crawlo 1.1.6__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 -40
  8. crawlo/commands/__init__.py +14 -13
  9. crawlo/commands/check.py +594 -594
  10. crawlo/commands/genspider.py +151 -151
  11. crawlo/commands/help.py +133 -0
  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 -110
  87. crawlo/templates/project/pipelines.py.tmpl +96 -97
  88. crawlo/templates/project/run.py.tmpl +46 -252
  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-1.1.6.dist-info → crawlo-1.1.9.dist-info}/METADATA +626 -401
  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-1.1.6.dist-info/RECORD +0 -189
  188. {crawlo-1.1.6.dist-info → crawlo-1.1.9.dist-info}/WHEEL +0 -0
  189. {crawlo-1.1.6.dist-info → crawlo-1.1.9.dist-info}/entry_points.txt +0 -0
  190. {crawlo-1.1.6.dist-info → crawlo-1.1.9.dist-info}/top_level.txt +0 -0
@@ -1,93 +1,93 @@
1
- #!/usr/bin/python
2
- # -*- coding: UTF-8 -*-
3
- """
4
- 测试动态下载器(Selenium和Playwright)的代理功能
5
- """
6
-
7
- import asyncio
8
- from crawlo.network.request import Request
9
- from crawlo.tools import AuthenticatedProxy
10
-
11
-
12
- def test_proxy_with_selenium():
13
- """测试Selenium下载器与认证代理"""
14
- print("=== 测试Selenium下载器与认证代理 ===")
15
-
16
- # 代理配置
17
- proxy_config = {
18
- "http": "http://dwe20241014:Dwe0101014@182.201.243.186:58111",
19
- "https": "http://dwe20241014:Dwe0101014@182.201.243.186:58111"
20
- }
21
-
22
- # 创建代理对象
23
- proxy_url = proxy_config["http"]
24
- proxy = AuthenticatedProxy(proxy_url)
25
-
26
- print(f"原始代理URL: {proxy_url}")
27
- print(f"清洁URL: {proxy.clean_url}")
28
- print(f"认证信息: {proxy.get_auth_credentials()}")
29
-
30
- # Selenium的代理设置方式
31
- print(f"Selenium代理设置方式:")
32
- print(f" 1. 在设置中配置: SELENIUM_PROXY = '{proxy.clean_url}'")
33
- print(f" 2. 认证信息需要通过其他方式处理")
34
-
35
- # 对于带认证的代理,Selenium需要特殊处理
36
- if proxy.username and proxy.password:
37
- print(f" 3. 认证信息:")
38
- print(f" 用户名: {proxy.username}")
39
- print(f" 密码: {proxy.password}")
40
- print(f" 认证头: {proxy.get_auth_header()}")
41
-
42
- print("Selenium测试完成!")
43
-
44
-
45
- async def test_proxy_with_playwright():
46
- """测试Playwright下载器与认证代理"""
47
- print("\n=== 测试Playwright下载器与认证代理 ===")
48
-
49
- # 代理配置
50
- proxy_config = {
51
- "http": "http://dwe20241014:Dwe0101014@182.201.243.186:58111",
52
- "https": "http://dwe20241014:Dwe0101014@182.201.243.186:58111"
53
- }
54
-
55
- # 创建代理对象
56
- proxy_url = proxy_config["http"]
57
- proxy = AuthenticatedProxy(proxy_url)
58
-
59
- print(f"原始代理URL: {proxy_url}")
60
- print(f"清洁URL: {proxy.clean_url}")
61
- print(f"认证信息: {proxy.get_auth_credentials()}")
62
-
63
- # Playwright的代理设置方式
64
- print(f"Playwright代理设置方式:")
65
- print(f" 1. 在启动浏览器时配置代理:")
66
- print(f" browser = await playwright.chromium.launch(proxy={{'server': '{proxy.clean_url}'}})")
67
-
68
- # 对于带认证的代理,Playwright需要在代理配置中包含认证信息
69
- if proxy.username and proxy.password:
70
- print(f" 2. 带认证的代理配置:")
71
- print(f" proxy_config = {{")
72
- print(f" 'server': '{proxy.clean_url}',")
73
- print(f" 'username': '{proxy.username}',")
74
- print(f" 'password': '{proxy.password}'")
75
- print(f" }}")
76
- print(f" browser = await playwright.chromium.launch(proxy=proxy_config)")
77
-
78
- print("Playwright测试完成!")
79
-
80
-
81
- async def main():
82
- """主测试函数"""
83
- print("开始测试动态下载器的代理功能...\n")
84
-
85
- # 测试各个下载器
86
- test_proxy_with_selenium()
87
- await test_proxy_with_playwright()
88
-
89
- print("\n所有测试完成!")
90
-
91
-
92
- if __name__ == "__main__":
1
+ #!/usr/bin/python
2
+ # -*- coding: UTF-8 -*-
3
+ """
4
+ 测试动态下载器(Selenium和Playwright)的代理功能
5
+ """
6
+
7
+ import asyncio
8
+ from crawlo.network.request import Request
9
+ from crawlo.tools import AuthenticatedProxy
10
+
11
+
12
+ def test_proxy_with_selenium():
13
+ """测试Selenium下载器与认证代理"""
14
+ print("=== 测试Selenium下载器与认证代理 ===")
15
+
16
+ # 代理配置
17
+ proxy_config = {
18
+ "http": "http://dwe20241014:Dwe0101014@182.201.243.186:58111",
19
+ "https": "http://dwe20241014:Dwe0101014@182.201.243.186:58111"
20
+ }
21
+
22
+ # 创建代理对象
23
+ proxy_url = proxy_config["http"]
24
+ proxy = AuthenticatedProxy(proxy_url)
25
+
26
+ print(f"原始代理URL: {proxy_url}")
27
+ print(f"清洁URL: {proxy.clean_url}")
28
+ print(f"认证信息: {proxy.get_auth_credentials()}")
29
+
30
+ # Selenium的代理设置方式
31
+ print(f"Selenium代理设置方式:")
32
+ print(f" 1. 在设置中配置: SELENIUM_PROXY = '{proxy.clean_url}'")
33
+ print(f" 2. 认证信息需要通过其他方式处理")
34
+
35
+ # 对于带认证的代理,Selenium需要特殊处理
36
+ if proxy.username and proxy.password:
37
+ print(f" 3. 认证信息:")
38
+ print(f" 用户名: {proxy.username}")
39
+ print(f" 密码: {proxy.password}")
40
+ print(f" 认证头: {proxy.get_auth_header()}")
41
+
42
+ print("Selenium测试完成!")
43
+
44
+
45
+ async def test_proxy_with_playwright():
46
+ """测试Playwright下载器与认证代理"""
47
+ print("\n=== 测试Playwright下载器与认证代理 ===")
48
+
49
+ # 代理配置
50
+ proxy_config = {
51
+ "http": "http://dwe20241014:Dwe0101014@182.201.243.186:58111",
52
+ "https": "http://dwe20241014:Dwe0101014@182.201.243.186:58111"
53
+ }
54
+
55
+ # 创建代理对象
56
+ proxy_url = proxy_config["http"]
57
+ proxy = AuthenticatedProxy(proxy_url)
58
+
59
+ print(f"原始代理URL: {proxy_url}")
60
+ print(f"清洁URL: {proxy.clean_url}")
61
+ print(f"认证信息: {proxy.get_auth_credentials()}")
62
+
63
+ # Playwright的代理设置方式
64
+ print(f"Playwright代理设置方式:")
65
+ print(f" 1. 在启动浏览器时配置代理:")
66
+ print(f" browser = await playwright.chromium.launch(proxy={{'server': '{proxy.clean_url}'}})")
67
+
68
+ # 对于带认证的代理,Playwright需要在代理配置中包含认证信息
69
+ if proxy.username and proxy.password:
70
+ print(f" 2. 带认证的代理配置:")
71
+ print(f" proxy_config = {{")
72
+ print(f" 'server': '{proxy.clean_url}',")
73
+ print(f" 'username': '{proxy.username}',")
74
+ print(f" 'password': '{proxy.password}'")
75
+ print(f" }}")
76
+ print(f" browser = await playwright.chromium.launch(proxy=proxy_config)")
77
+
78
+ print("Playwright测试完成!")
79
+
80
+
81
+ async def main():
82
+ """主测试函数"""
83
+ print("开始测试动态下载器的代理功能...\n")
84
+
85
+ # 测试各个下载器
86
+ test_proxy_with_selenium()
87
+ await test_proxy_with_playwright()
88
+
89
+ print("\n所有测试完成!")
90
+
91
+
92
+ if __name__ == "__main__":
93
93
  asyncio.run(main())
@@ -1,147 +1,147 @@
1
- #!/usr/bin/python
2
- # -*- coding: UTF-8 -*-
3
- """
4
- 测试动态下载器(Selenium和Playwright)的代理配置逻辑
5
- """
6
-
7
- from crawlo.tools import AuthenticatedProxy
8
-
9
-
10
- def test_selenium_proxy_logic():
11
- """测试Selenium下载器的代理配置逻辑"""
12
- print("=== 测试Selenium下载器的代理配置逻辑 ===")
13
-
14
- # 代理配置
15
- proxy_config = {
16
- "http": "http://dwe20241014:Dwe0101014@182.201.243.186:58111",
17
- "https": "http://dwe20241014:Dwe0101014@182.201.243.186:58111"
18
- }
19
-
20
- # 创建代理对象
21
- proxy_url = proxy_config["http"]
22
- proxy = AuthenticatedProxy(proxy_url)
23
-
24
- print(f"原始代理URL: {proxy_url}")
25
- print(f"清洁URL: {proxy.clean_url}")
26
- print(f"认证信息: {proxy.get_auth_credentials()}")
27
-
28
- # 模拟Selenium的代理配置逻辑
29
- print(f"\nSelenium代理配置逻辑:")
30
- print(f" 1. 在爬虫设置中配置:")
31
- print(f" settings = {{")
32
- print(f" 'SELENIUM_PROXY': '{proxy.clean_url}',")
33
- print(f" }}")
34
-
35
- # 对于带认证的代理,需要特殊处理
36
- if proxy.username and proxy.password:
37
- print(f"\n 2. 带认证代理的处理逻辑:")
38
- print(f" - 用户名: {proxy.username}")
39
- print(f" - 密码: {proxy.password}")
40
- print(f" - 认证头: {proxy.get_auth_header()}")
41
- print(f" - 处理方式: 通过浏览器扩展或手动输入认证信息")
42
-
43
- print("\nSelenium配置逻辑测试完成!")
44
-
45
-
46
- def test_playwright_proxy_logic():
47
- """测试Playwright下载器的代理配置逻辑"""
48
- print("\n=== 测试Playwright下载器的代理配置逻辑 ===")
49
-
50
- # 代理配置
51
- proxy_config = {
52
- "http": "http://dwe20241014:Dwe0101014@182.201.243.186:58111",
53
- "https": "http://dwe20241014:Dwe0101014@182.201.243.186:58111"
54
- }
55
-
56
- # 创建代理对象
57
- proxy_url = proxy_config["http"]
58
- proxy = AuthenticatedProxy(proxy_url)
59
-
60
- print(f"原始代理URL: {proxy_url}")
61
- print(f"清洁URL: {proxy.clean_url}")
62
- print(f"认证信息: {proxy.get_auth_credentials()}")
63
-
64
- # 模拟Playwright的代理配置逻辑
65
- print(f"\nPlaywright代理配置逻辑:")
66
- print(f" 1. 简单代理配置:")
67
- print(f" settings = {{")
68
- print(f" 'PLAYWRIGHT_PROXY': '{proxy.clean_url}',")
69
- print(f" }}")
70
-
71
- # 对于带认证的代理,Playwright可以直接在代理配置中包含认证信息
72
- if proxy.username and proxy.password:
73
- print(f"\n 2. 带认证的代理配置逻辑:")
74
- print(f" settings = {{")
75
- print(f" 'PLAYWRIGHT_PROXY': {{")
76
- print(f" 'server': '{proxy.clean_url}',")
77
- print(f" 'username': '{proxy.username}',")
78
- print(f" 'password': '{proxy.password}'")
79
- print(f" }}")
80
- print(f" }}")
81
- print(f" 实现方式: 在启动浏览器时传递proxy参数")
82
-
83
- print("\nPlaywright配置逻辑测试完成!")
84
-
85
-
86
- def show_proxy_configuration_examples():
87
- """显示代理配置示例"""
88
- print("\n=== 代理配置示例 ===")
89
-
90
- # 不同类型的代理配置示例
91
- examples = [
92
- {
93
- "name": "带认证HTTP代理",
94
- "url": "http://username:password@proxy.example.com:8080",
95
- "selenium_config": "SELENIUM_PROXY = 'http://proxy.example.com:8080'",
96
- "playwright_config": "PLAYWRIGHT_PROXY = {'server': 'http://proxy.example.com:8080', 'username': 'username', 'password': 'password'}"
97
- },
98
- {
99
- "name": "带认证HTTPS代理",
100
- "url": "https://user:pass@secure-proxy.example.com:443",
101
- "selenium_config": "SELENIUM_PROXY = 'https://secure-proxy.example.com:443'",
102
- "playwright_config": "PLAYWRIGHT_PROXY = {'server': 'https://secure-proxy.example.com:443', 'username': 'user', 'password': 'pass'}"
103
- },
104
- {
105
- "name": "SOCKS5代理",
106
- "url": "socks5://username:password@socks-proxy.example.com:1080",
107
- "selenium_config": "SELENIUM_PROXY = 'socks5://socks-proxy.example.com:1080'",
108
- "playwright_config": "PLAYWRIGHT_PROXY = {'server': 'socks5://socks-proxy.example.com:1080', 'username': 'username', 'password': 'password'}"
109
- },
110
- {
111
- "name": "不带认证代理",
112
- "url": "http://proxy.example.com:8080",
113
- "selenium_config": "SELENIUM_PROXY = 'http://proxy.example.com:8080'",
114
- "playwright_config": "PLAYWRIGHT_PROXY = 'http://proxy.example.com:8080'"
115
- }
116
- ]
117
-
118
- for i, example in enumerate(examples, 1):
119
- print(f"\n示例 {i}: {example['name']}")
120
- print(f" 代理URL: {example['url']}")
121
- proxy = AuthenticatedProxy(example['url'])
122
- print(f" 清洁URL: {proxy.clean_url}")
123
- print(f" 用户名: {proxy.username or '无'}")
124
- print(f" 密码: {proxy.password or '无'}")
125
- print(f" Selenium配置: {example['selenium_config']}")
126
- print(f" Playwright配置: {example['playwright_config']}")
127
-
128
-
129
- def main():
130
- """主函数"""
131
- print("开始测试动态下载器的代理配置逻辑...\n")
132
-
133
- # 测试各个下载器的配置逻辑
134
- test_selenium_proxy_logic()
135
- test_playwright_proxy_logic()
136
- show_proxy_configuration_examples()
137
-
138
- print("\n所有配置逻辑测试完成!")
139
- print("\n总结:")
140
- print("1. Selenium和Playwright都支持代理配置")
141
- print("2. 带认证的代理需要特殊处理")
142
- print("3. Playwright对带认证代理的支持更直接")
143
- print("4. Selenium需要通过扩展或其他方式处理认证")
144
-
145
-
146
- if __name__ == "__main__":
1
+ #!/usr/bin/python
2
+ # -*- coding: UTF-8 -*-
3
+ """
4
+ 测试动态下载器(Selenium和Playwright)的代理配置逻辑
5
+ """
6
+
7
+ from crawlo.tools import AuthenticatedProxy
8
+
9
+
10
+ def test_selenium_proxy_logic():
11
+ """测试Selenium下载器的代理配置逻辑"""
12
+ print("=== 测试Selenium下载器的代理配置逻辑 ===")
13
+
14
+ # 代理配置
15
+ proxy_config = {
16
+ "http": "http://dwe20241014:Dwe0101014@182.201.243.186:58111",
17
+ "https": "http://dwe20241014:Dwe0101014@182.201.243.186:58111"
18
+ }
19
+
20
+ # 创建代理对象
21
+ proxy_url = proxy_config["http"]
22
+ proxy = AuthenticatedProxy(proxy_url)
23
+
24
+ print(f"原始代理URL: {proxy_url}")
25
+ print(f"清洁URL: {proxy.clean_url}")
26
+ print(f"认证信息: {proxy.get_auth_credentials()}")
27
+
28
+ # 模拟Selenium的代理配置逻辑
29
+ print(f"\nSelenium代理配置逻辑:")
30
+ print(f" 1. 在爬虫设置中配置:")
31
+ print(f" settings = {{")
32
+ print(f" 'SELENIUM_PROXY': '{proxy.clean_url}',")
33
+ print(f" }}")
34
+
35
+ # 对于带认证的代理,需要特殊处理
36
+ if proxy.username and proxy.password:
37
+ print(f"\n 2. 带认证代理的处理逻辑:")
38
+ print(f" - 用户名: {proxy.username}")
39
+ print(f" - 密码: {proxy.password}")
40
+ print(f" - 认证头: {proxy.get_auth_header()}")
41
+ print(f" - 处理方式: 通过浏览器扩展或手动输入认证信息")
42
+
43
+ print("\nSelenium配置逻辑测试完成!")
44
+
45
+
46
+ def test_playwright_proxy_logic():
47
+ """测试Playwright下载器的代理配置逻辑"""
48
+ print("\n=== 测试Playwright下载器的代理配置逻辑 ===")
49
+
50
+ # 代理配置
51
+ proxy_config = {
52
+ "http": "http://dwe20241014:Dwe0101014@182.201.243.186:58111",
53
+ "https": "http://dwe20241014:Dwe0101014@182.201.243.186:58111"
54
+ }
55
+
56
+ # 创建代理对象
57
+ proxy_url = proxy_config["http"]
58
+ proxy = AuthenticatedProxy(proxy_url)
59
+
60
+ print(f"原始代理URL: {proxy_url}")
61
+ print(f"清洁URL: {proxy.clean_url}")
62
+ print(f"认证信息: {proxy.get_auth_credentials()}")
63
+
64
+ # 模拟Playwright的代理配置逻辑
65
+ print(f"\nPlaywright代理配置逻辑:")
66
+ print(f" 1. 简单代理配置:")
67
+ print(f" settings = {{")
68
+ print(f" 'PLAYWRIGHT_PROXY': '{proxy.clean_url}',")
69
+ print(f" }}")
70
+
71
+ # 对于带认证的代理,Playwright可以直接在代理配置中包含认证信息
72
+ if proxy.username and proxy.password:
73
+ print(f"\n 2. 带认证的代理配置逻辑:")
74
+ print(f" settings = {{")
75
+ print(f" 'PLAYWRIGHT_PROXY': {{")
76
+ print(f" 'server': '{proxy.clean_url}',")
77
+ print(f" 'username': '{proxy.username}',")
78
+ print(f" 'password': '{proxy.password}'")
79
+ print(f" }}")
80
+ print(f" }}")
81
+ print(f" 实现方式: 在启动浏览器时传递proxy参数")
82
+
83
+ print("\nPlaywright配置逻辑测试完成!")
84
+
85
+
86
+ def show_proxy_configuration_examples():
87
+ """显示代理配置示例"""
88
+ print("\n=== 代理配置示例 ===")
89
+
90
+ # 不同类型的代理配置示例
91
+ examples = [
92
+ {
93
+ "name": "带认证HTTP代理",
94
+ "url": "http://username:password@proxy.example.com:8080",
95
+ "selenium_config": "SELENIUM_PROXY = 'http://proxy.example.com:8080'",
96
+ "playwright_config": "PLAYWRIGHT_PROXY = {'server': 'http://proxy.example.com:8080', 'username': 'username', 'password': 'password'}"
97
+ },
98
+ {
99
+ "name": "带认证HTTPS代理",
100
+ "url": "https://user:pass@secure-proxy.example.com:443",
101
+ "selenium_config": "SELENIUM_PROXY = 'https://secure-proxy.example.com:443'",
102
+ "playwright_config": "PLAYWRIGHT_PROXY = {'server': 'https://secure-proxy.example.com:443', 'username': 'user', 'password': 'pass'}"
103
+ },
104
+ {
105
+ "name": "SOCKS5代理",
106
+ "url": "socks5://username:password@socks-proxy.example.com:1080",
107
+ "selenium_config": "SELENIUM_PROXY = 'socks5://socks-proxy.example.com:1080'",
108
+ "playwright_config": "PLAYWRIGHT_PROXY = {'server': 'socks5://socks-proxy.example.com:1080', 'username': 'username', 'password': 'password'}"
109
+ },
110
+ {
111
+ "name": "不带认证代理",
112
+ "url": "http://proxy.example.com:8080",
113
+ "selenium_config": "SELENIUM_PROXY = 'http://proxy.example.com:8080'",
114
+ "playwright_config": "PLAYWRIGHT_PROXY = 'http://proxy.example.com:8080'"
115
+ }
116
+ ]
117
+
118
+ for i, example in enumerate(examples, 1):
119
+ print(f"\n示例 {i}: {example['name']}")
120
+ print(f" 代理URL: {example['url']}")
121
+ proxy = AuthenticatedProxy(example['url'])
122
+ print(f" 清洁URL: {proxy.clean_url}")
123
+ print(f" 用户名: {proxy.username or '无'}")
124
+ print(f" 密码: {proxy.password or '无'}")
125
+ print(f" Selenium配置: {example['selenium_config']}")
126
+ print(f" Playwright配置: {example['playwright_config']}")
127
+
128
+
129
+ def main():
130
+ """主函数"""
131
+ print("开始测试动态下载器的代理配置逻辑...\n")
132
+
133
+ # 测试各个下载器的配置逻辑
134
+ test_selenium_proxy_logic()
135
+ test_playwright_proxy_logic()
136
+ show_proxy_configuration_examples()
137
+
138
+ print("\n所有配置逻辑测试完成!")
139
+ print("\n总结:")
140
+ print("1. Selenium和Playwright都支持代理配置")
141
+ print("2. 带认证的代理需要特殊处理")
142
+ print("3. Playwright对带认证代理的支持更直接")
143
+ print("4. Selenium需要通过扩展或其他方式处理认证")
144
+
145
+
146
+ if __name__ == "__main__":
147
147
  main()