crawlo 1.2.5__py3-none-any.whl → 1.2.7__py3-none-any.whl

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

Potentially problematic release.


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

Files changed (209) 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 +75 -88
  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 +138 -144
  12. crawlo/commands/list.py +155 -155
  13. crawlo/commands/run.py +323 -323
  14. crawlo/commands/startproject.py +436 -436
  15. crawlo/commands/stats.py +187 -187
  16. crawlo/commands/utils.py +186 -186
  17. crawlo/config.py +312 -312
  18. crawlo/config_validator.py +251 -251
  19. crawlo/core/__init__.py +2 -2
  20. crawlo/core/engine.py +365 -354
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +251 -143
  23. crawlo/crawler.py +1099 -1110
  24. crawlo/data/__init__.py +5 -5
  25. crawlo/data/user_agents.py +107 -107
  26. crawlo/downloader/__init__.py +266 -266
  27. crawlo/downloader/aiohttp_downloader.py +228 -221
  28. crawlo/downloader/cffi_downloader.py +256 -256
  29. crawlo/downloader/httpx_downloader.py +259 -259
  30. crawlo/downloader/hybrid_downloader.py +212 -212
  31. crawlo/downloader/playwright_downloader.py +402 -402
  32. crawlo/downloader/selenium_downloader.py +472 -472
  33. crawlo/event.py +11 -11
  34. crawlo/exceptions.py +81 -81
  35. crawlo/extension/__init__.py +39 -38
  36. crawlo/extension/health_check.py +141 -141
  37. crawlo/extension/log_interval.py +57 -57
  38. crawlo/extension/log_stats.py +81 -81
  39. crawlo/extension/logging_extension.py +43 -43
  40. crawlo/extension/memory_monitor.py +104 -104
  41. crawlo/extension/performance_profiler.py +133 -133
  42. crawlo/extension/request_recorder.py +107 -107
  43. crawlo/filters/__init__.py +154 -154
  44. crawlo/filters/aioredis_filter.py +234 -281
  45. crawlo/filters/memory_filter.py +269 -269
  46. crawlo/items/__init__.py +23 -23
  47. crawlo/items/base.py +21 -21
  48. crawlo/items/fields.py +52 -52
  49. crawlo/items/items.py +104 -104
  50. crawlo/middleware/__init__.py +21 -21
  51. crawlo/middleware/default_header.py +131 -131
  52. crawlo/middleware/download_delay.py +104 -104
  53. crawlo/middleware/middleware_manager.py +136 -135
  54. crawlo/middleware/offsite.py +114 -114
  55. crawlo/middleware/proxy.py +367 -367
  56. crawlo/middleware/request_ignore.py +86 -86
  57. crawlo/middleware/response_code.py +163 -163
  58. crawlo/middleware/response_filter.py +136 -136
  59. crawlo/middleware/retry.py +124 -124
  60. crawlo/mode_manager.py +211 -211
  61. crawlo/network/__init__.py +21 -21
  62. crawlo/network/request.py +338 -338
  63. crawlo/network/response.py +359 -359
  64. crawlo/pipelines/__init__.py +21 -21
  65. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  66. crawlo/pipelines/console_pipeline.py +39 -39
  67. crawlo/pipelines/csv_pipeline.py +316 -316
  68. crawlo/pipelines/database_dedup_pipeline.py +222 -222
  69. crawlo/pipelines/json_pipeline.py +218 -218
  70. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  71. crawlo/pipelines/mongo_pipeline.py +131 -131
  72. crawlo/pipelines/mysql_pipeline.py +317 -317
  73. crawlo/pipelines/pipeline_manager.py +62 -61
  74. crawlo/pipelines/redis_dedup_pipeline.py +166 -165
  75. crawlo/project.py +314 -279
  76. crawlo/queue/pqueue.py +37 -37
  77. crawlo/queue/queue_manager.py +377 -337
  78. crawlo/queue/redis_priority_queue.py +306 -299
  79. crawlo/settings/__init__.py +7 -7
  80. crawlo/settings/default_settings.py +219 -217
  81. crawlo/settings/setting_manager.py +122 -122
  82. crawlo/spider/__init__.py +639 -639
  83. crawlo/stats_collector.py +59 -59
  84. crawlo/subscriber.py +129 -129
  85. crawlo/task_manager.py +30 -30
  86. crawlo/templates/crawlo.cfg.tmpl +10 -10
  87. crawlo/templates/project/__init__.py.tmpl +3 -3
  88. crawlo/templates/project/items.py.tmpl +17 -17
  89. crawlo/templates/project/middlewares.py.tmpl +118 -118
  90. crawlo/templates/project/pipelines.py.tmpl +96 -96
  91. crawlo/templates/project/settings.py.tmpl +288 -324
  92. crawlo/templates/project/settings_distributed.py.tmpl +157 -154
  93. crawlo/templates/project/settings_gentle.py.tmpl +101 -128
  94. crawlo/templates/project/settings_high_performance.py.tmpl +135 -150
  95. crawlo/templates/project/settings_simple.py.tmpl +99 -103
  96. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  97. crawlo/templates/run.py.tmpl +45 -47
  98. crawlo/templates/spider/spider.py.tmpl +143 -143
  99. crawlo/tools/__init__.py +182 -182
  100. crawlo/tools/anti_crawler.py +268 -268
  101. crawlo/tools/authenticated_proxy.py +240 -240
  102. crawlo/tools/data_validator.py +180 -180
  103. crawlo/tools/date_tools.py +35 -35
  104. crawlo/tools/distributed_coordinator.py +386 -386
  105. crawlo/tools/retry_mechanism.py +220 -220
  106. crawlo/tools/scenario_adapter.py +262 -262
  107. crawlo/utils/__init__.py +35 -35
  108. crawlo/utils/batch_processor.py +259 -259
  109. crawlo/utils/controlled_spider_mixin.py +439 -439
  110. crawlo/utils/date_tools.py +290 -290
  111. crawlo/utils/db_helper.py +343 -343
  112. crawlo/utils/enhanced_error_handler.py +356 -356
  113. crawlo/utils/env_config.py +143 -106
  114. crawlo/utils/error_handler.py +123 -123
  115. crawlo/utils/func_tools.py +82 -82
  116. crawlo/utils/large_scale_config.py +286 -286
  117. crawlo/utils/large_scale_helper.py +344 -344
  118. crawlo/utils/log.py +128 -128
  119. crawlo/utils/performance_monitor.py +285 -285
  120. crawlo/utils/queue_helper.py +175 -175
  121. crawlo/utils/redis_connection_pool.py +351 -334
  122. crawlo/utils/redis_key_validator.py +198 -198
  123. crawlo/utils/request.py +267 -267
  124. crawlo/utils/request_serializer.py +218 -218
  125. crawlo/utils/spider_loader.py +61 -61
  126. crawlo/utils/system.py +11 -11
  127. crawlo/utils/tools.py +4 -4
  128. crawlo/utils/url.py +39 -39
  129. {crawlo-1.2.5.dist-info → crawlo-1.2.7.dist-info}/METADATA +764 -764
  130. crawlo-1.2.7.dist-info/RECORD +209 -0
  131. examples/__init__.py +7 -7
  132. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  133. tests/__init__.py +7 -7
  134. tests/advanced_tools_example.py +275 -275
  135. tests/authenticated_proxy_example.py +236 -236
  136. tests/cleaners_example.py +160 -160
  137. tests/config_validation_demo.py +102 -102
  138. tests/controlled_spider_example.py +205 -205
  139. tests/date_tools_example.py +180 -180
  140. tests/dynamic_loading_example.py +523 -523
  141. tests/dynamic_loading_test.py +104 -104
  142. tests/env_config_example.py +133 -133
  143. tests/error_handling_example.py +171 -171
  144. tests/redis_key_validation_demo.py +130 -130
  145. tests/response_improvements_example.py +144 -144
  146. tests/test_advanced_tools.py +148 -148
  147. tests/test_all_redis_key_configs.py +145 -145
  148. tests/test_authenticated_proxy.py +141 -141
  149. tests/test_cleaners.py +54 -54
  150. tests/test_comprehensive.py +146 -146
  151. tests/test_config_consistency.py +81 -0
  152. tests/test_config_validator.py +193 -193
  153. tests/test_crawlo_proxy_integration.py +172 -172
  154. tests/test_date_tools.py +123 -123
  155. tests/test_default_header_middleware.py +158 -158
  156. tests/test_double_crawlo_fix.py +207 -207
  157. tests/test_double_crawlo_fix_simple.py +124 -124
  158. tests/test_download_delay_middleware.py +221 -221
  159. tests/test_downloader_proxy_compatibility.py +268 -268
  160. tests/test_dynamic_downloaders_proxy.py +124 -124
  161. tests/test_dynamic_proxy.py +92 -92
  162. tests/test_dynamic_proxy_config.py +146 -146
  163. tests/test_dynamic_proxy_real.py +109 -109
  164. tests/test_edge_cases.py +303 -303
  165. tests/test_enhanced_error_handler.py +270 -270
  166. tests/test_env_config.py +121 -121
  167. tests/test_error_handler_compatibility.py +112 -112
  168. tests/test_final_validation.py +153 -153
  169. tests/test_framework_env_usage.py +103 -103
  170. tests/test_integration.py +356 -356
  171. tests/test_item_dedup_redis_key.py +122 -122
  172. tests/test_mode_consistency.py +52 -0
  173. tests/test_offsite_middleware.py +221 -221
  174. tests/test_parsel.py +29 -29
  175. tests/test_performance.py +327 -327
  176. tests/test_proxy_api.py +264 -264
  177. tests/test_proxy_health_check.py +32 -32
  178. tests/test_proxy_middleware.py +121 -121
  179. tests/test_proxy_middleware_enhanced.py +216 -216
  180. tests/test_proxy_middleware_integration.py +136 -136
  181. tests/test_proxy_providers.py +56 -56
  182. tests/test_proxy_stats.py +19 -19
  183. tests/test_proxy_strategies.py +59 -59
  184. tests/test_queue_manager_double_crawlo.py +173 -173
  185. tests/test_queue_manager_redis_key.py +176 -176
  186. tests/test_real_scenario_proxy.py +195 -195
  187. tests/test_redis_config.py +28 -28
  188. tests/test_redis_connection_pool.py +294 -294
  189. tests/test_redis_key_naming.py +181 -181
  190. tests/test_redis_key_validator.py +123 -123
  191. tests/test_redis_queue.py +224 -224
  192. tests/test_request_ignore_middleware.py +182 -182
  193. tests/test_request_serialization.py +70 -70
  194. tests/test_response_code_middleware.py +349 -349
  195. tests/test_response_filter_middleware.py +427 -427
  196. tests/test_response_improvements.py +152 -152
  197. tests/test_retry_middleware.py +241 -241
  198. tests/test_scheduler.py +252 -241
  199. tests/test_scheduler_config_update.py +134 -0
  200. tests/test_simple_response.py +61 -61
  201. tests/test_telecom_spider_redis_key.py +205 -205
  202. tests/test_template_content.py +87 -87
  203. tests/test_template_redis_key.py +134 -134
  204. tests/test_tools.py +153 -153
  205. tests/tools_example.py +257 -257
  206. crawlo-1.2.5.dist-info/RECORD +0 -206
  207. {crawlo-1.2.5.dist-info → crawlo-1.2.7.dist-info}/WHEEL +0 -0
  208. {crawlo-1.2.5.dist-info → crawlo-1.2.7.dist-info}/entry_points.txt +0 -0
  209. {crawlo-1.2.5.dist-info → crawlo-1.2.7.dist-info}/top_level.txt +0 -0
@@ -1,222 +1,222 @@
1
- #!/usr/bin/python
2
- # -*- coding:UTF-8 -*-
3
- """
4
- OffsiteMiddleware 测试文件
5
- 用于测试站外请求过滤中间件的功能
6
- """
7
-
8
- import asyncio
9
- import unittest
10
- from unittest.mock import Mock, patch
11
-
12
- from crawlo.middleware.offsite import OffsiteMiddleware
13
- from crawlo.exceptions import NotConfiguredError, IgnoreRequestError
14
- from crawlo.settings.setting_manager import SettingManager
15
-
16
-
17
- class MockLogger:
18
- """Mock Logger 类,用于测试日志输出"""
19
- def __init__(self, name, level=None):
20
- self.name = name
21
- self.level = level
22
- self.logs = []
23
-
24
- def debug(self, msg):
25
- self.logs.append(('debug', msg))
26
-
27
- def info(self, msg):
28
- self.logs.append(('info', msg))
29
-
30
- def warning(self, msg):
31
- self.logs.append(('warning', msg))
32
-
33
- def error(self, msg):
34
- self.logs.append(('error', msg))
35
-
36
-
37
- class MockStats:
38
- """Mock Stats 类,用于测试统计信息"""
39
- def __init__(self):
40
- self.stats = {}
41
-
42
- def inc_value(self, key, value=1):
43
- if key in self.stats:
44
- self.stats[key] += value
45
- else:
46
- self.stats[key] = value
47
-
48
-
49
- class TestOffsiteMiddleware(unittest.TestCase):
50
- """OffsiteMiddleware 测试类"""
51
-
52
- def setUp(self):
53
- """测试前准备"""
54
- # 创建设置管理器
55
- self.settings = SettingManager()
56
-
57
- # 创建爬虫模拟对象
58
- self.crawler = Mock()
59
- self.crawler.settings = self.settings
60
- self.crawler.stats = MockStats()
61
- self.crawler.logger = Mock()
62
-
63
- @patch('crawlo.utils.log.get_logger')
64
- def test_middleware_initialization_without_allowed_domains(self, mock_get_logger):
65
- """测试没有配置允许域名时中间件初始化"""
66
- mock_get_logger.return_value = MockLogger('OffsiteMiddleware')
67
-
68
- # 应该抛出NotConfiguredError异常
69
- with self.assertRaises(NotConfiguredError):
70
- OffsiteMiddleware.create_instance(self.crawler)
71
-
72
- @patch('crawlo.utils.log.get_logger')
73
- def test_middleware_initialization_with_allowed_domains(self, mock_get_logger):
74
- """测试配置允许域名时中间件初始化"""
75
- # 设置允许的域名
76
- self.settings.set('ALLOWED_DOMAINS', ['example.com', 'test.com'])
77
- self.settings.set('LOG_LEVEL', 'INFO')
78
-
79
- mock_get_logger.return_value = MockLogger('OffsiteMiddleware')
80
-
81
- # 应该正常创建实例
82
- middleware = OffsiteMiddleware.create_instance(self.crawler)
83
- self.assertIsInstance(middleware, OffsiteMiddleware)
84
- self.assertEqual(len(middleware.allowed_domains), 2)
85
- self.assertIn('example.com', middleware.allowed_domains)
86
- self.assertIn('test.com', middleware.allowed_domains)
87
-
88
- def test_is_offsite_request_with_valid_domain(self):
89
- """测试有效域名的站外请求判断"""
90
- # 设置允许的域名
91
- self.settings.set('ALLOWED_DOMAINS', ['example.com'])
92
- self.settings.set('LOG_LEVEL', 'INFO')
93
-
94
- # 创建中间件实例
95
- middleware = OffsiteMiddleware(
96
- stats=MockStats(),
97
- log_level='INFO',
98
- allowed_domains=['example.com']
99
- )
100
- middleware._compile_domains()
101
-
102
- # 创建请求对象
103
- request = Mock()
104
- request.url = 'http://example.com/page'
105
-
106
- # 应该不是站外请求
107
- self.assertFalse(middleware._is_offsite_request(request))
108
-
109
- def test_is_offsite_request_with_subdomain(self):
110
- """测试子域名的站外请求判断"""
111
- # 设置允许的域名
112
- self.settings.set('ALLOWED_DOMAINS', ['example.com'])
113
- self.settings.set('LOG_LEVEL', 'INFO')
114
-
115
- # 创建中间件实例
116
- middleware = OffsiteMiddleware(
117
- stats=MockStats(),
118
- log_level='INFO',
119
- allowed_domains=['example.com']
120
- )
121
- middleware._compile_domains()
122
-
123
- # 创建请求对象(子域名)
124
- request = Mock()
125
- request.url = 'http://sub.example.com/page'
126
-
127
- # 应该不是站外请求(子域名应该被允许)
128
- self.assertFalse(middleware._is_offsite_request(request))
129
-
130
- def test_is_offsite_request_with_invalid_domain(self):
131
- """测试无效域名的站外请求判断"""
132
- # 设置允许的域名
133
- self.settings.set('ALLOWED_DOMAINS', ['example.com'])
134
- self.settings.set('LOG_LEVEL', 'INFO')
135
-
136
- # 创建中间件实例
137
- middleware = OffsiteMiddleware(
138
- stats=MockStats(),
139
- log_level='INFO',
140
- allowed_domains=['example.com']
141
- )
142
- middleware._compile_domains()
143
-
144
- # 创建请求对象
145
- request = Mock()
146
- request.url = 'http://other.com/page'
147
-
148
- # 应该是站外请求
149
- self.assertTrue(middleware._is_offsite_request(request))
150
-
151
- def test_is_offsite_request_with_invalid_url(self):
152
- """测试无效URL的站外请求判断"""
153
- # 设置允许的域名
154
- self.settings.set('ALLOWED_DOMAINS', ['example.com'])
155
- self.settings.set('LOG_LEVEL', 'INFO')
156
-
157
- # 创建中间件实例
158
- middleware = OffsiteMiddleware(
159
- stats=MockStats(),
160
- log_level='INFO',
161
- allowed_domains=['example.com']
162
- )
163
- middleware._compile_domains()
164
-
165
- # 创建请求对象(无效URL)
166
- request = Mock()
167
- request.url = 'invalid-url'
168
-
169
- # 应该是站外请求
170
- self.assertTrue(middleware._is_offsite_request(request))
171
-
172
- @patch('crawlo.utils.log.get_logger')
173
- def test_process_request_with_offsite_request(self, mock_get_logger):
174
- """测试处理站外请求"""
175
- # 设置允许的域名
176
- self.settings.set('ALLOWED_DOMAINS', ['example.com'])
177
- self.settings.set('LOG_LEVEL', 'DEBUG')
178
-
179
- mock_logger = MockLogger('OffsiteMiddleware')
180
- mock_get_logger.return_value = mock_logger
181
-
182
- # 创建中间件实例
183
- middleware = OffsiteMiddleware.create_instance(self.crawler)
184
-
185
- # 创建请求对象(站外请求)
186
- request = Mock()
187
- request.url = 'http://other.com/page'
188
-
189
- # 应该抛出IgnoreRequestError异常
190
- with self.assertRaises(IgnoreRequestError):
191
- asyncio.run(middleware.process_request(request, Mock()))
192
-
193
- # 验证统计信息
194
- self.assertIn('offsite_request_count', self.crawler.stats.stats)
195
- self.assertEqual(self.crawler.stats.stats['offsite_request_count'], 1)
196
-
197
- @patch('crawlo.utils.log.get_logger')
198
- def test_process_request_with_valid_request(self, mock_get_logger):
199
- """测试处理有效请求"""
200
- # 设置允许的域名
201
- self.settings.set('ALLOWED_DOMAINS', ['example.com'])
202
- self.settings.set('LOG_LEVEL', 'DEBUG')
203
-
204
- mock_logger = MockLogger('OffsiteMiddleware')
205
- mock_get_logger.return_value = mock_logger
206
-
207
- # 创建中间件实例
208
- middleware = OffsiteMiddleware.create_instance(self.crawler)
209
-
210
- # 创建请求对象(有效请求)
211
- request = Mock()
212
- request.url = 'http://example.com/page'
213
-
214
- # 应该正常处理,不抛出异常
215
- result = asyncio.run(middleware.process_request(request, Mock()))
216
-
217
- # 返回None表示继续处理
218
- self.assertIsNone(result)
219
-
220
-
221
- if __name__ == '__main__':
1
+ #!/usr/bin/python
2
+ # -*- coding:UTF-8 -*-
3
+ """
4
+ OffsiteMiddleware 测试文件
5
+ 用于测试站外请求过滤中间件的功能
6
+ """
7
+
8
+ import asyncio
9
+ import unittest
10
+ from unittest.mock import Mock, patch
11
+
12
+ from crawlo.middleware.offsite import OffsiteMiddleware
13
+ from crawlo.exceptions import NotConfiguredError, IgnoreRequestError
14
+ from crawlo.settings.setting_manager import SettingManager
15
+
16
+
17
+ class MockLogger:
18
+ """Mock Logger 类,用于测试日志输出"""
19
+ def __init__(self, name, level=None):
20
+ self.name = name
21
+ self.level = level
22
+ self.logs = []
23
+
24
+ def debug(self, msg):
25
+ self.logs.append(('debug', msg))
26
+
27
+ def info(self, msg):
28
+ self.logs.append(('info', msg))
29
+
30
+ def warning(self, msg):
31
+ self.logs.append(('warning', msg))
32
+
33
+ def error(self, msg):
34
+ self.logs.append(('error', msg))
35
+
36
+
37
+ class MockStats:
38
+ """Mock Stats 类,用于测试统计信息"""
39
+ def __init__(self):
40
+ self.stats = {}
41
+
42
+ def inc_value(self, key, value=1):
43
+ if key in self.stats:
44
+ self.stats[key] += value
45
+ else:
46
+ self.stats[key] = value
47
+
48
+
49
+ class TestOffsiteMiddleware(unittest.TestCase):
50
+ """OffsiteMiddleware 测试类"""
51
+
52
+ def setUp(self):
53
+ """测试前准备"""
54
+ # 创建设置管理器
55
+ self.settings = SettingManager()
56
+
57
+ # 创建爬虫模拟对象
58
+ self.crawler = Mock()
59
+ self.crawler.settings = self.settings
60
+ self.crawler.stats = MockStats()
61
+ self.crawler.logger = Mock()
62
+
63
+ @patch('crawlo.utils.log.get_logger')
64
+ def test_middleware_initialization_without_allowed_domains(self, mock_get_logger):
65
+ """测试没有配置允许域名时中间件初始化"""
66
+ mock_get_logger.return_value = MockLogger('OffsiteMiddleware')
67
+
68
+ # 应该抛出NotConfiguredError异常
69
+ with self.assertRaises(NotConfiguredError):
70
+ OffsiteMiddleware.create_instance(self.crawler)
71
+
72
+ @patch('crawlo.utils.log.get_logger')
73
+ def test_middleware_initialization_with_allowed_domains(self, mock_get_logger):
74
+ """测试配置允许域名时中间件初始化"""
75
+ # 设置允许的域名
76
+ self.settings.set('ALLOWED_DOMAINS', ['example.com', 'test.com'])
77
+ self.settings.set('LOG_LEVEL', 'INFO')
78
+
79
+ mock_get_logger.return_value = MockLogger('OffsiteMiddleware')
80
+
81
+ # 应该正常创建实例
82
+ middleware = OffsiteMiddleware.create_instance(self.crawler)
83
+ self.assertIsInstance(middleware, OffsiteMiddleware)
84
+ self.assertEqual(len(middleware.allowed_domains), 2)
85
+ self.assertIn('example.com', middleware.allowed_domains)
86
+ self.assertIn('test.com', middleware.allowed_domains)
87
+
88
+ def test_is_offsite_request_with_valid_domain(self):
89
+ """测试有效域名的站外请求判断"""
90
+ # 设置允许的域名
91
+ self.settings.set('ALLOWED_DOMAINS', ['example.com'])
92
+ self.settings.set('LOG_LEVEL', 'INFO')
93
+
94
+ # 创建中间件实例
95
+ middleware = OffsiteMiddleware(
96
+ stats=MockStats(),
97
+ log_level='INFO',
98
+ allowed_domains=['example.com']
99
+ )
100
+ middleware._compile_domains()
101
+
102
+ # 创建请求对象
103
+ request = Mock()
104
+ request.url = 'http://example.com/page'
105
+
106
+ # 应该不是站外请求
107
+ self.assertFalse(middleware._is_offsite_request(request))
108
+
109
+ def test_is_offsite_request_with_subdomain(self):
110
+ """测试子域名的站外请求判断"""
111
+ # 设置允许的域名
112
+ self.settings.set('ALLOWED_DOMAINS', ['example.com'])
113
+ self.settings.set('LOG_LEVEL', 'INFO')
114
+
115
+ # 创建中间件实例
116
+ middleware = OffsiteMiddleware(
117
+ stats=MockStats(),
118
+ log_level='INFO',
119
+ allowed_domains=['example.com']
120
+ )
121
+ middleware._compile_domains()
122
+
123
+ # 创建请求对象(子域名)
124
+ request = Mock()
125
+ request.url = 'http://sub.example.com/page'
126
+
127
+ # 应该不是站外请求(子域名应该被允许)
128
+ self.assertFalse(middleware._is_offsite_request(request))
129
+
130
+ def test_is_offsite_request_with_invalid_domain(self):
131
+ """测试无效域名的站外请求判断"""
132
+ # 设置允许的域名
133
+ self.settings.set('ALLOWED_DOMAINS', ['example.com'])
134
+ self.settings.set('LOG_LEVEL', 'INFO')
135
+
136
+ # 创建中间件实例
137
+ middleware = OffsiteMiddleware(
138
+ stats=MockStats(),
139
+ log_level='INFO',
140
+ allowed_domains=['example.com']
141
+ )
142
+ middleware._compile_domains()
143
+
144
+ # 创建请求对象
145
+ request = Mock()
146
+ request.url = 'http://other.com/page'
147
+
148
+ # 应该是站外请求
149
+ self.assertTrue(middleware._is_offsite_request(request))
150
+
151
+ def test_is_offsite_request_with_invalid_url(self):
152
+ """测试无效URL的站外请求判断"""
153
+ # 设置允许的域名
154
+ self.settings.set('ALLOWED_DOMAINS', ['example.com'])
155
+ self.settings.set('LOG_LEVEL', 'INFO')
156
+
157
+ # 创建中间件实例
158
+ middleware = OffsiteMiddleware(
159
+ stats=MockStats(),
160
+ log_level='INFO',
161
+ allowed_domains=['example.com']
162
+ )
163
+ middleware._compile_domains()
164
+
165
+ # 创建请求对象(无效URL)
166
+ request = Mock()
167
+ request.url = 'invalid-url'
168
+
169
+ # 应该是站外请求
170
+ self.assertTrue(middleware._is_offsite_request(request))
171
+
172
+ @patch('crawlo.utils.log.get_logger')
173
+ def test_process_request_with_offsite_request(self, mock_get_logger):
174
+ """测试处理站外请求"""
175
+ # 设置允许的域名
176
+ self.settings.set('ALLOWED_DOMAINS', ['example.com'])
177
+ self.settings.set('LOG_LEVEL', 'DEBUG')
178
+
179
+ mock_logger = MockLogger('OffsiteMiddleware')
180
+ mock_get_logger.return_value = mock_logger
181
+
182
+ # 创建中间件实例
183
+ middleware = OffsiteMiddleware.create_instance(self.crawler)
184
+
185
+ # 创建请求对象(站外请求)
186
+ request = Mock()
187
+ request.url = 'http://other.com/page'
188
+
189
+ # 应该抛出IgnoreRequestError异常
190
+ with self.assertRaises(IgnoreRequestError):
191
+ asyncio.run(middleware.process_request(request, Mock()))
192
+
193
+ # 验证统计信息
194
+ self.assertIn('offsite_request_count', self.crawler.stats.stats)
195
+ self.assertEqual(self.crawler.stats.stats['offsite_request_count'], 1)
196
+
197
+ @patch('crawlo.utils.log.get_logger')
198
+ def test_process_request_with_valid_request(self, mock_get_logger):
199
+ """测试处理有效请求"""
200
+ # 设置允许的域名
201
+ self.settings.set('ALLOWED_DOMAINS', ['example.com'])
202
+ self.settings.set('LOG_LEVEL', 'DEBUG')
203
+
204
+ mock_logger = MockLogger('OffsiteMiddleware')
205
+ mock_get_logger.return_value = mock_logger
206
+
207
+ # 创建中间件实例
208
+ middleware = OffsiteMiddleware.create_instance(self.crawler)
209
+
210
+ # 创建请求对象(有效请求)
211
+ request = Mock()
212
+ request.url = 'http://example.com/page'
213
+
214
+ # 应该正常处理,不抛出异常
215
+ result = asyncio.run(middleware.process_request(request, Mock()))
216
+
217
+ # 返回None表示继续处理
218
+ self.assertIsNone(result)
219
+
220
+
221
+ if __name__ == '__main__':
222
222
  unittest.main()
tests/test_parsel.py CHANGED
@@ -1,30 +1,30 @@
1
- #!/usr/bin/python
2
- # -*- coding:UTF-8 -*-
3
- """
4
- parsel 库测试
5
- """
6
- import sys
7
- import os
8
-
9
- # 添加项目根目录到路径
10
- sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
11
-
12
- try:
13
- from parsel import Selector, SelectorList
14
- print("parsel 导入成功")
15
-
16
- # 测试基本功能
17
- html = "<html><body><h1>测试标题</h1></body></html>"
18
- selector = Selector(html)
19
- print("Selector 创建成功")
20
-
21
- elements = selector.css('h1')
22
- print("CSS 选择器执行成功")
23
-
24
- text = elements.get()
25
- print(f"获取文本: {text}")
26
-
27
- except Exception as e:
28
- print(f"错误: {e}")
29
- import traceback
1
+ #!/usr/bin/python
2
+ # -*- coding:UTF-8 -*-
3
+ """
4
+ parsel 库测试
5
+ """
6
+ import sys
7
+ import os
8
+
9
+ # 添加项目根目录到路径
10
+ sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
11
+
12
+ try:
13
+ from parsel import Selector, SelectorList
14
+ print("parsel 导入成功")
15
+
16
+ # 测试基本功能
17
+ html = "<html><body><h1>测试标题</h1></body></html>"
18
+ selector = Selector(html)
19
+ print("Selector 创建成功")
20
+
21
+ elements = selector.css('h1')
22
+ print("CSS 选择器执行成功")
23
+
24
+ text = elements.get()
25
+ print(f"获取文本: {text}")
26
+
27
+ except Exception as e:
28
+ print(f"错误: {e}")
29
+ import traceback
30
30
  traceback.print_exc()