crawlo 1.2.8__py3-none-any.whl → 1.2.9__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 (221) hide show
  1. crawlo/__init__.py +63 -61
  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 +323 -323
  10. crawlo/commands/startproject.py +436 -436
  11. crawlo/commands/stats.py +187 -187
  12. crawlo/commands/utils.py +186 -186
  13. crawlo/config.py +312 -312
  14. crawlo/config_validator.py +277 -251
  15. crawlo/core/__init__.py +2 -2
  16. crawlo/core/engine.py +366 -365
  17. crawlo/core/processor.py +40 -40
  18. crawlo/core/scheduler.py +256 -251
  19. crawlo/crawler.py +1103 -1100
  20. crawlo/data/__init__.py +5 -5
  21. crawlo/data/user_agents.py +194 -107
  22. crawlo/downloader/__init__.py +273 -266
  23. crawlo/downloader/aiohttp_downloader.py +226 -228
  24. crawlo/downloader/cffi_downloader.py +245 -256
  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 +43 -43
  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 +136 -136
  50. crawlo/middleware/offsite.py +114 -114
  51. crawlo/middleware/proxy.py +386 -368
  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 -0
  57. crawlo/mode_manager.py +211 -211
  58. crawlo/network/__init__.py +21 -21
  59. crawlo/network/request.py +379 -338
  60. crawlo/network/response.py +359 -359
  61. crawlo/pipelines/__init__.py +21 -21
  62. crawlo/pipelines/bloom_dedup_pipeline.py +157 -157
  63. crawlo/pipelines/console_pipeline.py +39 -39
  64. crawlo/pipelines/csv_pipeline.py +316 -316
  65. crawlo/pipelines/database_dedup_pipeline.py +223 -223
  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 +317 -317
  70. crawlo/pipelines/pipeline_manager.py +62 -62
  71. crawlo/pipelines/redis_dedup_pipeline.py +167 -167
  72. crawlo/project.py +290 -315
  73. crawlo/queue/pqueue.py +37 -37
  74. crawlo/queue/queue_manager.py +379 -378
  75. crawlo/queue/redis_priority_queue.py +306 -306
  76. crawlo/settings/__init__.py +7 -7
  77. crawlo/settings/default_settings.py +216 -220
  78. crawlo/settings/setting_manager.py +163 -122
  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 +261 -288
  89. crawlo/templates/project/settings_distributed.py.tmpl +174 -157
  90. crawlo/templates/project/settings_gentle.py.tmpl +95 -100
  91. crawlo/templates/project/settings_high_performance.py.tmpl +125 -134
  92. crawlo/templates/project/settings_minimal.py.tmpl +30 -0
  93. crawlo/templates/project/settings_simple.py.tmpl +96 -98
  94. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  95. crawlo/templates/run.py.tmpl +47 -47
  96. crawlo/templates/spider/spider.py.tmpl +143 -143
  97. crawlo/tools/__init__.py +200 -182
  98. crawlo/tools/anti_crawler.py +268 -268
  99. crawlo/tools/authenticated_proxy.py +240 -240
  100. crawlo/{cleaners → tools}/data_formatter.py +225 -225
  101. crawlo/tools/data_validator.py +180 -180
  102. crawlo/tools/date_tools.py +290 -36
  103. crawlo/tools/distributed_coordinator.py +388 -387
  104. crawlo/{cleaners → tools}/encoding_converter.py +127 -126
  105. crawlo/tools/request_tools.py +83 -0
  106. crawlo/tools/retry_mechanism.py +224 -221
  107. crawlo/tools/scenario_adapter.py +262 -262
  108. crawlo/{cleaners → tools}/text_cleaner.py +232 -232
  109. crawlo/utils/__init__.py +35 -35
  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 +187 -128
  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-1.2.8.dist-info → crawlo-1.2.9.dist-info}/METADATA +1011 -764
  131. crawlo-1.2.9.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 -237
  137. tests/cleaners_example.py +160 -160
  138. tests/config_validation_demo.py +143 -103
  139. tests/controlled_spider_example.py +205 -205
  140. tests/date_tools_example.py +180 -180
  141. tests/debug_pipelines.py +67 -0
  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 +151 -0
  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 +153 -0
  156. tests/test_config_validator.py +182 -193
  157. tests/test_crawlo_proxy_integration.py +109 -173
  158. tests/test_date_tools.py +123 -123
  159. tests/test_default_header_middleware.py +158 -158
  160. tests/test_distributed.py +65 -0
  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 -357
  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 +185 -0
  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 +73 -0
  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 +112 -0
  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 -153
  213. tests/test_user_agents.py +97 -0
  214. tests/tools_example.py +260 -257
  215. tests/verify_distributed.py +117 -0
  216. crawlo/cleaners/__init__.py +0 -61
  217. crawlo/utils/date_tools.py +0 -290
  218. crawlo-1.2.8.dist-info/RECORD +0 -209
  219. {crawlo-1.2.8.dist-info → crawlo-1.2.9.dist-info}/WHEEL +0 -0
  220. {crawlo-1.2.8.dist-info → crawlo-1.2.9.dist-info}/entry_points.txt +0 -0
  221. {crawlo-1.2.8.dist-info → crawlo-1.2.9.dist-info}/top_level.txt +0 -0
@@ -1,241 +1,241 @@
1
- #!/usr/bin/python
2
- # -*- coding: UTF-8 -*-
3
- """
4
- 带认证代理工具
5
- =============
6
- 支持带用户名密码认证的代理和非认证代理的统一处理工具
7
-
8
- 功能特性:
9
- - 支持HTTP/HTTPS/SOCKS代理
10
- - 支持带认证和不带认证的代理
11
- - 统一的代理格式处理
12
- - 代理有效性检测
13
- """
14
-
15
- from typing import Dict, Any, Optional, Union
16
- from urllib.parse import urlparse, urlunparse
17
-
18
-
19
- class AuthenticatedProxy:
20
- """带认证代理处理类"""
21
-
22
- def __init__(self, proxy_url: str):
23
- """
24
- 初始化代理对象
25
-
26
- Args:
27
- proxy_url (str): 代理URL,支持带认证信息的格式
28
- - 带认证: http://username:password@proxy.example.com:8080
29
- - 无认证: http://proxy.example.com:8080
30
- """
31
- self.proxy_url = proxy_url
32
- self.parsed = urlparse(proxy_url)
33
-
34
- # 提取认证信息
35
- self.username = self.parsed.username
36
- self.password = self.parsed.password
37
-
38
- # 构造不带认证信息的URL
39
- self.clean_url = urlunparse((
40
- self.parsed.scheme,
41
- f"{self.parsed.hostname}:{self.parsed.port}" if self.parsed.port else self.parsed.hostname,
42
- self.parsed.path,
43
- self.parsed.params,
44
- self.parsed.query,
45
- self.parsed.fragment
46
- ))
47
-
48
- # 构造下载器兼容的代理字典
49
- self.proxy_dict = {
50
- "http": self.clean_url,
51
- "https": self.clean_url
52
- }
53
-
54
- # 如果有认证信息,构造认证字符串
55
- if self.username and self.password:
56
- self.auth_string = f"{self.username}:{self.password}"
57
- else:
58
- self.auth_string = None
59
-
60
- def get_proxy_for_downloader(self) -> Union[str, Dict[str, str]]:
61
- """
62
- 获取适用于下载器的代理配置
63
-
64
- Returns:
65
- Union[str, Dict[str, str]]: 代理配置
66
- - 对于AioHttp/CurlCffi: 返回字典格式 {"http": "...", "https": "..."}
67
- - 对于HttpX: 可以直接使用字符串或字典格式
68
- """
69
- return self.proxy_dict
70
-
71
- def get_auth_credentials(self) -> Optional[Dict[str, str]]:
72
- """
73
- 获取认证凭据
74
-
75
- Returns:
76
- Optional[Dict[str, str]]: 认证凭据 {"username": "...", "password": "..."}
77
- """
78
- if self.username and self.password:
79
- return {
80
- "username": self.username,
81
- "password": self.password
82
- }
83
- return None
84
-
85
- def get_auth_header(self) -> Optional[str]:
86
- """
87
- 获取Basic Auth认证头
88
-
89
- Returns:
90
- Optional[str]: Basic Auth头信息
91
- """
92
- if self.username and self.password:
93
- import base64
94
- credentials = f"{self.username}:{self.password}"
95
- encoded = base64.b64encode(credentials.encode()).decode()
96
- return f"Basic {encoded}"
97
- return None
98
-
99
- def is_valid(self) -> bool:
100
- """
101
- 检查代理URL是否有效
102
-
103
- Returns:
104
- bool: 代理URL是否有效
105
- """
106
- # 检查协议
107
- if self.parsed.scheme not in ["http", "https", "socks4", "socks5"]:
108
- return False
109
-
110
- # 检查主机名
111
- if not self.parsed.hostname:
112
- return False
113
-
114
- # 检查端口(如果指定)
115
- if self.parsed.port and (self.parsed.port < 1 or self.parsed.port > 65535):
116
- return False
117
-
118
- return True
119
-
120
- def __str__(self) -> str:
121
- return self.proxy_url
122
-
123
- def __repr__(self) -> str:
124
- return f"AuthenticatedProxy(url='{self.proxy_url}', username={self.username is not None})"
125
-
126
-
127
- def create_proxy_config(proxy_url: str) -> Dict[str, Any]:
128
- """
129
- 创建代理配置,兼容各种下载器
130
-
131
- Args:
132
- proxy_url (str): 代理URL
133
-
134
- Returns:
135
- Dict[str, Any]: 代理配置字典
136
- """
137
- proxy = AuthenticatedProxy(proxy_url)
138
-
139
- if not proxy.is_valid():
140
- raise ValueError(f"Invalid proxy URL: {proxy_url}")
141
-
142
- config = {
143
- "url": proxy.clean_url,
144
- "proxy_dict": proxy.proxy_dict,
145
- "has_auth": proxy.auth_string is not None
146
- }
147
-
148
- if proxy.auth_string:
149
- config["auth"] = proxy.get_auth_credentials()
150
- config["auth_header"] = proxy.get_auth_header()
151
-
152
- return config
153
-
154
-
155
- def format_proxy_for_request(proxy_config: Dict[str, Any], downloader_type: str = "aiohttp") -> Dict[str, Any]:
156
- """
157
- 格式化代理配置以适配特定下载器
158
-
159
- Args:
160
- proxy_config (Dict[str, Any]): 代理配置
161
- downloader_type (str): 下载器类型 (aiohttp, httpx, curl_cffi)
162
-
163
- Returns:
164
- Dict[str, Any]: 适配下载器的代理配置
165
- """
166
- formatted = {}
167
-
168
- if downloader_type.lower() == "aiohttp":
169
- # AioHttp使用proxy和proxy_auth参数
170
- formatted["proxy"] = proxy_config["url"]
171
- if proxy_config.get("has_auth") and proxy_config.get("auth"):
172
- from aiohttp import BasicAuth
173
- auth = proxy_config["auth"]
174
- formatted["proxy_auth"] = BasicAuth(auth["username"], auth["password"])
175
-
176
- elif downloader_type.lower() == "httpx":
177
- # HttpX可以直接使用代理URL字符串或字典
178
- formatted["proxy"] = proxy_config["url"]
179
-
180
- elif downloader_type.lower() == "curl_cffi":
181
- # CurlCffi使用proxies字典
182
- formatted["proxies"] = proxy_config["proxy_dict"]
183
- # 认证信息包含在URL中或通过headers传递
184
- if proxy_config.get("auth_header"):
185
- formatted["headers"] = {"Proxy-Authorization": proxy_config["auth_header"]}
186
-
187
- return formatted
188
-
189
-
190
- # 便捷函数
191
- def parse_proxy_url(proxy_url: str) -> Dict[str, Any]:
192
- """
193
- 解析代理URL并返回详细信息
194
-
195
- Args:
196
- proxy_url (str): 代理URL
197
-
198
- Returns:
199
- Dict[str, Any]: 代理详细信息
200
- """
201
- return create_proxy_config(proxy_url)
202
-
203
-
204
- def validate_proxy_url(proxy_url: str) -> bool:
205
- """
206
- 验证代理URL是否有效
207
-
208
- Args:
209
- proxy_url (str): 代理URL
210
-
211
- Returns:
212
- bool: 是否有效
213
- """
214
- try:
215
- proxy = AuthenticatedProxy(proxy_url)
216
- return proxy.is_valid()
217
- except:
218
- return False
219
-
220
-
221
- def get_proxy_info(proxy_url: str) -> Dict[str, Any]:
222
- """
223
- 获取代理详细信息
224
-
225
- Args:
226
- proxy_url (str): 代理URL
227
-
228
- Returns:
229
- Dict[str, Any]: 代理详细信息
230
- """
231
- proxy = AuthenticatedProxy(proxy_url)
232
- return {
233
- "original_url": proxy.proxy_url,
234
- "clean_url": proxy.clean_url,
235
- "scheme": proxy.parsed.scheme,
236
- "hostname": proxy.parsed.hostname,
237
- "port": proxy.parsed.port,
238
- "has_auth": proxy.auth_string is not None,
239
- "username": proxy.username,
240
- "is_valid": proxy.is_valid()
1
+ #!/usr/bin/python
2
+ # -*- coding: UTF-8 -*-
3
+ """
4
+ 带认证代理工具
5
+ =============
6
+ 支持带用户名密码认证的代理和非认证代理的统一处理工具
7
+
8
+ 功能特性:
9
+ - 支持HTTP/HTTPS/SOCKS代理
10
+ - 支持带认证和不带认证的代理
11
+ - 统一的代理格式处理
12
+ - 代理有效性检测
13
+ """
14
+
15
+ from typing import Dict, Any, Optional, Union
16
+ from urllib.parse import urlparse, urlunparse
17
+
18
+
19
+ class AuthenticatedProxy:
20
+ """带认证代理处理类"""
21
+
22
+ def __init__(self, proxy_url: str):
23
+ """
24
+ 初始化代理对象
25
+
26
+ Args:
27
+ proxy_url (str): 代理URL,支持带认证信息的格式
28
+ - 带认证: http://username:password@proxy.example.com:8080
29
+ - 无认证: http://proxy.example.com:8080
30
+ """
31
+ self.proxy_url = proxy_url
32
+ self.parsed = urlparse(proxy_url)
33
+
34
+ # 提取认证信息
35
+ self.username = self.parsed.username
36
+ self.password = self.parsed.password
37
+
38
+ # 构造不带认证信息的URL
39
+ self.clean_url = urlunparse((
40
+ self.parsed.scheme,
41
+ f"{self.parsed.hostname}:{self.parsed.port}" if self.parsed.port else self.parsed.hostname,
42
+ self.parsed.path,
43
+ self.parsed.params,
44
+ self.parsed.query,
45
+ self.parsed.fragment
46
+ ))
47
+
48
+ # 构造下载器兼容的代理字典
49
+ self.proxy_dict = {
50
+ "http": self.clean_url,
51
+ "https": self.clean_url
52
+ }
53
+
54
+ # 如果有认证信息,构造认证字符串
55
+ if self.username and self.password:
56
+ self.auth_string = f"{self.username}:{self.password}"
57
+ else:
58
+ self.auth_string = None
59
+
60
+ def get_proxy_for_downloader(self) -> Union[str, Dict[str, str]]:
61
+ """
62
+ 获取适用于下载器的代理配置
63
+
64
+ Returns:
65
+ Union[str, Dict[str, str]]: 代理配置
66
+ - 对于AioHttp/CurlCffi: 返回字典格式 {"http": "...", "https": "..."}
67
+ - 对于HttpX: 可以直接使用字符串或字典格式
68
+ """
69
+ return self.proxy_dict
70
+
71
+ def get_auth_credentials(self) -> Optional[Dict[str, str]]:
72
+ """
73
+ 获取认证凭据
74
+
75
+ Returns:
76
+ Optional[Dict[str, str]]: 认证凭据 {"username": "...", "password": "..."}
77
+ """
78
+ if self.username and self.password:
79
+ return {
80
+ "username": self.username,
81
+ "password": self.password
82
+ }
83
+ return None
84
+
85
+ def get_auth_header(self) -> Optional[str]:
86
+ """
87
+ 获取Basic Auth认证头
88
+
89
+ Returns:
90
+ Optional[str]: Basic Auth头信息
91
+ """
92
+ if self.username and self.password:
93
+ import base64
94
+ credentials = f"{self.username}:{self.password}"
95
+ encoded = base64.b64encode(credentials.encode()).decode()
96
+ return f"Basic {encoded}"
97
+ return None
98
+
99
+ def is_valid(self) -> bool:
100
+ """
101
+ 检查代理URL是否有效
102
+
103
+ Returns:
104
+ bool: 代理URL是否有效
105
+ """
106
+ # 检查协议
107
+ if self.parsed.scheme not in ["http", "https", "socks4", "socks5"]:
108
+ return False
109
+
110
+ # 检查主机名
111
+ if not self.parsed.hostname:
112
+ return False
113
+
114
+ # 检查端口(如果指定)
115
+ if self.parsed.port and (self.parsed.port < 1 or self.parsed.port > 65535):
116
+ return False
117
+
118
+ return True
119
+
120
+ def __str__(self) -> str:
121
+ return self.proxy_url
122
+
123
+ def __repr__(self) -> str:
124
+ return f"AuthenticatedProxy(url='{self.proxy_url}', username={self.username is not None})"
125
+
126
+
127
+ def create_proxy_config(proxy_url: str) -> Dict[str, Any]:
128
+ """
129
+ 创建代理配置,兼容各种下载器
130
+
131
+ Args:
132
+ proxy_url (str): 代理URL
133
+
134
+ Returns:
135
+ Dict[str, Any]: 代理配置字典
136
+ """
137
+ proxy = AuthenticatedProxy(proxy_url)
138
+
139
+ if not proxy.is_valid():
140
+ raise ValueError(f"Invalid proxy URL: {proxy_url}")
141
+
142
+ config = {
143
+ "url": proxy.clean_url,
144
+ "proxy_dict": proxy.proxy_dict,
145
+ "has_auth": proxy.auth_string is not None
146
+ }
147
+
148
+ if proxy.auth_string:
149
+ config["auth"] = proxy.get_auth_credentials()
150
+ config["auth_header"] = proxy.get_auth_header()
151
+
152
+ return config
153
+
154
+
155
+ def format_proxy_for_request(proxy_config: Dict[str, Any], downloader_type: str = "aiohttp") -> Dict[str, Any]:
156
+ """
157
+ 格式化代理配置以适配特定下载器
158
+
159
+ Args:
160
+ proxy_config (Dict[str, Any]): 代理配置
161
+ downloader_type (str): 下载器类型 (aiohttp, httpx, curl_cffi)
162
+
163
+ Returns:
164
+ Dict[str, Any]: 适配下载器的代理配置
165
+ """
166
+ formatted = {}
167
+
168
+ if downloader_type.lower() == "aiohttp":
169
+ # AioHttp使用proxy和proxy_auth参数
170
+ formatted["proxy"] = proxy_config["url"]
171
+ if proxy_config.get("has_auth") and proxy_config.get("auth"):
172
+ from aiohttp import BasicAuth
173
+ auth = proxy_config["auth"]
174
+ formatted["proxy_auth"] = BasicAuth(auth["username"], auth["password"])
175
+
176
+ elif downloader_type.lower() == "httpx":
177
+ # HttpX可以直接使用代理URL字符串或字典
178
+ formatted["proxy"] = proxy_config["url"]
179
+
180
+ elif downloader_type.lower() == "curl_cffi":
181
+ # CurlCffi使用proxies字典
182
+ formatted["proxies"] = proxy_config["proxy_dict"]
183
+ # 认证信息包含在URL中或通过headers传递
184
+ if proxy_config.get("auth_header"):
185
+ formatted["headers"] = {"Proxy-Authorization": proxy_config["auth_header"]}
186
+
187
+ return formatted
188
+
189
+
190
+ # 便捷函数
191
+ def parse_proxy_url(proxy_url: str) -> Dict[str, Any]:
192
+ """
193
+ 解析代理URL并返回详细信息
194
+
195
+ Args:
196
+ proxy_url (str): 代理URL
197
+
198
+ Returns:
199
+ Dict[str, Any]: 代理详细信息
200
+ """
201
+ return create_proxy_config(proxy_url)
202
+
203
+
204
+ def validate_proxy_url(proxy_url: str) -> bool:
205
+ """
206
+ 验证代理URL是否有效
207
+
208
+ Args:
209
+ proxy_url (str): 代理URL
210
+
211
+ Returns:
212
+ bool: 是否有效
213
+ """
214
+ try:
215
+ proxy = AuthenticatedProxy(proxy_url)
216
+ return proxy.is_valid()
217
+ except:
218
+ return False
219
+
220
+
221
+ def get_proxy_info(proxy_url: str) -> Dict[str, Any]:
222
+ """
223
+ 获取代理详细信息
224
+
225
+ Args:
226
+ proxy_url (str): 代理URL
227
+
228
+ Returns:
229
+ Dict[str, Any]: 代理详细信息
230
+ """
231
+ proxy = AuthenticatedProxy(proxy_url)
232
+ return {
233
+ "original_url": proxy.proxy_url,
234
+ "clean_url": proxy.clean_url,
235
+ "scheme": proxy.parsed.scheme,
236
+ "hostname": proxy.parsed.hostname,
237
+ "port": proxy.parsed.port,
238
+ "has_auth": proxy.auth_string is not None,
239
+ "username": proxy.username,
240
+ "is_valid": proxy.is_valid()
241
241
  }