crawlo 1.3.1__py3-none-any.whl → 1.3.3__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 (219) hide show
  1. crawlo/__init__.py +63 -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 +322 -314
  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 +2 -2
  16. crawlo/core/engine.py +365 -365
  17. crawlo/core/processor.py +40 -40
  18. crawlo/core/scheduler.py +256 -256
  19. crawlo/crawler.py +1166 -1168
  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 +226 -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 +52 -45
  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/filters/__init__.py +154 -154
  40. crawlo/filters/aioredis_filter.py +234 -234
  41. crawlo/filters/memory_filter.py +269 -269
  42. crawlo/items/__init__.py +23 -23
  43. crawlo/items/base.py +21 -21
  44. crawlo/items/fields.py +52 -52
  45. crawlo/items/items.py +104 -104
  46. crawlo/middleware/__init__.py +21 -21
  47. crawlo/middleware/default_header.py +132 -132
  48. crawlo/middleware/download_delay.py +104 -104
  49. crawlo/middleware/middleware_manager.py +135 -135
  50. crawlo/middleware/offsite.py +123 -115
  51. crawlo/middleware/proxy.py +386 -386
  52. crawlo/middleware/request_ignore.py +86 -86
  53. crawlo/middleware/response_code.py +163 -163
  54. crawlo/middleware/response_filter.py +136 -136
  55. crawlo/middleware/retry.py +124 -124
  56. crawlo/middleware/simple_proxy.py +65 -65
  57. crawlo/mode_manager.py +187 -148
  58. crawlo/network/__init__.py +21 -21
  59. crawlo/network/request.py +379 -379
  60. crawlo/network/response.py +359 -359
  61. crawlo/pipelines/__init__.py +21 -21
  62. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  63. crawlo/pipelines/console_pipeline.py +39 -39
  64. crawlo/pipelines/csv_pipeline.py +316 -316
  65. crawlo/pipelines/database_dedup_pipeline.py +222 -222
  66. crawlo/pipelines/json_pipeline.py +218 -218
  67. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  68. crawlo/pipelines/mongo_pipeline.py +131 -131
  69. crawlo/pipelines/mysql_pipeline.py +318 -318
  70. crawlo/pipelines/pipeline_manager.py +75 -75
  71. crawlo/pipelines/redis_dedup_pipeline.py +166 -166
  72. crawlo/project.py +325 -297
  73. crawlo/queue/pqueue.py +37 -37
  74. crawlo/queue/queue_manager.py +379 -379
  75. crawlo/queue/redis_priority_queue.py +306 -306
  76. crawlo/settings/__init__.py +7 -7
  77. crawlo/settings/default_settings.py +225 -225
  78. crawlo/settings/setting_manager.py +198 -198
  79. crawlo/spider/__init__.py +639 -639
  80. crawlo/stats_collector.py +59 -59
  81. crawlo/subscriber.py +129 -129
  82. crawlo/task_manager.py +30 -30
  83. crawlo/templates/crawlo.cfg.tmpl +10 -10
  84. crawlo/templates/project/__init__.py.tmpl +3 -3
  85. crawlo/templates/project/items.py.tmpl +17 -17
  86. crawlo/templates/project/middlewares.py.tmpl +118 -118
  87. crawlo/templates/project/pipelines.py.tmpl +96 -96
  88. crawlo/templates/project/settings.py.tmpl +266 -261
  89. crawlo/templates/project/settings_distributed.py.tmpl +179 -174
  90. crawlo/templates/project/settings_gentle.py.tmpl +60 -95
  91. crawlo/templates/project/settings_high_performance.py.tmpl +130 -125
  92. crawlo/templates/project/settings_minimal.py.tmpl +34 -29
  93. crawlo/templates/project/settings_simple.py.tmpl +101 -96
  94. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  95. crawlo/templates/run.py.tmpl +38 -47
  96. crawlo/templates/spider/spider.py.tmpl +143 -143
  97. crawlo/tools/__init__.py +200 -200
  98. crawlo/tools/anti_crawler.py +268 -268
  99. crawlo/tools/authenticated_proxy.py +240 -240
  100. crawlo/tools/data_formatter.py +225 -225
  101. crawlo/tools/data_validator.py +180 -180
  102. crawlo/tools/date_tools.py +289 -289
  103. crawlo/tools/distributed_coordinator.py +388 -388
  104. crawlo/tools/encoding_converter.py +127 -127
  105. crawlo/tools/request_tools.py +82 -82
  106. crawlo/tools/retry_mechanism.py +224 -224
  107. crawlo/tools/scenario_adapter.py +262 -262
  108. crawlo/tools/text_cleaner.py +232 -232
  109. crawlo/utils/__init__.py +34 -34
  110. crawlo/utils/batch_processor.py +259 -259
  111. crawlo/utils/controlled_spider_mixin.py +439 -439
  112. crawlo/utils/db_helper.py +343 -343
  113. crawlo/utils/enhanced_error_handler.py +356 -356
  114. crawlo/utils/env_config.py +142 -142
  115. crawlo/utils/error_handler.py +123 -123
  116. crawlo/utils/func_tools.py +82 -82
  117. crawlo/utils/large_scale_config.py +286 -286
  118. crawlo/utils/large_scale_helper.py +344 -344
  119. crawlo/utils/log.py +199 -146
  120. crawlo/utils/performance_monitor.py +285 -285
  121. crawlo/utils/queue_helper.py +175 -175
  122. crawlo/utils/redis_connection_pool.py +351 -351
  123. crawlo/utils/redis_key_validator.py +198 -198
  124. crawlo/utils/request.py +267 -267
  125. crawlo/utils/request_serializer.py +218 -218
  126. crawlo/utils/spider_loader.py +61 -61
  127. crawlo/utils/system.py +11 -11
  128. crawlo/utils/tools.py +4 -4
  129. crawlo/utils/url.py +39 -39
  130. {crawlo-1.3.1.dist-info → crawlo-1.3.3.dist-info}/METADATA +1020 -1020
  131. crawlo-1.3.3.dist-info/RECORD +219 -0
  132. examples/__init__.py +7 -7
  133. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  134. tests/__init__.py +7 -7
  135. tests/advanced_tools_example.py +275 -275
  136. tests/authenticated_proxy_example.py +107 -107
  137. tests/cleaners_example.py +160 -160
  138. tests/config_validation_demo.py +142 -142
  139. tests/controlled_spider_example.py +205 -205
  140. tests/date_tools_example.py +180 -180
  141. tests/debug_pipelines.py +66 -66
  142. tests/dynamic_loading_example.py +523 -523
  143. tests/dynamic_loading_test.py +104 -104
  144. tests/env_config_example.py +133 -133
  145. tests/error_handling_example.py +171 -171
  146. tests/redis_key_validation_demo.py +130 -130
  147. tests/request_params_example.py +150 -150
  148. tests/response_improvements_example.py +144 -144
  149. tests/test_advanced_tools.py +148 -148
  150. tests/test_all_redis_key_configs.py +145 -145
  151. tests/test_authenticated_proxy.py +141 -141
  152. tests/test_cleaners.py +54 -54
  153. tests/test_comprehensive.py +146 -146
  154. tests/test_config_consistency.py +80 -80
  155. tests/test_config_merge.py +152 -152
  156. tests/test_config_validator.py +182 -182
  157. tests/test_crawlo_proxy_integration.py +108 -108
  158. tests/test_date_tools.py +123 -123
  159. tests/test_default_header_middleware.py +158 -158
  160. tests/test_distributed.py +65 -65
  161. tests/test_double_crawlo_fix.py +207 -207
  162. tests/test_double_crawlo_fix_simple.py +124 -124
  163. tests/test_download_delay_middleware.py +221 -221
  164. tests/test_downloader_proxy_compatibility.py +268 -268
  165. tests/test_dynamic_downloaders_proxy.py +124 -124
  166. tests/test_dynamic_proxy.py +92 -92
  167. tests/test_dynamic_proxy_config.py +146 -146
  168. tests/test_dynamic_proxy_real.py +109 -109
  169. tests/test_edge_cases.py +303 -303
  170. tests/test_enhanced_error_handler.py +270 -270
  171. tests/test_env_config.py +121 -121
  172. tests/test_error_handler_compatibility.py +112 -112
  173. tests/test_final_validation.py +153 -153
  174. tests/test_framework_env_usage.py +103 -103
  175. tests/test_integration.py +169 -169
  176. tests/test_item_dedup_redis_key.py +122 -122
  177. tests/test_mode_consistency.py +51 -51
  178. tests/test_offsite_middleware.py +221 -221
  179. tests/test_parsel.py +29 -29
  180. tests/test_performance.py +327 -327
  181. tests/test_proxy_api.py +264 -264
  182. tests/test_proxy_health_check.py +32 -32
  183. tests/test_proxy_middleware.py +121 -121
  184. tests/test_proxy_middleware_enhanced.py +216 -216
  185. tests/test_proxy_middleware_integration.py +136 -136
  186. tests/test_proxy_middleware_refactored.py +184 -184
  187. tests/test_proxy_providers.py +56 -56
  188. tests/test_proxy_stats.py +19 -19
  189. tests/test_proxy_strategies.py +59 -59
  190. tests/test_queue_manager_double_crawlo.py +173 -173
  191. tests/test_queue_manager_redis_key.py +176 -176
  192. tests/test_random_user_agent.py +72 -72
  193. tests/test_real_scenario_proxy.py +195 -195
  194. tests/test_redis_config.py +28 -28
  195. tests/test_redis_connection_pool.py +294 -294
  196. tests/test_redis_key_naming.py +181 -181
  197. tests/test_redis_key_validator.py +123 -123
  198. tests/test_redis_queue.py +224 -224
  199. tests/test_request_ignore_middleware.py +182 -182
  200. tests/test_request_params.py +111 -111
  201. tests/test_request_serialization.py +70 -70
  202. tests/test_response_code_middleware.py +349 -349
  203. tests/test_response_filter_middleware.py +427 -427
  204. tests/test_response_improvements.py +152 -152
  205. tests/test_retry_middleware.py +241 -241
  206. tests/test_scheduler.py +252 -252
  207. tests/test_scheduler_config_update.py +133 -133
  208. tests/test_simple_response.py +61 -61
  209. tests/test_telecom_spider_redis_key.py +205 -205
  210. tests/test_template_content.py +87 -87
  211. tests/test_template_redis_key.py +134 -134
  212. tests/test_tools.py +159 -159
  213. tests/test_user_agents.py +96 -96
  214. tests/tools_example.py +260 -260
  215. tests/verify_distributed.py +117 -117
  216. crawlo-1.3.1.dist-info/RECORD +0 -219
  217. {crawlo-1.3.1.dist-info → crawlo-1.3.3.dist-info}/WHEEL +0 -0
  218. {crawlo-1.3.1.dist-info → crawlo-1.3.3.dist-info}/entry_points.txt +0 -0
  219. {crawlo-1.3.1.dist-info → crawlo-1.3.3.dist-info}/top_level.txt +0 -0
@@ -1,52 +1,52 @@
1
- #!/usr/bin/env python3
2
- # -*- coding: utf-8 -*-
3
- """
4
- 测试模式一致性提示
5
- """
6
- import asyncio
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
- from crawlo.crawler import CrawlerProcess
14
- from crawlo.spider import Spider
15
- from crawlo import Request
16
-
17
-
18
- class TestSpider(Spider):
19
- name = "test_mode_spider"
20
-
21
- def start_requests(self):
22
- yield Request("https://httpbin.org/get")
23
-
24
- def parse(self, response):
25
- yield {"url": response.url, "status": response.status}
26
-
27
-
28
- async def test_mode_consistency():
29
- """测试模式一致性提示"""
30
- print("测试模式一致性提示...")
31
-
32
- try:
33
- # 创建爬虫进程
34
- process = CrawlerProcess()
35
-
36
- # 添加爬虫
37
- await process.crawl(TestSpider)
38
-
39
- print("模式一致性测试完成")
40
-
41
- except Exception as e:
42
- print(f"测试失败: {e}")
43
- import traceback
44
- traceback.print_exc()
45
-
46
-
47
- if __name__ == "__main__":
48
- # 设置日志级别
49
- import logging
50
- logging.basicConfig(level=logging.INFO)
51
-
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ """
4
+ 测试模式一致性提示
5
+ """
6
+ import asyncio
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
+ from crawlo.crawler import CrawlerProcess
14
+ from crawlo.spider import Spider
15
+ from crawlo import Request
16
+
17
+
18
+ class TestSpider(Spider):
19
+ name = "test_mode_spider"
20
+
21
+ def start_requests(self):
22
+ yield Request("https://httpbin.org/get")
23
+
24
+ def parse(self, response):
25
+ yield {"url": response.url, "status": response.status}
26
+
27
+
28
+ async def test_mode_consistency():
29
+ """测试模式一致性提示"""
30
+ print("测试模式一致性提示...")
31
+
32
+ try:
33
+ # 创建爬虫进程
34
+ process = CrawlerProcess()
35
+
36
+ # 添加爬虫
37
+ await process.crawl(TestSpider)
38
+
39
+ print("模式一致性测试完成")
40
+
41
+ except Exception as e:
42
+ print(f"测试失败: {e}")
43
+ import traceback
44
+ traceback.print_exc()
45
+
46
+
47
+ if __name__ == "__main__":
48
+ # 设置日志级别
49
+ import logging
50
+ logging.basicConfig(level=logging.INFO)
51
+
52
52
  asyncio.run(test_mode_consistency())
@@ -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()