crawlo 1.1.9__py3-none-any.whl → 1.2.1__py3-none-any.whl

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

Potentially problematic release.


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

Files changed (221) hide show
  1. crawlo/__init__.py +61 -61
  2. crawlo/__version__.py +1 -1
  3. crawlo/cleaners/__init__.py +60 -60
  4. crawlo/cleaners/data_formatter.py +225 -225
  5. crawlo/cleaners/encoding_converter.py +125 -125
  6. crawlo/cleaners/text_cleaner.py +232 -232
  7. crawlo/cli.py +65 -65
  8. crawlo/commands/__init__.py +14 -14
  9. crawlo/commands/check.py +594 -594
  10. crawlo/commands/genspider.py +151 -151
  11. crawlo/commands/help.py +142 -132
  12. crawlo/commands/list.py +155 -155
  13. crawlo/commands/run.py +292 -292
  14. crawlo/commands/startproject.py +418 -418
  15. crawlo/commands/stats.py +188 -188
  16. crawlo/commands/utils.py +186 -186
  17. crawlo/config.py +312 -312
  18. crawlo/config_validator.py +252 -252
  19. crawlo/core/__init__.py +2 -2
  20. crawlo/core/engine.py +354 -345
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +143 -136
  23. crawlo/crawler.py +1027 -1027
  24. crawlo/downloader/__init__.py +266 -266
  25. crawlo/downloader/aiohttp_downloader.py +220 -220
  26. crawlo/downloader/cffi_downloader.py +256 -256
  27. crawlo/downloader/httpx_downloader.py +259 -259
  28. crawlo/downloader/hybrid_downloader.py +213 -213
  29. crawlo/downloader/playwright_downloader.py +402 -402
  30. crawlo/downloader/selenium_downloader.py +472 -472
  31. crawlo/event.py +11 -11
  32. crawlo/exceptions.py +81 -81
  33. crawlo/extension/__init__.py +37 -37
  34. crawlo/extension/health_check.py +141 -141
  35. crawlo/extension/log_interval.py +57 -57
  36. crawlo/extension/log_stats.py +81 -81
  37. crawlo/extension/logging_extension.py +43 -43
  38. crawlo/extension/memory_monitor.py +104 -104
  39. crawlo/extension/performance_profiler.py +133 -133
  40. crawlo/extension/request_recorder.py +107 -107
  41. crawlo/filters/__init__.py +154 -154
  42. crawlo/filters/aioredis_filter.py +280 -280
  43. crawlo/filters/memory_filter.py +269 -269
  44. crawlo/items/__init__.py +23 -23
  45. crawlo/items/base.py +21 -21
  46. crawlo/items/fields.py +53 -53
  47. crawlo/items/items.py +104 -104
  48. crawlo/middleware/__init__.py +21 -21
  49. crawlo/middleware/default_header.py +132 -32
  50. crawlo/middleware/download_delay.py +105 -28
  51. crawlo/middleware/middleware_manager.py +135 -135
  52. crawlo/middleware/offsite.py +116 -0
  53. crawlo/middleware/proxy.py +366 -272
  54. crawlo/middleware/request_ignore.py +88 -30
  55. crawlo/middleware/response_code.py +164 -18
  56. crawlo/middleware/response_filter.py +138 -26
  57. crawlo/middleware/retry.py +124 -124
  58. crawlo/mode_manager.py +211 -211
  59. crawlo/network/__init__.py +21 -21
  60. crawlo/network/request.py +338 -338
  61. crawlo/network/response.py +359 -359
  62. crawlo/pipelines/__init__.py +21 -21
  63. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  64. crawlo/pipelines/console_pipeline.py +39 -39
  65. crawlo/pipelines/csv_pipeline.py +316 -316
  66. crawlo/pipelines/database_dedup_pipeline.py +224 -224
  67. crawlo/pipelines/json_pipeline.py +218 -218
  68. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  69. crawlo/pipelines/mongo_pipeline.py +131 -131
  70. crawlo/pipelines/mysql_pipeline.py +316 -316
  71. crawlo/pipelines/pipeline_manager.py +61 -61
  72. crawlo/pipelines/redis_dedup_pipeline.py +167 -167
  73. crawlo/project.py +187 -187
  74. crawlo/queue/pqueue.py +37 -37
  75. crawlo/queue/queue_manager.py +337 -334
  76. crawlo/queue/redis_priority_queue.py +298 -298
  77. crawlo/settings/__init__.py +7 -7
  78. crawlo/settings/default_settings.py +226 -219
  79. crawlo/settings/setting_manager.py +122 -122
  80. crawlo/spider/__init__.py +639 -639
  81. crawlo/stats_collector.py +59 -59
  82. crawlo/subscriber.py +130 -130
  83. crawlo/task_manager.py +30 -30
  84. crawlo/templates/crawlo.cfg.tmpl +10 -10
  85. crawlo/templates/project/__init__.py.tmpl +3 -3
  86. crawlo/templates/project/items.py.tmpl +17 -17
  87. crawlo/templates/project/middlewares.py.tmpl +118 -109
  88. crawlo/templates/project/pipelines.py.tmpl +96 -96
  89. crawlo/templates/project/run.py.tmpl +45 -45
  90. crawlo/templates/project/settings.py.tmpl +327 -326
  91. crawlo/templates/project/settings_distributed.py.tmpl +119 -119
  92. crawlo/templates/project/settings_gentle.py.tmpl +94 -94
  93. crawlo/templates/project/settings_high_performance.py.tmpl +151 -151
  94. crawlo/templates/project/settings_simple.py.tmpl +68 -68
  95. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  96. crawlo/templates/spider/spider.py.tmpl +143 -141
  97. crawlo/tools/__init__.py +182 -182
  98. crawlo/tools/anti_crawler.py +268 -268
  99. crawlo/tools/authenticated_proxy.py +240 -240
  100. crawlo/tools/data_validator.py +180 -180
  101. crawlo/tools/date_tools.py +35 -35
  102. crawlo/tools/distributed_coordinator.py +386 -386
  103. crawlo/tools/retry_mechanism.py +220 -220
  104. crawlo/tools/scenario_adapter.py +262 -262
  105. crawlo/utils/__init__.py +35 -35
  106. crawlo/utils/batch_processor.py +260 -260
  107. crawlo/utils/controlled_spider_mixin.py +439 -439
  108. crawlo/utils/date_tools.py +290 -290
  109. crawlo/utils/db_helper.py +343 -343
  110. crawlo/utils/enhanced_error_handler.py +359 -359
  111. crawlo/utils/env_config.py +105 -105
  112. crawlo/utils/error_handler.py +125 -125
  113. crawlo/utils/func_tools.py +82 -82
  114. crawlo/utils/large_scale_config.py +286 -286
  115. crawlo/utils/large_scale_helper.py +343 -343
  116. crawlo/utils/log.py +128 -128
  117. crawlo/utils/performance_monitor.py +284 -284
  118. crawlo/utils/queue_helper.py +175 -175
  119. crawlo/utils/redis_connection_pool.py +334 -334
  120. crawlo/utils/redis_key_validator.py +199 -199
  121. crawlo/utils/request.py +267 -267
  122. crawlo/utils/request_serializer.py +219 -219
  123. crawlo/utils/spider_loader.py +62 -62
  124. crawlo/utils/system.py +11 -11
  125. crawlo/utils/tools.py +4 -4
  126. crawlo/utils/url.py +39 -39
  127. crawlo-1.2.1.dist-info/METADATA +692 -0
  128. crawlo-1.2.1.dist-info/RECORD +220 -0
  129. examples/__init__.py +7 -7
  130. examples/aiohttp_settings.py +42 -0
  131. examples/curl_cffi_settings.py +41 -0
  132. examples/default_header_middleware_example.py +107 -0
  133. examples/default_header_spider_example.py +129 -0
  134. examples/download_delay_middleware_example.py +160 -0
  135. examples/httpx_settings.py +42 -0
  136. examples/multi_downloader_proxy_example.py +81 -0
  137. examples/offsite_middleware_example.py +55 -0
  138. examples/offsite_spider_example.py +107 -0
  139. examples/proxy_spider_example.py +166 -0
  140. examples/request_ignore_middleware_example.py +51 -0
  141. examples/request_ignore_spider_example.py +99 -0
  142. examples/response_code_middleware_example.py +52 -0
  143. examples/response_filter_middleware_example.py +67 -0
  144. examples/tong_hua_shun_settings.py +62 -0
  145. examples/tong_hua_shun_spider.py +170 -0
  146. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  147. tests/__init__.py +7 -7
  148. tests/advanced_tools_example.py +275 -275
  149. tests/authenticated_proxy_example.py +236 -236
  150. tests/cleaners_example.py +160 -160
  151. tests/config_validation_demo.py +102 -102
  152. tests/controlled_spider_example.py +205 -205
  153. tests/date_tools_example.py +180 -180
  154. tests/dynamic_loading_example.py +523 -523
  155. tests/dynamic_loading_test.py +104 -104
  156. tests/env_config_example.py +133 -133
  157. tests/error_handling_example.py +171 -171
  158. tests/redis_key_validation_demo.py +130 -130
  159. tests/response_improvements_example.py +144 -144
  160. tests/test_advanced_tools.py +148 -148
  161. tests/test_all_redis_key_configs.py +145 -145
  162. tests/test_authenticated_proxy.py +141 -141
  163. tests/test_cleaners.py +54 -54
  164. tests/test_comprehensive.py +146 -146
  165. tests/test_config_validator.py +193 -193
  166. tests/test_crawlo_proxy_integration.py +173 -0
  167. tests/test_date_tools.py +123 -123
  168. tests/test_default_header_middleware.py +159 -0
  169. tests/test_double_crawlo_fix.py +207 -207
  170. tests/test_double_crawlo_fix_simple.py +124 -124
  171. tests/test_download_delay_middleware.py +222 -0
  172. tests/test_downloader_proxy_compatibility.py +269 -0
  173. tests/test_dynamic_downloaders_proxy.py +124 -124
  174. tests/test_dynamic_proxy.py +92 -92
  175. tests/test_dynamic_proxy_config.py +146 -146
  176. tests/test_dynamic_proxy_real.py +109 -109
  177. tests/test_edge_cases.py +303 -303
  178. tests/test_enhanced_error_handler.py +270 -270
  179. tests/test_env_config.py +121 -121
  180. tests/test_error_handler_compatibility.py +112 -112
  181. tests/test_final_validation.py +153 -153
  182. tests/test_framework_env_usage.py +103 -103
  183. tests/test_integration.py +356 -356
  184. tests/test_item_dedup_redis_key.py +122 -122
  185. tests/test_offsite_middleware.py +222 -0
  186. tests/test_parsel.py +29 -29
  187. tests/test_performance.py +327 -327
  188. tests/test_proxy_api.py +265 -0
  189. tests/test_proxy_health_check.py +32 -32
  190. tests/test_proxy_middleware.py +122 -0
  191. tests/test_proxy_middleware_enhanced.py +217 -0
  192. tests/test_proxy_middleware_integration.py +136 -136
  193. tests/test_proxy_providers.py +56 -56
  194. tests/test_proxy_stats.py +19 -19
  195. tests/test_proxy_strategies.py +59 -59
  196. tests/test_queue_manager_double_crawlo.py +174 -231
  197. tests/test_queue_manager_redis_key.py +176 -176
  198. tests/test_real_scenario_proxy.py +196 -0
  199. tests/test_redis_config.py +28 -28
  200. tests/test_redis_connection_pool.py +294 -294
  201. tests/test_redis_key_naming.py +181 -181
  202. tests/test_redis_key_validator.py +123 -123
  203. tests/test_redis_queue.py +224 -224
  204. tests/test_request_ignore_middleware.py +183 -0
  205. tests/test_request_serialization.py +70 -70
  206. tests/test_response_code_middleware.py +350 -0
  207. tests/test_response_filter_middleware.py +428 -0
  208. tests/test_response_improvements.py +152 -152
  209. tests/test_retry_middleware.py +242 -0
  210. tests/test_scheduler.py +241 -241
  211. tests/test_simple_response.py +61 -61
  212. tests/test_telecom_spider_redis_key.py +205 -205
  213. tests/test_template_content.py +87 -87
  214. tests/test_template_redis_key.py +134 -134
  215. tests/test_tools.py +153 -153
  216. tests/tools_example.py +257 -257
  217. crawlo-1.1.9.dist-info/METADATA +0 -626
  218. crawlo-1.1.9.dist-info/RECORD +0 -190
  219. {crawlo-1.1.9.dist-info → crawlo-1.2.1.dist-info}/WHEEL +0 -0
  220. {crawlo-1.1.9.dist-info → crawlo-1.2.1.dist-info}/entry_points.txt +0 -0
  221. {crawlo-1.1.9.dist-info → crawlo-1.2.1.dist-info}/top_level.txt +0 -0
@@ -1,123 +1,123 @@
1
- #!/usr/bin/env python3
2
- # -*- coding: utf-8 -*-
3
- """
4
- 数据项去重Redis Key测试脚本
5
- 用于验证RedisDedupPipeline和示例项目中的Redis去重管道是否使用统一的Redis key命名规范
6
- """
7
- import sys
8
- import os
9
- import traceback
10
-
11
- # 添加项目根目录到路径
12
- sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
13
-
14
- from crawlo.pipelines.redis_dedup_pipeline import RedisDedupPipeline
15
-
16
-
17
- class MockSettings:
18
- """模拟设置类"""
19
- def __init__(self, project_name="test_project"):
20
- self.project_name = project_name
21
-
22
- def get(self, key, default=None):
23
- if key == 'PROJECT_NAME':
24
- return self.project_name
25
- elif key == 'REDIS_HOST':
26
- return 'localhost'
27
- elif key == 'REDIS_PORT':
28
- return 6379
29
- elif key == 'REDIS_DB':
30
- return 2
31
- elif key == 'REDIS_PASSWORD':
32
- return None
33
- elif key == 'LOG_LEVEL':
34
- return 'INFO'
35
- return default
36
-
37
- def getint(self, key, default=0):
38
- if key == 'REDIS_PORT':
39
- return 6379
40
- elif key == 'REDIS_DB':
41
- return 2
42
- return default
43
-
44
-
45
- class MockCrawler:
46
- """模拟爬虫类"""
47
- def __init__(self, project_name="test_project"):
48
- self.settings = MockSettings(project_name)
49
-
50
-
51
- async def test_item_dedup_redis_key():
52
- """测试数据项去重Redis key命名规范"""
53
- print("🔍 测试数据项去重Redis key命名规范...")
54
-
55
- try:
56
- # 测试不同的项目名称
57
- test_cases = [
58
- {
59
- "project_name": "books_distributed",
60
- "expected_key": "crawlo:books_distributed:item:fingerprint",
61
- "description": "书籍分布式项目"
62
- },
63
- {
64
- "project_name": "api_data_collection",
65
- "expected_key": "crawlo:api_data_collection:item:fingerprint",
66
- "description": "API数据采集项目"
67
- },
68
- {
69
- "project_name": "test_project",
70
- "expected_key": "crawlo:test_project:item:fingerprint",
71
- "description": "测试项目"
72
- }
73
- ]
74
-
75
- for i, test_case in enumerate(test_cases, 1):
76
- print(f" {i}. 测试 {test_case['description']}...")
77
-
78
- # 测试RedisDedupPipeline
79
- mock_crawler = MockCrawler(test_case["project_name"])
80
- pipeline = RedisDedupPipeline.from_crawler(mock_crawler)
81
-
82
- # 验证Redis key是否符合规范
83
- assert pipeline.redis_key == test_case["expected_key"], \
84
- f"Redis key不匹配: {pipeline.redis_key} != {test_case['expected_key']}"
85
-
86
- print(f" ✅ Redis key: {pipeline.redis_key}")
87
-
88
- print("✅ 数据项去重Redis key命名规范测试通过!")
89
- return True
90
-
91
- except Exception as e:
92
- print(f"❌ 数据项去重Redis key命名规范测试失败: {e}")
93
- traceback.print_exc()
94
- return False
95
-
96
-
97
- def main():
98
- """主测试函数"""
99
- print("🚀 开始数据项去重Redis key命名规范测试...")
100
- print("=" * 50)
101
-
102
- try:
103
- success = test_item_dedup_redis_key()
104
-
105
- print("=" * 50)
106
- if success:
107
- print("🎉 所有测试通过!数据项去重使用统一的Redis key命名规范")
108
- else:
109
- print("❌ 测试失败,请检查实现")
110
- return 1
111
-
112
- except Exception as e:
113
- print("=" * 50)
114
- print(f"❌ 测试过程中发生异常: {e}")
115
- traceback.print_exc()
116
- return 1
117
-
118
- return 0
119
-
120
-
121
- if __name__ == "__main__":
122
- exit_code = main()
1
+ #!/usr/bin/env python3
2
+ # -*- coding: utf-8 -*-
3
+ """
4
+ 数据项去重Redis Key测试脚本
5
+ 用于验证RedisDedupPipeline和示例项目中的Redis去重管道是否使用统一的Redis key命名规范
6
+ """
7
+ import sys
8
+ import os
9
+ import traceback
10
+
11
+ # 添加项目根目录到路径
12
+ sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
13
+
14
+ from crawlo.pipelines.redis_dedup_pipeline import RedisDedupPipeline
15
+
16
+
17
+ class MockSettings:
18
+ """模拟设置类"""
19
+ def __init__(self, project_name="test_project"):
20
+ self.project_name = project_name
21
+
22
+ def get(self, key, default=None):
23
+ if key == 'PROJECT_NAME':
24
+ return self.project_name
25
+ elif key == 'REDIS_HOST':
26
+ return 'localhost'
27
+ elif key == 'REDIS_PORT':
28
+ return 6379
29
+ elif key == 'REDIS_DB':
30
+ return 2
31
+ elif key == 'REDIS_PASSWORD':
32
+ return None
33
+ elif key == 'LOG_LEVEL':
34
+ return 'INFO'
35
+ return default
36
+
37
+ def getint(self, key, default=0):
38
+ if key == 'REDIS_PORT':
39
+ return 6379
40
+ elif key == 'REDIS_DB':
41
+ return 2
42
+ return default
43
+
44
+
45
+ class MockCrawler:
46
+ """模拟爬虫类"""
47
+ def __init__(self, project_name="test_project"):
48
+ self.settings = MockSettings(project_name)
49
+
50
+
51
+ async def test_item_dedup_redis_key():
52
+ """测试数据项去重Redis key命名规范"""
53
+ print("🔍 测试数据项去重Redis key命名规范...")
54
+
55
+ try:
56
+ # 测试不同的项目名称
57
+ test_cases = [
58
+ {
59
+ "project_name": "books_distributed",
60
+ "expected_key": "crawlo:books_distributed:item:fingerprint",
61
+ "description": "书籍分布式项目"
62
+ },
63
+ {
64
+ "project_name": "api_data_collection",
65
+ "expected_key": "crawlo:api_data_collection:item:fingerprint",
66
+ "description": "API数据采集项目"
67
+ },
68
+ {
69
+ "project_name": "test_project",
70
+ "expected_key": "crawlo:test_project:item:fingerprint",
71
+ "description": "测试项目"
72
+ }
73
+ ]
74
+
75
+ for i, test_case in enumerate(test_cases, 1):
76
+ print(f" {i}. 测试 {test_case['description']}...")
77
+
78
+ # 测试RedisDedupPipeline
79
+ mock_crawler = MockCrawler(test_case["project_name"])
80
+ pipeline = RedisDedupPipeline.from_crawler(mock_crawler)
81
+
82
+ # 验证Redis key是否符合规范
83
+ assert pipeline.redis_key == test_case["expected_key"], \
84
+ f"Redis key不匹配: {pipeline.redis_key} != {test_case['expected_key']}"
85
+
86
+ print(f" ✅ Redis key: {pipeline.redis_key}")
87
+
88
+ print("✅ 数据项去重Redis key命名规范测试通过!")
89
+ return True
90
+
91
+ except Exception as e:
92
+ print(f"❌ 数据项去重Redis key命名规范测试失败: {e}")
93
+ traceback.print_exc()
94
+ return False
95
+
96
+
97
+ def main():
98
+ """主测试函数"""
99
+ print("🚀 开始数据项去重Redis key命名规范测试...")
100
+ print("=" * 50)
101
+
102
+ try:
103
+ success = test_item_dedup_redis_key()
104
+
105
+ print("=" * 50)
106
+ if success:
107
+ print("🎉 所有测试通过!数据项去重使用统一的Redis key命名规范")
108
+ else:
109
+ print("❌ 测试失败,请检查实现")
110
+ return 1
111
+
112
+ except Exception as e:
113
+ print("=" * 50)
114
+ print(f"❌ 测试过程中发生异常: {e}")
115
+ traceback.print_exc()
116
+ return 1
117
+
118
+ return 0
119
+
120
+
121
+ if __name__ == "__main__":
122
+ exit_code = main()
123
123
  sys.exit(exit_code)
@@ -0,0 +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__':
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()