.error_history: List[Dict] = [] # 错误历史记录
71
+ self.max_history_size = 100 # 最大历史记录数
72
+
73
+ def handle_error(self, exception: Exception, context: Optional[ErrorContext] = None,
74
+ raise_error: bool = True, log_error: bool = True,
75
+ extra_info: Optional[Dict] = None) -> Dict:
76
+ """
77
+ 增强版错误处理
78
+
79
+ Args:
80
+ exception: 异常对象
81
+ context: 错误上下文信息
82
+ raise_error: 是否重新抛出异常
83
+ log_error: 是否记录错误日志
84
+ extra_info: 额外的错误信息
85
+
86
+ Returns:
87
+ 包含错误详情的字典
88
+ """
89
+ # 构建错误详情
90
+ error_details = {
91
+ "exception": exception,
92
+ "exception_type": type(exception).__name__,
93
+ "message": str(exception),
94
+ "context": str(context) if context else None,
95
+ "timestamp": datetime.now().isoformat(),
96
+ "traceback": traceback.format_exc() if log_error else None,
97
+ "extra_info": extra_info or {}
98
+ }
99
+
100
+ # 记录到历史
101
+ self._record_error(error_details)
102
+
103
+ # 记录日志
104
+ if log_error:
105
+ self._log_error(error_details)
106
+
107
+ # 重新抛出异常
108
+ if raise_error:
109
+ raise exception
110
+
111
+ return error_details
112
+
113
+ def _log_error(self, error_details: Dict):
114
+ """记录错误日志"""
115
+ # 基本错误信息
116
+ context_info = error_details.get("context", "")
117
+ message = error_details["message"]
118
+ error_msg = f"{message} [{context_info}]" if context_info else message
119
+
120
+ # 记录错误
121
+ self.logger.error(error_msg)
122
+
123
+ # 记录详细信息
124
+ if error_details.get("traceback"):
125
+ self.logger.debug(f"详细错误信息:\n{error_details['traceback']}")
126
+
127
+ # 记录额外信息
128
+ if error_details.get("extra_info"):
129
+ self.logger.debug(f"额外信息: {error_details['extra_info']}")
130
+
131
+ def _record_error(self, error_details: Dict):
132
+ """记录错误到历史"""
133
+ self.error_history.append(error_details)
134
+ # 限制历史记录大小
135
+ if len(self.error_history) > self.max_history_size:
136
+ self.error_history.pop(0)
137
+
138
+ def safe_call(self, func: Callable, *args, default_return=None,
139
+ context: Optional[ErrorContext] = None, **kwargs) -> Any:
140
+ """
141
+ 安全调用函数,捕获并处理异常
142
+
143
+ Args:
144
+ func: 要调用的函数
145
+ *args: 函数参数
146
+ default_return: 默认返回值
147
+ context: 错误上下文
148
+ **kwargs: 函数关键字参数
149
+
150
+ Returns:
151
+ 函数返回值或默认值
152
+ """
153
+ try:
154
+ return func(*args, **kwargs)
155
+ except Exception as e:
156
+ self.handle_error(e, context=context, raise_error=False)
157
+ return default_return
158
+
159
+ def retry_on_failure(self, max_retries: int = 3, delay: float = 1.0,
160
+ exceptions: tuple = (Exception,), backoff_factor: float = 1.0,
161
+ context: Optional[ErrorContext] = None):
162
+ """
163
+ 装饰器:失败时重试(增强版)
164
+
165
+ Args:
166
+ max_retries: 最大重试次数
167
+ delay: 初始重试间隔(秒)
168
+ exceptions: 需要重试的异常类型
169
+ backoff_factor: 退避因子(每次重试间隔乘以此因子)
170
+ context: 错误上下文
171
+ """
172
+ def decorator(func):
173
+ @wraps(func)
174
+ async def async_wrapper(*args, **kwargs):
175
+ last_exception = None
176
+ current_delay = delay
177
+
178
+ for attempt in range(max_retries + 1):
179
+ try:
180
+ return await func(*args, **kwargs)
181
+ except exceptions as e:
182
+ last_exception = e
183
+ if attempt < max_retries:
184
+ # 记录重试信息
185
+ retry_context = ErrorContext(
186
+ context=f"函数 {func.__name__} 执行失败 (尝试 {attempt + 1}/{max_retries + 1})",
187
+ module=context.module if context else "",
188
+ function=func.__name__
189
+ ) if context else None
190
+
191
+ self.logger.warning(
192
+ f"函数 {func.__name__} 执行失败 (尝试 {attempt + 1}/{max_retries + 1}): {e}"
193
+ )
194
+
195
+ import asyncio
196
+ await asyncio.sleep(current_delay)
197
+ current_delay *= backoff_factor # 指数退避
198
+ else:
199
+ # 最后一次尝试失败
200
+ final_context = ErrorContext(
201
+ context=f"函数 {func.__name__} 执行失败,已达到最大重试次数",
202
+ module=context.module if context else "",
203
+ function=func.__name__
204
+ ) if context else None
205
+
206
+ self.logger.error(
207
+ f"函数 {func.__name__} 执行失败,已达到最大重试次数: {e}"
208
+ )
209
+ raise last_exception
210
+
211
+ @wraps(func)
212
+ def sync_wrapper(*args, **kwargs):
213
+ last_exception = None
214
+ current_delay = delay
215
+
216
+ for attempt in range(max_retries + 1):
217
+ try:
218
+ return func(*args, **kwargs)
219
+ except exceptions as e:
220
+ last_exception = e
221
+ if attempt < max_retries:
222
+ # 记录重试信息
223
+ retry_context = ErrorContext(
224
+ context=f"函数 {func.__name__} 执行失败 (尝试 {attempt + 1}/{max_retries + 1})",
225
+ module=context.module if context else "",
226
+ function=func.__name__
227
+ ) if context else None
228
+
229
+ self.logger.warning(
230
+ f"函数 {func.__name__} 执行失败 (尝试 {attempt + 1}/{max_retries + 1}): {e}"
231
+ )
232
+
233
+ import time
234
+ time.sleep(current_delay)
235
+ current_delay *= backoff_factor # 指数退避
236
+ else:
237
+ # 最后一次尝试失败
238
+ final_context = ErrorContext(
239
+ context=f"函数 {func.__name__} 执行失败,已达到最大重试次数",
240
+ module=context.module if context else "",
241
+ function=func.__name__
242
+ ) if context else None
243
+
244
+ self.logger.error(
245
+ f"函数 {func.__name__} 执行失败,已达到最大重试次数: {e}"
246
+ )
247
+ raise last_exception
248
+
249
+ # 根据函数是否为异步函数返回相应的包装器
250
+ import inspect
251
+ if inspect.iscoroutinefunction(func):
252
+ return async_wrapper
253
+ else:
254
+ return sync_wrapper
255
+
256
+ return decorator
257
+
258
+ def get_error_history(self) -> List[Dict]:
259
+ """获取错误历史记录"""
260
+ return self.error_history.copy()
261
+
262
+ def clear_error_history(self):
263
+ """清空错误历史记录"""
264
+ self.error_history.clear()
265
+
266
+
267
+ # 全局增强错误处理器实例
268
+ enhanced_error_handler = EnhancedErrorHandler()
269
+
270
+
271
+ def handle_exception(context: str = "", module: str = "", function: str = "",
272
+ raise_error: bool = True, log_error: bool = True,
273
+ error_code: Optional[str] = None):
274
+ """
275
+ 装饰器:处理函数异常(增强版)
276
+
277
+ Args:
278
+ context: 错误上下文描述
279
+ module: 模块名称
280
+ function: 函数名称
281
+ raise_error: 是否重新抛出异常
282
+ log_error: 是否记录错误日志
283
+ error_code: 错误代码
284
+ """
285
+ def decorator(func):
286
+ @wraps(func)
287
+ async def async_wrapper(*args, **kwargs):
288
+ try:
289
+ return await func(*args, **kwargs)
290
+ except Exception as e:
291
+ error_context = ErrorContext(
292
+ context=f"{context} - {func.__name__}",
293
+ module=module,
294
+ function=func.__name__
295
+ )
296
+
297
+ # 如果是详细异常,保留原有信息
298
+ if isinstance(e, DetailedException):
299
+ # 确保上下文信息完整
300
+ if not e.context:
301
+ e.context = error_context
302
+ enhanced_error_handler.handle_error(
303
+ e, context=e.context,
304
+ raise_error=raise_error, log_error=log_error
305
+ )
306
+ else:
307
+ # 包装为详细异常
308
+ detailed_e = DetailedException(
309
+ str(e), context=error_context, error_code=error_code
310
+ )
311
+ enhanced_error_handler.handle_error(
312
+ detailed_e, context=error_context,
313
+ raise_error=raise_error, log_error=log_error
314
+ )
315
+ if not raise_error:
316
+ return None
317
+
318
+ @wraps(func)
319
+ def sync_wrapper(*args, **kwargs):
320
+ try:
321
+ return func(*args, **kwargs)
322
+ except Exception as e:
323
+ error_context = ErrorContext(
324
+ context=f"{context} - {func.__name__}",
325
+ module=module,
326
+ function=func.__name__
327
+ )
328
+
329
+ # 如果是详细异常,保留原有信息
330
+ if isinstance(e, DetailedException):
331
+ # 确保上下文信息完整
332
+ if not e.context:
333
+ e.context = error_context
334
+ enhanced_error_handler.handle_error(
335
+ e, context=e.context,
336
+ raise_error=raise_error, log_error=log_error
337
+ )
338
+ else:
339
+ # 包装为详细异常
340
+ detailed_e = DetailedException(
341
+ str(e), context=error_context, error_code=error_code
342
+ )
343
+ enhanced_error_handler.handle_error(
344
+ detailed_e, context=error_context,
345
+ raise_error=raise_error, log_error=log_error
346
+ )
347
+ if not raise_error:
348
+ return None
349
+
350
+ # 根据函数是否为异步函数返回相应的包装器
351
+ import inspect
352
+ if inspect.iscoroutinefunction(func):
353
+ return async_wrapper
354
+ else:
355
+ return sync_wrapper
356
+
357
357
  return decorator