crawlo 1.4.5__py3-none-any.whl → 1.4.7__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of crawlo might be problematic. Click here for more details.

Files changed (375) hide show
  1. crawlo/__init__.py +90 -89
  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 -138
  8. crawlo/commands/list.py +155 -155
  9. crawlo/commands/run.py +379 -341
  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 -312
  14. crawlo/config_validator.py +277 -277
  15. crawlo/core/__init__.py +52 -52
  16. crawlo/core/engine.py +451 -438
  17. crawlo/core/processor.py +47 -47
  18. crawlo/core/scheduler.py +290 -291
  19. crawlo/crawler.py +698 -657
  20. crawlo/data/__init__.py +5 -5
  21. crawlo/data/user_agents.py +194 -194
  22. crawlo/downloader/__init__.py +280 -276
  23. crawlo/downloader/aiohttp_downloader.py +233 -233
  24. crawlo/downloader/cffi_downloader.py +250 -245
  25. crawlo/downloader/httpx_downloader.py +265 -259
  26. crawlo/downloader/hybrid_downloader.py +212 -212
  27. crawlo/downloader/playwright_downloader.py +425 -402
  28. crawlo/downloader/selenium_downloader.py +486 -472
  29. crawlo/event.py +45 -11
  30. crawlo/exceptions.py +215 -82
  31. crawlo/extension/__init__.py +65 -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 -61
  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 -103
  42. crawlo/factories/registry.py +84 -84
  43. crawlo/factories/utils.py +135 -0
  44. crawlo/filters/__init__.py +170 -153
  45. crawlo/filters/aioredis_filter.py +348 -264
  46. crawlo/filters/memory_filter.py +261 -276
  47. crawlo/framework.py +306 -292
  48. crawlo/initialization/__init__.py +44 -44
  49. crawlo/initialization/built_in.py +391 -434
  50. crawlo/initialization/context.py +141 -141
  51. crawlo/initialization/core.py +240 -194
  52. crawlo/initialization/phases.py +230 -149
  53. crawlo/initialization/registry.py +143 -145
  54. crawlo/initialization/utils.py +49 -0
  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 -46
  61. crawlo/logging/config.py +277 -197
  62. crawlo/logging/factory.py +175 -171
  63. crawlo/logging/manager.py +104 -112
  64. crawlo/middleware/__init__.py +87 -24
  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 -386
  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 -253
  75. crawlo/network/__init__.py +21 -21
  76. crawlo/network/request.py +375 -379
  77. crawlo/network/response.py +569 -664
  78. crawlo/pipelines/__init__.py +53 -22
  79. crawlo/pipelines/base_pipeline.py +452 -0
  80. crawlo/pipelines/bloom_dedup_pipeline.py +146 -146
  81. crawlo/pipelines/console_pipeline.py +39 -39
  82. crawlo/pipelines/csv_pipeline.py +316 -316
  83. crawlo/pipelines/database_dedup_pipeline.py +197 -197
  84. crawlo/pipelines/json_pipeline.py +218 -218
  85. crawlo/pipelines/memory_dedup_pipeline.py +105 -105
  86. crawlo/pipelines/mongo_pipeline.py +140 -132
  87. crawlo/pipelines/mysql_pipeline.py +470 -326
  88. crawlo/pipelines/pipeline_manager.py +100 -100
  89. crawlo/pipelines/redis_dedup_pipeline.py +155 -156
  90. crawlo/project.py +347 -347
  91. crawlo/queue/__init__.py +10 -0
  92. crawlo/queue/pqueue.py +38 -38
  93. crawlo/queue/queue_manager.py +591 -525
  94. crawlo/queue/redis_priority_queue.py +519 -370
  95. crawlo/settings/__init__.py +7 -7
  96. crawlo/settings/default_settings.py +285 -270
  97. crawlo/settings/setting_manager.py +219 -219
  98. crawlo/spider/__init__.py +657 -657
  99. crawlo/stats_collector.py +82 -73
  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 +2 -4
  104. crawlo/templates/project/items.py.tmpl +13 -17
  105. crawlo/templates/project/middlewares.py.tmpl +38 -38
  106. crawlo/templates/project/pipelines.py.tmpl +35 -36
  107. crawlo/templates/project/settings.py.tmpl +110 -157
  108. crawlo/templates/project/settings_distributed.py.tmpl +156 -161
  109. crawlo/templates/project/settings_gentle.py.tmpl +170 -171
  110. crawlo/templates/project/settings_high_performance.py.tmpl +171 -172
  111. crawlo/templates/project/settings_minimal.py.tmpl +99 -77
  112. crawlo/templates/project/settings_simple.py.tmpl +168 -169
  113. crawlo/templates/project/spiders/__init__.py.tmpl +9 -9
  114. crawlo/templates/run.py.tmpl +23 -30
  115. crawlo/templates/spider/spider.py.tmpl +33 -144
  116. crawlo/templates/spiders_init.py.tmpl +5 -10
  117. crawlo/tools/__init__.py +86 -189
  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 +50 -50
  123. crawlo/utils/batch_processor.py +276 -259
  124. crawlo/utils/config_manager.py +442 -0
  125. crawlo/utils/controlled_spider_mixin.py +439 -439
  126. crawlo/utils/db_helper.py +250 -244
  127. crawlo/utils/error_handler.py +410 -410
  128. crawlo/utils/fingerprint.py +121 -121
  129. crawlo/utils/func_tools.py +82 -82
  130. crawlo/utils/large_scale_helper.py +344 -344
  131. crawlo/utils/leak_detector.py +335 -0
  132. crawlo/utils/log.py +79 -79
  133. crawlo/utils/misc.py +81 -81
  134. crawlo/utils/mongo_connection_pool.py +157 -0
  135. crawlo/utils/mysql_connection_pool.py +197 -0
  136. crawlo/utils/performance_monitor.py +285 -285
  137. crawlo/utils/queue_helper.py +175 -175
  138. crawlo/utils/redis_checker.py +91 -0
  139. crawlo/utils/redis_connection_pool.py +578 -388
  140. crawlo/utils/redis_key_validator.py +198 -198
  141. crawlo/utils/request.py +278 -256
  142. crawlo/utils/request_serializer.py +225 -225
  143. crawlo/utils/resource_manager.py +337 -0
  144. crawlo/utils/selector_helper.py +137 -137
  145. crawlo/utils/singleton.py +70 -0
  146. crawlo/utils/spider_loader.py +201 -201
  147. crawlo/utils/text_helper.py +94 -94
  148. crawlo/utils/{url.py → url_utils.py} +39 -39
  149. crawlo-1.4.7.dist-info/METADATA +689 -0
  150. crawlo-1.4.7.dist-info/RECORD +347 -0
  151. examples/__init__.py +7 -7
  152. tests/__init__.py +7 -7
  153. tests/advanced_tools_example.py +217 -275
  154. tests/authenticated_proxy_example.py +110 -106
  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 -0
  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 +77 -0
  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 -0
  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/scrapy.cfg +11 -11
  192. tests/optimized_performance_test.py +211 -211
  193. tests/performance_comparison.py +244 -244
  194. tests/queue_blocking_test.py +113 -113
  195. tests/queue_test.py +89 -89
  196. tests/redis_key_validation_demo.py +130 -130
  197. tests/request_params_example.py +150 -150
  198. tests/response_improvements_example.py +144 -144
  199. tests/scrapy_comparison/ofweek_scrapy.py +138 -138
  200. tests/scrapy_comparison/scrapy_test.py +133 -133
  201. tests/simple_cli_test.py +55 -0
  202. tests/simple_command_test.py +119 -119
  203. tests/simple_crawlo_test.py +126 -126
  204. tests/simple_follow_test.py +38 -38
  205. tests/simple_log_test2.py +137 -137
  206. tests/simple_optimization_test.py +128 -128
  207. tests/simple_queue_type_test.py +41 -41
  208. tests/simple_response_selector_test.py +94 -94
  209. tests/simple_selector_helper_test.py +154 -154
  210. tests/simple_selector_test.py +207 -207
  211. tests/simple_spider_test.py +49 -49
  212. tests/simple_url_test.py +73 -73
  213. tests/simulate_mysql_update_test.py +140 -0
  214. tests/spider_log_timing_test.py +177 -177
  215. tests/test_advanced_tools.py +148 -148
  216. tests/test_all_commands.py +230 -230
  217. tests/test_all_pipeline_fingerprints.py +133 -133
  218. tests/test_all_redis_key_configs.py +145 -145
  219. tests/test_asyncmy_usage.py +57 -0
  220. tests/test_batch_processor.py +178 -178
  221. tests/test_cleaners.py +54 -54
  222. tests/test_cli_arguments.py +119 -0
  223. tests/test_component_factory.py +174 -174
  224. tests/test_config_consistency.py +80 -80
  225. tests/test_config_merge.py +152 -152
  226. tests/test_config_validator.py +182 -182
  227. tests/test_controlled_spider_mixin.py +79 -79
  228. tests/test_crawler_process_import.py +38 -38
  229. tests/test_crawler_process_spider_modules.py +47 -47
  230. tests/test_crawlo_proxy_integration.py +114 -108
  231. tests/test_date_tools.py +123 -123
  232. tests/test_dedup_fix.py +220 -220
  233. tests/test_dedup_pipeline_consistency.py +124 -124
  234. tests/test_default_header_middleware.py +313 -313
  235. tests/test_distributed.py +65 -65
  236. tests/test_double_crawlo_fix.py +204 -204
  237. tests/test_double_crawlo_fix_simple.py +124 -124
  238. tests/test_download_delay_middleware.py +221 -221
  239. tests/test_downloader_proxy_compatibility.py +272 -268
  240. tests/test_edge_cases.py +305 -305
  241. tests/test_encoding_core.py +56 -56
  242. tests/test_encoding_detection.py +126 -126
  243. tests/test_enhanced_error_handler.py +270 -270
  244. tests/test_enhanced_error_handler_comprehensive.py +245 -245
  245. tests/test_error_handler_compatibility.py +112 -112
  246. tests/test_factories.py +252 -252
  247. tests/test_factory_compatibility.py +196 -196
  248. tests/test_final_validation.py +153 -153
  249. tests/test_fingerprint_consistency.py +135 -135
  250. tests/test_fingerprint_simple.py +51 -51
  251. tests/test_get_component_logger.py +83 -83
  252. tests/test_hash_performance.py +99 -99
  253. tests/test_integration.py +169 -169
  254. tests/test_item_dedup_redis_key.py +122 -122
  255. tests/test_large_scale_helper.py +235 -235
  256. tests/test_logging_enhancements.py +374 -374
  257. tests/test_logging_final.py +184 -184
  258. tests/test_logging_integration.py +312 -312
  259. tests/test_logging_system.py +282 -282
  260. tests/test_middleware_debug.py +141 -141
  261. tests/test_mode_consistency.py +51 -51
  262. tests/test_multi_directory.py +67 -67
  263. tests/test_multiple_spider_modules.py +80 -80
  264. tests/test_mysql_pipeline_config.py +165 -0
  265. tests/test_mysql_pipeline_error.py +99 -0
  266. tests/test_mysql_pipeline_init_log.py +83 -0
  267. tests/test_mysql_pipeline_integration.py +133 -0
  268. tests/test_mysql_pipeline_refactor.py +144 -0
  269. tests/test_mysql_pipeline_refactor_simple.py +86 -0
  270. tests/test_mysql_pipeline_robustness.py +196 -0
  271. tests/test_mysql_pipeline_types.py +89 -0
  272. tests/test_mysql_update_columns.py +94 -0
  273. tests/test_offsite_middleware.py +244 -244
  274. tests/test_offsite_middleware_simple.py +203 -203
  275. tests/test_optimized_selector_naming.py +100 -100
  276. tests/test_parsel.py +29 -29
  277. tests/test_performance.py +327 -327
  278. tests/test_performance_monitor.py +115 -115
  279. tests/test_pipeline_fingerprint_consistency.py +86 -86
  280. tests/test_priority_behavior.py +211 -211
  281. tests/test_priority_consistency.py +151 -151
  282. tests/test_priority_consistency_fixed.py +249 -249
  283. tests/test_proxy_health_check.py +32 -32
  284. tests/test_proxy_middleware.py +217 -121
  285. tests/test_proxy_middleware_enhanced.py +212 -216
  286. tests/test_proxy_middleware_integration.py +142 -137
  287. tests/test_proxy_middleware_refactored.py +207 -184
  288. tests/test_proxy_only.py +84 -0
  289. tests/test_proxy_providers.py +56 -56
  290. tests/test_proxy_stats.py +19 -19
  291. tests/test_proxy_strategies.py +59 -59
  292. tests/test_proxy_with_downloader.py +153 -0
  293. tests/test_queue_empty_check.py +41 -41
  294. tests/test_queue_manager_double_crawlo.py +173 -173
  295. tests/test_queue_manager_redis_key.py +179 -179
  296. tests/test_queue_naming.py +154 -154
  297. tests/test_queue_type.py +106 -106
  298. tests/test_queue_type_redis_config_consistency.py +130 -130
  299. tests/test_random_headers_default.py +322 -322
  300. tests/test_random_headers_necessity.py +308 -308
  301. tests/test_random_user_agent.py +72 -72
  302. tests/test_redis_config.py +28 -28
  303. tests/test_redis_connection_pool.py +294 -294
  304. tests/test_redis_key_naming.py +181 -181
  305. tests/test_redis_key_validator.py +123 -123
  306. tests/test_redis_queue.py +224 -224
  307. tests/test_redis_queue_name_fix.py +175 -175
  308. tests/test_redis_queue_type_fallback.py +129 -129
  309. tests/test_request_ignore_middleware.py +182 -182
  310. tests/test_request_params.py +111 -111
  311. tests/test_request_serialization.py +70 -70
  312. tests/test_response_code_middleware.py +349 -349
  313. tests/test_response_filter_middleware.py +427 -427
  314. tests/test_response_follow.py +104 -104
  315. tests/test_response_improvements.py +152 -152
  316. tests/test_response_selector_methods.py +92 -92
  317. tests/test_response_url_methods.py +70 -70
  318. tests/test_response_urljoin.py +86 -86
  319. tests/test_retry_middleware.py +333 -333
  320. tests/test_retry_middleware_realistic.py +273 -273
  321. tests/test_scheduler.py +252 -252
  322. tests/test_scheduler_config_update.py +133 -133
  323. tests/test_scrapy_style_encoding.py +112 -112
  324. tests/test_selector_helper.py +100 -100
  325. tests/test_selector_optimizations.py +146 -146
  326. tests/test_simple_response.py +61 -61
  327. tests/test_spider_loader.py +49 -49
  328. tests/test_spider_loader_comprehensive.py +69 -69
  329. tests/test_spider_modules.py +84 -84
  330. tests/test_spiders/test_spider.py +9 -9
  331. tests/test_telecom_spider_redis_key.py +205 -205
  332. tests/test_template_content.py +87 -87
  333. tests/test_template_redis_key.py +134 -134
  334. tests/test_tools.py +159 -159
  335. tests/test_user_agent_randomness.py +176 -176
  336. tests/test_user_agents.py +96 -96
  337. tests/untested_features_report.md +138 -138
  338. tests/verify_debug.py +51 -51
  339. tests/verify_distributed.py +117 -117
  340. tests/verify_log_fix.py +111 -111
  341. tests/verify_mysql_warnings.py +110 -0
  342. crawlo/logging/async_handler.py +0 -181
  343. crawlo/logging/monitor.py +0 -153
  344. crawlo/logging/sampler.py +0 -167
  345. crawlo/middleware/simple_proxy.py +0 -65
  346. crawlo/tools/authenticated_proxy.py +0 -241
  347. crawlo/tools/data_formatter.py +0 -226
  348. crawlo/tools/data_validator.py +0 -181
  349. crawlo/tools/encoding_converter.py +0 -127
  350. crawlo/tools/network_diagnostic.py +0 -365
  351. crawlo/tools/request_tools.py +0 -83
  352. crawlo/tools/retry_mechanism.py +0 -224
  353. crawlo/utils/env_config.py +0 -143
  354. crawlo/utils/large_scale_config.py +0 -287
  355. crawlo/utils/system.py +0 -11
  356. crawlo/utils/tools.py +0 -5
  357. crawlo-1.4.5.dist-info/METADATA +0 -329
  358. crawlo-1.4.5.dist-info/RECORD +0 -347
  359. tests/env_config_example.py +0 -134
  360. tests/ofweek_scrapy/ofweek_scrapy/spiders/ofweek_spider.py +0 -162
  361. tests/test_authenticated_proxy.py +0 -142
  362. tests/test_comprehensive.py +0 -147
  363. tests/test_dynamic_downloaders_proxy.py +0 -125
  364. tests/test_dynamic_proxy.py +0 -93
  365. tests/test_dynamic_proxy_config.py +0 -147
  366. tests/test_dynamic_proxy_real.py +0 -110
  367. tests/test_env_config.py +0 -122
  368. tests/test_framework_env_usage.py +0 -104
  369. tests/test_large_scale_config.py +0 -113
  370. tests/test_proxy_api.py +0 -265
  371. tests/test_real_scenario_proxy.py +0 -196
  372. tests/tools_example.py +0 -261
  373. {crawlo-1.4.5.dist-info → crawlo-1.4.7.dist-info}/WHEEL +0 -0
  374. {crawlo-1.4.5.dist-info → crawlo-1.4.7.dist-info}/entry_points.txt +0 -0
  375. {crawlo-1.4.5.dist-info → crawlo-1.4.7.dist-info}/top_level.txt +0 -0
@@ -1,287 +0,0 @@
1
- #!/usr/bin/env python3
2
- # -*- coding: utf-8 -*-
3
- """
4
- 大规模爬虫配置助手
5
- 提供针对上万请求场景的优化配置
6
- """
7
- from typing import Dict, Any
8
-
9
- from crawlo.utils.queue_helper import QueueHelper
10
-
11
-
12
- class LargeScaleConfig:
13
- """大规模爬虫配置类"""
14
-
15
- @staticmethod
16
- def conservative_config(concurrency: int = 8) -> Dict[str, Any]:
17
- """
18
- 保守配置 - 适用于资源有限的环境
19
-
20
- 特点:
21
- - 较小的队列容量
22
- - 较低的并发数
23
- - 较长的延迟
24
- """
25
- config = QueueHelper.use_redis_queue(
26
- queue_name="crawlo:conservative",
27
- max_retries=3,
28
- timeout=300
29
- )
30
-
31
- config.update({
32
- # 并发控制
33
- 'CONCURRENCY': concurrency,
34
- 'SCHEDULER_MAX_QUEUE_SIZE': concurrency * 10, # 队列容量为并发数的10倍
35
- 'MAX_RUNNING_SPIDERS': 1,
36
-
37
- # 请求控制
38
- 'DOWNLOAD_DELAY': 0.2,
39
- 'RANDOMNESS': True,
40
- 'RANDOM_RANGE': (0.8, 1.5),
41
-
42
- # 内存控制
43
- 'DOWNLOAD_MAXSIZE': 5 * 1024 * 1024, # 5MB
44
- 'CONNECTION_POOL_LIMIT': concurrency * 2,
45
-
46
- # 重试策略
47
- 'MAX_RETRY_TIMES': 2,
48
-
49
- # 使用增强引擎
50
- 'ENGINE_CLASS': 'crawlo.core.engine.Engine'
51
- })
52
-
53
- return config
54
-
55
- @staticmethod
56
- def balanced_config(concurrency: int = 16) -> Dict[str, Any]:
57
- """
58
- 平衡配置 - 适用于一般生产环境
59
-
60
- 特点:
61
- - 中等的队列容量
62
- - 平衡的并发数
63
- - 适中的延迟
64
- """
65
- config = QueueHelper.use_redis_queue(
66
- queue_name="crawlo:balanced",
67
- max_retries=5,
68
- timeout=600
69
- )
70
-
71
- config.update({
72
- # 并发控制
73
- 'CONCURRENCY': concurrency,
74
- 'SCHEDULER_MAX_QUEUE_SIZE': concurrency * 15,
75
- 'MAX_RUNNING_SPIDERS': 2,
76
-
77
- # 请求控制
78
- 'DOWNLOAD_DELAY': 0.1,
79
- 'RANDOMNESS': True,
80
- 'RANDOM_RANGE': (0.5, 1.2),
81
-
82
- # 内存控制
83
- 'DOWNLOAD_MAXSIZE': 10 * 1024 * 1024, # 10MB
84
- 'CONNECTION_POOL_LIMIT': concurrency * 3,
85
-
86
- # 重试策略
87
- 'MAX_RETRY_TIMES': 3,
88
-
89
- # 使用增强引擎
90
- 'ENGINE_CLASS': 'crawlo.core.engine.Engine'
91
- })
92
-
93
- return config
94
-
95
- @staticmethod
96
- def aggressive_config(concurrency: int = 32) -> Dict[str, Any]:
97
- """
98
- 激进配置 - 适用于高性能环境
99
-
100
- 特点:
101
- - 大的队列容量
102
- - 高并发数
103
- - 较短的延迟
104
- """
105
- config = QueueHelper.use_redis_queue(
106
- queue_name="crawlo:aggressive",
107
- max_retries=10,
108
- timeout=900
109
- )
110
-
111
- config.update({
112
- # 并发控制
113
- 'CONCURRENCY': concurrency,
114
- 'SCHEDULER_MAX_QUEUE_SIZE': concurrency * 20,
115
- 'MAX_RUNNING_SPIDERS': 3,
116
-
117
- # 请求控制
118
- 'DOWNLOAD_DELAY': 0.05,
119
- 'RANDOMNESS': True,
120
- 'RANDOM_RANGE': (0.3, 1.0),
121
-
122
- # 内存控制
123
- 'DOWNLOAD_MAXSIZE': 20 * 1024 * 1024, # 20MB
124
- 'CONNECTION_POOL_LIMIT': concurrency * 4,
125
-
126
- # 重试策略
127
- 'MAX_RETRY_TIMES': 5,
128
-
129
- # 使用增强引擎
130
- 'ENGINE_CLASS': 'crawlo.core.engine.Engine'
131
- })
132
-
133
- return config
134
-
135
- @staticmethod
136
- def memory_optimized_config(concurrency: int = 12) -> Dict[str, Any]:
137
- """
138
- 内存优化配置 - 适用于大规模但内存受限的场景
139
-
140
- 特点:
141
- - 小队列,快速流转
142
- - 严格的内存控制
143
- - 使用Redis减少内存压力
144
- """
145
- config = QueueHelper.use_redis_queue(
146
- queue_name="crawlo:memory_optimized",
147
- max_retries=3,
148
- timeout=300
149
- )
150
-
151
- config.update({
152
- # 并发控制
153
- 'CONCURRENCY': concurrency,
154
- 'SCHEDULER_MAX_QUEUE_SIZE': concurrency * 5, # 小队列
155
- 'MAX_RUNNING_SPIDERS': 1,
156
-
157
- # 请求控制
158
- 'DOWNLOAD_DELAY': 0.1,
159
- 'RANDOMNESS': False, # 减少随机性降低内存使用
160
-
161
- # 严格的内存控制
162
- 'DOWNLOAD_MAXSIZE': 2 * 1024 * 1024, # 2MB
163
- 'DOWNLOAD_WARN_SIZE': 512 * 1024, # 512KB
164
- 'CONNECTION_POOL_LIMIT': concurrency,
165
-
166
- # 重试策略
167
- 'MAX_RETRY_TIMES': 2,
168
-
169
- # 使用增强引擎
170
- 'ENGINE_CLASS': 'crawlo.core.engine.Engine'
171
- })
172
-
173
- return config
174
-
175
-
176
- def apply_large_scale_config(settings_dict: Dict[str, Any], config_type: str = "balanced", concurrency: int = None):
177
- """
178
- 应用大规模配置
179
-
180
- Args:
181
- settings_dict: 设置字典
182
- config_type: 配置类型 ("conservative", "balanced", "aggressive", "memory_optimized")
183
- concurrency: 并发数(可选,不指定则使用默认值)
184
- """
185
- config_map = {
186
- "conservative": LargeScaleConfig.conservative_config,
187
- "balanced": LargeScaleConfig.balanced_config,
188
- "aggressive": LargeScaleConfig.aggressive_config,
189
- "memory_optimized": LargeScaleConfig.memory_optimized_config
190
- }
191
-
192
- if config_type not in config_map:
193
- raise ValueError(f"不支持的配置类型: {config_type}")
194
-
195
- if concurrency:
196
- config = config_map[config_type](concurrency)
197
- else:
198
- config = config_map[config_type]()
199
-
200
- settings_dict.update(config)
201
-
202
- return config
203
-
204
-
205
- # 使用示例和说明
206
- USAGE_GUIDE = """
207
- # 大规模爬虫配置使用指南
208
-
209
- ## 1. 选择合适的配置类型
210
-
211
- ### Conservative (保守型)
212
- - 适用场景:资源受限、网络不稳定的环境
213
- - 并发数:8 (默认)
214
- - 队列容量:80
215
- - 延迟:200ms
216
- - 使用场景:个人开发、小规模爬取
217
-
218
- ### Balanced (平衡型)
219
- - 适用场景:一般生产环境
220
- - 并发数:16 (默认)
221
- - 队列容量:240
222
- - 延迟:100ms
223
- - 使用场景:中小企业生产环境
224
-
225
- ### Aggressive (激进型)
226
- - 适用场景:高性能服务器、对速度要求高
227
- - 并发数:32 (默认)
228
- - 队列容量:640
229
- - 延迟:50ms
230
- - 使用场景:大公司、高并发需求
231
-
232
- ### Memory Optimized (内存优化型)
233
- - 适用场景:大规模爬取但内存受限
234
- - 并发数:12 (默认)
235
- - 队列容量:60 (小队列快速流转)
236
- - 延迟:100ms
237
- - 使用场景:处理数万/数十万请求但内存有限
238
-
239
- ## 2. 使用方法
240
-
241
- ```python
242
- # 方法1:在 settings.py 中直接配置
243
- from crawlo.utils.large_scale_config import apply_large_scale_config
244
-
245
- # 使用平衡配置,16并发
246
- apply_large_scale_config(locals(), "balanced", 16)
247
-
248
- # 方法2:在爬虫代码中动态配置
249
- from crawlo.crawler import CrawlerProcess
250
- from crawlo.utils.large_scale_config import LargeScaleConfig
251
-
252
- process = CrawlerProcess()
253
- config = LargeScaleConfig.memory_optimized_config(20) # 20并发的内存优化配置
254
- process.settings.update(config)
255
-
256
- # 方法3:自定义配置
257
- config = LargeScaleConfig.balanced_config(24) # 24并发
258
- config['DOWNLOAD_DELAY'] = 0.05 # 自定义延迟
259
- process.settings.update(config)
260
- ```
261
-
262
- ## 3. 针对不同场景的建议
263
-
264
- ### 处理5万+请求
265
- ```python
266
- # 推荐内存优化配置
267
- apply_large_scale_config(locals(), "memory_optimized", 20)
268
- ```
269
-
270
- ### 高速爬取但服务器性能好
271
- ```python
272
- # 推荐激进配置
273
- apply_large_scale_config(locals(), "aggressive", 40)
274
- ```
275
-
276
- ### 资源受限但要稳定运行
277
- ```python
278
- # 推荐保守配置
279
- apply_large_scale_config(locals(), "conservative", 6)
280
- ```
281
-
282
- ### 平衡性能和稳定性
283
- ```python
284
- # 推荐平衡配置
285
- apply_large_scale_config(locals(), "balanced", 18)
286
- ```
287
- """
crawlo/utils/system.py DELETED
@@ -1,11 +0,0 @@
1
- #!/usr/bin/python
2
- # -*- coding:UTF-8 -*-
3
- import platform
4
-
5
- system_name = platform.system().lower()
6
- if system_name == 'windows':
7
- import asyncio
8
- asyncio.set_event_loop_policy(
9
- asyncio.WindowsSelectorEventLoopPolicy()
10
- )
11
-
crawlo/utils/tools.py DELETED
@@ -1,5 +0,0 @@
1
- def custom_extractor_proxy(data: dict, key: str='proxy') -> dict | str | None:
2
- """只负责从 API 返回数据中提取代理部分"""
3
- if data.get("status") == 0:
4
- return data.get(key) # 返回 {"http": "...", "https": "..."} 整个字典
5
- return None
@@ -1,329 +0,0 @@
1
- Metadata-Version: 2.4
2
- Name: crawlo
3
- Version: 1.4.5
4
- Summary: Crawlo 是一款基于异步IO的高性能Python爬虫框架,支持分布式抓取。
5
- Home-page: https://github.com/crawl-coder/Crawlo.git
6
- Author: crawl-coder
7
- Author-email: crawlo@qq.com
8
- License: MIT
9
- Classifier: Programming Language :: Python :: 3
10
- Classifier: License :: OSI Approved :: MIT License
11
- Classifier: Operating System :: OS Independent
12
- Requires-Python: >=3.6
13
- Description-Content-Type: text/markdown
14
- Requires-Dist: aiohttp>=3.12.14
15
- Requires-Dist: aiomysql>=0.2.0
16
- Requires-Dist: aioredis>=2.0.1
17
- Requires-Dist: asyncmy>=0.2.10
18
- Requires-Dist: cssselect>=1.2.0
19
- Requires-Dist: dateparser>=1.2.2
20
- Requires-Dist: httpx[http2]>=0.27.0
21
- Requires-Dist: curl-cffi>=0.13.0
22
- Requires-Dist: lxml>=5.2.1
23
- Requires-Dist: motor>=3.7.0
24
- Requires-Dist: parsel>=1.9.1
25
- Requires-Dist: pydantic>=2.11.7
26
- Requires-Dist: pymongo>=4.11
27
- Requires-Dist: PyMySQL>=1.1.1
28
- Requires-Dist: python-dateutil>=2.9.0.post0
29
- Requires-Dist: redis>=6.2.0
30
- Requires-Dist: requests>=2.32.4
31
- Requires-Dist: six>=1.17.0
32
- Requires-Dist: ujson>=5.9.0
33
- Requires-Dist: urllib3>=2.5.0
34
- Requires-Dist: w3lib>=2.1.2
35
- Requires-Dist: rich>=14.1.0
36
- Requires-Dist: astor>=0.8.1
37
- Requires-Dist: watchdog>=6.0.0
38
- Provides-Extra: render
39
- Requires-Dist: webdriver-manager>=4.0.0; extra == "render"
40
- Requires-Dist: playwright; extra == "render"
41
- Requires-Dist: selenium>=3.141.0; extra == "render"
42
- Provides-Extra: all
43
- Requires-Dist: bitarray>=1.5.3; extra == "all"
44
- Requires-Dist: PyExecJS>=1.5.1; extra == "all"
45
- Requires-Dist: pymongo>=3.10.1; extra == "all"
46
- Requires-Dist: redis-py-cluster>=2.1.0; extra == "all"
47
- Requires-Dist: webdriver-manager>=4.0.0; extra == "all"
48
- Requires-Dist: playwright; extra == "all"
49
- Requires-Dist: selenium>=3.141.0; extra == "all"
50
-
51
- # Crawlo 爬虫框架
52
-
53
- Crawlo 是一个高性能、可扩展的 Python 爬虫框架,支持单机和分布式部署。
54
-
55
- ## 特性
56
-
57
- - 高性能异步爬取
58
- - 支持多种下载器 (aiohttp, httpx, curl-cffi)
59
- - 内置数据清洗和验证
60
- - 分布式爬取支持
61
- - 灵活的中间件系统
62
- - 强大的配置管理系统
63
- - 详细的日志记录和监控
64
- - Windows 和 Linux 兼容
65
-
66
- ## 安装
67
-
68
- ```bash
69
- pip install crawlo
70
- ```
71
-
72
- 或者从源码安装:
73
-
74
- ```bash
75
- git clone git@github.com:crawl-coder/Crawlo.git
76
- cd crawlo
77
- pip install -r requirements.txt
78
- pip install .
79
- ```
80
-
81
- ## 快速开始
82
-
83
- ```python
84
- from crawlo import Spider
85
-
86
- class MySpider(Spider):
87
- name = 'example'
88
-
89
- def parse(self, response):
90
- # 解析逻辑
91
- pass
92
-
93
- # 运行爬虫
94
- # crawlo run example
95
- ```
96
-
97
- ## Response 对象功能
98
-
99
- Crawlo 框架对 Response 对象进行了增强,提供了更多便捷方法:
100
-
101
- ### URL 处理
102
-
103
- 使用 Response 对象封装的 URL 处理方法可以方便地处理各种 URL 操作,无需手动导入 `urllib.parse` 中的函数:
104
-
105
- ```python
106
- class MySpider(Spider):
107
- def parse(self, response):
108
- # 1. 处理相对URL和绝对URL
109
- absolute_url = response.urljoin('/relative/path')
110
-
111
- # 2. 解析URL组件
112
- parsed = response.urlparse() # 解析当前响应URL
113
- scheme = parsed.scheme
114
- domain = parsed.netloc
115
- path = parsed.path
116
-
117
- # 3. 解析查询参数
118
- query_params = response.parse_qs() # 解析当前URL的查询参数
119
-
120
- # 4. 编码查询参数
121
- new_query = response.urlencode({'key': 'value', 'name': '测试'})
122
-
123
- # 5. URL编码/解码
124
- encoded = response.quote('hello world 你好')
125
- decoded = response.unquote(encoded)
126
-
127
- # 6. 移除URL片段
128
- url_without_fragment, fragment = response.urldefrag('http://example.com/path#section')
129
-
130
- yield Request(url=absolute_url, callback=self.parse_detail)
131
- ```
132
-
133
- ### 编码检测优化
134
-
135
- Crawlo 框架参考 Scrapy 的设计模式对 Response 对象的编码检测功能进行了优化,提供了更准确和可靠的编码检测:
136
-
137
- ```python
138
- class MySpider(Spider):
139
- def parse(self, response):
140
- # 自动检测响应编码
141
- encoding = response.encoding
142
-
143
- # 获取声明的编码(Request编码 > BOM > HTTP头部 > HTML meta标签)
144
- declared_encoding = response._declared_encoding()
145
-
146
- # 响应文本已自动使用正确的编码解码
147
- text = response.text
148
-
149
- # 处理解码后的内容
150
- # ...
151
- ```
152
-
153
- 编码检测优先级:
154
- 1. Request 中指定的编码
155
- 2. BOM 字节顺序标记
156
- 3. HTTP Content-Type 头部
157
- 4. HTML meta 标签声明
158
- 5. 内容自动检测
159
- 6. 默认编码 (utf-8)
160
-
161
- ### 选择器方法优化
162
-
163
- Crawlo 框架对 Response 对象的选择器方法进行了优化,提供了更便捷的数据提取功能,方法命名更加直观和统一:
164
-
165
- ```python
166
- class MySpider(Spider):
167
- def parse(self, response):
168
- # 1. 提取单个元素文本(支持CSS和XPath)
169
- title = response.extract_text('title') # CSS选择器
170
- title = response.extract_text('//title') # XPath选择器
171
-
172
- # 2. 提取多个元素文本
173
- paragraphs = response.extract_texts('.content p') # CSS选择器
174
- paragraphs = response.extract_texts('//div[@class="content"]//p') # XPath选择器
175
-
176
- # 3. 提取单个元素属性
177
- link_href = response.extract_attr('a', 'href') # CSS选择器
178
- link_href = response.extract_attr('//a[@class="link"]', 'href') # XPath选择器
179
-
180
- # 4. 提取多个元素属性
181
- all_links = response.extract_attrs('a', 'href') # CSS选择器
182
- all_links = response.extract_attrs('//a[@class="link"]', 'href') # XPath选择器
183
-
184
- yield {
185
- 'title': title,
186
- 'paragraphs': paragraphs,
187
- 'links': all_links
188
- }
189
- ```
190
-
191
- 所有选择器方法都采用了简洁直观的命名风格,便于记忆和使用。
192
-
193
- ### 工具模块
194
-
195
- Crawlo 框架提供了丰富的工具模块,用于处理各种常见任务。选择器相关的辅助函数现在位于 `crawlo.utils.selector_helper` 模块中:
196
-
197
- ```python
198
- from crawlo.utils import (
199
- extract_text,
200
- extract_texts,
201
- extract_attr,
202
- extract_attrs,
203
- is_xpath
204
- )
205
-
206
- # 在自定义代码中使用这些工具函数
207
- title_elements = response.css('title')
208
- title_text = extract_text(title_elements)
209
-
210
- li_elements = response.css('.list li')
211
- li_texts = extract_texts(li_elements)
212
-
213
- link_elements = response.css('.link')
214
- link_href = extract_attr(link_elements, 'href')
215
-
216
- all_links = response.css('a')
217
- all_hrefs = extract_attrs(all_links, 'href')
218
- ```
219
-
220
- ## 日志系统
221
-
222
- Crawlo 拥有一个功能强大的日志系统,支持多种配置选项:
223
-
224
- ### 基本配置
225
-
226
- ```python
227
- from crawlo.logging import configure_logging, get_logger
228
-
229
- # 配置日志系统
230
- configure_logging(
231
- LOG_LEVEL='INFO',
232
- LOG_FILE='logs/app.log',
233
- LOG_MAX_BYTES=10*1024*1024, # 10MB
234
- LOG_BACKUP_COUNT=5
235
- )
236
-
237
- # 获取logger
238
- logger = get_logger('my_module')
239
- logger.info('这是一条日志消息')
240
- ```
241
-
242
- ### 高级配置
243
-
244
- ```python
245
- # 分别配置控制台和文件日志级别
246
- configure_logging(
247
- LOG_LEVEL='INFO',
248
- LOG_CONSOLE_LEVEL='WARNING', # 控制台只显示WARNING及以上级别
249
- LOG_FILE_LEVEL='DEBUG', # 文件记录DEBUG及以上级别
250
- LOG_FILE='logs/app.log',
251
- LOG_INCLUDE_THREAD_ID=True, # 包含线程ID
252
- LOG_INCLUDE_PROCESS_ID=True # 包含进程ID
253
- )
254
-
255
- # 模块特定日志级别
256
- configure_logging(
257
- LOG_LEVEL='WARNING',
258
- LOG_LEVELS={
259
- 'my_module.debug': 'DEBUG',
260
- 'my_module.info': 'INFO'
261
- }
262
- )
263
- ```
264
-
265
- ### 性能监控
266
-
267
- ```python
268
- from crawlo.logging import get_monitor
269
-
270
- # 启用日志性能监控
271
- monitor = get_monitor()
272
- monitor.enable_monitoring()
273
-
274
- # 获取性能报告
275
- report = monitor.get_performance_report()
276
- print(report)
277
- ```
278
-
279
- ### 日志采样
280
-
281
- ```python
282
- from crawlo.logging import get_sampler
283
-
284
- # 设置采样率(只记录30%的日志)
285
- sampler = get_sampler()
286
- sampler.set_sample_rate('my_module', 0.3)
287
-
288
- # 设置速率限制(每秒最多100条日志)
289
- sampler.set_rate_limit('my_module', 100)
290
- ```
291
-
292
- ## Windows 兼容性说明
293
-
294
- 在 Windows 系统上使用日志轮转功能时,可能会遇到文件锁定问题。为了解决这个问题,建议安装 `concurrent-log-handler` 库:
295
-
296
- ```bash
297
- pip install concurrent-log-handler
298
- ```
299
-
300
- Crawlo 框架会自动检测并使用这个库来提供更好的 Windows 兼容性。
301
-
302
- 如果未安装 `concurrent-log-handler`,在 Windows 上运行时可能会出现以下错误:
303
- ```
304
- PermissionError: [WinError 32] 另一个程序正在使用此文件,进程无法访问。
305
- ```
306
-
307
- ## 爬虫自动发现
308
-
309
- Crawlo 框架支持通过 `SPIDER_MODULES` 配置自动发现和加载爬虫,类似于 Scrapy 的机制:
310
-
311
- ```python
312
- # settings.py
313
- SPIDER_MODULES = [
314
- 'myproject.spiders',
315
- 'myproject.more_spiders',
316
- ]
317
-
318
- SPIDER_LOADER_WARN_ONLY = True # 加载错误时只警告不报错
319
- ```
320
-
321
- 框架会自动扫描配置的模块目录,发现并注册其中的爬虫类。
322
-
323
- ## 文档
324
-
325
- 请查看 [文档](https://your-docs-url.com) 获取更多信息。
326
-
327
- ## 许可证
328
-
329
- MIT