crawlo 1.3.4__py3-none-any.whl → 1.3.6__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 (289) hide show
  1. crawlo/__init__.py +87 -87
  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 +151 -151
  7. crawlo/commands/help.py +138 -138
  8. crawlo/commands/list.py +155 -155
  9. crawlo/commands/run.py +341 -341
  10. crawlo/commands/startproject.py +436 -436
  11. crawlo/commands/stats.py +187 -187
  12. crawlo/commands/utils.py +196 -196
  13. crawlo/config.py +312 -312
  14. crawlo/config_validator.py +277 -277
  15. crawlo/core/__init__.py +45 -45
  16. crawlo/core/engine.py +439 -439
  17. crawlo/core/processor.py +40 -40
  18. crawlo/core/scheduler.py +257 -257
  19. crawlo/crawler.py +638 -638
  20. crawlo/data/__init__.py +5 -5
  21. crawlo/data/user_agents.py +194 -194
  22. crawlo/downloader/__init__.py +273 -273
  23. crawlo/downloader/aiohttp_downloader.py +228 -228
  24. crawlo/downloader/cffi_downloader.py +245 -245
  25. crawlo/downloader/httpx_downloader.py +259 -259
  26. crawlo/downloader/hybrid_downloader.py +212 -212
  27. crawlo/downloader/playwright_downloader.py +402 -402
  28. crawlo/downloader/selenium_downloader.py +472 -472
  29. crawlo/event.py +11 -11
  30. crawlo/exceptions.py +81 -81
  31. crawlo/extension/__init__.py +39 -39
  32. crawlo/extension/health_check.py +141 -141
  33. crawlo/extension/log_interval.py +57 -57
  34. crawlo/extension/log_stats.py +81 -81
  35. crawlo/extension/logging_extension.py +61 -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 +103 -103
  42. crawlo/factories/registry.py +84 -84
  43. crawlo/filters/__init__.py +154 -154
  44. crawlo/filters/aioredis_filter.py +257 -257
  45. crawlo/filters/memory_filter.py +269 -269
  46. crawlo/framework.py +292 -291
  47. crawlo/initialization/__init__.py +39 -39
  48. crawlo/initialization/built_in.py +425 -425
  49. crawlo/initialization/context.py +141 -141
  50. crawlo/initialization/core.py +193 -193
  51. crawlo/initialization/phases.py +148 -148
  52. crawlo/initialization/registry.py +145 -145
  53. crawlo/items/__init__.py +23 -23
  54. crawlo/items/base.py +23 -23
  55. crawlo/items/fields.py +52 -52
  56. crawlo/items/items.py +104 -104
  57. crawlo/logging/__init__.py +37 -37
  58. crawlo/logging/config.py +96 -96
  59. crawlo/logging/factory.py +128 -128
  60. crawlo/logging/manager.py +111 -111
  61. crawlo/middleware/__init__.py +21 -21
  62. crawlo/middleware/default_header.py +132 -132
  63. crawlo/middleware/download_delay.py +104 -104
  64. crawlo/middleware/middleware_manager.py +135 -135
  65. crawlo/middleware/offsite.py +123 -123
  66. crawlo/middleware/proxy.py +386 -386
  67. crawlo/middleware/request_ignore.py +86 -86
  68. crawlo/middleware/response_code.py +163 -163
  69. crawlo/middleware/response_filter.py +136 -136
  70. crawlo/middleware/retry.py +124 -124
  71. crawlo/middleware/simple_proxy.py +65 -65
  72. crawlo/mode_manager.py +212 -212
  73. crawlo/network/__init__.py +21 -21
  74. crawlo/network/request.py +379 -379
  75. crawlo/network/response.py +359 -359
  76. crawlo/pipelines/__init__.py +21 -21
  77. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  78. crawlo/pipelines/console_pipeline.py +39 -39
  79. crawlo/pipelines/csv_pipeline.py +316 -316
  80. crawlo/pipelines/database_dedup_pipeline.py +222 -222
  81. crawlo/pipelines/json_pipeline.py +218 -218
  82. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  83. crawlo/pipelines/mongo_pipeline.py +131 -131
  84. crawlo/pipelines/mysql_pipeline.py +325 -318
  85. crawlo/pipelines/pipeline_manager.py +76 -76
  86. crawlo/pipelines/redis_dedup_pipeline.py +166 -166
  87. crawlo/project.py +327 -327
  88. crawlo/queue/pqueue.py +42 -42
  89. crawlo/queue/queue_manager.py +503 -503
  90. crawlo/queue/redis_priority_queue.py +326 -326
  91. crawlo/settings/__init__.py +7 -7
  92. crawlo/settings/default_settings.py +321 -321
  93. crawlo/settings/setting_manager.py +214 -214
  94. crawlo/spider/__init__.py +657 -657
  95. crawlo/stats_collector.py +73 -73
  96. crawlo/subscriber.py +129 -129
  97. crawlo/task_manager.py +138 -138
  98. crawlo/templates/crawlo.cfg.tmpl +10 -10
  99. crawlo/templates/project/__init__.py.tmpl +3 -3
  100. crawlo/templates/project/items.py.tmpl +17 -17
  101. crawlo/templates/project/middlewares.py.tmpl +118 -118
  102. crawlo/templates/project/pipelines.py.tmpl +96 -96
  103. crawlo/templates/project/settings.py.tmpl +167 -167
  104. crawlo/templates/project/settings_distributed.py.tmpl +166 -166
  105. crawlo/templates/project/settings_gentle.py.tmpl +166 -166
  106. crawlo/templates/project/settings_high_performance.py.tmpl +167 -167
  107. crawlo/templates/project/settings_minimal.py.tmpl +65 -65
  108. crawlo/templates/project/settings_simple.py.tmpl +164 -164
  109. crawlo/templates/project/spiders/__init__.py.tmpl +9 -9
  110. crawlo/templates/run.py.tmpl +34 -34
  111. crawlo/templates/spider/spider.py.tmpl +143 -143
  112. crawlo/templates/spiders_init.py.tmpl +9 -9
  113. crawlo/tools/__init__.py +200 -200
  114. crawlo/tools/anti_crawler.py +268 -268
  115. crawlo/tools/authenticated_proxy.py +240 -240
  116. crawlo/tools/data_formatter.py +225 -225
  117. crawlo/tools/data_validator.py +180 -180
  118. crawlo/tools/date_tools.py +289 -289
  119. crawlo/tools/distributed_coordinator.py +388 -388
  120. crawlo/tools/encoding_converter.py +127 -127
  121. crawlo/tools/network_diagnostic.py +364 -364
  122. crawlo/tools/request_tools.py +82 -82
  123. crawlo/tools/retry_mechanism.py +224 -224
  124. crawlo/tools/scenario_adapter.py +262 -262
  125. crawlo/tools/text_cleaner.py +232 -232
  126. crawlo/utils/__init__.py +34 -34
  127. crawlo/utils/batch_processor.py +259 -259
  128. crawlo/utils/class_loader.py +25 -25
  129. crawlo/utils/controlled_spider_mixin.py +439 -439
  130. crawlo/utils/db_helper.py +343 -343
  131. crawlo/utils/enhanced_error_handler.py +356 -356
  132. crawlo/utils/env_config.py +142 -142
  133. crawlo/utils/error_handler.py +165 -165
  134. crawlo/utils/func_tools.py +82 -82
  135. crawlo/utils/large_scale_config.py +286 -286
  136. crawlo/utils/large_scale_helper.py +344 -344
  137. crawlo/utils/log.py +80 -44
  138. crawlo/utils/performance_monitor.py +285 -285
  139. crawlo/utils/queue_helper.py +175 -175
  140. crawlo/utils/redis_connection_pool.py +388 -388
  141. crawlo/utils/redis_key_validator.py +198 -198
  142. crawlo/utils/request.py +267 -267
  143. crawlo/utils/request_serializer.py +225 -225
  144. crawlo/utils/spider_loader.py +61 -61
  145. crawlo/utils/system.py +11 -11
  146. crawlo/utils/tools.py +4 -4
  147. crawlo/utils/url.py +39 -39
  148. {crawlo-1.3.4.dist-info → crawlo-1.3.6.dist-info}/METADATA +1126 -1126
  149. crawlo-1.3.6.dist-info/RECORD +290 -0
  150. examples/__init__.py +7 -7
  151. tests/__init__.py +7 -7
  152. tests/advanced_tools_example.py +275 -275
  153. tests/authenticated_proxy_example.py +106 -106
  154. tests/baidu_performance_test.py +108 -108
  155. tests/baidu_test.py +59 -59
  156. tests/cleaners_example.py +160 -160
  157. tests/comprehensive_framework_test.py +212 -212
  158. tests/comprehensive_test.py +81 -81
  159. tests/comprehensive_testing_summary.md +186 -186
  160. tests/config_validation_demo.py +142 -142
  161. tests/controlled_spider_example.py +205 -205
  162. tests/date_tools_example.py +180 -180
  163. tests/debug_configure.py +69 -69
  164. tests/debug_framework_logger.py +84 -84
  165. tests/debug_log_config.py +127 -0
  166. tests/debug_log_levels.py +63 -63
  167. tests/debug_pipelines.py +66 -66
  168. tests/detailed_log_test.py +234 -0
  169. tests/distributed_test.py +66 -66
  170. tests/distributed_test_debug.py +76 -76
  171. tests/dynamic_loading_example.py +523 -523
  172. tests/dynamic_loading_test.py +104 -104
  173. tests/env_config_example.py +133 -133
  174. tests/error_handling_example.py +171 -171
  175. tests/final_comprehensive_test.py +151 -151
  176. tests/final_log_test.py +261 -0
  177. tests/final_validation_test.py +182 -182
  178. tests/fix_log_test.py +143 -0
  179. tests/framework_performance_test.py +202 -202
  180. tests/log_buffering_test.py +112 -0
  181. tests/log_generation_timing_test.py +154 -0
  182. tests/optimized_performance_test.py +211 -211
  183. tests/performance_comparison.py +245 -245
  184. tests/queue_blocking_test.py +113 -113
  185. tests/queue_test.py +89 -89
  186. tests/redis_key_validation_demo.py +130 -130
  187. tests/request_params_example.py +150 -150
  188. tests/response_improvements_example.py +144 -144
  189. tests/scrapy_comparison/ofweek_scrapy.py +138 -138
  190. tests/scrapy_comparison/scrapy_test.py +133 -133
  191. tests/simple_command_test.py +119 -119
  192. tests/simple_crawlo_test.py +127 -127
  193. tests/simple_log_test.py +57 -57
  194. tests/simple_log_test2.py +138 -0
  195. tests/simple_optimization_test.py +128 -128
  196. tests/simple_queue_type_test.py +42 -0
  197. tests/simple_spider_test.py +49 -49
  198. tests/simple_test.py +47 -47
  199. tests/spider_log_timing_test.py +178 -0
  200. tests/test_advanced_tools.py +148 -148
  201. tests/test_all_commands.py +230 -230
  202. tests/test_all_redis_key_configs.py +145 -145
  203. tests/test_authenticated_proxy.py +141 -141
  204. tests/test_batch_processor.py +178 -178
  205. tests/test_cleaners.py +54 -54
  206. tests/test_component_factory.py +174 -174
  207. tests/test_comprehensive.py +146 -146
  208. tests/test_config_consistency.py +80 -80
  209. tests/test_config_merge.py +152 -152
  210. tests/test_config_validator.py +182 -182
  211. tests/test_controlled_spider_mixin.py +79 -79
  212. tests/test_crawlo_proxy_integration.py +108 -108
  213. tests/test_date_tools.py +123 -123
  214. tests/test_default_header_middleware.py +158 -158
  215. tests/test_distributed.py +65 -65
  216. tests/test_double_crawlo_fix.py +207 -207
  217. tests/test_double_crawlo_fix_simple.py +124 -124
  218. tests/test_download_delay_middleware.py +221 -221
  219. tests/test_downloader_proxy_compatibility.py +268 -268
  220. tests/test_dynamic_downloaders_proxy.py +124 -124
  221. tests/test_dynamic_proxy.py +92 -92
  222. tests/test_dynamic_proxy_config.py +146 -146
  223. tests/test_dynamic_proxy_real.py +109 -109
  224. tests/test_edge_cases.py +303 -303
  225. tests/test_enhanced_error_handler.py +270 -270
  226. tests/test_enhanced_error_handler_comprehensive.py +245 -245
  227. tests/test_env_config.py +121 -121
  228. tests/test_error_handler_compatibility.py +112 -112
  229. tests/test_factories.py +252 -252
  230. tests/test_final_validation.py +153 -153
  231. tests/test_framework_env_usage.py +103 -103
  232. tests/test_framework_logger.py +66 -66
  233. tests/test_framework_startup.py +64 -64
  234. tests/test_get_component_logger.py +84 -0
  235. tests/test_integration.py +169 -169
  236. tests/test_item_dedup_redis_key.py +122 -122
  237. tests/test_large_scale_config.py +112 -112
  238. tests/test_large_scale_helper.py +235 -235
  239. tests/test_logging_system.py +283 -0
  240. tests/test_mode_change.py +72 -72
  241. tests/test_mode_consistency.py +51 -51
  242. tests/test_offsite_middleware.py +221 -221
  243. tests/test_parsel.py +29 -29
  244. tests/test_performance.py +327 -327
  245. tests/test_performance_monitor.py +115 -115
  246. tests/test_proxy_api.py +264 -264
  247. tests/test_proxy_health_check.py +32 -32
  248. tests/test_proxy_middleware.py +121 -121
  249. tests/test_proxy_middleware_enhanced.py +216 -216
  250. tests/test_proxy_middleware_integration.py +136 -136
  251. tests/test_proxy_middleware_refactored.py +184 -184
  252. tests/test_proxy_providers.py +56 -56
  253. tests/test_proxy_stats.py +19 -19
  254. tests/test_proxy_strategies.py +59 -59
  255. tests/test_queue_empty_check.py +41 -41
  256. tests/test_queue_manager_double_crawlo.py +173 -173
  257. tests/test_queue_manager_redis_key.py +176 -176
  258. tests/test_queue_type.py +107 -0
  259. tests/test_random_user_agent.py +72 -72
  260. tests/test_real_scenario_proxy.py +195 -195
  261. tests/test_redis_config.py +28 -28
  262. tests/test_redis_connection_pool.py +294 -294
  263. tests/test_redis_key_naming.py +181 -181
  264. tests/test_redis_key_validator.py +123 -123
  265. tests/test_redis_queue.py +224 -224
  266. tests/test_request_ignore_middleware.py +182 -182
  267. tests/test_request_params.py +111 -111
  268. tests/test_request_serialization.py +70 -70
  269. tests/test_response_code_middleware.py +349 -349
  270. tests/test_response_filter_middleware.py +427 -427
  271. tests/test_response_improvements.py +152 -152
  272. tests/test_retry_middleware.py +241 -241
  273. tests/test_scheduler.py +252 -252
  274. tests/test_scheduler_config_update.py +133 -133
  275. tests/test_simple_response.py +61 -61
  276. tests/test_telecom_spider_redis_key.py +205 -205
  277. tests/test_template_content.py +87 -87
  278. tests/test_template_redis_key.py +134 -134
  279. tests/test_tools.py +159 -159
  280. tests/test_user_agents.py +96 -96
  281. tests/tools_example.py +260 -260
  282. tests/untested_features_report.md +138 -138
  283. tests/verify_debug.py +51 -51
  284. tests/verify_distributed.py +117 -117
  285. tests/verify_log_fix.py +111 -111
  286. crawlo-1.3.4.dist-info/RECORD +0 -278
  287. {crawlo-1.3.4.dist-info → crawlo-1.3.6.dist-info}/WHEEL +0 -0
  288. {crawlo-1.3.4.dist-info → crawlo-1.3.6.dist-info}/entry_points.txt +0 -0
  289. {crawlo-1.3.4.dist-info → crawlo-1.3.6.dist-info}/top_level.txt +0 -0
tests/verify_log_fix.py CHANGED
@@ -1,112 +1,112 @@
1
- #!/usr/bin/python
2
- # -*- coding: UTF-8 -*-
3
- """
4
- 验证日志级别修复效果
5
- 创建一个简化的测试来验证控制台和日志文件级别的一致性
6
- """
7
- import sys
8
- import os
9
- import tempfile
10
-
11
- # 添加项目根目录到Python路径
12
- sys.path.insert(0, '/')
13
-
14
- from crawlo.utils.log import LoggerManager, get_logger
15
-
16
-
17
- def main():
18
- """验证日志级别修复效果"""
19
- print("🔧 验证日志级别修复效果")
20
- print("=" * 50)
21
-
22
- # 创建临时日志文件
23
- temp_log = tempfile.NamedTemporaryFile(mode='w+', suffix='.log', delete=False)
24
- temp_log_path = temp_log.name
25
- temp_log.close()
26
-
27
- try:
28
- # 重置LoggerManager状态
29
- LoggerManager.reset()
30
-
31
- # 使用INFO级别配置
32
- LoggerManager.configure(
33
- LOG_LEVEL='INFO',
34
- LOG_FILE=temp_log_path,
35
- LOG_FORMAT='%(asctime)s - [%(name)s] - %(levelname)s: %(message)s'
36
- )
37
-
38
- print(f"✅ 配置完成:")
39
- print(f" 默认级别: {LoggerManager._default_level}")
40
- print(f" 控制台级别: {LoggerManager._default_console_level}")
41
- print(f" 文件级别: {LoggerManager._default_file_level}")
42
- print(f" 日志文件: {temp_log_path}")
43
-
44
- # 创建测试logger
45
- test_logger = get_logger('crawlo.test')
46
-
47
- # 检查handler配置
48
- print(f"\n📋 Handler配置:")
49
- for i, handler in enumerate(test_logger.handlers):
50
- handler_type = type(handler).__name__
51
- handler_level = handler.level
52
- print(f" Handler {i} ({handler_type}): 级别 {handler_level}")
53
-
54
- # 测试日志输出
55
- print(f"\n📝 测试日志输出(控制台):")
56
- test_logger.debug("这是DEBUG级别日志 - 不应该显示")
57
- test_logger.info("这是INFO级别日志 - 应该显示")
58
- test_logger.warning("这是WARNING级别日志 - 应该显示")
59
- test_logger.error("这是ERROR级别日志 - 应该显示")
60
-
61
- # 检查日志文件内容
62
- print(f"\n📄 检查日志文件内容:")
63
- with open(temp_log_path, 'r', encoding='utf-8') as f:
64
- log_content = f.read()
65
- if log_content:
66
- print("日志文件内容:")
67
- print(log_content)
68
- else:
69
- print("❌ 日志文件为空")
70
-
71
- # 分析结果
72
- lines = log_content.strip().split('\n') if log_content.strip() else []
73
- debug_lines = [line for line in lines if '- DEBUG:' in line]
74
- info_lines = [line for line in lines if '- INFO:' in line]
75
- warning_lines = [line for line in lines if '- WARNING:' in line]
76
- error_lines = [line for line in lines if '- ERROR:' in line]
77
-
78
- print(f"\n📊 分析结果:")
79
- print(f" DEBUG级别日志: {len(debug_lines)}条 {'✅ 正确' if len(debug_lines) == 0 else '❌ 错误'}")
80
- print(f" INFO级别日志: {len(info_lines)}条 {'✅ 正确' if len(info_lines) >= 1 else '❌ 错误'}")
81
- print(f" WARNING级别日志: {len(warning_lines)}条 {'✅ 正确' if len(warning_lines) >= 1 else '❌ 错误'}")
82
- print(f" ERROR级别日志: {len(error_lines)}条 {'✅ 正确' if len(error_lines) >= 1 else '❌ 错误'}")
83
-
84
- # 判断修复是否成功
85
- success = (len(debug_lines) == 0 and len(info_lines) >= 1 and
86
- len(warning_lines) >= 1 and len(error_lines) >= 1)
87
-
88
- print(f"\n🎯 修复结果: {'✅ 成功' if success else '❌ 失败'}")
89
-
90
- if success:
91
- print("📋 控制台和日志文件现在使用相同的INFO级别")
92
- print("🎉 日志级别一致性问题已解决")
93
- else:
94
- print("❌ 仍存在日志级别不一致问题,需要进一步调试")
95
-
96
- except Exception as e:
97
- print(f"❌ 验证过程中发生错误: {e}")
98
- import traceback
99
- traceback.print_exc()
100
- return 1
101
- finally:
102
- # 清理临时文件
103
- try:
104
- os.unlink(temp_log_path)
105
- except:
106
- pass
107
-
108
- return 0 if success else 1
109
-
110
-
111
- if __name__ == '__main__':
1
+ #!/usr/bin/python
2
+ # -*- coding: UTF-8 -*-
3
+ """
4
+ 验证日志级别修复效果
5
+ 创建一个简化的测试来验证控制台和日志文件级别的一致性
6
+ """
7
+ import sys
8
+ import os
9
+ import tempfile
10
+
11
+ # 添加项目根目录到Python路径
12
+ sys.path.insert(0, '/')
13
+
14
+ from crawlo.utils.log import LoggerManager, get_logger
15
+
16
+
17
+ def main():
18
+ """验证日志级别修复效果"""
19
+ print("🔧 验证日志级别修复效果")
20
+ print("=" * 50)
21
+
22
+ # 创建临时日志文件
23
+ temp_log = tempfile.NamedTemporaryFile(mode='w+', suffix='.log', delete=False)
24
+ temp_log_path = temp_log.name
25
+ temp_log.close()
26
+
27
+ try:
28
+ # 重置LoggerManager状态
29
+ LoggerManager.reset()
30
+
31
+ # 使用INFO级别配置
32
+ LoggerManager.configure(
33
+ LOG_LEVEL='INFO',
34
+ LOG_FILE=temp_log_path,
35
+ LOG_FORMAT='%(asctime)s - [%(name)s] - %(levelname)s: %(message)s'
36
+ )
37
+
38
+ print(f"✅ 配置完成:")
39
+ print(f" 默认级别: {LoggerManager._default_level}")
40
+ print(f" 控制台级别: {LoggerManager._default_console_level}")
41
+ print(f" 文件级别: {LoggerManager._default_file_level}")
42
+ print(f" 日志文件: {temp_log_path}")
43
+
44
+ # 创建测试logger
45
+ test_logger = get_logger('crawlo.test')
46
+
47
+ # 检查handler配置
48
+ print(f"\n📋 Handler配置:")
49
+ for i, handler in enumerate(test_logger.handlers):
50
+ handler_type = type(handler).__name__
51
+ handler_level = handler.level
52
+ print(f" Handler {i} ({handler_type}): 级别 {handler_level}")
53
+
54
+ # 测试日志输出
55
+ print(f"\n📝 测试日志输出(控制台):")
56
+ test_logger.debug("这是DEBUG级别日志 - 不应该显示")
57
+ test_logger.info("这是INFO级别日志 - 应该显示")
58
+ test_logger.warning("这是WARNING级别日志 - 应该显示")
59
+ test_logger.error("这是ERROR级别日志 - 应该显示")
60
+
61
+ # 检查日志文件内容
62
+ print(f"\n📄 检查日志文件内容:")
63
+ with open(temp_log_path, 'r', encoding='utf-8') as f:
64
+ log_content = f.read()
65
+ if log_content:
66
+ print("日志文件内容:")
67
+ print(log_content)
68
+ else:
69
+ print("❌ 日志文件为空")
70
+
71
+ # 分析结果
72
+ lines = log_content.strip().split('\n') if log_content.strip() else []
73
+ debug_lines = [line for line in lines if '- DEBUG:' in line]
74
+ info_lines = [line for line in lines if '- INFO:' in line]
75
+ warning_lines = [line for line in lines if '- WARNING:' in line]
76
+ error_lines = [line for line in lines if '- ERROR:' in line]
77
+
78
+ print(f"\n📊 分析结果:")
79
+ print(f" DEBUG级别日志: {len(debug_lines)}条 {'✅ 正确' if len(debug_lines) == 0 else '❌ 错误'}")
80
+ print(f" INFO级别日志: {len(info_lines)}条 {'✅ 正确' if len(info_lines) >= 1 else '❌ 错误'}")
81
+ print(f" WARNING级别日志: {len(warning_lines)}条 {'✅ 正确' if len(warning_lines) >= 1 else '❌ 错误'}")
82
+ print(f" ERROR级别日志: {len(error_lines)}条 {'✅ 正确' if len(error_lines) >= 1 else '❌ 错误'}")
83
+
84
+ # 判断修复是否成功
85
+ success = (len(debug_lines) == 0 and len(info_lines) >= 1 and
86
+ len(warning_lines) >= 1 and len(error_lines) >= 1)
87
+
88
+ print(f"\n🎯 修复结果: {'✅ 成功' if success else '❌ 失败'}")
89
+
90
+ if success:
91
+ print("📋 控制台和日志文件现在使用相同的INFO级别")
92
+ print("🎉 日志级别一致性问题已解决")
93
+ else:
94
+ print("❌ 仍存在日志级别不一致问题,需要进一步调试")
95
+
96
+ except Exception as e:
97
+ print(f"❌ 验证过程中发生错误: {e}")
98
+ import traceback
99
+ traceback.print_exc()
100
+ return 1
101
+ finally:
102
+ # 清理临时文件
103
+ try:
104
+ os.unlink(temp_log_path)
105
+ except:
106
+ pass
107
+
108
+ return 0 if success else 1
109
+
110
+
111
+ if __name__ == '__main__':
112
112
  sys.exit(main())
@@ -1,278 +0,0 @@
1
- crawlo/__init__.py,sha256=rCeDq1OoX6mmcBxuK60eUpEp1cIg5T8Zgic3FUQAOkA,2318
2
- crawlo/__version__.py,sha256=znOUWqTRUyFzytrxffOUq80wt0j_tYutMKHTUCSPrAo,22
3
- crawlo/cli.py,sha256=OXprmcTUbFK02ptw_Gq8Gk4-ZCU-WEMJgzU1ztgP6Bk,2327
4
- crawlo/config.py,sha256=dNoNyTkXLe2msQ7bZx3YTQItk1m49nIg5-g89FQDNwE,9486
5
- crawlo/config_validator.py,sha256=gsiLqf5swWd9ISDvoLqCdG7iSXr-ZdBPD4iT6ug1ua4,11239
6
- crawlo/crawler.py,sha256=wd8_jrfUBwlIw4NiaNeCwMj-CXS7F2ngeUhQ74P0wJE,25656
7
- crawlo/event.py,sha256=7-y6HNv_EIJSYQNzsj0mVK-Gg4ON3wdQeMdQjfFJPlw,313
8
- crawlo/exceptions.py,sha256=sMay0wnWLfc_FXWslqxm60qz6b66LXs3EdN_w8ygE9k,1166
9
- crawlo/framework.py,sha256=N0N9_GOWWYafob5iYqGT4wGAKTxSMWFbWTJuE9PRkqI,9062
10
- crawlo/mode_manager.py,sha256=JP8_jkH2p9LMg1-g1e05PhSggSvt4jO_oO2h51pLVYQ,7399
11
- crawlo/project.py,sha256=DooXmO0nmcHPVRsnDBTE0dOrX-KOqnJe6A0s_-qOxRI,12147
12
- crawlo/stats_collector.py,sha256=copzmfWTArYZCkMeZJsJfJcdC36s7_LM88hxAYttoeE,2306
13
- crawlo/subscriber.py,sha256=D3hzE7Pc_zJjc-zR7lct5pt32bz6LsDYeC8uHlS4Hso,4986
14
- crawlo/task_manager.py,sha256=a9JWpqiozFEhReH4PwD9HsDs050HERwi9X9LNGdOp0E,5828
15
- crawlo/commands/__init__.py,sha256=QbhGAmItiwVrtlTr9UUbEJMegLJo-SdzaKX2PUhBgfI,378
16
- crawlo/commands/check.py,sha256=7pD43s97DD-fSLO9OEOuNcNr7o-2g94rJULL8fUzdaI,22605
17
- crawlo/commands/genspider.py,sha256=HhtvBLkIuhYtJUzom6PquItiC22vU9LNpOkjDUiqdM4,4937
18
- crawlo/commands/help.py,sha256=gwfHibRpdYDmZO6waUMOEn8SMJ_ubdjL-prD5fiuVY8,4973
19
- crawlo/commands/list.py,sha256=BqlPjBa5FLotjAlyZ3-nGmXg5cWcCNbHi8U5znb2_D8,5722
20
- crawlo/commands/run.py,sha256=gQ14PN3ZxsRNapRsyGZ4qdhbqzh70EnuS2YPaIUA8q0,12828
21
- crawlo/commands/startproject.py,sha256=aqKRJarKqTf5XjJnGXwjRpp0uYF16LreFbwwQLGpK-0,16070
22
- crawlo/commands/stats.py,sha256=8wTubR1RQ1JPTlpOKArcGcQ39bM-0cuH27lDpndnwPQ,6014
23
- crawlo/commands/utils.py,sha256=Psfu2tKrmDloMq0WnfXLaxx0lJFitMZ-FWS3HAIrziQ,5382
24
- crawlo/core/__init__.py,sha256=nikMDqFwnDfE8ugqwAIfycBtIqIVZpeprjEYW-H5Dkw,1272
25
- crawlo/core/engine.py,sha256=0l7TVNf2R8EHJAZ4ktj71j-qysrq84cYqf_7LEzzYJM,19096
26
- crawlo/core/processor.py,sha256=qmCqAeqhwYu-UE86evYesaGt9qpuSIfH-ZIZKcXFCZc,1140
27
- crawlo/core/scheduler.py,sha256=By1JB0iukcss5j0nrj1rq1Lk-VmmUHIiGl0RLCH9YUs,12630
28
- crawlo/data/__init__.py,sha256=8MgDxcMhx-emFARcLAw_ODOZNz0neYBcx7kEbzothd8,116
29
- crawlo/data/user_agents.py,sha256=6V34lYHREWV5ZR5wH-1pCnr1Y3ZYC7iMLfC6vZHyhZQ,9697
30
- crawlo/downloader/__init__.py,sha256=PB8oluLFMX2PBmeb3NBKkM6GaceX0ujFId8t2URy1ks,8624
31
- crawlo/downloader/aiohttp_downloader.py,sha256=rkCgEfX_s7w-cRK2ZoX43Unt9C7pPPYP64q22ShJMso,9107
32
- crawlo/downloader/cffi_downloader.py,sha256=BpA1q6Udz7sSXJ0gX94xGnzy8cdgK-vlr_Q6YA4QIxE,10243
33
- crawlo/downloader/httpx_downloader.py,sha256=7jfQfvAtfk8yD_mvwUbWLhYOxMM7r1nudiU7m_Jl9wc,12037
34
- crawlo/downloader/hybrid_downloader.py,sha256=4SzOPEwBlSZVzUAWR3DyxMx2Tsx15YrpBvQS4it4Vps,8028
35
- crawlo/downloader/playwright_downloader.py,sha256=Lnc7k5cXhVnURXSxgZFCYMJkBxLg5F_OE67rtf3G7Ig,16261
36
- crawlo/downloader/selenium_downloader.py,sha256=B_0muNi-GQ_hgoYHcf7wgu01V68q7xKnSh-0kzlUiio,21036
37
- crawlo/extension/__init__.py,sha256=Y3GOEmT7YtRoWf6fxEGCnRXgn_yaXsXCJ1Y6uwjFnM8,1605
38
- crawlo/extension/health_check.py,sha256=0GveZgUtFwjYEKlm3qbwIvCmb4FR0qrIKc8cEF1yQV8,5516
39
- crawlo/extension/log_interval.py,sha256=VCIeNqXcWDnxj4m6l77cjqgRzV8LfsPMb22X0Xc1Vwc,2417
40
- crawlo/extension/log_stats.py,sha256=vrChs3bj_Dvay3kxxkBOp4-w0K-IG-2XZ0PoSUahTPs,2908
41
- crawlo/extension/logging_extension.py,sha256=8KT-WJRK5tocS2kBOiSquree53L11qD1vLg-P8ob40U,2354
42
- crawlo/extension/memory_monitor.py,sha256=4aszl3C0GMQbqFhGZjZq5iQuXQR1sOz06VHjjEHgkyE,4290
43
- crawlo/extension/performance_profiler.py,sha256=EPiNuXuPPDU0Jtgy8arYHpr_8ASK13cCI2BytdJnu_I,4899
44
- crawlo/extension/request_recorder.py,sha256=RC23yzXClnVv9j2ljQvjBkUfWznfnDHsrQejKhE9y5E,4074
45
- crawlo/factories/__init__.py,sha256=-rkCL85okQ975DvadK5Eby7EF1FDW0uBHWKy0BtokS8,687
46
- crawlo/factories/base.py,sha256=whzJrbU2KReYdf6wrALQBTrMoWO3I8QLu0XwWtvYn0I,1764
47
- crawlo/factories/crawler.py,sha256=XpCb0_Ojbc04z8FVj_h4OkeNsKEsYWTnZw6lwTxDc_k,3095
48
- crawlo/factories/registry.py,sha256=LrtH7wMGQ2ZrswxnHDM9s43ckJ1isJKL7R8uyMQ8hCc,2511
49
- crawlo/filters/__init__.py,sha256=XC_Q4ykZtSNYizYlAcehVwBBNO3lZ2zuWwafzXiuWyQ,4241
50
- crawlo/filters/aioredis_filter.py,sha256=ZEApX23-S-7ruO_TSTKI0Noh8SEwjdZznf8TySeEtbQ,9255
51
- crawlo/filters/memory_filter.py,sha256=mO4oBPV5_uAiBQF3a16tU5tcD8244dOjKoNX_MU8cEw,9292
52
- crawlo/initialization/__init__.py,sha256=Y7pLI5MDiAgG1NuRvkIhwzaE6438_2ZP5jK317utgUQ,1084
53
- crawlo/initialization/built_in.py,sha256=EkZIPBrqsvFf0CuBL6POk2IJiDFf8q30eRGMqcL2N8M,15333
54
- crawlo/initialization/context.py,sha256=SL2ge47EmyLHzB5yldISA-xr__ZOV1xnQP_-1RF5v0Y,4722
55
- crawlo/initialization/core.py,sha256=ZR6veRDkKU5erQGXGKzgX6TU2_i6YkWsuFUeWnOEVjo,6679
56
- crawlo/initialization/phases.py,sha256=Kx3oTaMFfIKEB0mAVoz2IU29jprjnw3n7Bj_p5L7bIE,4028
57
- crawlo/initialization/registry.py,sha256=1iE7GUNel36lNxnp6iB376D0COFgqcr9amPPB5uXlmw,4774
58
- crawlo/items/__init__.py,sha256=bqekZrRlDhxfWie0UbCs656TptYseoe9QJ67I4E7Elk,386
59
- crawlo/items/base.py,sha256=VDxIH-vy85oHQZJJKqGS-7Ri7LcE1UZW7iQlpMbCLJo,579
60
- crawlo/items/fields.py,sha256=jCG0-PS8mVO48lP_ioTZCQCa0vjP5Sfv-sAyvYQqr-s,1800
61
- crawlo/items/items.py,sha256=e-3nXI9ckD64vcDxxQiAU6ufbtJMs09gbZQcYjxgwHY,3374
62
- crawlo/logging/__init__.py,sha256=8kQuBmcAf_qkCjh1XjaE75ODlmISpLDZ_xeT4FHu5LY,886
63
- crawlo/logging/config.py,sha256=KUIvg_xkYF4KzXVwkN-y25bNL43AtoMD8vGdoaqlS8k,3190
64
- crawlo/logging/factory.py,sha256=A5NNrIlzKLqdy0zWXIdEpmpurVZA_ANdSWinpRz9aDg,4045
65
- crawlo/logging/manager.py,sha256=hbdwyFGnnyRFrVDXoqzHs8oERx72NHrf7KqwCf4oPc4,3071
66
- crawlo/middleware/__init__.py,sha256=ldaGFNbiJnK9Fx12Vdf9fDNfzXxoETtShp5r-vodtw0,549
67
- crawlo/middleware/default_header.py,sha256=wQ7BrUHd-hRosFoKsReV9hwNNr_jwK6V0ZfxL6MOGrk,5032
68
- crawlo/middleware/download_delay.py,sha256=zt9R5g2HWErWA_MAOnGcw_D8l6HD769Kyaw-Hv-vcTc,3438
69
- crawlo/middleware/middleware_manager.py,sha256=bQuIxn-i2oud-0hDkv890sa3YvNMbuJIR8zuAmIdLKA,6289
70
- crawlo/middleware/offsite.py,sha256=FIWZvkkzlDJfvQc7Ud7BdfDZ78Sa85qlEEwAR76hSBk,4559
71
- crawlo/middleware/proxy.py,sha256=NquB6tqHAgHs3-2_1_5220kJYfjNG5JyHRJyo_2j4wo,15636
72
- crawlo/middleware/request_ignore.py,sha256=xcyZ1c7r_HhbzR3r9pfjsLGW7L7FBVeYvlNt8cpP2wY,2577
73
- crawlo/middleware/response_code.py,sha256=-Aa9Mm9nJN-WdddN7iTanJRMA83_LYYgSEz3XLQGvMo,4934
74
- crawlo/middleware/response_filter.py,sha256=6VBUe04mu8C7XxmOak6XyhGMWZPYEm3AMo5Kt_r1SXY,4248
75
- crawlo/middleware/retry.py,sha256=HxeIf7DibeLCpZ_y4rNARWMyzlrsdq5UR2CaFZInA3s,4124
76
- crawlo/middleware/simple_proxy.py,sha256=V_v28L-faiMJtt8vi-u5O4za-aU77_JTqNTCYSfWzCE,2191
77
- crawlo/network/__init__.py,sha256=BLPERYPo22g1BXrW--wUnlolrdFUmOPjgOB8XQQJlck,397
78
- crawlo/network/request.py,sha256=9kV-gqb_d6aCsSBAwyzxnP9a70cAViwX8qvpyYV7Ym4,13799
79
- crawlo/network/response.py,sha256=EZiG4LjuIb7PxdGou4H-oSOQhec1ZdBRTkO-5fl8JTo,12701
80
- crawlo/pipelines/__init__.py,sha256=lrdVDjeHLNkA4_MAwI1auk_I9xfeU1SlBWXiammb6lc,616
81
- crawlo/pipelines/bloom_dedup_pipeline.py,sha256=omB_gHtoacbco0sn_c6HO6PHCh6xylSecK7UbJIeLq8,5661
82
- crawlo/pipelines/console_pipeline.py,sha256=KABkR3J-rqO0Awox7lizxKR2XuHfVhWPiVRgIybwwu4,1248
83
- crawlo/pipelines/csv_pipeline.py,sha256=6FBT2AoU6iNU-5NfgWRq7-JpF9dK2nBokjxx-y4jIas,12174
84
- crawlo/pipelines/database_dedup_pipeline.py,sha256=Ao_5jvVPl5QikxXhPeIrcB7_3tinR9bPNRV5Fu5zfDU,7978
85
- crawlo/pipelines/json_pipeline.py,sha256=vlu1nqbD2mtqtExt9cL5nibx1CwJM1RNqd4WGjZRHAY,8367
86
- crawlo/pipelines/memory_dedup_pipeline.py,sha256=oIksbIrmSw9s9jMh6JJMfVbv6hzseVMV_g9S8UHQUP4,3837
87
- crawlo/pipelines/mongo_pipeline.py,sha256=k7gNqAO-g2MtIfArphC6z5ZzkKVRkBKcv-2ImziPFA0,5706
88
- crawlo/pipelines/mysql_pipeline.py,sha256=CKll3rNFXc0-BGQ_0A6QOSm2-ymHtdjdybX6bSB8i2g,13500
89
- crawlo/pipelines/pipeline_manager.py,sha256=rtKZEgDc9oMDYaTrSSQYCc7rVJ-a65TQw4p3dWHF1SM,3116
90
- crawlo/pipelines/redis_dedup_pipeline.py,sha256=POYRiWAOp1pqDW9iTPJ8h3VcpLALeLrpw74MvJJqPiM,6342
91
- crawlo/queue/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
92
- crawlo/queue/pqueue.py,sha256=j2ISmyays5t1tuI36xM6EcELwSpq2xIjAScSBWSRZms,1220
93
- crawlo/queue/queue_manager.py,sha256=t-49ygGHAvOZ08v5zj4F06Iq2JUCSK5vZldRg-4sVtI,19669
94
- crawlo/queue/redis_priority_queue.py,sha256=5mEgMjqg7XrQrWOhWpwGwycmA-qcwfHtr8w7cKHs4-E,13657
95
- crawlo/settings/__init__.py,sha256=xsukVKn_h2Hopm1Nj-bXkhbfyS62QTTvJi7fhZUwR9M,123
96
- crawlo/settings/default_settings.py,sha256=vmacY04PZqumteQn7URMo0r3JWwJCctXaJcoxlW5-M0,13144
97
- crawlo/settings/setting_manager.py,sha256=AWPvvhOGo04Yv_q3jqEMyzhEpbxOX_Wr8tSHmI2sUnA,8109
98
- crawlo/spider/__init__.py,sha256=oi9LEYq9xaCSjktAIRUgjpGQQI7rTtN61ESdHeWb1x4,21224
99
- crawlo/templates/crawlo.cfg.tmpl,sha256=9BAmwEibS5Tvy6HIcGXPb0BGeuesmibebmTW0iAEkmo,230
100
- crawlo/templates/run.py.tmpl,sha256=yZuY8Sd0Vv8KLsneE2eY5s8iFPKIECpRZIJOIIu1k8U,926
101
- crawlo/templates/spiders_init.py.tmpl,sha256=pDB5X9NO7KIko3V5X0qz38JHy_k-UbEEqRFgCSJHvUU,345
102
- crawlo/templates/project/__init__.py.tmpl,sha256=f3ETIXw_O6K-lkL6lXM5znMPJW1FZYGFrwDs2BnHcnQ,58
103
- crawlo/templates/project/items.py.tmpl,sha256=mt1Mm--H2Ouos3r7JPkYh0r33rgYJf1YOMz0OZy8TYs,297
104
- crawlo/templates/project/middlewares.py.tmpl,sha256=T67p8j0laL4NJJ_3xzPM9yivgZRjTEMiEtEWLPwbkmw,4160
105
- crawlo/templates/project/pipelines.py.tmpl,sha256=GBHYU0Jx8sKDCdGJp44FMSH7u2slxoFg6a-R9Uwg_-I,2608
106
- crawlo/templates/project/settings.py.tmpl,sha256=qat0jBxnWXZDhCdmHh86JC4eDodRuNW9mKQ6mIBaiCY,6685
107
- crawlo/templates/project/settings_distributed.py.tmpl,sha256=q1v2HBS6NF1Ebwb1ia9z5DV9Zv3CREZPDJSDuCryv58,6783
108
- crawlo/templates/project/settings_gentle.py.tmpl,sha256=ZT6d-1Ao0h90vT82W9BSZuF8tsdyC4RU3446u1mh104,6631
109
- crawlo/templates/project/settings_high_performance.py.tmpl,sha256=Z_oWA4_a2yKOFAPG8lsLue2L6RzuKp8flq_NscAQvqA,6720
110
- crawlo/templates/project/settings_minimal.py.tmpl,sha256=6_7R0T9iIBOInTP9HX-icEvPOhd8-B3lmiZEz30kzV0,2485
111
- crawlo/templates/project/settings_simple.py.tmpl,sha256=31syWnuj-wswhTimUPnN7yhAF3OljeK2JW_UC6WXGpU,6485
112
- crawlo/templates/project/spiders/__init__.py.tmpl,sha256=D_41tcNocSlFpr2abwwjOL62rmQHhjjATNpDHXyABxg,207
113
- crawlo/templates/spider/spider.py.tmpl,sha256=jMhzyxpIpV_KigB-pmN-5mGMiYtu4mfQIOvpZcCGGJI,5055
114
- crawlo/tools/__init__.py,sha256=8igeUXLD0vJ5ta2X91QyTvna6dOioKCn0z7EF4oHvHI,3942
115
- crawlo/tools/anti_crawler.py,sha256=MU6KEPT0q85e_-Px8Rmw1fxdwlmOdpXfo0KYVpPlivU,9163
116
- crawlo/tools/authenticated_proxy.py,sha256=L93WeXajIZ3si8xNcE7bBPv34FvqSyTvVfD78fJAKQE,7032
117
- crawlo/tools/data_formatter.py,sha256=NEj3NqPiyG67V6qDgn2KNj9VNHWOLNwX-7p_nad0znc,7583
118
- crawlo/tools/data_validator.py,sha256=hxPN28YtJDFFLjBBYhDjHmR8ShNTEjgIsv-cmcDKIu8,5310
119
- crawlo/tools/date_tools.py,sha256=jjP5xA0-aDgm9UIK1RG2qaNagBzHFQ-BBDMo_YzSlLQ,8906
120
- crawlo/tools/distributed_coordinator.py,sha256=Au20nZ4qUiAZUD2A1yfwD3soaHADpkEZt1hRyegp6M4,12323
121
- crawlo/tools/encoding_converter.py,sha256=7P9Z7J1ALw_PPNApmjFsHZDpRxgxzduiViluenlSLEU,4043
122
- crawlo/tools/network_diagnostic.py,sha256=92diB7Ppo_TKGDYCRLzy7uvQMGApgGLwv7P5w4OpCms,12649
123
- crawlo/tools/request_tools.py,sha256=CjyFBtRQf_vFjQhaVwgHSGai4ZaWS8IIaF1flSfJxDs,2338
124
- crawlo/tools/retry_mechanism.py,sha256=aT5hEs5O7B09K1IaNFZEOWR9e_mX52Dtq4gx-onsyRI,7553
125
- crawlo/tools/scenario_adapter.py,sha256=JouFxI3513PRe1ObwHWc72vBvptNpNv0Ew3pRaEKjQQ,9398
126
- crawlo/tools/text_cleaner.py,sha256=SOgT9frD6Cg-2D7ZIzrixrxFYfYisLPU48ir9U2ZbA0,6458
127
- crawlo/utils/__init__.py,sha256=to1N8t0rNoczU9pteGt_RxhNrvfjtDxQidRwsTKcIjI,563
128
- crawlo/utils/batch_processor.py,sha256=_J-dKj98csB9LdhTBHh_dKvV4OzHiP22-5OWxavDglQ,8883
129
- crawlo/utils/class_loader.py,sha256=HnRuATNiHPsvAfikAiyi-Oo8wp8jkXVCo7ZV9_hq1xk,650
130
- crawlo/utils/controlled_spider_mixin.py,sha256=RVRAf9Wbi7z9NAlog4763xhHUEjl5r33aVMk7Oj4HCA,16497
131
- crawlo/utils/db_helper.py,sha256=3ib5-agrlwf2t5S_QtLRYH75wvJDlYbRqRmDEbpH5Bo,10559
132
- crawlo/utils/enhanced_error_handler.py,sha256=hj5AElt3ajfqnP4csQnEfEnzkbIep9k65DNQiCbmTFo,13858
133
- crawlo/utils/env_config.py,sha256=HbZOEKkeQ0FMdZYJu9SgmSNEmfPJrmAzA7lHu5Du1DA,3937
134
- crawlo/utils/error_handler.py,sha256=nDfDA99q2sirE2pe7OT2bcA54GqUiAYgtdAh38uFEX4,5290
135
- crawlo/utils/func_tools.py,sha256=WUZEGpWMuDDX7g-QySM7iaiC74erW2SSkZoUvDw1NjM,2369
136
- crawlo/utils/large_scale_config.py,sha256=j7wQ5ty7pQlBRygw2vhRJ7OI19RYBZKPfYMP3WeF2WI,8154
137
- crawlo/utils/large_scale_helper.py,sha256=Kxdy3WMuqjzQTyCc6z4xEYxXDi4xnYKJzsVwaBYZrrg,12108
138
- crawlo/utils/log.py,sha256=Q9AO7GGWZlA86fjhRz_Fb9MluCx9yihYmzsFIcK-0-w,1532
139
- crawlo/utils/performance_monitor.py,sha256=Q9xxuXBIfFoig_U-FQPOUuPAh1axO3MzYgpielDyku0,9547
140
- crawlo/utils/queue_helper.py,sha256=xpUUTOqlU1xz2Pb9NKAVGo3AfAO-7Xvx8Lm1q65Dgck,4743
141
- crawlo/utils/redis_connection_pool.py,sha256=wh_qYYeYAW3a3hfgq41PS7Lo2CPvugi7t6PXGafEDyk,12187
142
- crawlo/utils/redis_key_validator.py,sha256=M461uMU5mRZfYRSwf-fXJUi4UITNKUAZmLe-cvytm9c,5611
143
- crawlo/utils/request.py,sha256=yoLB2rY8d78vgPjIWpdhY5SalIKjyLIvTG_UH6EMdVI,8798
144
- crawlo/utils/request_serializer.py,sha256=nuaAThB97MWQS0GFxAyStZNn-VaAzuc6Tdazwvabrj0,8706
145
- crawlo/utils/spider_loader.py,sha256=WK9gL99sOeIrFC-a0Y10lygtryQR7-wfdGks-uwMYTM,2172
146
- crawlo/utils/system.py,sha256=HvWV1acxou0Rn0L7pNq4CnV_GWFeU0Tmjy3_nLD8M64,237
147
- crawlo/utils/tools.py,sha256=5Uv25Wy4m_ndZY0-n-eX-t3PxvaZ6wR3-Wvx-o7_Vrs,271
148
- crawlo/utils/url.py,sha256=rlgX2VlJv6JvLmCDTsbxzMSXE6R5ZL_0dLEqprsA-JU,1482
149
- examples/__init__.py,sha256=6i631BPnS_TR_BWUjtjB5CBO-zv9kRkwQTQvSya2wHE,123
150
- tests/__init__.py,sha256=scL1IPVT1iucth7v8ffrjRdeW7QrC_Y7AMmFVMdTY1Y,129
151
- tests/advanced_tools_example.py,sha256=7nlFLRVMVYzDz_CAdgQa9fJu7o0M6jBMo7PTvUsRbo0,9065
152
- tests/authenticated_proxy_example.py,sha256=rsLmILsrf9PpR77ekGi8KpB1dAYZdF26hlxkBjm4rSQ,2913
153
- tests/baidu_performance_test.py,sha256=XmBdEmedEvaI2JS83Sh3Y6m5Q7msDp_ECPxZmt9xYrM,3866
154
- tests/baidu_test.py,sha256=wsizbYFQ93SAO8tfdZHKo5RmWPzjSEsnHBfDc5Y9I_c,1815
155
- tests/cleaners_example.py,sha256=J6rT4rTbNzeN2YWf7IfLVwCGm3-UcSxE4LhH5AV-CE0,5164
156
- tests/comprehensive_framework_test.py,sha256=oRUQE3TGIFJ78ngHPHxmbFXPwq9iipr0oQsV5k6zzVU,5765
157
- tests/comprehensive_test.py,sha256=gKni2_e_04eUHeR1V03oeEqKewg0VCpp1vCsS1bwHO4,2888
158
- tests/comprehensive_testing_summary.md,sha256=1-v48HOCGIZnRqp7-hydqRfKFM_rHYbwTYbXL-wWQbE,6327
159
- tests/config_validation_demo.py,sha256=5MzW5P7ZX6xoMW_zC6XmIA50KWMTu0iB5H2hTe42Sb8,4029
160
- tests/controlled_spider_example.py,sha256=SP_k4mdKPvD1JCPs9UCm68jcy2Frg84vvXv9-14RC6I,7776
161
- tests/date_tools_example.py,sha256=x_-duqnVZ-Hrk-SaNplIfcIV6W3c6u6MTxW35u1i0F0,4862
162
- tests/debug_configure.py,sha256=E-6Djz8kk7tf2pzEqrGdekW2W20vrJeZN7iNm9ArWKk,2144
163
- tests/debug_framework_logger.py,sha256=l2OX6igGu-pCUGrlwdWqcenqSSK9wMDheZ47XhEUqPg,3341
164
- tests/debug_log_levels.py,sha256=yPyKRNwz9kNWU1QMVLRD989Wh2sb6CrH4GAsMO0PHW8,2117
165
- tests/debug_pipelines.py,sha256=VpUmoYlt6Ci7foIGuQIotUu42xp6TzoA1cBDeagBzDk,2098
166
- tests/distributed_test.py,sha256=qZpFAMQTFcg0KUEdp2RUpkuYauSCf4C3lbbosyIDqgw,1759
167
- tests/distributed_test_debug.py,sha256=XOX8UlH0sQiuicoAqrSmAwteBfgTyGaOA5TNNMDFrH8,2105
168
- tests/dynamic_loading_example.py,sha256=NI0SCg4lPME0RCcNpDDw1HjErjmCgJntCN0ahAEw61g,18263
169
- tests/dynamic_loading_test.py,sha256=DYbMrEewerx0VGXixci3p9VYgDDQvCPevA92CNjq1Jo,3309
170
- tests/env_config_example.py,sha256=sKE8DvMBhM3uy439LpgLHd4wF7MGUrUc-X6E7g9qsz0,4818
171
- tests/error_handling_example.py,sha256=goF8fnTXxU3CgHcX4ALEcidVPd-zACn2tDqqQislRPA,5123
172
- tests/final_command_test_report.md,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
173
- tests/final_comprehensive_test.py,sha256=XhOjHBbetZIf4PcT3sgFSCUa913U93tta2MQuxXBwks,4163
174
- tests/final_validation_test.py,sha256=p5V2bpRBT1CA1l74nggwk6Is4roaRQSR5K7lNqZ3GBc,5062
175
- tests/framework_performance_test.py,sha256=B-s-w5iKcxDDamJICIQP8UZXZ0ZryvfKu5k33S6b7EQ,6783
176
- tests/optimized_performance_test.py,sha256=m1wRrhQM6d5UhG2dwCqurNdi-kU5hk7Znz6y_vq-BN4,7168
177
- tests/performance_comparison.py,sha256=2amQ_nnWxuXQDCFNUnFlNNJ4cPwTrCp9ZAwG9LBkpPg,9057
178
- tests/queue_blocking_test.py,sha256=xgIgo3Itj7ndFL5tsdc2uWjWQJkaP7jGDvWhbs_3TS0,3842
179
- tests/queue_test.py,sha256=9jyBDgX_Ff0hLpHJTBxSA3GP8Uo-Q9DKGvSDtjlf3cQ,2600
180
- tests/redis_key_validation_demo.py,sha256=FxqEXRgJllkgjyIyEuegQrLDuXAvi9N-dfMlvFotRZ4,4337
181
- tests/request_params_example.py,sha256=bjHxK_ca6UO7kBff88nmoxXY1odiLQCGC36okjEi7gM,4100
182
- tests/response_improvements_example.py,sha256=wnYGJO6MKj5_jbwKLDlbXu_Dli5XC7vlWdzByi82_5Y,5258
183
- tests/simple_command_test.py,sha256=GJ4KfxKxAZ8JJFuccJQn4SMPzWJcApaVVSvhz9SzvM8,3569
184
- tests/simple_crawlo_test.py,sha256=8x8DNL7O_1DNtOQ_K7YsOFIZoWeGmpeEP9mKWHlkbHg,4721
185
- tests/simple_log_test.py,sha256=4daRH0bqTViz-BmyPcAZY9xKGks7G5kb39MH5W7v2XI,1700
186
- tests/simple_optimization_test.py,sha256=CyhyzW9lhPlTDAwrJu7gTWwcEQuCBL_Bnm9mkS_-iFo,3550
187
- tests/simple_spider_test.py,sha256=X5oFRV02mkOXUd5lpzOBF7gX8K62j4ZwAUXoBEZ0KKE,1119
188
- tests/simple_test.py,sha256=kzMspCmfJxdnAIXXJv9tmDW1gpodkD9pznW5vA_gL84,1211
189
- tests/test_advanced_tools.py,sha256=3R8EfKVyBHEb6FA5TP3ieaWeHZhobVgSx8t3phipCrE,5250
190
- tests/test_all_commands.py,sha256=yGPw8zMrB5Z5w5LkaymSzKRLOcZsBPBXLvllCkgEY4I,7488
191
- tests/test_all_redis_key_configs.py,sha256=SGoip8M7oB2LNWC_31aJ4ECcDRmx0psr7i7DGzuaH7c,5565
192
- tests/test_authenticated_proxy.py,sha256=s4pr5JyBTHYQgRq_IymiVKE08vyW1MwR27pSwrrVLVk,4198
193
- tests/test_batch_processor.py,sha256=gMPoQcnUMm2-G_d7Zt9QnrRjCx1urzT31tYqoFNEklc,7034
194
- tests/test_cleaners.py,sha256=UD-X_eLnQic6GYbtFzYnAKqG4XKOSGIDd1X2fAl7Jso,1762
195
- tests/test_component_factory.py,sha256=xmgOjkEhdcyEyEp7fYVIpPXwvZz0qYW6Qk_1vHPtyNk,5635
196
- tests/test_comprehensive.py,sha256=kGNcJ9UkQxysYqvsBu0YxAaPleOvN9_hztLy7ljkfc4,5036
197
- tests/test_config_consistency.py,sha256=DJaAQxGL7RXHs-DWF_B4yhHFGSGHWHUoDmLFiMi4aJg,1921
198
- tests/test_config_merge.py,sha256=d8i8sU1XKS3egNKEYPZ2a6CBnJRx2M3p6q04wYufAcw,5454
199
- tests/test_config_validator.py,sha256=5ivB71KstHGNi2BPzcclf9hBukXEgt_B8N4l1HRjBFc,6020
200
- tests/test_controlled_spider_mixin.py,sha256=7t6VGWr6Hxw0xtIFyToLH8_deSagUtsdqSJpibXHMY8,2785
201
- tests/test_crawlo_proxy_integration.py,sha256=_L62_soaHRYy_0fShjiZSmv-RtGICw7_kzhTNRoyFfc,2620
202
- tests/test_date_tools.py,sha256=CQdAmIS6bpAdwQH9ETDH__06l2gGL7EHUQuh7mdTF-A,3930
203
- tests/test_default_header_middleware.py,sha256=7kpONSsGMsmWgTX2pCpseme54_-82Baak0xVz6gclJk,5845
204
- tests/test_distributed.py,sha256=RQHUpDfRNG2x_1Cdr9DLk25IBcgapm_u0xSBMObE0Xc,1725
205
- tests/test_double_crawlo_fix.py,sha256=ZNkRDgWW2WN-QRNZhvIgTHonY-T_U_R_MOIBLuyJd_I,7770
206
- tests/test_double_crawlo_fix_simple.py,sha256=MlWUqo51kOQ7Gu6Neoler8FVyRs0jpmQWoORHMBENz0,4644
207
- tests/test_download_delay_middleware.py,sha256=Va79gsH_8BVrVVLA8gSwFEbrRJ7qwJMCC1cDJN6il_0,8886
208
- tests/test_downloader_proxy_compatibility.py,sha256=3Jn7RJd1R2ywuitHp2Jju1yYNg57R4QmKwjuHGojDUE,8635
209
- tests/test_dynamic_downloaders_proxy.py,sha256=PtEW-pnVijeX2yX34UcoXYEY23yTBxb-kyNYh-WDljQ,4326
210
- tests/test_dynamic_proxy.py,sha256=YL2sghNKG7k27-SaHMh4boNLVBHhfSttUwUqiSsOEX4,3080
211
- tests/test_dynamic_proxy_config.py,sha256=uYXZ804ULI9qYMF-uNjMbi3L_NGzoMqLJcEZAl7aZ2I,5707
212
- tests/test_dynamic_proxy_real.py,sha256=DTjP8JnSwBnNZ3Ls1BjDAmt6xSuye_6CxwZ4LBisPTM,3402
213
- tests/test_edge_cases.py,sha256=4XZIUPOtNM9WCoAV1dJYAK8T6NiWp18rcwLLwnpxILE,10426
214
- tests/test_enhanced_error_handler.py,sha256=YYKyjT9ARcIcyKDOObaQTws18HfsHN923BOTAzaxYF8,8311
215
- tests/test_enhanced_error_handler_comprehensive.py,sha256=XAgyEaN3Q65AOJphIKHVgrWbxsCKDy5KZ55GmZLUrcs,9124
216
- tests/test_env_config.py,sha256=nfP4nCG9ZHeJUfxo1JKUmiihYbhSeWx_oNW5mMfDHfQ,4746
217
- tests/test_error_handler_compatibility.py,sha256=o5JLLLdo25Sl_3hpMx6I2fqSgZFAcnI4E6Ci-KxAxwA,4129
218
- tests/test_factories.py,sha256=vXI8tx42iuBivCKQoY2kH7G6c0i_QCmCq77krEgQiGU,8613
219
- tests/test_final_validation.py,sha256=aAiWLzhDCcv-GEXg9sauaVIfq5rz3s2vm67Gk2_lmBI,4813
220
- tests/test_framework_env_usage.py,sha256=HYpTwORXeaJHMffCYAGHGvc_a6ax4lo28xP8BYOaKxk,4098
221
- tests/test_framework_logger.py,sha256=HNkOlyA-dQKEdE6H4VaUHfF3aeVkKRoISSr53Hw90qQ,2506
222
- tests/test_framework_startup.py,sha256=I0zUfJUjkM7JgUBChO2w9cIL-tDJwUHdzKm3QjuEEJM,2215
223
- tests/test_integration.py,sha256=OCkjyv76Wop7CrXEko6rfoDsIK6SESA18KgCaTwL7Q4,4670
224
- tests/test_item_dedup_redis_key.py,sha256=QxLuXHUx0xqT6y7lQzOWcrLkRui7Qs7C6NgRvjzIypA,3720
225
- tests/test_large_scale_config.py,sha256=wyeMOMjGYhbZ6mrcnLH3Eh6GfspJwhavwWoyOy1y90c,4184
226
- tests/test_large_scale_helper.py,sha256=spvL0MPyXMAUDpzI2fY6-OQdSxOHtgJ1yuSUIbydyHY,8136
227
- tests/test_mode_change.py,sha256=kh5C4ut7T5dZ8b2dDot4RbLWMXJidv4FHzuTIgDxMBI,2605
228
- tests/test_mode_consistency.py,sha256=YJXf0SqAYVnFXy8eeBLC-zGTFAyO2fnsR4qLB76gZts,1225
229
- tests/test_offsite_middleware.py,sha256=L5YT9ZqcQwBunUv0Ddj-sLZcW4IMlAlgaJCwICHFWxI,7543
230
- tests/test_parsel.py,sha256=KYskaN_4HBc1XDTltjVo12v1i7JAThB2UIwcWZ-mwbY,672
231
- tests/test_performance.py,sha256=gOJ1EpU9uGynIxETLAroe98OA4QPcX1wchCDJoO41Kc,11130
232
- tests/test_performance_monitor.py,sha256=5oEHPJfjZXdtDK2nW_2MuGbOFgTTZyEhLapV9Ug1iHY,4072
233
- tests/test_proxy_api.py,sha256=dVqGElyL3K0_9IqkXzn7Ka2jSuhvYfR1BfZgyVukNM0,10749
234
- tests/test_proxy_health_check.py,sha256=xo3QMP1YNw9hu7JDHZOYCUZmFFKLJpHSh4SbxXhCRPQ,1091
235
- tests/test_proxy_middleware.py,sha256=qm2B0lepBZqzUpXNi4t1gjrQxUV4MQ2wvpmcaYV6O5A,3900
236
- tests/test_proxy_middleware_enhanced.py,sha256=YQRZs4bniU2CR-eKRc-sS4zZ6cjdSHwijUWL0T4Tq1w,6819
237
- tests/test_proxy_middleware_integration.py,sha256=zcl7fR9Toc-I-stSUTzKZPwcfh3kgrpjI5SbkZ6AVmE,4305
238
- tests/test_proxy_middleware_refactored.py,sha256=QiV9OodRb6hUcPnjDs-jraV8hlBBVLsUJE04geWHoD8,6776
239
- tests/test_proxy_providers.py,sha256=XwWZCywTYguSsUxSm6fsbaoH1p9dKjqSIx9-sqKZehA,1693
240
- tests/test_proxy_stats.py,sha256=Til_yksrRz2yBVw-yJi5-36LhNW3vTwpXTm4BdR9PUM,507
241
- tests/test_proxy_strategies.py,sha256=ZkziozkvZd3KWOQnpHQ8Upd3WpyoX7gN0qFGluNm348,1809
242
- tests/test_queue_empty_check.py,sha256=FsFoThG8qXzhXtG9Gu4hHuz--iVZHSbFbGJh4vgq_ec,1141
243
- tests/test_queue_manager_double_crawlo.py,sha256=YzM6PnoyRSST-f2NVyI97bpPcoYWL06HUwf08Fyx3Qg,6784
244
- tests/test_queue_manager_redis_key.py,sha256=nCCMnpKPNP5fyd4zb4LG2kmJAUcLoa8ODhBGcz4GcCU,6231
245
- tests/test_random_user_agent.py,sha256=LuyR8WaKfqOap9WBQl4WEBcZDmKxhW80T-_wXbuo2Qw,2230
246
- tests/test_real_scenario_proxy.py,sha256=LGtxEvCiTgn6aTPGd7ZuqaCjApsjosD2DunJrd8-jFE,8259
247
- tests/test_redis_config.py,sha256=DBrqURBQt517Rt1h1l2iIKrKDfbkJzQSRUEYYbapcy4,875
248
- tests/test_redis_connection_pool.py,sha256=WIUQlI6K3IINan14vknI4oFf9a8wpHCWi87KSfoB7_E,9034
249
- tests/test_redis_key_naming.py,sha256=7_X_PSzFQn5m0n_7qLlCjFvY4ZKScC36cqWFu1PAFRw,6730
250
- tests/test_redis_key_validator.py,sha256=VFuawmaA0G7VSHueCvZEQNKY-L2IdDGlEcyuJ9nZu7Q,4295
251
- tests/test_redis_queue.py,sha256=2OZJHn5fN9b6XEgEs4Ht1AL6TOJ_H-IR9JxPzzvqMpg,6534
252
- tests/test_request_ignore_middleware.py,sha256=8_2E6JU27eOWI3iHeh3YscLnp3SIHaubWdA477Ki6PE,6047
253
- tests/test_request_params.py,sha256=9vNksaOrFbuSb0UffruPxUHhJXZxVYyjQw9J69FSzH8,4176
254
- tests/test_request_serialization.py,sha256=TPBIzjaifcAjFWCFSFZ5ewRn814jSGPL28MGTwvrr_w,2262
255
- tests/test_response_code_middleware.py,sha256=EAPHsNN3J4ShJ5UfpzcZpOPjDvYgYJgcpNxpRgpQBaE,11844
256
- tests/test_response_filter_middleware.py,sha256=yVXl7LYxKxziGQg-YpdbVc6CVhmfmNOAZ86SaEVfMyI,15900
257
- tests/test_response_improvements.py,sha256=zvbkTkWhgdlFYtRu_ckgq6wGDGwpe_PTECYqpLDM3BU,5876
258
- tests/test_retry_middleware.py,sha256=g7QPDDLaX7hu3jqlWbDsjfuCbQXisTvs7YrcMLmn1Hw,7856
259
- tests/test_scheduler.py,sha256=j1t-ItXkCHZpoLI4T_2SFzl0Wbcg81LYeOOfnjsYKuk,7930
260
- tests/test_scheduler_config_update.py,sha256=eVE9lr7pTHlPCra9rtDge5rp4csiY3veYlG43qc34Fg,4128
261
- tests/test_simple_response.py,sha256=6RYOBRzAtyNvJ9a5JVTNubM-rvxnuX8jQOvq3sUZxwo,1488
262
- tests/test_telecom_spider_redis_key.py,sha256=hL_gjLJQbv6Tnli6Id7jXJcP-bgIQzhuWLUTBok6iv0,7420
263
- tests/test_template_content.py,sha256=q3OYI26e-qpmCYb1qmg5qg0kl7A8BhYbK2QjvKGaS0o,2816
264
- tests/test_template_redis_key.py,sha256=wJGAgWGO3hpSWoAUHHpBexXF7J2UP_tM6Z_PBjJl96Q,4742
265
- tests/test_tools.py,sha256=9t9FXZ61MfdB70nck9NYzCq97yd3SLVlLiMybEAlClk,5345
266
- tests/test_user_agents.py,sha256=rUotyuE2iJDi2LQBrUh980U-dAMTs4ARPMJxICOoQFY,3231
267
- tests/tools_example.py,sha256=MtIypR-OFiWwi-skurwmq4fM0cGTt-GUX4hSekYs7BY,7739
268
- tests/untested_features_report.md,sha256=hzlIKQlzFVO-G5ebF2KEusm-2XSf2WxXjpsA_OjqAbk,4031
269
- tests/verify_debug.py,sha256=V69y2qikGK5xxN1m8lFV-BCMmHaq_imQJkaU9YR8g6k,1513
270
- tests/verify_distributed.py,sha256=krnYYA5Qx9xXDMWc9YF5DxPSplGvawDg2n0l-3CAqoM,3928
271
- tests/verify_log_fix.py,sha256=TD7M1R22NxLqQPufvgE-H33u9tUjyz-rSR2ayIXozRU,4225
272
- tests/scrapy_comparison/ofweek_scrapy.py,sha256=2Hvpi6DRTubUxBy6RyJApQxMQONPLc1zWjKTQO_i5U4,5652
273
- tests/scrapy_comparison/scrapy_test.py,sha256=5sw7jOHhaTmQ8bsUd1TiolAUTRQYQOe-f49HPfysqbI,5466
274
- crawlo-1.3.4.dist-info/METADATA,sha256=MaE6HSo6UIybOmQrY0SUMnUXvPAdmclmsPtcWAil3bY,29742
275
- crawlo-1.3.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
276
- crawlo-1.3.4.dist-info/entry_points.txt,sha256=5HoVoTSPxI8SCa5B7pQYxLSrkOdiunyO9tqNsLMv52g,43
277
- crawlo-1.3.4.dist-info/top_level.txt,sha256=keG_67pbZ_wZL2dmDRA9RMaNHTaV_x_oxZ9DKNgwvR0,22
278
- crawlo-1.3.4.dist-info/RECORD,,
File without changes