crawlo 1.4.7__py3-none-any.whl → 1.4.8__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 (348) hide show
  1. crawlo/__init__.py +90 -90
  2. crawlo/__version__.py +1 -1
  3. crawlo/cli.py +75 -75
  4. crawlo/commands/__init__.py +14 -14
  5. crawlo/commands/check.py +594 -594
  6. crawlo/commands/genspider.py +186 -186
  7. crawlo/commands/help.py +140 -140
  8. crawlo/commands/list.py +155 -155
  9. crawlo/commands/run.py +379 -379
  10. crawlo/commands/startproject.py +460 -460
  11. crawlo/commands/stats.py +187 -187
  12. crawlo/commands/utils.py +196 -196
  13. crawlo/config.py +320 -320
  14. crawlo/config_validator.py +277 -277
  15. crawlo/core/__init__.py +52 -52
  16. crawlo/core/engine.py +451 -451
  17. crawlo/core/processor.py +47 -47
  18. crawlo/core/scheduler.py +290 -290
  19. crawlo/crawler.py +698 -698
  20. crawlo/data/__init__.py +5 -5
  21. crawlo/data/user_agents.py +194 -194
  22. crawlo/downloader/__init__.py +280 -280
  23. crawlo/downloader/aiohttp_downloader.py +233 -233
  24. crawlo/downloader/cffi_downloader.py +250 -250
  25. crawlo/downloader/httpx_downloader.py +265 -265
  26. crawlo/downloader/hybrid_downloader.py +212 -212
  27. crawlo/downloader/playwright_downloader.py +425 -425
  28. crawlo/downloader/selenium_downloader.py +486 -486
  29. crawlo/event.py +45 -45
  30. crawlo/exceptions.py +214 -214
  31. crawlo/extension/__init__.py +64 -64
  32. crawlo/extension/health_check.py +141 -141
  33. crawlo/extension/log_interval.py +94 -94
  34. crawlo/extension/log_stats.py +70 -70
  35. crawlo/extension/logging_extension.py +53 -53
  36. crawlo/extension/memory_monitor.py +104 -104
  37. crawlo/extension/performance_profiler.py +133 -133
  38. crawlo/extension/request_recorder.py +107 -107
  39. crawlo/factories/__init__.py +27 -27
  40. crawlo/factories/base.py +68 -68
  41. crawlo/factories/crawler.py +104 -104
  42. crawlo/factories/registry.py +84 -84
  43. crawlo/factories/utils.py +134 -134
  44. crawlo/filters/__init__.py +170 -170
  45. crawlo/filters/aioredis_filter.py +347 -347
  46. crawlo/filters/memory_filter.py +261 -261
  47. crawlo/framework.py +306 -306
  48. crawlo/initialization/__init__.py +44 -44
  49. crawlo/initialization/built_in.py +391 -391
  50. crawlo/initialization/context.py +141 -141
  51. crawlo/initialization/core.py +240 -240
  52. crawlo/initialization/phases.py +229 -229
  53. crawlo/initialization/registry.py +143 -143
  54. crawlo/initialization/utils.py +48 -48
  55. crawlo/interfaces.py +23 -23
  56. crawlo/items/__init__.py +23 -23
  57. crawlo/items/base.py +23 -23
  58. crawlo/items/fields.py +52 -52
  59. crawlo/items/items.py +104 -104
  60. crawlo/logging/__init__.py +42 -42
  61. crawlo/logging/config.py +280 -276
  62. crawlo/logging/factory.py +175 -175
  63. crawlo/logging/manager.py +104 -104
  64. crawlo/middleware/__init__.py +87 -87
  65. crawlo/middleware/default_header.py +132 -132
  66. crawlo/middleware/download_delay.py +104 -104
  67. crawlo/middleware/middleware_manager.py +142 -142
  68. crawlo/middleware/offsite.py +123 -123
  69. crawlo/middleware/proxy.py +209 -209
  70. crawlo/middleware/request_ignore.py +86 -86
  71. crawlo/middleware/response_code.py +150 -150
  72. crawlo/middleware/response_filter.py +136 -136
  73. crawlo/middleware/retry.py +124 -124
  74. crawlo/mode_manager.py +287 -287
  75. crawlo/network/__init__.py +21 -21
  76. crawlo/network/request.py +408 -376
  77. crawlo/network/response.py +598 -569
  78. crawlo/pipelines/__init__.py +52 -52
  79. crawlo/pipelines/base_pipeline.py +452 -452
  80. crawlo/pipelines/bloom_dedup_pipeline.py +145 -146
  81. crawlo/pipelines/console_pipeline.py +39 -39
  82. crawlo/pipelines/csv_pipeline.py +316 -316
  83. crawlo/pipelines/database_dedup_pipeline.py +196 -197
  84. crawlo/pipelines/json_pipeline.py +218 -218
  85. crawlo/pipelines/memory_dedup_pipeline.py +104 -105
  86. crawlo/pipelines/mongo_pipeline.py +140 -139
  87. crawlo/pipelines/mysql_pipeline.py +468 -469
  88. crawlo/pipelines/pipeline_manager.py +100 -100
  89. crawlo/pipelines/redis_dedup_pipeline.py +155 -155
  90. crawlo/project.py +347 -347
  91. crawlo/queue/__init__.py +9 -9
  92. crawlo/queue/pqueue.py +38 -38
  93. crawlo/queue/queue_manager.py +591 -591
  94. crawlo/queue/redis_priority_queue.py +518 -518
  95. crawlo/settings/__init__.py +7 -7
  96. crawlo/settings/default_settings.py +287 -284
  97. crawlo/settings/setting_manager.py +219 -219
  98. crawlo/spider/__init__.py +658 -657
  99. crawlo/stats_collector.py +81 -81
  100. crawlo/subscriber.py +129 -129
  101. crawlo/task_manager.py +138 -138
  102. crawlo/templates/crawlo.cfg.tmpl +10 -10
  103. crawlo/templates/project/__init__.py.tmpl +1 -1
  104. crawlo/templates/project/items.py.tmpl +13 -13
  105. crawlo/templates/project/middlewares.py.tmpl +38 -38
  106. crawlo/templates/project/pipelines.py.tmpl +35 -35
  107. crawlo/templates/project/settings.py.tmpl +113 -109
  108. crawlo/templates/project/settings_distributed.py.tmpl +160 -156
  109. crawlo/templates/project/settings_gentle.py.tmpl +174 -170
  110. crawlo/templates/project/settings_high_performance.py.tmpl +175 -171
  111. crawlo/templates/project/settings_minimal.py.tmpl +102 -98
  112. crawlo/templates/project/settings_simple.py.tmpl +172 -168
  113. crawlo/templates/project/spiders/__init__.py.tmpl +9 -9
  114. crawlo/templates/run.py.tmpl +23 -23
  115. crawlo/templates/spider/spider.py.tmpl +32 -32
  116. crawlo/templates/spiders_init.py.tmpl +4 -4
  117. crawlo/tools/__init__.py +86 -86
  118. crawlo/tools/date_tools.py +289 -289
  119. crawlo/tools/distributed_coordinator.py +384 -384
  120. crawlo/tools/scenario_adapter.py +262 -262
  121. crawlo/tools/text_cleaner.py +232 -232
  122. crawlo/utils/__init__.py +74 -50
  123. crawlo/utils/batch_processor.py +276 -276
  124. crawlo/utils/config_manager.py +442 -442
  125. crawlo/utils/controlled_spider_mixin.py +439 -439
  126. crawlo/utils/db_helper.py +250 -250
  127. crawlo/utils/encoding_helper.py +190 -0
  128. crawlo/utils/error_handler.py +410 -410
  129. crawlo/utils/fingerprint.py +121 -121
  130. crawlo/utils/func_tools.py +82 -82
  131. crawlo/utils/large_scale_helper.py +344 -344
  132. crawlo/utils/leak_detector.py +335 -335
  133. crawlo/utils/misc.py +81 -81
  134. crawlo/utils/mongo_connection_pool.py +157 -157
  135. crawlo/utils/mysql_connection_pool.py +197 -197
  136. crawlo/utils/performance_monitor.py +285 -285
  137. crawlo/utils/queue_helper.py +175 -175
  138. crawlo/utils/redis_checker.py +90 -90
  139. crawlo/utils/redis_connection_pool.py +578 -578
  140. crawlo/utils/redis_key_validator.py +198 -198
  141. crawlo/utils/request.py +278 -278
  142. crawlo/utils/request_serializer.py +225 -225
  143. crawlo/utils/resource_manager.py +337 -337
  144. crawlo/utils/response_helper.py +113 -0
  145. crawlo/utils/selector_helper.py +138 -137
  146. crawlo/utils/singleton.py +69 -69
  147. crawlo/utils/spider_loader.py +201 -201
  148. crawlo/utils/text_helper.py +94 -94
  149. {crawlo-1.4.7.dist-info → crawlo-1.4.8.dist-info}/METADATA +831 -689
  150. crawlo-1.4.8.dist-info/RECORD +347 -0
  151. examples/__init__.py +7 -7
  152. tests/__init__.py +7 -7
  153. tests/advanced_tools_example.py +217 -217
  154. tests/authenticated_proxy_example.py +110 -110
  155. tests/baidu_performance_test.py +108 -108
  156. tests/baidu_test.py +59 -59
  157. tests/bug_check_test.py +250 -250
  158. tests/cleaners_example.py +160 -160
  159. tests/comprehensive_framework_test.py +212 -212
  160. tests/comprehensive_test.py +81 -81
  161. tests/comprehensive_testing_summary.md +186 -186
  162. tests/config_validation_demo.py +142 -142
  163. tests/controlled_spider_example.py +205 -205
  164. tests/date_tools_example.py +180 -180
  165. tests/debug_configure.py +69 -69
  166. tests/debug_framework_logger.py +84 -84
  167. tests/debug_log_config.py +126 -126
  168. tests/debug_log_levels.py +63 -63
  169. tests/debug_pipelines.py +66 -66
  170. tests/detailed_log_test.py +233 -233
  171. tests/direct_selector_helper_test.py +96 -96
  172. tests/distributed_dedup_test.py +467 -467
  173. tests/distributed_test.py +66 -66
  174. tests/distributed_test_debug.py +76 -76
  175. tests/dynamic_loading_example.py +523 -523
  176. tests/dynamic_loading_test.py +104 -104
  177. tests/error_handling_example.py +171 -171
  178. tests/explain_mysql_update_behavior.py +76 -76
  179. tests/final_comprehensive_test.py +151 -151
  180. tests/final_log_test.py +260 -260
  181. tests/final_validation_test.py +182 -182
  182. tests/fix_log_test.py +142 -142
  183. tests/framework_performance_test.py +202 -202
  184. tests/log_buffering_test.py +111 -111
  185. tests/log_generation_timing_test.py +153 -153
  186. tests/monitor_redis_dedup.sh +72 -72
  187. tests/ofweek_scrapy/ofweek_scrapy/items.py +12 -12
  188. tests/ofweek_scrapy/ofweek_scrapy/middlewares.py +100 -100
  189. tests/ofweek_scrapy/ofweek_scrapy/pipelines.py +13 -13
  190. tests/ofweek_scrapy/ofweek_scrapy/settings.py +84 -84
  191. tests/ofweek_scrapy/ofweek_scrapy/spiders/__init__.py +4 -4
  192. tests/ofweek_scrapy/scrapy.cfg +11 -11
  193. tests/optimized_performance_test.py +211 -211
  194. tests/performance_comparison.py +244 -244
  195. tests/queue_blocking_test.py +113 -113
  196. tests/queue_test.py +89 -89
  197. tests/redis_key_validation_demo.py +130 -130
  198. tests/request_params_example.py +150 -150
  199. tests/response_improvements_example.py +144 -144
  200. tests/scrapy_comparison/ofweek_scrapy.py +138 -138
  201. tests/scrapy_comparison/scrapy_test.py +133 -133
  202. tests/simple_cli_test.py +54 -54
  203. tests/simple_command_test.py +119 -119
  204. tests/simple_crawlo_test.py +126 -126
  205. tests/simple_follow_test.py +38 -38
  206. tests/simple_log_test2.py +137 -137
  207. tests/simple_optimization_test.py +128 -128
  208. tests/simple_queue_type_test.py +41 -41
  209. tests/simple_response_selector_test.py +94 -94
  210. tests/simple_selector_helper_test.py +154 -154
  211. tests/simple_selector_test.py +207 -207
  212. tests/simple_spider_test.py +49 -49
  213. tests/simple_url_test.py +73 -73
  214. tests/simulate_mysql_update_test.py +139 -139
  215. tests/spider_log_timing_test.py +177 -177
  216. tests/test_advanced_tools.py +148 -148
  217. tests/test_all_commands.py +230 -230
  218. tests/test_all_pipeline_fingerprints.py +133 -133
  219. tests/test_all_redis_key_configs.py +145 -145
  220. tests/test_asyncmy_usage.py +56 -56
  221. tests/test_batch_processor.py +178 -178
  222. tests/test_cleaners.py +54 -54
  223. tests/test_cli_arguments.py +118 -118
  224. tests/test_component_factory.py +174 -174
  225. tests/test_config_consistency.py +80 -80
  226. tests/test_config_merge.py +152 -152
  227. tests/test_config_validator.py +182 -182
  228. tests/test_controlled_spider_mixin.py +79 -79
  229. tests/test_crawler_process_import.py +38 -38
  230. tests/test_crawler_process_spider_modules.py +47 -47
  231. tests/test_crawlo_proxy_integration.py +114 -114
  232. tests/test_date_tools.py +123 -123
  233. tests/test_dedup_fix.py +220 -220
  234. tests/test_dedup_pipeline_consistency.py +124 -124
  235. tests/test_default_header_middleware.py +313 -313
  236. tests/test_distributed.py +65 -65
  237. tests/test_double_crawlo_fix.py +204 -204
  238. tests/test_double_crawlo_fix_simple.py +124 -124
  239. tests/test_download_delay_middleware.py +221 -221
  240. tests/test_downloader_proxy_compatibility.py +272 -272
  241. tests/test_edge_cases.py +305 -305
  242. tests/test_encoding_core.py +56 -56
  243. tests/test_encoding_detection.py +126 -126
  244. tests/test_enhanced_error_handler.py +270 -270
  245. tests/test_enhanced_error_handler_comprehensive.py +245 -245
  246. tests/test_error_handler_compatibility.py +112 -112
  247. tests/test_factories.py +252 -252
  248. tests/test_factory_compatibility.py +196 -196
  249. tests/test_final_validation.py +153 -153
  250. tests/test_fingerprint_consistency.py +135 -135
  251. tests/test_fingerprint_simple.py +51 -51
  252. tests/test_get_component_logger.py +83 -83
  253. tests/test_hash_performance.py +99 -99
  254. tests/test_integration.py +169 -169
  255. tests/test_item_dedup_redis_key.py +122 -122
  256. tests/test_large_scale_helper.py +235 -235
  257. tests/test_logging_enhancements.py +374 -374
  258. tests/test_logging_final.py +184 -184
  259. tests/test_logging_integration.py +312 -312
  260. tests/test_logging_system.py +282 -282
  261. tests/test_middleware_debug.py +141 -141
  262. tests/test_mode_consistency.py +51 -51
  263. tests/test_multi_directory.py +67 -67
  264. tests/test_multiple_spider_modules.py +80 -80
  265. tests/test_mysql_pipeline_config.py +164 -164
  266. tests/test_mysql_pipeline_error.py +98 -98
  267. tests/test_mysql_pipeline_init_log.py +82 -82
  268. tests/test_mysql_pipeline_integration.py +132 -132
  269. tests/test_mysql_pipeline_refactor.py +143 -143
  270. tests/test_mysql_pipeline_refactor_simple.py +85 -85
  271. tests/test_mysql_pipeline_robustness.py +195 -195
  272. tests/test_mysql_pipeline_types.py +88 -88
  273. tests/test_mysql_update_columns.py +93 -93
  274. tests/test_offsite_middleware.py +244 -244
  275. tests/test_offsite_middleware_simple.py +203 -203
  276. tests/test_optimized_selector_naming.py +100 -100
  277. tests/test_parsel.py +29 -29
  278. tests/test_performance.py +327 -327
  279. tests/test_performance_monitor.py +115 -115
  280. tests/test_pipeline_fingerprint_consistency.py +86 -86
  281. tests/test_priority_behavior.py +211 -211
  282. tests/test_priority_consistency.py +151 -151
  283. tests/test_priority_consistency_fixed.py +249 -249
  284. tests/test_proxy_health_check.py +32 -32
  285. tests/test_proxy_middleware.py +217 -217
  286. tests/test_proxy_middleware_enhanced.py +212 -212
  287. tests/test_proxy_middleware_integration.py +142 -142
  288. tests/test_proxy_middleware_refactored.py +207 -207
  289. tests/test_proxy_only.py +83 -83
  290. tests/test_proxy_providers.py +56 -56
  291. tests/test_proxy_stats.py +19 -19
  292. tests/test_proxy_strategies.py +59 -59
  293. tests/test_proxy_with_downloader.py +152 -152
  294. tests/test_queue_empty_check.py +41 -41
  295. tests/test_queue_manager_double_crawlo.py +173 -173
  296. tests/test_queue_manager_redis_key.py +179 -179
  297. tests/test_queue_naming.py +154 -154
  298. tests/test_queue_type.py +106 -106
  299. tests/test_queue_type_redis_config_consistency.py +130 -130
  300. tests/test_random_headers_default.py +322 -322
  301. tests/test_random_headers_necessity.py +308 -308
  302. tests/test_random_user_agent.py +72 -72
  303. tests/test_redis_config.py +28 -28
  304. tests/test_redis_connection_pool.py +294 -294
  305. tests/test_redis_key_naming.py +181 -181
  306. tests/test_redis_key_validator.py +123 -123
  307. tests/test_redis_queue.py +224 -224
  308. tests/test_redis_queue_name_fix.py +175 -175
  309. tests/test_redis_queue_type_fallback.py +129 -129
  310. tests/test_request_ignore_middleware.py +182 -182
  311. tests/test_request_params.py +111 -111
  312. tests/test_request_serialization.py +70 -70
  313. tests/test_response_code_middleware.py +349 -349
  314. tests/test_response_filter_middleware.py +427 -427
  315. tests/test_response_follow.py +104 -104
  316. tests/test_response_improvements.py +152 -152
  317. tests/test_response_selector_methods.py +92 -92
  318. tests/test_response_url_methods.py +70 -70
  319. tests/test_response_urljoin.py +86 -86
  320. tests/test_retry_middleware.py +333 -333
  321. tests/test_retry_middleware_realistic.py +273 -273
  322. tests/test_scheduler.py +252 -252
  323. tests/test_scheduler_config_update.py +133 -133
  324. tests/test_scrapy_style_encoding.py +112 -112
  325. tests/test_selector_helper.py +100 -100
  326. tests/test_selector_optimizations.py +146 -146
  327. tests/test_simple_response.py +61 -61
  328. tests/test_spider_loader.py +49 -49
  329. tests/test_spider_loader_comprehensive.py +69 -69
  330. tests/test_spider_modules.py +84 -84
  331. tests/test_spiders/test_spider.py +9 -9
  332. tests/test_telecom_spider_redis_key.py +205 -205
  333. tests/test_template_content.py +87 -87
  334. tests/test_template_redis_key.py +134 -134
  335. tests/test_tools.py +159 -159
  336. tests/test_user_agent_randomness.py +176 -176
  337. tests/test_user_agents.py +96 -96
  338. tests/untested_features_report.md +138 -138
  339. tests/verify_debug.py +51 -51
  340. tests/verify_distributed.py +117 -117
  341. tests/verify_log_fix.py +111 -111
  342. tests/verify_mysql_warnings.py +109 -109
  343. crawlo/utils/log.py +0 -80
  344. crawlo/utils/url_utils.py +0 -40
  345. crawlo-1.4.7.dist-info/RECORD +0 -347
  346. {crawlo-1.4.7.dist-info → crawlo-1.4.8.dist-info}/WHEEL +0 -0
  347. {crawlo-1.4.7.dist-info → crawlo-1.4.8.dist-info}/entry_points.txt +0 -0
  348. {crawlo-1.4.7.dist-info → crawlo-1.4.8.dist-info}/top_level.txt +0 -0
@@ -1,452 +1,452 @@
1
- # -*- coding: utf-8 -*-
2
- """
3
- Pipeline基类 - 提供统一的资源管理
4
- ====================================
5
-
6
- Pipeline体系说明:
7
- - BasePipeline: 基础抽象类,定义Pipeline接口规范
8
- - ResourceManagedPipeline: 提供资源管理功能的基类(推荐)
9
- - FileBasedPipeline: 文件操作专用基类
10
- - DatabasePipeline: 数据库操作专用基类
11
- - CacheBasedPipeline: 缓存操作专用基类
12
-
13
- 与 PipelineManager 的关系:
14
- - base_pipeline.py: 定义单个Pipeline的实现规范(本文件)
15
- - pipeline_manager.py: 协调多个Pipeline的执行流程
16
- - 两者分工明确,互相配合,不是重复设计
17
-
18
- 使用方法:
19
- # 简单场景 - 直接继承BasePipeline
20
- class SimplePipeline(BasePipeline):
21
- @classmethod
22
- def from_crawler(cls, crawler):
23
- return cls()
24
-
25
- async def process_item(self, item, spider):
26
- return item
27
-
28
- # 复杂场景 - 使用ResourceManagedPipeline(推荐)
29
- class MyPipeline(ResourceManagedPipeline):
30
- async def _initialize_resources(self):
31
- # 初始化资源
32
- pass
33
-
34
- async def _cleanup_resources(self):
35
- # 清理资源
36
- pass
37
-
38
- async def process_item(self, item, spider):
39
- # 处理逻辑
40
- return item
41
- """
42
-
43
- import asyncio
44
- from abc import ABC, abstractmethod
45
- from pathlib import Path
46
- from typing import Optional, Any, Callable
47
-
48
- from crawlo.items import Item
49
- from crawlo.spider import Spider
50
- from crawlo.logging import get_logger
51
- from crawlo.utils.resource_manager import ResourceManager, ResourceType
52
-
53
-
54
- class BasePipeline(ABC):
55
- """
56
- Pipeline基础抽象类
57
-
58
- 所有Pipeline都应继承此基类,确保统一的接口规范。
59
- 简单场景可直接使用,复杂场景建议使用ResourceManagedPipeline。
60
- """
61
-
62
- @classmethod
63
- @abstractmethod
64
- def from_crawler(cls, crawler):
65
- """从Crawler创建Pipeline实例"""
66
- raise NotImplementedError("子类必须实现from_crawler方法")
67
-
68
- @abstractmethod
69
- async def process_item(self, item: Item, spider: Spider, **kwargs) -> Optional[Item]:
70
- """处理Item的核心方法"""
71
- raise NotImplementedError("子类必须实现process_item方法")
72
-
73
- @classmethod
74
- def create_instance(cls, crawler):
75
- """兼容旧版本的创建方法,内部调用from_crawler"""
76
- return cls.from_crawler(crawler)
77
-
78
-
79
- class ResourceManagedPipeline(BasePipeline):
80
- """
81
- 资源管理Pipeline基类
82
-
83
- 提供统一的资源管理功能,自动注册到ResourceManager
84
-
85
- 特性:
86
- - 自动资源清理
87
- - LIFO清理顺序
88
- - 异常容错
89
- - 批量数据刷新
90
- """
91
-
92
- def __init__(self, crawler):
93
- """
94
- 初始化Pipeline
95
-
96
- Args:
97
- crawler: Crawler实例
98
- """
99
- self.crawler = crawler
100
- self.settings = crawler.settings
101
- self.logger = get_logger(
102
- self.__class__.__name__,
103
- self.settings.get('LOG_LEVEL')
104
- )
105
-
106
- # 资源管理器
107
- self._resource_manager = ResourceManager(
108
- name=f"pipeline.{self.__class__.__name__}"
109
- )
110
-
111
- # 初始化标志
112
- self._initialized = False
113
- self._init_lock = asyncio.Lock()
114
-
115
- # 批量缓冲区(子类可选使用)
116
- self.batch_buffer = []
117
- self.batch_size = self.settings.get_int('PIPELINE_BATCH_SIZE', 100)
118
- self.use_batch = self.settings.get_bool('PIPELINE_USE_BATCH', False)
119
-
120
- # 注册关闭事件
121
- crawler.subscriber.subscribe(self._on_spider_closed, event='spider_closed')
122
-
123
- self.logger.debug(f"{self.__class__.__name__} 已初始化")
124
-
125
- async def _ensure_initialized(self):
126
- """确保资源已初始化(线程安全)"""
127
- if self._initialized:
128
- return
129
-
130
- async with self._init_lock:
131
- if not self._initialized:
132
- try:
133
- await self._initialize_resources()
134
- self._initialized = True
135
- self.logger.info(f"{self.__class__.__name__} 资源初始化完成")
136
- except Exception as e:
137
- self.logger.error(f"资源初始化失败: {e}")
138
- raise
139
-
140
- @abstractmethod
141
- async def _initialize_resources(self):
142
- """
143
- 初始化资源(子类实现)
144
-
145
- 示例:
146
- # 初始化数据库连接池
147
- self.pool = await create_pool(...)
148
-
149
- # 注册到资源管理器
150
- self._resource_manager.register(
151
- resource=self.pool,
152
- cleanup_func=self._close_pool,
153
- resource_type=ResourceType.DATABASE,
154
- name="db_pool"
155
- )
156
- """
157
- pass
158
-
159
- @abstractmethod
160
- async def _cleanup_resources(self):
161
- """
162
- 清理资源(子类实现)
163
-
164
- 通常由ResourceManager自动调用,但也可以手动实现额外清理逻辑
165
- """
166
- pass
167
-
168
- async def _flush_batch(self, spider: Spider):
169
- """
170
- 刷新批量缓冲区(子类可重写)
171
-
172
- Args:
173
- spider: Spider实例
174
- """
175
- if not self.batch_buffer:
176
- return
177
-
178
- self.logger.warning(
179
- f"批量缓冲区还有 {len(self.batch_buffer)} 条数据,"
180
- f"但未实现 _flush_batch 方法"
181
- )
182
-
183
- async def _on_spider_closed(self):
184
- """
185
- 爬虫关闭事件处理
186
-
187
- 自动执行:
188
- 1. 刷新批量数据
189
- 2. 清理所有注册的资源
190
- 3. 生成统计报告
191
- """
192
- self.logger.info(f"{self.__class__.__name__} 开始清理资源...")
193
-
194
- try:
195
- # 1. 刷新批量数据
196
- if self.use_batch and self.batch_buffer:
197
- spider = self.crawler.spider
198
- await self._flush_batch(spider)
199
- self.logger.info(f"批量数据已刷新,共 {len(self.batch_buffer)} 条")
200
-
201
- # 2. 调用子类的清理方法
202
- await self._cleanup_resources()
203
-
204
- # 3. 使用资源管理器统一清理
205
- cleanup_result = await self._resource_manager.cleanup_all()
206
-
207
- # 4. 记录清理结果
208
- if cleanup_result['success_count'] > 0:
209
- self.logger.info(
210
- f"资源清理完成: 成功 {cleanup_result['success_count']} 个, "
211
- f"失败 {cleanup_result['failed_count']} 个"
212
- )
213
-
214
- if cleanup_result['errors']:
215
- self.logger.warning(f"清理时出现错误: {cleanup_result['errors']}")
216
-
217
- except Exception as e:
218
- self.logger.error(f"资源清理失败: {e}", exc_info=True)
219
-
220
- def register_resource(
221
- self,
222
- resource: Any,
223
- cleanup_func: Callable,
224
- resource_type: ResourceType = ResourceType.OTHER,
225
- name: Optional[str] = None
226
- ):
227
- """
228
- 注册需要清理的资源
229
-
230
- Args:
231
- resource: 资源对象
232
- cleanup_func: 清理函数
233
- resource_type: 资源类型
234
- name: 资源名称
235
- """
236
- self._resource_manager.register(
237
- resource=resource,
238
- cleanup_func=cleanup_func,
239
- resource_type=resource_type,
240
- name=name or str(id(resource))
241
- )
242
- self.logger.debug(f"注册资源: {name} ({resource_type})")
243
-
244
-
245
- class FileBasedPipeline(ResourceManagedPipeline):
246
- """
247
- 文件型Pipeline基类
248
-
249
- 提供文件操作的通用功能:
250
- - 自动创建目录
251
- - 文件句柄管理
252
- - 自动刷新缓冲区
253
- """
254
-
255
- def __init__(self, crawler):
256
- super().__init__(crawler)
257
- self.file_handle: Optional[Any] = None
258
- self.file_path: Optional[Path] = None
259
- self._file_lock = asyncio.Lock()
260
-
261
- def _get_file_path(self, config_key: str, default_prefix: str, extension: str) -> Path:
262
- """
263
- 获取输出文件路径
264
-
265
- Args:
266
- config_key: 配置键名
267
- default_prefix: 默认前缀
268
- extension: 文件扩展名
269
-
270
- Returns:
271
- Path对象
272
- """
273
- from datetime import datetime
274
-
275
- file_path = (
276
- self.settings.get(config_key) or
277
- getattr(self.crawler.spider, config_key.lower(), None) or
278
- f"output/{self.crawler.spider.name}_{default_prefix}_{datetime.now().strftime('%Y%m%d_%H%M%S')}.{extension}"
279
- )
280
-
281
- path = Path(file_path)
282
- path.parent.mkdir(parents=True, exist_ok=True)
283
- return path
284
-
285
- async def _open_file(self, mode: str = 'w', **kwargs):
286
- """
287
- 打开文件并注册到资源管理器
288
-
289
- Args:
290
- mode: 文件打开模式
291
- **kwargs: 传递给open()的其他参数
292
- """
293
- if self.file_handle is not None:
294
- return
295
-
296
- async with self._file_lock:
297
- if self.file_handle is None:
298
- if self.file_path is None:
299
- raise ValueError("文件路径未设置")
300
-
301
- self.file_handle = open(
302
- self.file_path,
303
- mode,
304
- encoding=kwargs.get('encoding', 'utf-8'),
305
- **{k: v for k, v in kwargs.items() if k != 'encoding'}
306
- )
307
-
308
- # 注册文件句柄到资源管理器
309
- self.register_resource(
310
- resource=self.file_handle,
311
- cleanup_func=self._close_file,
312
- resource_type=ResourceType.OTHER, # 使用OTHER类型
313
- name=str(self.file_path)
314
- )
315
-
316
- self.logger.info(f"文件已打开: {self.file_path}")
317
-
318
- async def _close_file(self, file_handle):
319
- """关闭文件句柄"""
320
- if file_handle and not file_handle.closed:
321
- file_handle.close()
322
- self.logger.info(f"文件已关闭: {self.file_path}")
323
-
324
- async def _initialize_resources(self):
325
- """初始化文件资源"""
326
- # 子类应该调用 _open_file() 来打开文件
327
- pass
328
-
329
- async def _cleanup_resources(self):
330
- """清理由ResourceManager管理的资源"""
331
- # 文件句柄由ResourceManager自动清理
332
- pass
333
-
334
-
335
- class DatabasePipeline(ResourceManagedPipeline):
336
- """
337
- 数据库Pipeline基类
338
-
339
- 提供数据库操作的通用功能:
340
- - 连接池管理
341
- - 自动重连
342
- - 批量写入优化
343
- - 事务支持
344
- """
345
-
346
- def __init__(self, crawler):
347
- super().__init__(crawler)
348
- self.pool = None
349
- self._pool_lock = asyncio.Lock()
350
- self._pool_initialized = False
351
-
352
- async def _ensure_pool_initialized(self):
353
- """确保连接池已初始化"""
354
- if self._pool_initialized and self.pool:
355
- return
356
-
357
- async with self._pool_lock:
358
- if not self._pool_initialized:
359
- await self._create_pool()
360
- self._pool_initialized = True
361
- self.logger.info(f"{self.__class__.__name__} 连接池已初始化")
362
-
363
- @abstractmethod
364
- async def _create_pool(self):
365
- """
366
- 创建数据库连接池(子类实现)
367
-
368
- 示例:
369
- self.pool = await create_pool(...)
370
-
371
- # 注册到资源管理器
372
- self.register_resource(
373
- resource=self.pool,
374
- cleanup_func=self._close_pool,
375
- resource_type=ResourceType.DATABASE,
376
- name="db_pool"
377
- )
378
- """
379
- raise NotImplementedError("子类必须实现 _create_pool 方法")
380
-
381
- @abstractmethod
382
- async def _close_pool(self, pool):
383
- """关闭连接池(子类实现)"""
384
- raise NotImplementedError("子类必须实现 _close_pool 方法")
385
-
386
- async def _initialize_resources(self):
387
- """初始化数据库资源"""
388
- await self._ensure_pool_initialized()
389
-
390
- async def _cleanup_resources(self):
391
- """清理由ResourceManager管理的资源"""
392
- # 连接池由ResourceManager自动清理
393
- pass
394
-
395
-
396
- class CacheBasedPipeline(ResourceManagedPipeline):
397
- """
398
- 缓存型Pipeline基类
399
-
400
- 提供缓存操作的通用功能:
401
- - Redis/Memcached连接管理
402
- - 自动关闭连接
403
- """
404
-
405
- def __init__(self, crawler):
406
- super().__init__(crawler)
407
- self.client = None
408
- self._client_lock = asyncio.Lock()
409
- self._client_initialized = False
410
-
411
- async def _ensure_client_initialized(self):
412
- """确保缓存客户端已初始化"""
413
- if self._client_initialized and self.client:
414
- return
415
-
416
- async with self._client_lock:
417
- if not self._client_initialized:
418
- await self._create_client()
419
- self._client_initialized = True
420
- self.logger.info(f"{self.__class__.__name__} 缓存客户端已初始化")
421
-
422
- @abstractmethod
423
- async def _create_client(self):
424
- """
425
- 创建缓存客户端(子类实现)
426
-
427
- 示例:
428
- self.client = redis.Redis(...)
429
-
430
- # 注册到资源管理器
431
- self.register_resource(
432
- resource=self.client,
433
- cleanup_func=self._close_client,
434
- resource_type=ResourceType.NETWORK,
435
- name="cache_client"
436
- )
437
- """
438
- raise NotImplementedError("子类必须实现 _create_client 方法")
439
-
440
- @abstractmethod
441
- async def _close_client(self, client):
442
- """关闭缓存客户端(子类实现)"""
443
- raise NotImplementedError("子类必须实现 _close_client 方法")
444
-
445
- async def _initialize_resources(self):
446
- """初始化缓存资源"""
447
- await self._ensure_client_initialized()
448
-
449
- async def _cleanup_resources(self):
450
- """清理由ResourceManager管理的资源"""
451
- # 客户端由ResourceManager自动清理
452
- pass
1
+ # -*- coding: utf-8 -*-
2
+ """
3
+ Pipeline基类 - 提供统一的资源管理
4
+ ====================================
5
+
6
+ Pipeline体系说明:
7
+ - BasePipeline: 基础抽象类,定义Pipeline接口规范
8
+ - ResourceManagedPipeline: 提供资源管理功能的基类(推荐)
9
+ - FileBasedPipeline: 文件操作专用基类
10
+ - DatabasePipeline: 数据库操作专用基类
11
+ - CacheBasedPipeline: 缓存操作专用基类
12
+
13
+ 与 PipelineManager 的关系:
14
+ - base_pipeline.py: 定义单个Pipeline的实现规范(本文件)
15
+ - pipeline_manager.py: 协调多个Pipeline的执行流程
16
+ - 两者分工明确,互相配合,不是重复设计
17
+
18
+ 使用方法:
19
+ # 简单场景 - 直接继承BasePipeline
20
+ class SimplePipeline(BasePipeline):
21
+ @classmethod
22
+ def from_crawler(cls, crawler):
23
+ return cls()
24
+
25
+ async def process_item(self, item, spider):
26
+ return item
27
+
28
+ # 复杂场景 - 使用ResourceManagedPipeline(推荐)
29
+ class MyPipeline(ResourceManagedPipeline):
30
+ async def _initialize_resources(self):
31
+ # 初始化资源
32
+ pass
33
+
34
+ async def _cleanup_resources(self):
35
+ # 清理资源
36
+ pass
37
+
38
+ async def process_item(self, item, spider):
39
+ # 处理逻辑
40
+ return item
41
+ """
42
+
43
+ import asyncio
44
+ from abc import ABC, abstractmethod
45
+ from pathlib import Path
46
+ from typing import Optional, Any, Callable
47
+
48
+ from crawlo.items import Item
49
+ from crawlo.spider import Spider
50
+ from crawlo.logging import get_logger
51
+ from crawlo.utils.resource_manager import ResourceManager, ResourceType
52
+
53
+
54
+ class BasePipeline(ABC):
55
+ """
56
+ Pipeline基础抽象类
57
+
58
+ 所有Pipeline都应继承此基类,确保统一的接口规范。
59
+ 简单场景可直接使用,复杂场景建议使用ResourceManagedPipeline。
60
+ """
61
+
62
+ @classmethod
63
+ @abstractmethod
64
+ def from_crawler(cls, crawler):
65
+ """从Crawler创建Pipeline实例"""
66
+ raise NotImplementedError("子类必须实现from_crawler方法")
67
+
68
+ @abstractmethod
69
+ async def process_item(self, item: Item, spider: Spider, **kwargs) -> Optional[Item]:
70
+ """处理Item的核心方法"""
71
+ raise NotImplementedError("子类必须实现process_item方法")
72
+
73
+ @classmethod
74
+ def create_instance(cls, crawler):
75
+ """兼容旧版本的创建方法,内部调用from_crawler"""
76
+ return cls.from_crawler(crawler)
77
+
78
+
79
+ class ResourceManagedPipeline(BasePipeline):
80
+ """
81
+ 资源管理Pipeline基类
82
+
83
+ 提供统一的资源管理功能,自动注册到ResourceManager
84
+
85
+ 特性:
86
+ - 自动资源清理
87
+ - LIFO清理顺序
88
+ - 异常容错
89
+ - 批量数据刷新
90
+ """
91
+
92
+ def __init__(self, crawler):
93
+ """
94
+ 初始化Pipeline
95
+
96
+ Args:
97
+ crawler: Crawler实例
98
+ """
99
+ self.crawler = crawler
100
+ self.settings = crawler.settings
101
+ self.logger = get_logger(
102
+ self.__class__.__name__,
103
+ self.settings.get('LOG_LEVEL')
104
+ )
105
+
106
+ # 资源管理器
107
+ self._resource_manager = ResourceManager(
108
+ name=f"pipeline.{self.__class__.__name__}"
109
+ )
110
+
111
+ # 初始化标志
112
+ self._initialized = False
113
+ self._init_lock = asyncio.Lock()
114
+
115
+ # 批量缓冲区(子类可选使用)
116
+ self.batch_buffer = []
117
+ self.batch_size = self.settings.get_int('PIPELINE_BATCH_SIZE', 100)
118
+ self.use_batch = self.settings.get_bool('PIPELINE_USE_BATCH', False)
119
+
120
+ # 注册关闭事件
121
+ crawler.subscriber.subscribe(self._on_spider_closed, event='spider_closed')
122
+
123
+ self.logger.debug(f"{self.__class__.__name__} 已初始化")
124
+
125
+ async def _ensure_initialized(self):
126
+ """确保资源已初始化(线程安全)"""
127
+ if self._initialized:
128
+ return
129
+
130
+ async with self._init_lock:
131
+ if not self._initialized:
132
+ try:
133
+ await self._initialize_resources()
134
+ self._initialized = True
135
+ self.logger.info(f"{self.__class__.__name__} 资源初始化完成")
136
+ except Exception as e:
137
+ self.logger.error(f"资源初始化失败: {e}")
138
+ raise
139
+
140
+ @abstractmethod
141
+ async def _initialize_resources(self):
142
+ """
143
+ 初始化资源(子类实现)
144
+
145
+ 示例:
146
+ # 初始化数据库连接池
147
+ self.pool = await create_pool(...)
148
+
149
+ # 注册到资源管理器
150
+ self._resource_manager.register(
151
+ resource=self.pool,
152
+ cleanup_func=self._close_pool,
153
+ resource_type=ResourceType.DATABASE,
154
+ name="db_pool"
155
+ )
156
+ """
157
+ pass
158
+
159
+ @abstractmethod
160
+ async def _cleanup_resources(self):
161
+ """
162
+ 清理资源(子类实现)
163
+
164
+ 通常由ResourceManager自动调用,但也可以手动实现额外清理逻辑
165
+ """
166
+ pass
167
+
168
+ async def _flush_batch(self, spider: Spider):
169
+ """
170
+ 刷新批量缓冲区(子类可重写)
171
+
172
+ Args:
173
+ spider: Spider实例
174
+ """
175
+ if not self.batch_buffer:
176
+ return
177
+
178
+ self.logger.warning(
179
+ f"批量缓冲区还有 {len(self.batch_buffer)} 条数据,"
180
+ f"但未实现 _flush_batch 方法"
181
+ )
182
+
183
+ async def _on_spider_closed(self):
184
+ """
185
+ 爬虫关闭事件处理
186
+
187
+ 自动执行:
188
+ 1. 刷新批量数据
189
+ 2. 清理所有注册的资源
190
+ 3. 生成统计报告
191
+ """
192
+ self.logger.info(f"{self.__class__.__name__} 开始清理资源...")
193
+
194
+ try:
195
+ # 1. 刷新批量数据
196
+ if self.use_batch and self.batch_buffer:
197
+ spider = self.crawler.spider
198
+ await self._flush_batch(spider)
199
+ self.logger.info(f"批量数据已刷新,共 {len(self.batch_buffer)} 条")
200
+
201
+ # 2. 调用子类的清理方法
202
+ await self._cleanup_resources()
203
+
204
+ # 3. 使用资源管理器统一清理
205
+ cleanup_result = await self._resource_manager.cleanup_all()
206
+
207
+ # 4. 记录清理结果
208
+ if cleanup_result['success_count'] > 0:
209
+ self.logger.info(
210
+ f"资源清理完成: 成功 {cleanup_result['success_count']} 个, "
211
+ f"失败 {cleanup_result['failed_count']} 个"
212
+ )
213
+
214
+ if cleanup_result['errors']:
215
+ self.logger.warning(f"清理时出现错误: {cleanup_result['errors']}")
216
+
217
+ except Exception as e:
218
+ self.logger.error(f"资源清理失败: {e}", exc_info=True)
219
+
220
+ def register_resource(
221
+ self,
222
+ resource: Any,
223
+ cleanup_func: Callable,
224
+ resource_type: ResourceType = ResourceType.OTHER,
225
+ name: Optional[str] = None
226
+ ):
227
+ """
228
+ 注册需要清理的资源
229
+
230
+ Args:
231
+ resource: 资源对象
232
+ cleanup_func: 清理函数
233
+ resource_type: 资源类型
234
+ name: 资源名称
235
+ """
236
+ self._resource_manager.register(
237
+ resource=resource,
238
+ cleanup_func=cleanup_func,
239
+ resource_type=resource_type,
240
+ name=name or str(id(resource))
241
+ )
242
+ self.logger.debug(f"注册资源: {name} ({resource_type})")
243
+
244
+
245
+ class FileBasedPipeline(ResourceManagedPipeline):
246
+ """
247
+ 文件型Pipeline基类
248
+
249
+ 提供文件操作的通用功能:
250
+ - 自动创建目录
251
+ - 文件句柄管理
252
+ - 自动刷新缓冲区
253
+ """
254
+
255
+ def __init__(self, crawler):
256
+ super().__init__(crawler)
257
+ self.file_handle: Optional[Any] = None
258
+ self.file_path: Optional[Path] = None
259
+ self._file_lock = asyncio.Lock()
260
+
261
+ def _get_file_path(self, config_key: str, default_prefix: str, extension: str) -> Path:
262
+ """
263
+ 获取输出文件路径
264
+
265
+ Args:
266
+ config_key: 配置键名
267
+ default_prefix: 默认前缀
268
+ extension: 文件扩展名
269
+
270
+ Returns:
271
+ Path对象
272
+ """
273
+ from datetime import datetime
274
+
275
+ file_path = (
276
+ self.settings.get(config_key) or
277
+ getattr(self.crawler.spider, config_key.lower(), None) or
278
+ f"output/{self.crawler.spider.name}_{default_prefix}_{datetime.now().strftime('%Y%m%d_%H%M%S')}.{extension}"
279
+ )
280
+
281
+ path = Path(file_path)
282
+ path.parent.mkdir(parents=True, exist_ok=True)
283
+ return path
284
+
285
+ async def _open_file(self, mode: str = 'w', **kwargs):
286
+ """
287
+ 打开文件并注册到资源管理器
288
+
289
+ Args:
290
+ mode: 文件打开模式
291
+ **kwargs: 传递给open()的其他参数
292
+ """
293
+ if self.file_handle is not None:
294
+ return
295
+
296
+ async with self._file_lock:
297
+ if self.file_handle is None:
298
+ if self.file_path is None:
299
+ raise ValueError("文件路径未设置")
300
+
301
+ self.file_handle = open(
302
+ self.file_path,
303
+ mode,
304
+ encoding=kwargs.get('encoding', 'utf-8'),
305
+ **{k: v for k, v in kwargs.items() if k != 'encoding'}
306
+ )
307
+
308
+ # 注册文件句柄到资源管理器
309
+ self.register_resource(
310
+ resource=self.file_handle,
311
+ cleanup_func=self._close_file,
312
+ resource_type=ResourceType.OTHER, # 使用OTHER类型
313
+ name=str(self.file_path)
314
+ )
315
+
316
+ self.logger.info(f"文件已打开: {self.file_path}")
317
+
318
+ async def _close_file(self, file_handle):
319
+ """关闭文件句柄"""
320
+ if file_handle and not file_handle.closed:
321
+ file_handle.close()
322
+ self.logger.info(f"文件已关闭: {self.file_path}")
323
+
324
+ async def _initialize_resources(self):
325
+ """初始化文件资源"""
326
+ # 子类应该调用 _open_file() 来打开文件
327
+ pass
328
+
329
+ async def _cleanup_resources(self):
330
+ """清理由ResourceManager管理的资源"""
331
+ # 文件句柄由ResourceManager自动清理
332
+ pass
333
+
334
+
335
+ class DatabasePipeline(ResourceManagedPipeline):
336
+ """
337
+ 数据库Pipeline基类
338
+
339
+ 提供数据库操作的通用功能:
340
+ - 连接池管理
341
+ - 自动重连
342
+ - 批量写入优化
343
+ - 事务支持
344
+ """
345
+
346
+ def __init__(self, crawler):
347
+ super().__init__(crawler)
348
+ self.pool = None
349
+ self._pool_lock = asyncio.Lock()
350
+ self._pool_initialized = False
351
+
352
+ async def _ensure_pool_initialized(self):
353
+ """确保连接池已初始化"""
354
+ if self._pool_initialized and self.pool:
355
+ return
356
+
357
+ async with self._pool_lock:
358
+ if not self._pool_initialized:
359
+ await self._create_pool()
360
+ self._pool_initialized = True
361
+ self.logger.info(f"{self.__class__.__name__} 连接池已初始化")
362
+
363
+ @abstractmethod
364
+ async def _create_pool(self):
365
+ """
366
+ 创建数据库连接池(子类实现)
367
+
368
+ 示例:
369
+ self.pool = await create_pool(...)
370
+
371
+ # 注册到资源管理器
372
+ self.register_resource(
373
+ resource=self.pool,
374
+ cleanup_func=self._close_pool,
375
+ resource_type=ResourceType.DATABASE,
376
+ name="db_pool"
377
+ )
378
+ """
379
+ raise NotImplementedError("子类必须实现 _create_pool 方法")
380
+
381
+ @abstractmethod
382
+ async def _close_pool(self, pool):
383
+ """关闭连接池(子类实现)"""
384
+ raise NotImplementedError("子类必须实现 _close_pool 方法")
385
+
386
+ async def _initialize_resources(self):
387
+ """初始化数据库资源"""
388
+ await self._ensure_pool_initialized()
389
+
390
+ async def _cleanup_resources(self):
391
+ """清理由ResourceManager管理的资源"""
392
+ # 连接池由ResourceManager自动清理
393
+ pass
394
+
395
+
396
+ class CacheBasedPipeline(ResourceManagedPipeline):
397
+ """
398
+ 缓存型Pipeline基类
399
+
400
+ 提供缓存操作的通用功能:
401
+ - Redis/Memcached连接管理
402
+ - 自动关闭连接
403
+ """
404
+
405
+ def __init__(self, crawler):
406
+ super().__init__(crawler)
407
+ self.client = None
408
+ self._client_lock = asyncio.Lock()
409
+ self._client_initialized = False
410
+
411
+ async def _ensure_client_initialized(self):
412
+ """确保缓存客户端已初始化"""
413
+ if self._client_initialized and self.client:
414
+ return
415
+
416
+ async with self._client_lock:
417
+ if not self._client_initialized:
418
+ await self._create_client()
419
+ self._client_initialized = True
420
+ self.logger.info(f"{self.__class__.__name__} 缓存客户端已初始化")
421
+
422
+ @abstractmethod
423
+ async def _create_client(self):
424
+ """
425
+ 创建缓存客户端(子类实现)
426
+
427
+ 示例:
428
+ self.client = redis.Redis(...)
429
+
430
+ # 注册到资源管理器
431
+ self.register_resource(
432
+ resource=self.client,
433
+ cleanup_func=self._close_client,
434
+ resource_type=ResourceType.NETWORK,
435
+ name="cache_client"
436
+ )
437
+ """
438
+ raise NotImplementedError("子类必须实现 _create_client 方法")
439
+
440
+ @abstractmethod
441
+ async def _close_client(self, client):
442
+ """关闭缓存客户端(子类实现)"""
443
+ raise NotImplementedError("子类必须实现 _close_client 方法")
444
+
445
+ async def _initialize_resources(self):
446
+ """初始化缓存资源"""
447
+ await self._ensure_client_initialized()
448
+
449
+ async def _cleanup_resources(self):
450
+ """清理由ResourceManager管理的资源"""
451
+ # 客户端由ResourceManager自动清理
452
+ pass