crawlo 1.2.0__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 (220) 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 -354
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +143 -143
  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 -337
  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-1.2.0.dist-info → crawlo-1.2.1.dist-info}/METADATA +692 -697
  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 +173 -173
  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-1.2.0.dist-info/RECORD +0 -190
  218. {crawlo-1.2.0.dist-info → crawlo-1.2.1.dist-info}/WHEEL +0 -0
  219. {crawlo-1.2.0.dist-info → crawlo-1.2.1.dist-info}/entry_points.txt +0 -0
  220. {crawlo-1.2.0.dist-info → crawlo-1.2.1.dist-info}/top_level.txt +0 -0
@@ -1,206 +1,206 @@
1
- #!/usr/bin/env python3
2
- # -*- coding: utf-8 -*-
3
- """
4
- 电信设备许可证爬虫Redis Key测试脚本
5
- 用于验证分布式爬虫是否符合新的Redis key命名规范
6
- """
7
- import sys
8
- import os
9
- import asyncio
10
- import tempfile
11
- import shutil
12
- from pathlib import Path
13
-
14
- # 添加项目根目录到路径
15
- sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
16
-
17
- # 导入相关模块
18
- from crawlo.queue.queue_manager import QueueManager, QueueConfig, QueueType
19
- from crawlo.filters.aioredis_filter import AioRedisFilter
20
- from crawlo.pipelines.redis_dedup_pipeline import RedisDedupPipeline
21
-
22
-
23
- class MockSettings:
24
- """模拟设置类"""
25
- def __init__(self, project_name="telecom_licenses_distributed"):
26
- self.project_name = project_name
27
- self.REDIS_HOST = '127.0.0.1'
28
- self.REDIS_PORT = 6379
29
- self.REDIS_PASSWORD = ''
30
- self.REDIS_DB = 2
31
- self.REDIS_URL = f'redis://127.0.0.1:6379/{self.REDIS_DB}'
32
- self.REDIS_TTL = 0
33
- self.CLEANUP_FP = 0
34
- self.FILTER_DEBUG = True
35
- self.LOG_LEVEL = "INFO"
36
- self.DECODE_RESPONSES = True
37
- self.SCHEDULER_QUEUE_NAME = f'crawlo:{project_name}:queue:requests'
38
-
39
- def get(self, key, default=None):
40
- if key == 'PROJECT_NAME':
41
- return self.project_name
42
- elif key == 'REDIS_HOST':
43
- return self.REDIS_HOST
44
- elif key == 'REDIS_PASSWORD':
45
- return self.REDIS_PASSWORD
46
- elif key == 'REDIS_URL':
47
- return self.REDIS_URL
48
- elif key == 'FILTER_DEBUG':
49
- return self.FILTER_DEBUG
50
- elif key == 'LOG_LEVEL':
51
- return self.LOG_LEVEL
52
- elif key == 'DECODE_RESPONSES':
53
- return self.DECODE_RESPONSES
54
- elif key == 'SCHEDULER_QUEUE_NAME':
55
- return self.SCHEDULER_QUEUE_NAME
56
- return default
57
-
58
- def get_bool(self, key, default=False):
59
- if key == 'FILTER_DEBUG':
60
- return self.FILTER_DEBUG
61
- elif key == 'DECODE_RESPONSES':
62
- return self.DECODE_RESPONSES
63
- elif key == 'CLEANUP_FP':
64
- return self.CLEANUP_FP
65
- return default
66
-
67
- def get_int(self, key, default=0): # 修复方法名
68
- if key == 'REDIS_TTL':
69
- return self.REDIS_TTL
70
- elif key == 'REDIS_PORT':
71
- return self.REDIS_PORT
72
- elif key == 'REDIS_DB':
73
- return self.REDIS_DB
74
- elif key == 'SCHEDULER_MAX_QUEUE_SIZE':
75
- return 1000
76
- elif key == 'QUEUE_MAX_RETRIES':
77
- return 3
78
- elif key == 'QUEUE_TIMEOUT':
79
- return 300
80
- return default
81
-
82
-
83
- class MockCrawler:
84
- """模拟爬虫类"""
85
- def __init__(self, project_name="telecom_licenses_distributed"):
86
- self.settings = MockSettings(project_name)
87
- self.stats = {}
88
-
89
-
90
- async def test_telecom_spider_redis_key():
91
- """测试电信设备许可证爬虫Redis key命名规范"""
92
- print("🔍 测试电信设备许可证爬虫Redis key命名规范...")
93
-
94
- project_name = "telecom_licenses_distributed"
95
- expected_prefix = f"crawlo:{project_name}"
96
-
97
- try:
98
- # 1. 测试QueueManager和RedisPriorityQueue
99
- print(" 1. 测试队列管理器...")
100
- queue_config = QueueConfig(
101
- queue_type=QueueType.REDIS,
102
- redis_url="redis://127.0.0.1:6379/2",
103
- queue_name=f"crawlo:{project_name}:queue:requests", # 使用统一命名规范
104
- max_queue_size=1000,
105
- max_retries=3,
106
- timeout=300
107
- )
108
-
109
- queue_manager = QueueManager(queue_config)
110
- queue = await queue_manager._create_queue(QueueType.REDIS)
111
-
112
- # 验证队列名称是否符合规范
113
- expected_queue_name = f"{expected_prefix}:queue:requests"
114
- expected_processing_queue = f"{expected_prefix}:queue:processing"
115
- expected_failed_queue = f"{expected_prefix}:queue:failed"
116
-
117
- assert queue.queue_name == expected_queue_name, f"队列名称不匹配: {queue.queue_name} != {expected_queue_name}"
118
- assert queue.processing_queue == expected_processing_queue, f"处理中队列名称不匹配: {queue.processing_queue} != {expected_processing_queue}"
119
- assert queue.failed_queue == expected_failed_queue, f"失败队列名称不匹配: {queue.failed_queue} != {expected_failed_queue}"
120
-
121
- print(f" ✅ 请求队列: {queue.queue_name}")
122
- print(f" ✅ 处理中队列: {queue.processing_queue}")
123
- print(f" ✅ 失败队列: {queue.failed_queue}")
124
-
125
- # 2. 测试AioRedisFilter
126
- print(" 2. 测试请求去重过滤器...")
127
- mock_crawler = MockCrawler(project_name)
128
- filter_instance = AioRedisFilter.create_instance(mock_crawler)
129
-
130
- expected_filter_key = f"{expected_prefix}:filter:fingerprint"
131
- assert filter_instance.redis_key == expected_filter_key, f"过滤器key不匹配: {filter_instance.redis_key} != {expected_filter_key}"
132
-
133
- print(f" ✅ 请求去重key: {filter_instance.redis_key}")
134
-
135
- # 3. 测试RedisDedupPipeline
136
- print(" 3. 测试数据项去重管道...")
137
- dedup_pipeline = RedisDedupPipeline.from_crawler(mock_crawler)
138
-
139
- expected_item_key = f"{expected_prefix}:item:fingerprint"
140
- assert dedup_pipeline.redis_key == expected_item_key, f"数据项去重key不匹配: {dedup_pipeline.redis_key} != {expected_item_key}"
141
-
142
- print(f" ✅ 数据项去重key: {dedup_pipeline.redis_key}")
143
-
144
- # 4. 验证所有key都使用统一前缀
145
- print(" 4. 验证统一前缀...")
146
- all_keys = [
147
- queue.queue_name,
148
- queue.processing_queue,
149
- queue.failed_queue,
150
- filter_instance.redis_key,
151
- dedup_pipeline.redis_key
152
- ]
153
-
154
- for key in all_keys:
155
- assert key.startswith(expected_prefix), f"Key未使用统一前缀: {key}"
156
- print(f" ✅ {key}")
157
-
158
- print("✅ 电信设备许可证爬虫Redis key命名规范测试通过!")
159
- return True
160
-
161
- except Exception as e:
162
- print(f"❌ 测试失败: {e}")
163
- import traceback
164
- traceback.print_exc()
165
- return False
166
- finally:
167
- # 清理资源
168
- try:
169
- if 'queue' in locals():
170
- await queue.close()
171
- if 'filter_instance' in locals() and hasattr(filter_instance, 'redis'):
172
- await filter_instance.redis.close()
173
- if 'dedup_pipeline' in locals() and hasattr(dedup_pipeline, 'redis_client'):
174
- dedup_pipeline.redis_client.close()
175
- except:
176
- pass
177
-
178
-
179
- async def main():
180
- """主测试函数"""
181
- print("🚀 开始电信设备许可证爬虫Redis key命名规范测试...")
182
- print("=" * 60)
183
-
184
- try:
185
- success = await test_telecom_spider_redis_key()
186
-
187
- print("=" * 60)
188
- if success:
189
- print("🎉 所有测试通过!电信设备许可证爬虫符合新的Redis key命名规范")
190
- else:
191
- print("❌ 测试失败,请检查实现")
192
- return 1
193
-
194
- except Exception as e:
195
- print("=" * 60)
196
- print(f"❌ 测试过程中发生异常: {e}")
197
- import traceback
198
- traceback.print_exc()
199
- return 1
200
-
201
- return 0
202
-
203
-
204
- if __name__ == "__main__":
205
- exit_code = asyncio.run(main())
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ """
4
+ 电信设备许可证爬虫Redis Key测试脚本
5
+ 用于验证分布式爬虫是否符合新的Redis key命名规范
6
+ """
7
+ import sys
8
+ import os
9
+ import asyncio
10
+ import tempfile
11
+ import shutil
12
+ from pathlib import Path
13
+
14
+ # 添加项目根目录到路径
15
+ sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
16
+
17
+ # 导入相关模块
18
+ from crawlo.queue.queue_manager import QueueManager, QueueConfig, QueueType
19
+ from crawlo.filters.aioredis_filter import AioRedisFilter
20
+ from crawlo.pipelines.redis_dedup_pipeline import RedisDedupPipeline
21
+
22
+
23
+ class MockSettings:
24
+ """模拟设置类"""
25
+ def __init__(self, project_name="telecom_licenses_distributed"):
26
+ self.project_name = project_name
27
+ self.REDIS_HOST = '127.0.0.1'
28
+ self.REDIS_PORT = 6379
29
+ self.REDIS_PASSWORD = ''
30
+ self.REDIS_DB = 2
31
+ self.REDIS_URL = f'redis://127.0.0.1:6379/{self.REDIS_DB}'
32
+ self.REDIS_TTL = 0
33
+ self.CLEANUP_FP = 0
34
+ self.FILTER_DEBUG = True
35
+ self.LOG_LEVEL = "INFO"
36
+ self.DECODE_RESPONSES = True
37
+ self.SCHEDULER_QUEUE_NAME = f'crawlo:{project_name}:queue:requests'
38
+
39
+ def get(self, key, default=None):
40
+ if key == 'PROJECT_NAME':
41
+ return self.project_name
42
+ elif key == 'REDIS_HOST':
43
+ return self.REDIS_HOST
44
+ elif key == 'REDIS_PASSWORD':
45
+ return self.REDIS_PASSWORD
46
+ elif key == 'REDIS_URL':
47
+ return self.REDIS_URL
48
+ elif key == 'FILTER_DEBUG':
49
+ return self.FILTER_DEBUG
50
+ elif key == 'LOG_LEVEL':
51
+ return self.LOG_LEVEL
52
+ elif key == 'DECODE_RESPONSES':
53
+ return self.DECODE_RESPONSES
54
+ elif key == 'SCHEDULER_QUEUE_NAME':
55
+ return self.SCHEDULER_QUEUE_NAME
56
+ return default
57
+
58
+ def get_bool(self, key, default=False):
59
+ if key == 'FILTER_DEBUG':
60
+ return self.FILTER_DEBUG
61
+ elif key == 'DECODE_RESPONSES':
62
+ return self.DECODE_RESPONSES
63
+ elif key == 'CLEANUP_FP':
64
+ return self.CLEANUP_FP
65
+ return default
66
+
67
+ def get_int(self, key, default=0): # 修复方法名
68
+ if key == 'REDIS_TTL':
69
+ return self.REDIS_TTL
70
+ elif key == 'REDIS_PORT':
71
+ return self.REDIS_PORT
72
+ elif key == 'REDIS_DB':
73
+ return self.REDIS_DB
74
+ elif key == 'SCHEDULER_MAX_QUEUE_SIZE':
75
+ return 1000
76
+ elif key == 'QUEUE_MAX_RETRIES':
77
+ return 3
78
+ elif key == 'QUEUE_TIMEOUT':
79
+ return 300
80
+ return default
81
+
82
+
83
+ class MockCrawler:
84
+ """模拟爬虫类"""
85
+ def __init__(self, project_name="telecom_licenses_distributed"):
86
+ self.settings = MockSettings(project_name)
87
+ self.stats = {}
88
+
89
+
90
+ async def test_telecom_spider_redis_key():
91
+ """测试电信设备许可证爬虫Redis key命名规范"""
92
+ print("🔍 测试电信设备许可证爬虫Redis key命名规范...")
93
+
94
+ project_name = "telecom_licenses_distributed"
95
+ expected_prefix = f"crawlo:{project_name}"
96
+
97
+ try:
98
+ # 1. 测试QueueManager和RedisPriorityQueue
99
+ print(" 1. 测试队列管理器...")
100
+ queue_config = QueueConfig(
101
+ queue_type=QueueType.REDIS,
102
+ redis_url="redis://127.0.0.1:6379/2",
103
+ queue_name=f"crawlo:{project_name}:queue:requests", # 使用统一命名规范
104
+ max_queue_size=1000,
105
+ max_retries=3,
106
+ timeout=300
107
+ )
108
+
109
+ queue_manager = QueueManager(queue_config)
110
+ queue = await queue_manager._create_queue(QueueType.REDIS)
111
+
112
+ # 验证队列名称是否符合规范
113
+ expected_queue_name = f"{expected_prefix}:queue:requests"
114
+ expected_processing_queue = f"{expected_prefix}:queue:processing"
115
+ expected_failed_queue = f"{expected_prefix}:queue:failed"
116
+
117
+ assert queue.queue_name == expected_queue_name, f"队列名称不匹配: {queue.queue_name} != {expected_queue_name}"
118
+ assert queue.processing_queue == expected_processing_queue, f"处理中队列名称不匹配: {queue.processing_queue} != {expected_processing_queue}"
119
+ assert queue.failed_queue == expected_failed_queue, f"失败队列名称不匹配: {queue.failed_queue} != {expected_failed_queue}"
120
+
121
+ print(f" ✅ 请求队列: {queue.queue_name}")
122
+ print(f" ✅ 处理中队列: {queue.processing_queue}")
123
+ print(f" ✅ 失败队列: {queue.failed_queue}")
124
+
125
+ # 2. 测试AioRedisFilter
126
+ print(" 2. 测试请求去重过滤器...")
127
+ mock_crawler = MockCrawler(project_name)
128
+ filter_instance = AioRedisFilter.create_instance(mock_crawler)
129
+
130
+ expected_filter_key = f"{expected_prefix}:filter:fingerprint"
131
+ assert filter_instance.redis_key == expected_filter_key, f"过滤器key不匹配: {filter_instance.redis_key} != {expected_filter_key}"
132
+
133
+ print(f" ✅ 请求去重key: {filter_instance.redis_key}")
134
+
135
+ # 3. 测试RedisDedupPipeline
136
+ print(" 3. 测试数据项去重管道...")
137
+ dedup_pipeline = RedisDedupPipeline.from_crawler(mock_crawler)
138
+
139
+ expected_item_key = f"{expected_prefix}:item:fingerprint"
140
+ assert dedup_pipeline.redis_key == expected_item_key, f"数据项去重key不匹配: {dedup_pipeline.redis_key} != {expected_item_key}"
141
+
142
+ print(f" ✅ 数据项去重key: {dedup_pipeline.redis_key}")
143
+
144
+ # 4. 验证所有key都使用统一前缀
145
+ print(" 4. 验证统一前缀...")
146
+ all_keys = [
147
+ queue.queue_name,
148
+ queue.processing_queue,
149
+ queue.failed_queue,
150
+ filter_instance.redis_key,
151
+ dedup_pipeline.redis_key
152
+ ]
153
+
154
+ for key in all_keys:
155
+ assert key.startswith(expected_prefix), f"Key未使用统一前缀: {key}"
156
+ print(f" ✅ {key}")
157
+
158
+ print("✅ 电信设备许可证爬虫Redis key命名规范测试通过!")
159
+ return True
160
+
161
+ except Exception as e:
162
+ print(f"❌ 测试失败: {e}")
163
+ import traceback
164
+ traceback.print_exc()
165
+ return False
166
+ finally:
167
+ # 清理资源
168
+ try:
169
+ if 'queue' in locals():
170
+ await queue.close()
171
+ if 'filter_instance' in locals() and hasattr(filter_instance, 'redis'):
172
+ await filter_instance.redis.close()
173
+ if 'dedup_pipeline' in locals() and hasattr(dedup_pipeline, 'redis_client'):
174
+ dedup_pipeline.redis_client.close()
175
+ except:
176
+ pass
177
+
178
+
179
+ async def main():
180
+ """主测试函数"""
181
+ print("🚀 开始电信设备许可证爬虫Redis key命名规范测试...")
182
+ print("=" * 60)
183
+
184
+ try:
185
+ success = await test_telecom_spider_redis_key()
186
+
187
+ print("=" * 60)
188
+ if success:
189
+ print("🎉 所有测试通过!电信设备许可证爬虫符合新的Redis key命名规范")
190
+ else:
191
+ print("❌ 测试失败,请检查实现")
192
+ return 1
193
+
194
+ except Exception as e:
195
+ print("=" * 60)
196
+ print(f"❌ 测试过程中发生异常: {e}")
197
+ import traceback
198
+ traceback.print_exc()
199
+ return 1
200
+
201
+ return 0
202
+
203
+
204
+ if __name__ == "__main__":
205
+ exit_code = asyncio.run(main())
206
206
  sys.exit(exit_code)
@@ -1,88 +1,88 @@
1
- #!/usr/bin/env python3
2
- # -*- coding: utf-8 -*-
3
- """
4
- 模板文件内容测试脚本
5
- 用于验证模板文件是否符合新的Redis key命名规范
6
- """
7
- import sys
8
- import os
9
-
10
- # 添加项目根目录到路径
11
- sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
12
-
13
-
14
- def test_template_content():
15
- """测试模板文件内容"""
16
- print("🔍 测试模板文件内容...")
17
-
18
- try:
19
- # 检查settings.py.tmpl模板文件
20
- template_file = "crawlo/templates/project/settings.py.tmpl"
21
- if not os.path.exists(template_file):
22
- print(f"❌ 模板文件不存在: {template_file}")
23
- return False
24
-
25
- with open(template_file, 'r', encoding='utf-8') as f:
26
- content = f.read()
27
-
28
- # 检查是否移除了旧的REDIS_KEY配置
29
- old_config = "REDIS_KEY = f'{{project_name}}:fingerprint'"
30
- if old_config in content:
31
- print("❌ 仍然存在旧的REDIS_KEY配置")
32
- return False
33
- print(" ✅ 已移除旧的REDIS_KEY配置")
34
-
35
- # 检查是否添加了新的注释
36
- filter_comment = "# crawlo:{project_name}:filter:fingerprint (请求去重)"
37
- if filter_comment not in content:
38
- print("❌ 缺少请求去重的Redis key命名规范注释")
39
- return False
40
- print(" ✅ 包含请求去重的Redis key命名规范注释")
41
-
42
- item_comment = "# crawlo:{project_name}:item:fingerprint (数据项去重)"
43
- if item_comment not in content:
44
- print("❌ 缺少数据项去重的Redis key命名规范注释")
45
- return False
46
- print(" ✅ 包含数据项去重的Redis key命名规范注释")
47
-
48
- # 检查是否保留了队列名称配置
49
- queue_config = "SCHEDULER_QUEUE_NAME = f'crawlo:{{project_name}}:queue:requests'"
50
- if queue_config not in content:
51
- print("❌ 缺少队列名称配置")
52
- return False
53
- print(" ✅ 包含队列名称配置")
54
-
55
- print("✅ 模板文件内容测试通过!")
56
- return True
57
-
58
- except Exception as e:
59
- print(f"❌ 测试过程中发生错误: {e}")
60
- return False
61
-
62
-
63
- def main():
64
- """主测试函数"""
65
- print("🚀 开始模板文件内容测试...")
66
- print("=" * 50)
67
-
68
- try:
69
- success = test_template_content()
70
-
71
- print("=" * 50)
72
- if success:
73
- print("🎉 所有测试通过!模板文件符合新的Redis key命名规范")
74
- else:
75
- print("❌ 测试失败,请检查模板文件")
76
- return 1
77
-
78
- except Exception as e:
79
- print("=" * 50)
80
- print(f"❌ 测试过程中发生异常: {e}")
81
- return 1
82
-
83
- return 0
84
-
85
-
86
- if __name__ == "__main__":
87
- exit_code = main()
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ """
4
+ 模板文件内容测试脚本
5
+ 用于验证模板文件是否符合新的Redis key命名规范
6
+ """
7
+ import sys
8
+ import os
9
+
10
+ # 添加项目根目录到路径
11
+ sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
12
+
13
+
14
+ def test_template_content():
15
+ """测试模板文件内容"""
16
+ print("🔍 测试模板文件内容...")
17
+
18
+ try:
19
+ # 检查settings.py.tmpl模板文件
20
+ template_file = "crawlo/templates/project/settings.py.tmpl"
21
+ if not os.path.exists(template_file):
22
+ print(f"❌ 模板文件不存在: {template_file}")
23
+ return False
24
+
25
+ with open(template_file, 'r', encoding='utf-8') as f:
26
+ content = f.read()
27
+
28
+ # 检查是否移除了旧的REDIS_KEY配置
29
+ old_config = "REDIS_KEY = f'{{project_name}}:fingerprint'"
30
+ if old_config in content:
31
+ print("❌ 仍然存在旧的REDIS_KEY配置")
32
+ return False
33
+ print(" ✅ 已移除旧的REDIS_KEY配置")
34
+
35
+ # 检查是否添加了新的注释
36
+ filter_comment = "# crawlo:{project_name}:filter:fingerprint (请求去重)"
37
+ if filter_comment not in content:
38
+ print("❌ 缺少请求去重的Redis key命名规范注释")
39
+ return False
40
+ print(" ✅ 包含请求去重的Redis key命名规范注释")
41
+
42
+ item_comment = "# crawlo:{project_name}:item:fingerprint (数据项去重)"
43
+ if item_comment not in content:
44
+ print("❌ 缺少数据项去重的Redis key命名规范注释")
45
+ return False
46
+ print(" ✅ 包含数据项去重的Redis key命名规范注释")
47
+
48
+ # 检查是否保留了队列名称配置
49
+ queue_config = "SCHEDULER_QUEUE_NAME = f'crawlo:{{project_name}}:queue:requests'"
50
+ if queue_config not in content:
51
+ print("❌ 缺少队列名称配置")
52
+ return False
53
+ print(" ✅ 包含队列名称配置")
54
+
55
+ print("✅ 模板文件内容测试通过!")
56
+ return True
57
+
58
+ except Exception as e:
59
+ print(f"❌ 测试过程中发生错误: {e}")
60
+ return False
61
+
62
+
63
+ def main():
64
+ """主测试函数"""
65
+ print("🚀 开始模板文件内容测试...")
66
+ print("=" * 50)
67
+
68
+ try:
69
+ success = test_template_content()
70
+
71
+ print("=" * 50)
72
+ if success:
73
+ print("🎉 所有测试通过!模板文件符合新的Redis key命名规范")
74
+ else:
75
+ print("❌ 测试失败,请检查模板文件")
76
+ return 1
77
+
78
+ except Exception as e:
79
+ print("=" * 50)
80
+ print(f"❌ 测试过程中发生异常: {e}")
81
+ return 1
82
+
83
+ return 0
84
+
85
+
86
+ if __name__ == "__main__":
87
+ exit_code = main()
88
88
  sys.exit(exit_code)