crawlo 1.2.0__py3-none-any.whl → 1.2.2__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 (220) 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 +81 -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 +143 -133
  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 -354
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +143 -143
  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 -337
  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-1.2.0.dist-info → crawlo-1.2.2.dist-info}/METADATA +692 -697
  128. crawlo-1.2.2.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 +173 -173
  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-1.2.0.dist-info/RECORD +0 -190
  218. {crawlo-1.2.0.dist-info → crawlo-1.2.2.dist-info}/WHEEL +0 -0
  219. {crawlo-1.2.0.dist-info → crawlo-1.2.2.dist-info}/entry_points.txt +0 -0
  220. {crawlo-1.2.0.dist-info → crawlo-1.2.2.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
  }