crawlo 1.1.9__py3-none-any.whl → 1.2.1__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 (221) hide show
  1. crawlo/__init__.py +61 -61
  2. crawlo/__version__.py +1 -1
  3. crawlo/cleaners/__init__.py +60 -60
  4. crawlo/cleaners/data_formatter.py +225 -225
  5. crawlo/cleaners/encoding_converter.py +125 -125
  6. crawlo/cleaners/text_cleaner.py +232 -232
  7. crawlo/cli.py +65 -65
  8. crawlo/commands/__init__.py +14 -14
  9. crawlo/commands/check.py +594 -594
  10. crawlo/commands/genspider.py +151 -151
  11. crawlo/commands/help.py +142 -132
  12. crawlo/commands/list.py +155 -155
  13. crawlo/commands/run.py +292 -292
  14. crawlo/commands/startproject.py +418 -418
  15. crawlo/commands/stats.py +188 -188
  16. crawlo/commands/utils.py +186 -186
  17. crawlo/config.py +312 -312
  18. crawlo/config_validator.py +252 -252
  19. crawlo/core/__init__.py +2 -2
  20. crawlo/core/engine.py +354 -345
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +143 -136
  23. crawlo/crawler.py +1027 -1027
  24. crawlo/downloader/__init__.py +266 -266
  25. crawlo/downloader/aiohttp_downloader.py +220 -220
  26. crawlo/downloader/cffi_downloader.py +256 -256
  27. crawlo/downloader/httpx_downloader.py +259 -259
  28. crawlo/downloader/hybrid_downloader.py +213 -213
  29. crawlo/downloader/playwright_downloader.py +402 -402
  30. crawlo/downloader/selenium_downloader.py +472 -472
  31. crawlo/event.py +11 -11
  32. crawlo/exceptions.py +81 -81
  33. crawlo/extension/__init__.py +37 -37
  34. crawlo/extension/health_check.py +141 -141
  35. crawlo/extension/log_interval.py +57 -57
  36. crawlo/extension/log_stats.py +81 -81
  37. crawlo/extension/logging_extension.py +43 -43
  38. crawlo/extension/memory_monitor.py +104 -104
  39. crawlo/extension/performance_profiler.py +133 -133
  40. crawlo/extension/request_recorder.py +107 -107
  41. crawlo/filters/__init__.py +154 -154
  42. crawlo/filters/aioredis_filter.py +280 -280
  43. crawlo/filters/memory_filter.py +269 -269
  44. crawlo/items/__init__.py +23 -23
  45. crawlo/items/base.py +21 -21
  46. crawlo/items/fields.py +53 -53
  47. crawlo/items/items.py +104 -104
  48. crawlo/middleware/__init__.py +21 -21
  49. crawlo/middleware/default_header.py +132 -32
  50. crawlo/middleware/download_delay.py +105 -28
  51. crawlo/middleware/middleware_manager.py +135 -135
  52. crawlo/middleware/offsite.py +116 -0
  53. crawlo/middleware/proxy.py +366 -272
  54. crawlo/middleware/request_ignore.py +88 -30
  55. crawlo/middleware/response_code.py +164 -18
  56. crawlo/middleware/response_filter.py +138 -26
  57. crawlo/middleware/retry.py +124 -124
  58. crawlo/mode_manager.py +211 -211
  59. crawlo/network/__init__.py +21 -21
  60. crawlo/network/request.py +338 -338
  61. crawlo/network/response.py +359 -359
  62. crawlo/pipelines/__init__.py +21 -21
  63. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  64. crawlo/pipelines/console_pipeline.py +39 -39
  65. crawlo/pipelines/csv_pipeline.py +316 -316
  66. crawlo/pipelines/database_dedup_pipeline.py +224 -224
  67. crawlo/pipelines/json_pipeline.py +218 -218
  68. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  69. crawlo/pipelines/mongo_pipeline.py +131 -131
  70. crawlo/pipelines/mysql_pipeline.py +316 -316
  71. crawlo/pipelines/pipeline_manager.py +61 -61
  72. crawlo/pipelines/redis_dedup_pipeline.py +167 -167
  73. crawlo/project.py +187 -187
  74. crawlo/queue/pqueue.py +37 -37
  75. crawlo/queue/queue_manager.py +337 -334
  76. crawlo/queue/redis_priority_queue.py +298 -298
  77. crawlo/settings/__init__.py +7 -7
  78. crawlo/settings/default_settings.py +226 -219
  79. crawlo/settings/setting_manager.py +122 -122
  80. crawlo/spider/__init__.py +639 -639
  81. crawlo/stats_collector.py +59 -59
  82. crawlo/subscriber.py +130 -130
  83. crawlo/task_manager.py +30 -30
  84. crawlo/templates/crawlo.cfg.tmpl +10 -10
  85. crawlo/templates/project/__init__.py.tmpl +3 -3
  86. crawlo/templates/project/items.py.tmpl +17 -17
  87. crawlo/templates/project/middlewares.py.tmpl +118 -109
  88. crawlo/templates/project/pipelines.py.tmpl +96 -96
  89. crawlo/templates/project/run.py.tmpl +45 -45
  90. crawlo/templates/project/settings.py.tmpl +327 -326
  91. crawlo/templates/project/settings_distributed.py.tmpl +119 -119
  92. crawlo/templates/project/settings_gentle.py.tmpl +94 -94
  93. crawlo/templates/project/settings_high_performance.py.tmpl +151 -151
  94. crawlo/templates/project/settings_simple.py.tmpl +68 -68
  95. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  96. crawlo/templates/spider/spider.py.tmpl +143 -141
  97. crawlo/tools/__init__.py +182 -182
  98. crawlo/tools/anti_crawler.py +268 -268
  99. crawlo/tools/authenticated_proxy.py +240 -240
  100. crawlo/tools/data_validator.py +180 -180
  101. crawlo/tools/date_tools.py +35 -35
  102. crawlo/tools/distributed_coordinator.py +386 -386
  103. crawlo/tools/retry_mechanism.py +220 -220
  104. crawlo/tools/scenario_adapter.py +262 -262
  105. crawlo/utils/__init__.py +35 -35
  106. crawlo/utils/batch_processor.py +260 -260
  107. crawlo/utils/controlled_spider_mixin.py +439 -439
  108. crawlo/utils/date_tools.py +290 -290
  109. crawlo/utils/db_helper.py +343 -343
  110. crawlo/utils/enhanced_error_handler.py +359 -359
  111. crawlo/utils/env_config.py +105 -105
  112. crawlo/utils/error_handler.py +125 -125
  113. crawlo/utils/func_tools.py +82 -82
  114. crawlo/utils/large_scale_config.py +286 -286
  115. crawlo/utils/large_scale_helper.py +343 -343
  116. crawlo/utils/log.py +128 -128
  117. crawlo/utils/performance_monitor.py +284 -284
  118. crawlo/utils/queue_helper.py +175 -175
  119. crawlo/utils/redis_connection_pool.py +334 -334
  120. crawlo/utils/redis_key_validator.py +199 -199
  121. crawlo/utils/request.py +267 -267
  122. crawlo/utils/request_serializer.py +219 -219
  123. crawlo/utils/spider_loader.py +62 -62
  124. crawlo/utils/system.py +11 -11
  125. crawlo/utils/tools.py +4 -4
  126. crawlo/utils/url.py +39 -39
  127. crawlo-1.2.1.dist-info/METADATA +692 -0
  128. crawlo-1.2.1.dist-info/RECORD +220 -0
  129. examples/__init__.py +7 -7
  130. examples/aiohttp_settings.py +42 -0
  131. examples/curl_cffi_settings.py +41 -0
  132. examples/default_header_middleware_example.py +107 -0
  133. examples/default_header_spider_example.py +129 -0
  134. examples/download_delay_middleware_example.py +160 -0
  135. examples/httpx_settings.py +42 -0
  136. examples/multi_downloader_proxy_example.py +81 -0
  137. examples/offsite_middleware_example.py +55 -0
  138. examples/offsite_spider_example.py +107 -0
  139. examples/proxy_spider_example.py +166 -0
  140. examples/request_ignore_middleware_example.py +51 -0
  141. examples/request_ignore_spider_example.py +99 -0
  142. examples/response_code_middleware_example.py +52 -0
  143. examples/response_filter_middleware_example.py +67 -0
  144. examples/tong_hua_shun_settings.py +62 -0
  145. examples/tong_hua_shun_spider.py +170 -0
  146. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  147. tests/__init__.py +7 -7
  148. tests/advanced_tools_example.py +275 -275
  149. tests/authenticated_proxy_example.py +236 -236
  150. tests/cleaners_example.py +160 -160
  151. tests/config_validation_demo.py +102 -102
  152. tests/controlled_spider_example.py +205 -205
  153. tests/date_tools_example.py +180 -180
  154. tests/dynamic_loading_example.py +523 -523
  155. tests/dynamic_loading_test.py +104 -104
  156. tests/env_config_example.py +133 -133
  157. tests/error_handling_example.py +171 -171
  158. tests/redis_key_validation_demo.py +130 -130
  159. tests/response_improvements_example.py +144 -144
  160. tests/test_advanced_tools.py +148 -148
  161. tests/test_all_redis_key_configs.py +145 -145
  162. tests/test_authenticated_proxy.py +141 -141
  163. tests/test_cleaners.py +54 -54
  164. tests/test_comprehensive.py +146 -146
  165. tests/test_config_validator.py +193 -193
  166. tests/test_crawlo_proxy_integration.py +173 -0
  167. tests/test_date_tools.py +123 -123
  168. tests/test_default_header_middleware.py +159 -0
  169. tests/test_double_crawlo_fix.py +207 -207
  170. tests/test_double_crawlo_fix_simple.py +124 -124
  171. tests/test_download_delay_middleware.py +222 -0
  172. tests/test_downloader_proxy_compatibility.py +269 -0
  173. tests/test_dynamic_downloaders_proxy.py +124 -124
  174. tests/test_dynamic_proxy.py +92 -92
  175. tests/test_dynamic_proxy_config.py +146 -146
  176. tests/test_dynamic_proxy_real.py +109 -109
  177. tests/test_edge_cases.py +303 -303
  178. tests/test_enhanced_error_handler.py +270 -270
  179. tests/test_env_config.py +121 -121
  180. tests/test_error_handler_compatibility.py +112 -112
  181. tests/test_final_validation.py +153 -153
  182. tests/test_framework_env_usage.py +103 -103
  183. tests/test_integration.py +356 -356
  184. tests/test_item_dedup_redis_key.py +122 -122
  185. tests/test_offsite_middleware.py +222 -0
  186. tests/test_parsel.py +29 -29
  187. tests/test_performance.py +327 -327
  188. tests/test_proxy_api.py +265 -0
  189. tests/test_proxy_health_check.py +32 -32
  190. tests/test_proxy_middleware.py +122 -0
  191. tests/test_proxy_middleware_enhanced.py +217 -0
  192. tests/test_proxy_middleware_integration.py +136 -136
  193. tests/test_proxy_providers.py +56 -56
  194. tests/test_proxy_stats.py +19 -19
  195. tests/test_proxy_strategies.py +59 -59
  196. tests/test_queue_manager_double_crawlo.py +174 -231
  197. tests/test_queue_manager_redis_key.py +176 -176
  198. tests/test_real_scenario_proxy.py +196 -0
  199. tests/test_redis_config.py +28 -28
  200. tests/test_redis_connection_pool.py +294 -294
  201. tests/test_redis_key_naming.py +181 -181
  202. tests/test_redis_key_validator.py +123 -123
  203. tests/test_redis_queue.py +224 -224
  204. tests/test_request_ignore_middleware.py +183 -0
  205. tests/test_request_serialization.py +70 -70
  206. tests/test_response_code_middleware.py +350 -0
  207. tests/test_response_filter_middleware.py +428 -0
  208. tests/test_response_improvements.py +152 -152
  209. tests/test_retry_middleware.py +242 -0
  210. tests/test_scheduler.py +241 -241
  211. tests/test_simple_response.py +61 -61
  212. tests/test_telecom_spider_redis_key.py +205 -205
  213. tests/test_template_content.py +87 -87
  214. tests/test_template_redis_key.py +134 -134
  215. tests/test_tools.py +153 -153
  216. tests/tools_example.py +257 -257
  217. crawlo-1.1.9.dist-info/METADATA +0 -626
  218. crawlo-1.1.9.dist-info/RECORD +0 -190
  219. {crawlo-1.1.9.dist-info → crawlo-1.2.1.dist-info}/WHEEL +0 -0
  220. {crawlo-1.1.9.dist-info → crawlo-1.2.1.dist-info}/entry_points.txt +0 -0
  221. {crawlo-1.1.9.dist-info → crawlo-1.2.1.dist-info}/top_level.txt +0 -0
@@ -1,208 +1,208 @@
1
- #!/usr/bin/env python3
2
- # -*- coding: utf-8 -*-
3
- """
4
- 双重 crawlo 前缀问题修复测试脚本
5
- 用于验证 Redis 队列名称中双重 crawlo 前缀问题的修复
6
- """
7
- import sys
8
- import os
9
- import asyncio
10
- import traceback
11
-
12
- # 添加项目根目录到路径
13
- sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
14
-
15
- # 导入相关模块
16
- from crawlo.queue.queue_manager import QueueManager, QueueConfig, QueueType
17
- from crawlo.queue.redis_priority_queue import RedisPriorityQueue
18
-
19
-
20
- async def test_redis_queue_naming():
21
- """测试 Redis 队列命名修复"""
22
- print("🚀 开始测试 Redis 队列命名修复...")
23
- print("=" * 50)
24
-
25
- test_cases = [
26
- {
27
- "name": "正常命名",
28
- "queue_name": "crawlo:test_project:queue:requests",
29
- "expected_module": "test_project",
30
- "expected_queue": "crawlo:test_project:queue:requests",
31
- "expected_processing": "crawlo:test_project:queue:processing",
32
- "expected_failed": "crawlo:test_project:queue:failed"
33
- },
34
- {
35
- "name": "双重 crawlo 前缀",
36
- "queue_name": "crawlo:crawlo:queue:requests",
37
- "expected_module": "crawlo",
38
- "expected_queue": "crawlo:crawlo:queue:requests",
39
- "expected_processing": "crawlo:crawlo:queue:processing",
40
- "expected_failed": "crawlo:crawlo:queue:failed"
41
- },
42
- {
43
- "name": "三重 crawlo 前缀",
44
- "queue_name": "crawlo:crawlo:crawlo:queue:requests",
45
- "expected_module": "crawlo",
46
- "expected_queue": "crawlo:crawlo:queue:requests",
47
- "expected_processing": "crawlo:crawlo:queue:processing",
48
- "expected_failed": "crawlo:crawlo:queue:failed"
49
- },
50
- {
51
- "name": "无 crawlo 前缀",
52
- "queue_name": "test_project:queue:requests",
53
- "expected_module": "test_project",
54
- "expected_queue": "crawlo:test_project:queue:requests",
55
- "expected_processing": "crawlo:test_project:queue:processing",
56
- "expected_failed": "crawlo:test_project:queue:failed"
57
- }
58
- ]
59
-
60
- try:
61
- for i, test_case in enumerate(test_cases, 1):
62
- print(f"测试 {i}: {test_case['name']}")
63
- print(f" 输入队列名称: {test_case['queue_name']}")
64
-
65
- # 测试 RedisPriorityQueue 直接初始化
66
- try:
67
- queue = RedisPriorityQueue(
68
- redis_url="redis://127.0.0.1:6379/15",
69
- queue_name=test_case['queue_name'],
70
- module_name=test_case['expected_module']
71
- )
72
-
73
- print(f" 修复后队列名称: {queue.queue_name}")
74
- print(f" 修复后处理队列: {queue.processing_queue}")
75
- print(f" 修复后失败队列: {queue.failed_queue}")
76
-
77
- # 验证结果
78
- assert queue.queue_name == test_case['expected_queue'], \
79
- f"队列名称不匹配: {queue.queue_name} != {test_case['expected_queue']}"
80
- assert queue.processing_queue == test_case['expected_processing'], \
81
- f"处理队列名称不匹配: {queue.processing_queue} != {test_case['expected_processing']}"
82
- assert queue.failed_queue == test_case['expected_failed'], \
83
- f"失败队列名称不匹配: {queue.failed_queue} != {test_case['expected_failed']}"
84
-
85
- print(" ✅ 测试通过")
86
- except Exception as e:
87
- print(f" ❌ 测试失败: {e}")
88
- traceback.print_exc()
89
- return False
90
-
91
- print()
92
-
93
- print("✅ Redis 队列命名修复测试通过!")
94
- return True
95
-
96
- except Exception as e:
97
- print(f"❌ Redis 队列命名修复测试失败: {e}")
98
- traceback.print_exc()
99
- return False
100
-
101
-
102
- async def test_queue_manager_naming():
103
- """测试队列管理器中的项目名称提取"""
104
- print("🚀 开始测试队列管理器项目名称提取...")
105
- print("=" * 50)
106
-
107
- test_cases = [
108
- {
109
- "name": "正常命名",
110
- "queue_name": "crawlo:test_project:queue:requests",
111
- "expected_module": "test_project"
112
- },
113
- {
114
- "name": "双重 crawlo 前缀",
115
- "queue_name": "crawlo:crawlo:queue:requests",
116
- "expected_module": "crawlo"
117
- },
118
- {
119
- "name": "三重 crawlo 前缀",
120
- "queue_name": "crawlo:crawlo:crawlo:queue:requests",
121
- "expected_module": "crawlo"
122
- },
123
- {
124
- "name": "无 crawlo 前缀",
125
- "queue_name": "test_project:queue:requests",
126
- "expected_module": "test_project"
127
- }
128
- ]
129
-
130
- try:
131
- for i, test_case in enumerate(test_cases, 1):
132
- print(f"测试 {i}: {test_case['name']}")
133
- print(f" 输入队列名称: {test_case['queue_name']}")
134
-
135
- # 测试队列管理器中的项目名称提取逻辑
136
- if ':' in test_case['queue_name']:
137
- parts = test_case['queue_name'].split(':')
138
- if len(parts) >= 2:
139
- # 处理可能的双重 crawlo 前缀
140
- if parts[0] == "crawlo" and parts[1] == "crawlo":
141
- # 双重 crawlo 前缀,取第三个部分作为项目名称
142
- if len(parts) >= 3:
143
- project_name = parts[2]
144
- else:
145
- project_name = "default"
146
- elif parts[0] == "crawlo":
147
- # 正常的 crawlo 前缀,取第二个部分作为项目名称
148
- project_name = parts[1]
149
- else:
150
- # 没有 crawlo 前缀,使用第一个部分作为项目名称
151
- project_name = parts[0]
152
- else:
153
- project_name = test_case['queue_name'] or "default"
154
- else:
155
- project_name = test_case['queue_name'] or "default"
156
-
157
- print(f" 提取的项目名称: {project_name}")
158
- print(f" 期望的项目名称: {test_case['expected_module']}")
159
-
160
- # 验证结果
161
- assert project_name == test_case['expected_module'], \
162
- f"项目名称不匹配: {project_name} != {test_case['expected_module']}"
163
-
164
- print(" ✅ 测试通过")
165
- print()
166
-
167
- print("✅ 队列管理器项目名称提取测试通过!")
168
- return True
169
-
170
- except Exception as e:
171
- print(f"❌ 队列管理器项目名称提取测试失败: {e}")
172
- traceback.print_exc()
173
- return False
174
-
175
-
176
- async def main():
177
- """主测试函数"""
178
- print("🚀 开始双重 crawlo 前缀问题修复测试...")
179
- print("=" * 50)
180
-
181
- try:
182
- # 测试 Redis 队列命名修复
183
- redis_test_success = await test_redis_queue_naming()
184
- print()
185
-
186
- # 测试队列管理器项目名称提取
187
- manager_test_success = await test_queue_manager_naming()
188
- print()
189
-
190
- print("=" * 50)
191
- if redis_test_success and manager_test_success:
192
- print("🎉 所有测试通过!双重 crawlo 前缀问题已修复")
193
- else:
194
- print("❌ 部分测试失败,请检查实现")
195
- return 1
196
-
197
- except Exception as e:
198
- print("=" * 50)
199
- print(f"❌ 测试过程中发生异常: {e}")
200
- traceback.print_exc()
201
- return 1
202
-
203
- return 0
204
-
205
-
206
- if __name__ == "__main__":
207
- exit_code = asyncio.run(main())
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ """
4
+ 双重 crawlo 前缀问题修复测试脚本
5
+ 用于验证 Redis 队列名称中双重 crawlo 前缀问题的修复
6
+ """
7
+ import sys
8
+ import os
9
+ import asyncio
10
+ import traceback
11
+
12
+ # 添加项目根目录到路径
13
+ sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
14
+
15
+ # 导入相关模块
16
+ from crawlo.queue.queue_manager import QueueManager, QueueConfig, QueueType
17
+ from crawlo.queue.redis_priority_queue import RedisPriorityQueue
18
+
19
+
20
+ async def test_redis_queue_naming():
21
+ """测试 Redis 队列命名修复"""
22
+ print("🚀 开始测试 Redis 队列命名修复...")
23
+ print("=" * 50)
24
+
25
+ test_cases = [
26
+ {
27
+ "name": "正常命名",
28
+ "queue_name": "crawlo:test_project:queue:requests",
29
+ "expected_module": "test_project",
30
+ "expected_queue": "crawlo:test_project:queue:requests",
31
+ "expected_processing": "crawlo:test_project:queue:processing",
32
+ "expected_failed": "crawlo:test_project:queue:failed"
33
+ },
34
+ {
35
+ "name": "双重 crawlo 前缀",
36
+ "queue_name": "crawlo:crawlo:queue:requests",
37
+ "expected_module": "crawlo",
38
+ "expected_queue": "crawlo:crawlo:queue:requests",
39
+ "expected_processing": "crawlo:crawlo:queue:processing",
40
+ "expected_failed": "crawlo:crawlo:queue:failed"
41
+ },
42
+ {
43
+ "name": "三重 crawlo 前缀",
44
+ "queue_name": "crawlo:crawlo:crawlo:queue:requests",
45
+ "expected_module": "crawlo",
46
+ "expected_queue": "crawlo:crawlo:queue:requests",
47
+ "expected_processing": "crawlo:crawlo:queue:processing",
48
+ "expected_failed": "crawlo:crawlo:queue:failed"
49
+ },
50
+ {
51
+ "name": "无 crawlo 前缀",
52
+ "queue_name": "test_project:queue:requests",
53
+ "expected_module": "test_project",
54
+ "expected_queue": "crawlo:test_project:queue:requests",
55
+ "expected_processing": "crawlo:test_project:queue:processing",
56
+ "expected_failed": "crawlo:test_project:queue:failed"
57
+ }
58
+ ]
59
+
60
+ try:
61
+ for i, test_case in enumerate(test_cases, 1):
62
+ print(f"测试 {i}: {test_case['name']}")
63
+ print(f" 输入队列名称: {test_case['queue_name']}")
64
+
65
+ # 测试 RedisPriorityQueue 直接初始化
66
+ try:
67
+ queue = RedisPriorityQueue(
68
+ redis_url="redis://127.0.0.1:6379/15",
69
+ queue_name=test_case['queue_name'],
70
+ module_name=test_case['expected_module']
71
+ )
72
+
73
+ print(f" 修复后队列名称: {queue.queue_name}")
74
+ print(f" 修复后处理队列: {queue.processing_queue}")
75
+ print(f" 修复后失败队列: {queue.failed_queue}")
76
+
77
+ # 验证结果
78
+ assert queue.queue_name == test_case['expected_queue'], \
79
+ f"队列名称不匹配: {queue.queue_name} != {test_case['expected_queue']}"
80
+ assert queue.processing_queue == test_case['expected_processing'], \
81
+ f"处理队列名称不匹配: {queue.processing_queue} != {test_case['expected_processing']}"
82
+ assert queue.failed_queue == test_case['expected_failed'], \
83
+ f"失败队列名称不匹配: {queue.failed_queue} != {test_case['expected_failed']}"
84
+
85
+ print(" ✅ 测试通过")
86
+ except Exception as e:
87
+ print(f" ❌ 测试失败: {e}")
88
+ traceback.print_exc()
89
+ return False
90
+
91
+ print()
92
+
93
+ print("✅ Redis 队列命名修复测试通过!")
94
+ return True
95
+
96
+ except Exception as e:
97
+ print(f"❌ Redis 队列命名修复测试失败: {e}")
98
+ traceback.print_exc()
99
+ return False
100
+
101
+
102
+ async def test_queue_manager_naming():
103
+ """测试队列管理器中的项目名称提取"""
104
+ print("🚀 开始测试队列管理器项目名称提取...")
105
+ print("=" * 50)
106
+
107
+ test_cases = [
108
+ {
109
+ "name": "正常命名",
110
+ "queue_name": "crawlo:test_project:queue:requests",
111
+ "expected_module": "test_project"
112
+ },
113
+ {
114
+ "name": "双重 crawlo 前缀",
115
+ "queue_name": "crawlo:crawlo:queue:requests",
116
+ "expected_module": "crawlo"
117
+ },
118
+ {
119
+ "name": "三重 crawlo 前缀",
120
+ "queue_name": "crawlo:crawlo:crawlo:queue:requests",
121
+ "expected_module": "crawlo"
122
+ },
123
+ {
124
+ "name": "无 crawlo 前缀",
125
+ "queue_name": "test_project:queue:requests",
126
+ "expected_module": "test_project"
127
+ }
128
+ ]
129
+
130
+ try:
131
+ for i, test_case in enumerate(test_cases, 1):
132
+ print(f"测试 {i}: {test_case['name']}")
133
+ print(f" 输入队列名称: {test_case['queue_name']}")
134
+
135
+ # 测试队列管理器中的项目名称提取逻辑
136
+ if ':' in test_case['queue_name']:
137
+ parts = test_case['queue_name'].split(':')
138
+ if len(parts) >= 2:
139
+ # 处理可能的双重 crawlo 前缀
140
+ if parts[0] == "crawlo" and parts[1] == "crawlo":
141
+ # 双重 crawlo 前缀,取第三个部分作为项目名称
142
+ if len(parts) >= 3:
143
+ project_name = parts[2]
144
+ else:
145
+ project_name = "default"
146
+ elif parts[0] == "crawlo":
147
+ # 正常的 crawlo 前缀,取第二个部分作为项目名称
148
+ project_name = parts[1]
149
+ else:
150
+ # 没有 crawlo 前缀,使用第一个部分作为项目名称
151
+ project_name = parts[0]
152
+ else:
153
+ project_name = test_case['queue_name'] or "default"
154
+ else:
155
+ project_name = test_case['queue_name'] or "default"
156
+
157
+ print(f" 提取的项目名称: {project_name}")
158
+ print(f" 期望的项目名称: {test_case['expected_module']}")
159
+
160
+ # 验证结果
161
+ assert project_name == test_case['expected_module'], \
162
+ f"项目名称不匹配: {project_name} != {test_case['expected_module']}"
163
+
164
+ print(" ✅ 测试通过")
165
+ print()
166
+
167
+ print("✅ 队列管理器项目名称提取测试通过!")
168
+ return True
169
+
170
+ except Exception as e:
171
+ print(f"❌ 队列管理器项目名称提取测试失败: {e}")
172
+ traceback.print_exc()
173
+ return False
174
+
175
+
176
+ async def main():
177
+ """主测试函数"""
178
+ print("🚀 开始双重 crawlo 前缀问题修复测试...")
179
+ print("=" * 50)
180
+
181
+ try:
182
+ # 测试 Redis 队列命名修复
183
+ redis_test_success = await test_redis_queue_naming()
184
+ print()
185
+
186
+ # 测试队列管理器项目名称提取
187
+ manager_test_success = await test_queue_manager_naming()
188
+ print()
189
+
190
+ print("=" * 50)
191
+ if redis_test_success and manager_test_success:
192
+ print("🎉 所有测试通过!双重 crawlo 前缀问题已修复")
193
+ else:
194
+ print("❌ 部分测试失败,请检查实现")
195
+ return 1
196
+
197
+ except Exception as e:
198
+ print("=" * 50)
199
+ print(f"❌ 测试过程中发生异常: {e}")
200
+ traceback.print_exc()
201
+ return 1
202
+
203
+ return 0
204
+
205
+
206
+ if __name__ == "__main__":
207
+ exit_code = asyncio.run(main())
208
208
  sys.exit(exit_code)