crawlo 1.3.3__py3-none-any.whl → 1.3.4__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 (279) hide show
  1. crawlo/__init__.py +87 -63
  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 -323
  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 +46 -2
  16. crawlo/core/engine.py +439 -365
  17. crawlo/core/processor.py +40 -40
  18. crawlo/core/scheduler.py +257 -256
  19. crawlo/crawler.py +639 -1167
  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 -226
  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 -52
  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 +28 -0
  40. crawlo/factories/base.py +69 -0
  41. crawlo/factories/crawler.py +104 -0
  42. crawlo/factories/registry.py +85 -0
  43. crawlo/filters/__init__.py +154 -154
  44. crawlo/filters/aioredis_filter.py +257 -234
  45. crawlo/filters/memory_filter.py +269 -269
  46. crawlo/framework.py +292 -0
  47. crawlo/initialization/__init__.py +40 -0
  48. crawlo/initialization/built_in.py +426 -0
  49. crawlo/initialization/context.py +142 -0
  50. crawlo/initialization/core.py +194 -0
  51. crawlo/initialization/phases.py +149 -0
  52. crawlo/initialization/registry.py +146 -0
  53. crawlo/items/__init__.py +23 -23
  54. crawlo/items/base.py +23 -22
  55. crawlo/items/fields.py +52 -52
  56. crawlo/items/items.py +104 -104
  57. crawlo/logging/__init__.py +38 -0
  58. crawlo/logging/config.py +97 -0
  59. crawlo/logging/factory.py +129 -0
  60. crawlo/logging/manager.py +112 -0
  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 -187
  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 +318 -318
  85. crawlo/pipelines/pipeline_manager.py +76 -75
  86. crawlo/pipelines/redis_dedup_pipeline.py +166 -166
  87. crawlo/project.py +327 -325
  88. crawlo/queue/pqueue.py +43 -37
  89. crawlo/queue/queue_manager.py +503 -379
  90. crawlo/queue/redis_priority_queue.py +326 -306
  91. crawlo/settings/__init__.py +7 -7
  92. crawlo/settings/default_settings.py +321 -225
  93. crawlo/settings/setting_manager.py +214 -198
  94. crawlo/spider/__init__.py +657 -639
  95. crawlo/stats_collector.py +73 -59
  96. crawlo/subscriber.py +129 -129
  97. crawlo/task_manager.py +139 -30
  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 +168 -267
  104. crawlo/templates/project/settings_distributed.py.tmpl +167 -180
  105. crawlo/templates/project/settings_gentle.py.tmpl +167 -61
  106. crawlo/templates/project/settings_high_performance.py.tmpl +168 -131
  107. crawlo/templates/project/settings_minimal.py.tmpl +66 -35
  108. crawlo/templates/project/settings_simple.py.tmpl +165 -102
  109. crawlo/templates/project/spiders/__init__.py.tmpl +10 -6
  110. crawlo/templates/run.py.tmpl +34 -38
  111. crawlo/templates/spider/spider.py.tmpl +143 -143
  112. crawlo/templates/spiders_init.py.tmpl +10 -0
  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 +365 -0
  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 +26 -0
  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 -124
  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 +44 -200
  138. crawlo/utils/performance_monitor.py +285 -285
  139. crawlo/utils/queue_helper.py +175 -175
  140. crawlo/utils/redis_connection_pool.py +388 -351
  141. crawlo/utils/redis_key_validator.py +198 -198
  142. crawlo/utils/request.py +267 -267
  143. crawlo/utils/request_serializer.py +225 -218
  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-1.3.3.dist-info → crawlo-1.3.4.dist-info}/METADATA +1126 -1020
  149. crawlo-1.3.4.dist-info/RECORD +278 -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 +107 -107
  154. tests/baidu_performance_test.py +109 -0
  155. tests/baidu_test.py +60 -0
  156. tests/cleaners_example.py +160 -160
  157. tests/comprehensive_framework_test.py +213 -0
  158. tests/comprehensive_test.py +82 -0
  159. tests/comprehensive_testing_summary.md +187 -0
  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 +70 -0
  164. tests/debug_framework_logger.py +85 -0
  165. tests/debug_log_levels.py +64 -0
  166. tests/debug_pipelines.py +66 -66
  167. tests/distributed_test.py +67 -0
  168. tests/distributed_test_debug.py +77 -0
  169. tests/dynamic_loading_example.py +523 -523
  170. tests/dynamic_loading_test.py +104 -104
  171. tests/env_config_example.py +133 -133
  172. tests/error_handling_example.py +171 -171
  173. tests/final_command_test_report.md +0 -0
  174. tests/final_comprehensive_test.py +152 -0
  175. tests/final_validation_test.py +183 -0
  176. tests/framework_performance_test.py +203 -0
  177. tests/optimized_performance_test.py +212 -0
  178. tests/performance_comparison.py +246 -0
  179. tests/queue_blocking_test.py +114 -0
  180. tests/queue_test.py +90 -0
  181. tests/redis_key_validation_demo.py +130 -130
  182. tests/request_params_example.py +150 -150
  183. tests/response_improvements_example.py +144 -144
  184. tests/scrapy_comparison/ofweek_scrapy.py +139 -0
  185. tests/scrapy_comparison/scrapy_test.py +134 -0
  186. tests/simple_command_test.py +120 -0
  187. tests/simple_crawlo_test.py +128 -0
  188. tests/simple_log_test.py +58 -0
  189. tests/simple_optimization_test.py +129 -0
  190. tests/simple_spider_test.py +50 -0
  191. tests/simple_test.py +48 -0
  192. tests/test_advanced_tools.py +148 -148
  193. tests/test_all_commands.py +231 -0
  194. tests/test_all_redis_key_configs.py +145 -145
  195. tests/test_authenticated_proxy.py +141 -141
  196. tests/test_batch_processor.py +179 -0
  197. tests/test_cleaners.py +54 -54
  198. tests/test_component_factory.py +175 -0
  199. tests/test_comprehensive.py +146 -146
  200. tests/test_config_consistency.py +80 -80
  201. tests/test_config_merge.py +152 -152
  202. tests/test_config_validator.py +182 -182
  203. tests/test_controlled_spider_mixin.py +80 -0
  204. tests/test_crawlo_proxy_integration.py +108 -108
  205. tests/test_date_tools.py +123 -123
  206. tests/test_default_header_middleware.py +158 -158
  207. tests/test_distributed.py +65 -65
  208. tests/test_double_crawlo_fix.py +207 -207
  209. tests/test_double_crawlo_fix_simple.py +124 -124
  210. tests/test_download_delay_middleware.py +221 -221
  211. tests/test_downloader_proxy_compatibility.py +268 -268
  212. tests/test_dynamic_downloaders_proxy.py +124 -124
  213. tests/test_dynamic_proxy.py +92 -92
  214. tests/test_dynamic_proxy_config.py +146 -146
  215. tests/test_dynamic_proxy_real.py +109 -109
  216. tests/test_edge_cases.py +303 -303
  217. tests/test_enhanced_error_handler.py +270 -270
  218. tests/test_enhanced_error_handler_comprehensive.py +246 -0
  219. tests/test_env_config.py +121 -121
  220. tests/test_error_handler_compatibility.py +112 -112
  221. tests/test_factories.py +253 -0
  222. tests/test_final_validation.py +153 -153
  223. tests/test_framework_env_usage.py +103 -103
  224. tests/test_framework_logger.py +67 -0
  225. tests/test_framework_startup.py +65 -0
  226. tests/test_integration.py +169 -169
  227. tests/test_item_dedup_redis_key.py +122 -122
  228. tests/test_large_scale_config.py +113 -0
  229. tests/test_large_scale_helper.py +236 -0
  230. tests/test_mode_change.py +73 -0
  231. tests/test_mode_consistency.py +51 -51
  232. tests/test_offsite_middleware.py +221 -221
  233. tests/test_parsel.py +29 -29
  234. tests/test_performance.py +327 -327
  235. tests/test_performance_monitor.py +116 -0
  236. tests/test_proxy_api.py +264 -264
  237. tests/test_proxy_health_check.py +32 -32
  238. tests/test_proxy_middleware.py +121 -121
  239. tests/test_proxy_middleware_enhanced.py +216 -216
  240. tests/test_proxy_middleware_integration.py +136 -136
  241. tests/test_proxy_middleware_refactored.py +184 -184
  242. tests/test_proxy_providers.py +56 -56
  243. tests/test_proxy_stats.py +19 -19
  244. tests/test_proxy_strategies.py +59 -59
  245. tests/test_queue_empty_check.py +42 -0
  246. tests/test_queue_manager_double_crawlo.py +173 -173
  247. tests/test_queue_manager_redis_key.py +176 -176
  248. tests/test_random_user_agent.py +72 -72
  249. tests/test_real_scenario_proxy.py +195 -195
  250. tests/test_redis_config.py +28 -28
  251. tests/test_redis_connection_pool.py +294 -294
  252. tests/test_redis_key_naming.py +181 -181
  253. tests/test_redis_key_validator.py +123 -123
  254. tests/test_redis_queue.py +224 -224
  255. tests/test_request_ignore_middleware.py +182 -182
  256. tests/test_request_params.py +111 -111
  257. tests/test_request_serialization.py +70 -70
  258. tests/test_response_code_middleware.py +349 -349
  259. tests/test_response_filter_middleware.py +427 -427
  260. tests/test_response_improvements.py +152 -152
  261. tests/test_retry_middleware.py +241 -241
  262. tests/test_scheduler.py +252 -252
  263. tests/test_scheduler_config_update.py +133 -133
  264. tests/test_simple_response.py +61 -61
  265. tests/test_telecom_spider_redis_key.py +205 -205
  266. tests/test_template_content.py +87 -87
  267. tests/test_template_redis_key.py +134 -134
  268. tests/test_tools.py +159 -159
  269. tests/test_user_agents.py +96 -96
  270. tests/tools_example.py +260 -260
  271. tests/untested_features_report.md +139 -0
  272. tests/verify_debug.py +52 -0
  273. tests/verify_distributed.py +117 -117
  274. tests/verify_log_fix.py +112 -0
  275. crawlo-1.3.3.dist-info/RECORD +0 -219
  276. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +0 -82
  277. {crawlo-1.3.3.dist-info → crawlo-1.3.4.dist-info}/WHEEL +0 -0
  278. {crawlo-1.3.3.dist-info → crawlo-1.3.4.dist-info}/entry_points.txt +0 -0
  279. {crawlo-1.3.3.dist-info → crawlo-1.3.4.dist-info}/top_level.txt +0 -0
tests/test_date_tools.py CHANGED
@@ -1,124 +1,124 @@
1
- #!/usr/bin/python
2
- # -*- coding: UTF-8 -*-
3
- """
4
- 日期工具测试
5
- """
6
- import unittest
7
- from crawlo.tools import (
8
- TimeUtils,
9
- parse_time,
10
- format_time,
11
- time_diff,
12
- to_timestamp,
13
- to_datetime,
14
- now,
15
- to_timezone,
16
- to_utc,
17
- to_local
18
- )
19
-
20
-
21
- class TestDateTools(unittest.TestCase):
22
- """日期工具测试类"""
23
-
24
- def test_date_parsing(self):
25
- """测试日期解析功能"""
26
- # 测试标准格式
27
- dt = parse_time("2025-09-10 14:30:00")
28
- self.assertIsNotNone(dt)
29
- self.assertEqual(dt.year, 2025)
30
- self.assertEqual(dt.month, 9)
31
- self.assertEqual(dt.day, 10)
32
- self.assertEqual(dt.hour, 14)
33
- self.assertEqual(dt.minute, 30)
34
- self.assertEqual(dt.second, 0)
35
-
36
- # 测试不同格式
37
- dt2 = parse_time("September 10, 2025 2:30 PM")
38
- self.assertIsNotNone(dt2)
39
- self.assertEqual(dt2.year, 2025)
40
- self.assertEqual(dt2.month, 9)
41
- self.assertEqual(dt2.day, 10)
42
- self.assertEqual(dt2.hour, 14)
43
- self.assertEqual(dt2.minute, 30)
44
-
45
- def test_date_formatting(self):
46
- """测试日期格式化功能"""
47
- dt = parse_time("2025-09-10 14:30:00")
48
-
49
- # 测试标准格式
50
- formatted = format_time(dt, "%Y-%m-%d")
51
- self.assertEqual(formatted, "2025-09-10")
52
-
53
- # 测试中文格式
54
- formatted_cn = format_time(dt, "%Y年%m月%d日")
55
- self.assertEqual(formatted_cn, "2025年09月10日")
56
-
57
- def test_time_difference(self):
58
- """测试时间差计算功能"""
59
- start_time = "2025-09-10 10:00:00"
60
- end_time = "2025-09-10 14:30:45"
61
-
62
- # 测试秒级差值
63
- diff_seconds = time_diff(start_time, end_time, "seconds")
64
- self.assertEqual(diff_seconds, 16245) # 4小时30分45秒 = 16245秒
65
-
66
- # 测试分钟级差值
67
- diff_minutes = time_diff(start_time, end_time, "minutes")
68
- self.assertEqual(diff_minutes, 270) # 270分钟
69
-
70
- # 测试小时级差值
71
- diff_hours = time_diff(start_time, end_time, "hours")
72
- self.assertEqual(diff_hours, 4) # 4小时
73
-
74
- def test_timestamp_conversion(self):
75
- """测试时间戳转换功能"""
76
- # 测试转换为时间戳
77
- dt = parse_time("2025-09-10 14:30:00")
78
- timestamp = to_timestamp(dt)
79
- self.assertIsInstance(timestamp, float)
80
-
81
- # 测试从时间戳转换
82
- dt_from_ts = to_datetime(timestamp)
83
- self.assertEqual(dt.year, dt_from_ts.year)
84
- self.assertEqual(dt.month, dt_from_ts.month)
85
- self.assertEqual(dt.day, dt_from_ts.day)
86
- self.assertEqual(dt.hour, dt_from_ts.hour)
87
- self.assertEqual(dt.minute, dt_from_ts.minute)
88
- self.assertEqual(dt.second, dt_from_ts.second)
89
-
90
- def test_timezone_conversion(self):
91
- """测试时区转换功能"""
92
- dt = parse_time("2025-09-10 14:30:00")
93
-
94
- # 测试UTC转换
95
- utc_time = to_utc(dt)
96
- self.assertIsNotNone(utc_time)
97
-
98
- # 测试本地时区转换
99
- local_time = to_local(dt)
100
- self.assertIsNotNone(local_time)
101
-
102
- # 测试指定时区转换
103
- ny_time = to_timezone(dt, "America/New_York")
104
- self.assertIsNotNone(ny_time)
105
-
106
- def test_time_utils_class(self):
107
- """测试TimeUtils类方法"""
108
- # 测试日期加减
109
- base_date = "2025-09-10"
110
- plus_30_days = TimeUtils.add_days(base_date, 30)
111
- self.assertEqual(plus_30_days.month, 10)
112
- self.assertEqual(plus_30_days.day, 10)
113
-
114
- # 测试月份加减
115
- plus_3_months = TimeUtils.add_months(base_date, 3)
116
- self.assertEqual(plus_3_months.month, 12)
117
-
118
- # 测试闰年判断
119
- self.assertTrue(TimeUtils.is_leap_year(2024))
120
- self.assertFalse(TimeUtils.is_leap_year(2025))
121
-
122
-
123
- if __name__ == '__main__':
1
+ #!/usr/bin/python
2
+ # -*- coding: UTF-8 -*-
3
+ """
4
+ 日期工具测试
5
+ """
6
+ import unittest
7
+ from crawlo.tools import (
8
+ TimeUtils,
9
+ parse_time,
10
+ format_time,
11
+ time_diff,
12
+ to_timestamp,
13
+ to_datetime,
14
+ now,
15
+ to_timezone,
16
+ to_utc,
17
+ to_local
18
+ )
19
+
20
+
21
+ class TestDateTools(unittest.TestCase):
22
+ """日期工具测试类"""
23
+
24
+ def test_date_parsing(self):
25
+ """测试日期解析功能"""
26
+ # 测试标准格式
27
+ dt = parse_time("2025-09-10 14:30:00")
28
+ self.assertIsNotNone(dt)
29
+ self.assertEqual(dt.year, 2025)
30
+ self.assertEqual(dt.month, 9)
31
+ self.assertEqual(dt.day, 10)
32
+ self.assertEqual(dt.hour, 14)
33
+ self.assertEqual(dt.minute, 30)
34
+ self.assertEqual(dt.second, 0)
35
+
36
+ # 测试不同格式
37
+ dt2 = parse_time("September 10, 2025 2:30 PM")
38
+ self.assertIsNotNone(dt2)
39
+ self.assertEqual(dt2.year, 2025)
40
+ self.assertEqual(dt2.month, 9)
41
+ self.assertEqual(dt2.day, 10)
42
+ self.assertEqual(dt2.hour, 14)
43
+ self.assertEqual(dt2.minute, 30)
44
+
45
+ def test_date_formatting(self):
46
+ """测试日期格式化功能"""
47
+ dt = parse_time("2025-09-10 14:30:00")
48
+
49
+ # 测试标准格式
50
+ formatted = format_time(dt, "%Y-%m-%d")
51
+ self.assertEqual(formatted, "2025-09-10")
52
+
53
+ # 测试中文格式
54
+ formatted_cn = format_time(dt, "%Y年%m月%d日")
55
+ self.assertEqual(formatted_cn, "2025年09月10日")
56
+
57
+ def test_time_difference(self):
58
+ """测试时间差计算功能"""
59
+ start_time = "2025-09-10 10:00:00"
60
+ end_time = "2025-09-10 14:30:45"
61
+
62
+ # 测试秒级差值
63
+ diff_seconds = time_diff(start_time, end_time, "seconds")
64
+ self.assertEqual(diff_seconds, 16245) # 4小时30分45秒 = 16245秒
65
+
66
+ # 测试分钟级差值
67
+ diff_minutes = time_diff(start_time, end_time, "minutes")
68
+ self.assertEqual(diff_minutes, 270) # 270分钟
69
+
70
+ # 测试小时级差值
71
+ diff_hours = time_diff(start_time, end_time, "hours")
72
+ self.assertEqual(diff_hours, 4) # 4小时
73
+
74
+ def test_timestamp_conversion(self):
75
+ """测试时间戳转换功能"""
76
+ # 测试转换为时间戳
77
+ dt = parse_time("2025-09-10 14:30:00")
78
+ timestamp = to_timestamp(dt)
79
+ self.assertIsInstance(timestamp, float)
80
+
81
+ # 测试从时间戳转换
82
+ dt_from_ts = to_datetime(timestamp)
83
+ self.assertEqual(dt.year, dt_from_ts.year)
84
+ self.assertEqual(dt.month, dt_from_ts.month)
85
+ self.assertEqual(dt.day, dt_from_ts.day)
86
+ self.assertEqual(dt.hour, dt_from_ts.hour)
87
+ self.assertEqual(dt.minute, dt_from_ts.minute)
88
+ self.assertEqual(dt.second, dt_from_ts.second)
89
+
90
+ def test_timezone_conversion(self):
91
+ """测试时区转换功能"""
92
+ dt = parse_time("2025-09-10 14:30:00")
93
+
94
+ # 测试UTC转换
95
+ utc_time = to_utc(dt)
96
+ self.assertIsNotNone(utc_time)
97
+
98
+ # 测试本地时区转换
99
+ local_time = to_local(dt)
100
+ self.assertIsNotNone(local_time)
101
+
102
+ # 测试指定时区转换
103
+ ny_time = to_timezone(dt, "America/New_York")
104
+ self.assertIsNotNone(ny_time)
105
+
106
+ def test_time_utils_class(self):
107
+ """测试TimeUtils类方法"""
108
+ # 测试日期加减
109
+ base_date = "2025-09-10"
110
+ plus_30_days = TimeUtils.add_days(base_date, 30)
111
+ self.assertEqual(plus_30_days.month, 10)
112
+ self.assertEqual(plus_30_days.day, 10)
113
+
114
+ # 测试月份加减
115
+ plus_3_months = TimeUtils.add_months(base_date, 3)
116
+ self.assertEqual(plus_3_months.month, 12)
117
+
118
+ # 测试闰年判断
119
+ self.assertTrue(TimeUtils.is_leap_year(2024))
120
+ self.assertFalse(TimeUtils.is_leap_year(2025))
121
+
122
+
123
+ if __name__ == '__main__':
124
124
  unittest.main()
@@ -1,159 +1,159 @@
1
- #!/usr/bin/python
2
- # -*- coding:UTF-8 -*-
3
- """
4
- DefaultHeaderMiddleware 测试文件
5
- 用于测试默认请求头中间件的功能
6
- """
7
-
8
- import unittest
9
- from unittest.mock import Mock, patch
10
-
11
- from crawlo.middleware.default_header import DefaultHeaderMiddleware
12
- from crawlo.exceptions import NotConfiguredError
13
- from crawlo.settings.setting_manager import SettingManager
14
-
15
-
16
- class MockLogger:
17
- """Mock Logger 类,用于测试日志输出"""
18
- def __init__(self, name, level=None):
19
- self.name = name
20
- self.level = level
21
- self.logs = []
22
-
23
- def debug(self, msg):
24
- self.logs.append(('debug', msg))
25
-
26
- def info(self, msg):
27
- self.logs.append(('info', msg))
28
-
29
- def warning(self, msg):
30
- self.logs.append(('warning', msg))
31
-
32
- def error(self, msg):
33
- self.logs.append(('error', msg))
34
-
35
-
36
- class TestDefaultHeaderMiddleware(unittest.TestCase):
37
- """DefaultHeaderMiddleware 测试类"""
38
-
39
- def setUp(self):
40
- """测试前准备"""
41
- # 创建设置管理器
42
- self.settings = SettingManager()
43
-
44
- # 创建爬虫模拟对象
45
- self.crawler = Mock()
46
- self.crawler.settings = self.settings
47
-
48
- @patch('crawlo.utils.log.get_logger')
49
- def test_middleware_initialization_without_config(self, mock_get_logger):
50
- """测试没有配置时中间件初始化(清除默认配置)"""
51
- # 清除默认的请求头配置
52
- self.settings.set('DEFAULT_REQUEST_HEADERS', {})
53
- self.settings.set('USER_AGENT', None)
54
- self.settings.set('USER_AGENTS', [])
55
- self.settings.set('RANDOM_HEADERS', {})
56
- self.settings.set('LOG_LEVEL', 'INFO')
57
-
58
- mock_get_logger.return_value = MockLogger('DefaultHeaderMiddleware')
59
-
60
- # 应该抛出NotConfiguredError异常
61
- with self.assertRaises(NotConfiguredError):
62
- DefaultHeaderMiddleware.create_instance(self.crawler)
63
-
64
- @patch('crawlo.utils.log.get_logger')
65
- def test_middleware_initialization_with_default_headers(self, mock_get_logger):
66
- """测试配置默认请求头时中间件初始化"""
67
- # 设置默认请求头
68
- self.settings.set('DEFAULT_REQUEST_HEADERS', {
69
- 'User-Agent': 'Test-Agent',
70
- 'Accept': 'text/html'
71
- })
72
- self.settings.set('LOG_LEVEL', 'INFO')
73
-
74
- mock_get_logger.return_value = MockLogger('DefaultHeaderMiddleware')
75
-
76
- # 应该正常创建实例
77
- middleware = DefaultHeaderMiddleware.create_instance(self.crawler)
78
- self.assertIsInstance(middleware, DefaultHeaderMiddleware)
79
- self.assertIn('User-Agent', middleware.headers)
80
- self.assertIn('Accept', middleware.headers)
81
-
82
- @patch('crawlo.utils.log.get_logger')
83
- def test_middleware_initialization_with_user_agent(self, mock_get_logger):
84
- """测试配置User-Agent时中间件初始化"""
85
- # 清除默认的请求头配置
86
- self.settings.set('DEFAULT_REQUEST_HEADERS', {})
87
- # 设置User-Agent
88
- self.settings.set('USER_AGENT', 'Custom-Agent')
89
- self.settings.set('LOG_LEVEL', 'INFO')
90
-
91
- mock_get_logger.return_value = MockLogger('DefaultHeaderMiddleware')
92
-
93
- # 应该正常创建实例
94
- middleware = DefaultHeaderMiddleware.create_instance(self.crawler)
95
- self.assertIsInstance(middleware, DefaultHeaderMiddleware)
96
- self.assertIn('User-Agent', middleware.headers)
97
- self.assertEqual(middleware.headers['User-Agent'], 'Custom-Agent')
98
-
99
- @patch('crawlo.utils.log.get_logger')
100
- def test_process_request_with_default_headers(self, mock_get_logger):
101
- """测试处理请求时添加默认请求头"""
102
- # 设置默认请求头
103
- self.settings.set('DEFAULT_REQUEST_HEADERS', {
104
- 'User-Agent': 'Test-Agent',
105
- 'Accept': 'text/html'
106
- })
107
- self.settings.set('LOG_LEVEL', 'DEBUG')
108
-
109
- mock_logger = MockLogger('DefaultHeaderMiddleware')
110
- mock_get_logger.return_value = mock_logger
111
-
112
- middleware = DefaultHeaderMiddleware.create_instance(self.crawler)
113
-
114
- # 创建请求对象
115
- request = Mock()
116
- request.headers = {}
117
- request.url = 'http://example.com'
118
-
119
- # 处理请求
120
- middleware.process_request(request, Mock())
121
-
122
- # 验证请求头被添加
123
- self.assertIn('User-Agent', request.headers)
124
- self.assertEqual(request.headers['User-Agent'], 'Test-Agent')
125
- self.assertIn('Accept', request.headers)
126
- self.assertEqual(request.headers['Accept'], 'text/html')
127
-
128
- @patch('crawlo.utils.log.get_logger')
129
- def test_process_request_without_overwriting_existing_headers(self, mock_get_logger):
130
- """测试处理请求时不覆盖已存在的请求头"""
131
- # 设置默认请求头
132
- self.settings.set('DEFAULT_REQUEST_HEADERS', {
133
- 'User-Agent': 'Test-Agent',
134
- 'Accept': 'text/html'
135
- })
136
- self.settings.set('LOG_LEVEL', 'DEBUG')
137
-
138
- mock_logger = MockLogger('DefaultHeaderMiddleware')
139
- mock_get_logger.return_value = mock_logger
140
-
141
- middleware = DefaultHeaderMiddleware.create_instance(self.crawler)
142
-
143
- # 创建请求对象,已包含User-Agent
144
- request = Mock()
145
- request.headers = {'User-Agent': 'Existing-Agent'}
146
- request.url = 'http://example.com'
147
-
148
- # 处理请求
149
- middleware.process_request(request, Mock())
150
-
151
- # 验证已存在的请求头未被覆盖
152
- self.assertEqual(request.headers['User-Agent'], 'Existing-Agent')
153
- # 验证其他请求头被添加
154
- self.assertIn('Accept', request.headers)
155
- self.assertEqual(request.headers['Accept'], 'text/html')
156
-
157
-
158
- if __name__ == '__main__':
1
+ #!/usr/bin/python
2
+ # -*- coding:UTF-8 -*-
3
+ """
4
+ DefaultHeaderMiddleware 测试文件
5
+ 用于测试默认请求头中间件的功能
6
+ """
7
+
8
+ import unittest
9
+ from unittest.mock import Mock, patch
10
+
11
+ from crawlo.middleware.default_header import DefaultHeaderMiddleware
12
+ from crawlo.exceptions import NotConfiguredError
13
+ from crawlo.settings.setting_manager import SettingManager
14
+
15
+
16
+ class MockLogger:
17
+ """Mock Logger 类,用于测试日志输出"""
18
+ def __init__(self, name, level=None):
19
+ self.name = name
20
+ self.level = level
21
+ self.logs = []
22
+
23
+ def debug(self, msg):
24
+ self.logs.append(('debug', msg))
25
+
26
+ def info(self, msg):
27
+ self.logs.append(('info', msg))
28
+
29
+ def warning(self, msg):
30
+ self.logs.append(('warning', msg))
31
+
32
+ def error(self, msg):
33
+ self.logs.append(('error', msg))
34
+
35
+
36
+ class TestDefaultHeaderMiddleware(unittest.TestCase):
37
+ """DefaultHeaderMiddleware 测试类"""
38
+
39
+ def setUp(self):
40
+ """测试前准备"""
41
+ # 创建设置管理器
42
+ self.settings = SettingManager()
43
+
44
+ # 创建爬虫模拟对象
45
+ self.crawler = Mock()
46
+ self.crawler.settings = self.settings
47
+
48
+ @patch('crawlo.utils.log.get_logger')
49
+ def test_middleware_initialization_without_config(self, mock_get_logger):
50
+ """测试没有配置时中间件初始化(清除默认配置)"""
51
+ # 清除默认的请求头配置
52
+ self.settings.set('DEFAULT_REQUEST_HEADERS', {})
53
+ self.settings.set('USER_AGENT', None)
54
+ self.settings.set('USER_AGENTS', [])
55
+ self.settings.set('RANDOM_HEADERS', {})
56
+ self.settings.set('LOG_LEVEL', 'INFO')
57
+
58
+ mock_get_logger.return_value = MockLogger('DefaultHeaderMiddleware')
59
+
60
+ # 应该抛出NotConfiguredError异常
61
+ with self.assertRaises(NotConfiguredError):
62
+ DefaultHeaderMiddleware.create_instance(self.crawler)
63
+
64
+ @patch('crawlo.utils.log.get_logger')
65
+ def test_middleware_initialization_with_default_headers(self, mock_get_logger):
66
+ """测试配置默认请求头时中间件初始化"""
67
+ # 设置默认请求头
68
+ self.settings.set('DEFAULT_REQUEST_HEADERS', {
69
+ 'User-Agent': 'Test-Agent',
70
+ 'Accept': 'text/html'
71
+ })
72
+ self.settings.set('LOG_LEVEL', 'INFO')
73
+
74
+ mock_get_logger.return_value = MockLogger('DefaultHeaderMiddleware')
75
+
76
+ # 应该正常创建实例
77
+ middleware = DefaultHeaderMiddleware.create_instance(self.crawler)
78
+ self.assertIsInstance(middleware, DefaultHeaderMiddleware)
79
+ self.assertIn('User-Agent', middleware.headers)
80
+ self.assertIn('Accept', middleware.headers)
81
+
82
+ @patch('crawlo.utils.log.get_logger')
83
+ def test_middleware_initialization_with_user_agent(self, mock_get_logger):
84
+ """测试配置User-Agent时中间件初始化"""
85
+ # 清除默认的请求头配置
86
+ self.settings.set('DEFAULT_REQUEST_HEADERS', {})
87
+ # 设置User-Agent
88
+ self.settings.set('USER_AGENT', 'Custom-Agent')
89
+ self.settings.set('LOG_LEVEL', 'INFO')
90
+
91
+ mock_get_logger.return_value = MockLogger('DefaultHeaderMiddleware')
92
+
93
+ # 应该正常创建实例
94
+ middleware = DefaultHeaderMiddleware.create_instance(self.crawler)
95
+ self.assertIsInstance(middleware, DefaultHeaderMiddleware)
96
+ self.assertIn('User-Agent', middleware.headers)
97
+ self.assertEqual(middleware.headers['User-Agent'], 'Custom-Agent')
98
+
99
+ @patch('crawlo.utils.log.get_logger')
100
+ def test_process_request_with_default_headers(self, mock_get_logger):
101
+ """测试处理请求时添加默认请求头"""
102
+ # 设置默认请求头
103
+ self.settings.set('DEFAULT_REQUEST_HEADERS', {
104
+ 'User-Agent': 'Test-Agent',
105
+ 'Accept': 'text/html'
106
+ })
107
+ self.settings.set('LOG_LEVEL', 'DEBUG')
108
+
109
+ mock_logger = MockLogger('DefaultHeaderMiddleware')
110
+ mock_get_logger.return_value = mock_logger
111
+
112
+ middleware = DefaultHeaderMiddleware.create_instance(self.crawler)
113
+
114
+ # 创建请求对象
115
+ request = Mock()
116
+ request.headers = {}
117
+ request.url = 'http://example.com'
118
+
119
+ # 处理请求
120
+ middleware.process_request(request, Mock())
121
+
122
+ # 验证请求头被添加
123
+ self.assertIn('User-Agent', request.headers)
124
+ self.assertEqual(request.headers['User-Agent'], 'Test-Agent')
125
+ self.assertIn('Accept', request.headers)
126
+ self.assertEqual(request.headers['Accept'], 'text/html')
127
+
128
+ @patch('crawlo.utils.log.get_logger')
129
+ def test_process_request_without_overwriting_existing_headers(self, mock_get_logger):
130
+ """测试处理请求时不覆盖已存在的请求头"""
131
+ # 设置默认请求头
132
+ self.settings.set('DEFAULT_REQUEST_HEADERS', {
133
+ 'User-Agent': 'Test-Agent',
134
+ 'Accept': 'text/html'
135
+ })
136
+ self.settings.set('LOG_LEVEL', 'DEBUG')
137
+
138
+ mock_logger = MockLogger('DefaultHeaderMiddleware')
139
+ mock_get_logger.return_value = mock_logger
140
+
141
+ middleware = DefaultHeaderMiddleware.create_instance(self.crawler)
142
+
143
+ # 创建请求对象,已包含User-Agent
144
+ request = Mock()
145
+ request.headers = {'User-Agent': 'Existing-Agent'}
146
+ request.url = 'http://example.com'
147
+
148
+ # 处理请求
149
+ middleware.process_request(request, Mock())
150
+
151
+ # 验证已存在的请求头未被覆盖
152
+ self.assertEqual(request.headers['User-Agent'], 'Existing-Agent')
153
+ # 验证其他请求头被添加
154
+ self.assertIn('Accept', request.headers)
155
+ self.assertEqual(request.headers['Accept'], 'text/html')
156
+
157
+
158
+ if __name__ == '__main__':
159
159
  unittest.main()