crawlo 1.1.8__py3-none-any.whl → 1.2.0__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 (191) 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 +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 +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 +337 -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-1.2.0.dist-info/METADATA +697 -0
  127. crawlo-1.2.0.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 +174 -231
  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/METADATA +0 -626
  188. crawlo-1.1.8.dist-info/RECORD +0 -190
  189. {crawlo-1.1.8.dist-info → crawlo-1.2.0.dist-info}/WHEEL +0 -0
  190. {crawlo-1.1.8.dist-info → crawlo-1.2.0.dist-info}/entry_points.txt +0 -0
  191. {crawlo-1.1.8.dist-info → crawlo-1.2.0.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
  }