crawlo 1.1.8__py3-none-any.whl → 1.1.9__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 (190) 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 +132 -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 +345 -345
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +136 -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 +32 -32
  50. crawlo/middleware/download_delay.py +28 -28
  51. crawlo/middleware/middleware_manager.py +135 -135
  52. crawlo/middleware/proxy.py +272 -272
  53. crawlo/middleware/request_ignore.py +30 -30
  54. crawlo/middleware/response_code.py +18 -18
  55. crawlo/middleware/response_filter.py +26 -26
  56. crawlo/middleware/retry.py +124 -124
  57. crawlo/mode_manager.py +211 -211
  58. crawlo/network/__init__.py +21 -21
  59. crawlo/network/request.py +338 -338
  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 +224 -224
  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 +316 -316
  70. crawlo/pipelines/pipeline_manager.py +61 -61
  71. crawlo/pipelines/redis_dedup_pipeline.py +167 -167
  72. crawlo/project.py +187 -187
  73. crawlo/queue/pqueue.py +37 -37
  74. crawlo/queue/queue_manager.py +334 -334
  75. crawlo/queue/redis_priority_queue.py +298 -298
  76. crawlo/settings/__init__.py +7 -7
  77. crawlo/settings/default_settings.py +219 -219
  78. crawlo/settings/setting_manager.py +122 -122
  79. crawlo/spider/__init__.py +639 -639
  80. crawlo/stats_collector.py +59 -59
  81. crawlo/subscriber.py +130 -130
  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 +109 -109
  87. crawlo/templates/project/pipelines.py.tmpl +96 -96
  88. crawlo/templates/project/run.py.tmpl +45 -45
  89. crawlo/templates/project/settings.py.tmpl +326 -326
  90. crawlo/templates/project/settings_distributed.py.tmpl +119 -119
  91. crawlo/templates/project/settings_gentle.py.tmpl +94 -94
  92. crawlo/templates/project/settings_high_performance.py.tmpl +151 -151
  93. crawlo/templates/project/settings_simple.py.tmpl +68 -68
  94. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  95. crawlo/templates/spider/spider.py.tmpl +141 -141
  96. crawlo/tools/__init__.py +182 -182
  97. crawlo/tools/anti_crawler.py +268 -268
  98. crawlo/tools/authenticated_proxy.py +240 -240
  99. crawlo/tools/data_validator.py +180 -180
  100. crawlo/tools/date_tools.py +35 -35
  101. crawlo/tools/distributed_coordinator.py +386 -386
  102. crawlo/tools/retry_mechanism.py +220 -220
  103. crawlo/tools/scenario_adapter.py +262 -262
  104. crawlo/utils/__init__.py +35 -35
  105. crawlo/utils/batch_processor.py +260 -260
  106. crawlo/utils/controlled_spider_mixin.py +439 -439
  107. crawlo/utils/date_tools.py +290 -290
  108. crawlo/utils/db_helper.py +343 -343
  109. crawlo/utils/enhanced_error_handler.py +359 -359
  110. crawlo/utils/env_config.py +105 -105
  111. crawlo/utils/error_handler.py +125 -125
  112. crawlo/utils/func_tools.py +82 -82
  113. crawlo/utils/large_scale_config.py +286 -286
  114. crawlo/utils/large_scale_helper.py +343 -343
  115. crawlo/utils/log.py +128 -128
  116. crawlo/utils/performance_monitor.py +284 -284
  117. crawlo/utils/queue_helper.py +175 -175
  118. crawlo/utils/redis_connection_pool.py +334 -334
  119. crawlo/utils/redis_key_validator.py +199 -199
  120. crawlo/utils/request.py +267 -267
  121. crawlo/utils/request_serializer.py +219 -219
  122. crawlo/utils/spider_loader.py +62 -62
  123. crawlo/utils/system.py +11 -11
  124. crawlo/utils/tools.py +4 -4
  125. crawlo/utils/url.py +39 -39
  126. {crawlo-1.1.8.dist-info → crawlo-1.1.9.dist-info}/METADATA +626 -626
  127. crawlo-1.1.9.dist-info/RECORD +190 -0
  128. examples/__init__.py +7 -7
  129. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  130. tests/__init__.py +7 -7
  131. tests/advanced_tools_example.py +275 -275
  132. tests/authenticated_proxy_example.py +236 -236
  133. tests/cleaners_example.py +160 -160
  134. tests/config_validation_demo.py +102 -102
  135. tests/controlled_spider_example.py +205 -205
  136. tests/date_tools_example.py +180 -180
  137. tests/dynamic_loading_example.py +523 -523
  138. tests/dynamic_loading_test.py +104 -104
  139. tests/env_config_example.py +133 -133
  140. tests/error_handling_example.py +171 -171
  141. tests/redis_key_validation_demo.py +130 -130
  142. tests/response_improvements_example.py +144 -144
  143. tests/test_advanced_tools.py +148 -148
  144. tests/test_all_redis_key_configs.py +145 -145
  145. tests/test_authenticated_proxy.py +141 -141
  146. tests/test_cleaners.py +54 -54
  147. tests/test_comprehensive.py +146 -146
  148. tests/test_config_validator.py +193 -193
  149. tests/test_date_tools.py +123 -123
  150. tests/test_double_crawlo_fix.py +207 -207
  151. tests/test_double_crawlo_fix_simple.py +124 -124
  152. tests/test_dynamic_downloaders_proxy.py +124 -124
  153. tests/test_dynamic_proxy.py +92 -92
  154. tests/test_dynamic_proxy_config.py +146 -146
  155. tests/test_dynamic_proxy_real.py +109 -109
  156. tests/test_edge_cases.py +303 -303
  157. tests/test_enhanced_error_handler.py +270 -270
  158. tests/test_env_config.py +121 -121
  159. tests/test_error_handler_compatibility.py +112 -112
  160. tests/test_final_validation.py +153 -153
  161. tests/test_framework_env_usage.py +103 -103
  162. tests/test_integration.py +356 -356
  163. tests/test_item_dedup_redis_key.py +122 -122
  164. tests/test_parsel.py +29 -29
  165. tests/test_performance.py +327 -327
  166. tests/test_proxy_health_check.py +32 -32
  167. tests/test_proxy_middleware_integration.py +136 -136
  168. tests/test_proxy_providers.py +56 -56
  169. tests/test_proxy_stats.py +19 -19
  170. tests/test_proxy_strategies.py +59 -59
  171. tests/test_queue_manager_double_crawlo.py +230 -230
  172. tests/test_queue_manager_redis_key.py +176 -176
  173. tests/test_redis_config.py +28 -28
  174. tests/test_redis_connection_pool.py +294 -294
  175. tests/test_redis_key_naming.py +181 -181
  176. tests/test_redis_key_validator.py +123 -123
  177. tests/test_redis_queue.py +224 -224
  178. tests/test_request_serialization.py +70 -70
  179. tests/test_response_improvements.py +152 -152
  180. tests/test_scheduler.py +241 -241
  181. tests/test_simple_response.py +61 -61
  182. tests/test_telecom_spider_redis_key.py +205 -205
  183. tests/test_template_content.py +87 -87
  184. tests/test_template_redis_key.py +134 -134
  185. tests/test_tools.py +153 -153
  186. tests/tools_example.py +257 -257
  187. crawlo-1.1.8.dist-info/RECORD +0 -190
  188. {crawlo-1.1.8.dist-info → crawlo-1.1.9.dist-info}/WHEEL +0 -0
  189. {crawlo-1.1.8.dist-info → crawlo-1.1.9.dist-info}/entry_points.txt +0 -0
  190. {crawlo-1.1.8.dist-info → crawlo-1.1.9.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)
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()