crawlo 1.4.7__py3-none-any.whl → 1.4.8__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 (348) hide show
  1. crawlo/__init__.py +90 -90
  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 +186 -186
  7. crawlo/commands/help.py +140 -140
  8. crawlo/commands/list.py +155 -155
  9. crawlo/commands/run.py +379 -379
  10. crawlo/commands/startproject.py +460 -460
  11. crawlo/commands/stats.py +187 -187
  12. crawlo/commands/utils.py +196 -196
  13. crawlo/config.py +320 -320
  14. crawlo/config_validator.py +277 -277
  15. crawlo/core/__init__.py +52 -52
  16. crawlo/core/engine.py +451 -451
  17. crawlo/core/processor.py +47 -47
  18. crawlo/core/scheduler.py +290 -290
  19. crawlo/crawler.py +698 -698
  20. crawlo/data/__init__.py +5 -5
  21. crawlo/data/user_agents.py +194 -194
  22. crawlo/downloader/__init__.py +280 -280
  23. crawlo/downloader/aiohttp_downloader.py +233 -233
  24. crawlo/downloader/cffi_downloader.py +250 -250
  25. crawlo/downloader/httpx_downloader.py +265 -265
  26. crawlo/downloader/hybrid_downloader.py +212 -212
  27. crawlo/downloader/playwright_downloader.py +425 -425
  28. crawlo/downloader/selenium_downloader.py +486 -486
  29. crawlo/event.py +45 -45
  30. crawlo/exceptions.py +214 -214
  31. crawlo/extension/__init__.py +64 -64
  32. crawlo/extension/health_check.py +141 -141
  33. crawlo/extension/log_interval.py +94 -94
  34. crawlo/extension/log_stats.py +70 -70
  35. crawlo/extension/logging_extension.py +53 -53
  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/factories/__init__.py +27 -27
  40. crawlo/factories/base.py +68 -68
  41. crawlo/factories/crawler.py +104 -104
  42. crawlo/factories/registry.py +84 -84
  43. crawlo/factories/utils.py +134 -134
  44. crawlo/filters/__init__.py +170 -170
  45. crawlo/filters/aioredis_filter.py +347 -347
  46. crawlo/filters/memory_filter.py +261 -261
  47. crawlo/framework.py +306 -306
  48. crawlo/initialization/__init__.py +44 -44
  49. crawlo/initialization/built_in.py +391 -391
  50. crawlo/initialization/context.py +141 -141
  51. crawlo/initialization/core.py +240 -240
  52. crawlo/initialization/phases.py +229 -229
  53. crawlo/initialization/registry.py +143 -143
  54. crawlo/initialization/utils.py +48 -48
  55. crawlo/interfaces.py +23 -23
  56. crawlo/items/__init__.py +23 -23
  57. crawlo/items/base.py +23 -23
  58. crawlo/items/fields.py +52 -52
  59. crawlo/items/items.py +104 -104
  60. crawlo/logging/__init__.py +42 -42
  61. crawlo/logging/config.py +280 -276
  62. crawlo/logging/factory.py +175 -175
  63. crawlo/logging/manager.py +104 -104
  64. crawlo/middleware/__init__.py +87 -87
  65. crawlo/middleware/default_header.py +132 -132
  66. crawlo/middleware/download_delay.py +104 -104
  67. crawlo/middleware/middleware_manager.py +142 -142
  68. crawlo/middleware/offsite.py +123 -123
  69. crawlo/middleware/proxy.py +209 -209
  70. crawlo/middleware/request_ignore.py +86 -86
  71. crawlo/middleware/response_code.py +150 -150
  72. crawlo/middleware/response_filter.py +136 -136
  73. crawlo/middleware/retry.py +124 -124
  74. crawlo/mode_manager.py +287 -287
  75. crawlo/network/__init__.py +21 -21
  76. crawlo/network/request.py +408 -376
  77. crawlo/network/response.py +598 -569
  78. crawlo/pipelines/__init__.py +52 -52
  79. crawlo/pipelines/base_pipeline.py +452 -452
  80. crawlo/pipelines/bloom_dedup_pipeline.py +145 -146
  81. crawlo/pipelines/console_pipeline.py +39 -39
  82. crawlo/pipelines/csv_pipeline.py +316 -316
  83. crawlo/pipelines/database_dedup_pipeline.py +196 -197
  84. crawlo/pipelines/json_pipeline.py +218 -218
  85. crawlo/pipelines/memory_dedup_pipeline.py +104 -105
  86. crawlo/pipelines/mongo_pipeline.py +140 -139
  87. crawlo/pipelines/mysql_pipeline.py +468 -469
  88. crawlo/pipelines/pipeline_manager.py +100 -100
  89. crawlo/pipelines/redis_dedup_pipeline.py +155 -155
  90. crawlo/project.py +347 -347
  91. crawlo/queue/__init__.py +9 -9
  92. crawlo/queue/pqueue.py +38 -38
  93. crawlo/queue/queue_manager.py +591 -591
  94. crawlo/queue/redis_priority_queue.py +518 -518
  95. crawlo/settings/__init__.py +7 -7
  96. crawlo/settings/default_settings.py +287 -284
  97. crawlo/settings/setting_manager.py +219 -219
  98. crawlo/spider/__init__.py +658 -657
  99. crawlo/stats_collector.py +81 -81
  100. crawlo/subscriber.py +129 -129
  101. crawlo/task_manager.py +138 -138
  102. crawlo/templates/crawlo.cfg.tmpl +10 -10
  103. crawlo/templates/project/__init__.py.tmpl +1 -1
  104. crawlo/templates/project/items.py.tmpl +13 -13
  105. crawlo/templates/project/middlewares.py.tmpl +38 -38
  106. crawlo/templates/project/pipelines.py.tmpl +35 -35
  107. crawlo/templates/project/settings.py.tmpl +113 -109
  108. crawlo/templates/project/settings_distributed.py.tmpl +160 -156
  109. crawlo/templates/project/settings_gentle.py.tmpl +174 -170
  110. crawlo/templates/project/settings_high_performance.py.tmpl +175 -171
  111. crawlo/templates/project/settings_minimal.py.tmpl +102 -98
  112. crawlo/templates/project/settings_simple.py.tmpl +172 -168
  113. crawlo/templates/project/spiders/__init__.py.tmpl +9 -9
  114. crawlo/templates/run.py.tmpl +23 -23
  115. crawlo/templates/spider/spider.py.tmpl +32 -32
  116. crawlo/templates/spiders_init.py.tmpl +4 -4
  117. crawlo/tools/__init__.py +86 -86
  118. crawlo/tools/date_tools.py +289 -289
  119. crawlo/tools/distributed_coordinator.py +384 -384
  120. crawlo/tools/scenario_adapter.py +262 -262
  121. crawlo/tools/text_cleaner.py +232 -232
  122. crawlo/utils/__init__.py +74 -50
  123. crawlo/utils/batch_processor.py +276 -276
  124. crawlo/utils/config_manager.py +442 -442
  125. crawlo/utils/controlled_spider_mixin.py +439 -439
  126. crawlo/utils/db_helper.py +250 -250
  127. crawlo/utils/encoding_helper.py +190 -0
  128. crawlo/utils/error_handler.py +410 -410
  129. crawlo/utils/fingerprint.py +121 -121
  130. crawlo/utils/func_tools.py +82 -82
  131. crawlo/utils/large_scale_helper.py +344 -344
  132. crawlo/utils/leak_detector.py +335 -335
  133. crawlo/utils/misc.py +81 -81
  134. crawlo/utils/mongo_connection_pool.py +157 -157
  135. crawlo/utils/mysql_connection_pool.py +197 -197
  136. crawlo/utils/performance_monitor.py +285 -285
  137. crawlo/utils/queue_helper.py +175 -175
  138. crawlo/utils/redis_checker.py +90 -90
  139. crawlo/utils/redis_connection_pool.py +578 -578
  140. crawlo/utils/redis_key_validator.py +198 -198
  141. crawlo/utils/request.py +278 -278
  142. crawlo/utils/request_serializer.py +225 -225
  143. crawlo/utils/resource_manager.py +337 -337
  144. crawlo/utils/response_helper.py +113 -0
  145. crawlo/utils/selector_helper.py +138 -137
  146. crawlo/utils/singleton.py +69 -69
  147. crawlo/utils/spider_loader.py +201 -201
  148. crawlo/utils/text_helper.py +94 -94
  149. {crawlo-1.4.7.dist-info → crawlo-1.4.8.dist-info}/METADATA +831 -689
  150. crawlo-1.4.8.dist-info/RECORD +347 -0
  151. examples/__init__.py +7 -7
  152. tests/__init__.py +7 -7
  153. tests/advanced_tools_example.py +217 -217
  154. tests/authenticated_proxy_example.py +110 -110
  155. tests/baidu_performance_test.py +108 -108
  156. tests/baidu_test.py +59 -59
  157. tests/bug_check_test.py +250 -250
  158. tests/cleaners_example.py +160 -160
  159. tests/comprehensive_framework_test.py +212 -212
  160. tests/comprehensive_test.py +81 -81
  161. tests/comprehensive_testing_summary.md +186 -186
  162. tests/config_validation_demo.py +142 -142
  163. tests/controlled_spider_example.py +205 -205
  164. tests/date_tools_example.py +180 -180
  165. tests/debug_configure.py +69 -69
  166. tests/debug_framework_logger.py +84 -84
  167. tests/debug_log_config.py +126 -126
  168. tests/debug_log_levels.py +63 -63
  169. tests/debug_pipelines.py +66 -66
  170. tests/detailed_log_test.py +233 -233
  171. tests/direct_selector_helper_test.py +96 -96
  172. tests/distributed_dedup_test.py +467 -467
  173. tests/distributed_test.py +66 -66
  174. tests/distributed_test_debug.py +76 -76
  175. tests/dynamic_loading_example.py +523 -523
  176. tests/dynamic_loading_test.py +104 -104
  177. tests/error_handling_example.py +171 -171
  178. tests/explain_mysql_update_behavior.py +76 -76
  179. tests/final_comprehensive_test.py +151 -151
  180. tests/final_log_test.py +260 -260
  181. tests/final_validation_test.py +182 -182
  182. tests/fix_log_test.py +142 -142
  183. tests/framework_performance_test.py +202 -202
  184. tests/log_buffering_test.py +111 -111
  185. tests/log_generation_timing_test.py +153 -153
  186. tests/monitor_redis_dedup.sh +72 -72
  187. tests/ofweek_scrapy/ofweek_scrapy/items.py +12 -12
  188. tests/ofweek_scrapy/ofweek_scrapy/middlewares.py +100 -100
  189. tests/ofweek_scrapy/ofweek_scrapy/pipelines.py +13 -13
  190. tests/ofweek_scrapy/ofweek_scrapy/settings.py +84 -84
  191. tests/ofweek_scrapy/ofweek_scrapy/spiders/__init__.py +4 -4
  192. tests/ofweek_scrapy/scrapy.cfg +11 -11
  193. tests/optimized_performance_test.py +211 -211
  194. tests/performance_comparison.py +244 -244
  195. tests/queue_blocking_test.py +113 -113
  196. tests/queue_test.py +89 -89
  197. tests/redis_key_validation_demo.py +130 -130
  198. tests/request_params_example.py +150 -150
  199. tests/response_improvements_example.py +144 -144
  200. tests/scrapy_comparison/ofweek_scrapy.py +138 -138
  201. tests/scrapy_comparison/scrapy_test.py +133 -133
  202. tests/simple_cli_test.py +54 -54
  203. tests/simple_command_test.py +119 -119
  204. tests/simple_crawlo_test.py +126 -126
  205. tests/simple_follow_test.py +38 -38
  206. tests/simple_log_test2.py +137 -137
  207. tests/simple_optimization_test.py +128 -128
  208. tests/simple_queue_type_test.py +41 -41
  209. tests/simple_response_selector_test.py +94 -94
  210. tests/simple_selector_helper_test.py +154 -154
  211. tests/simple_selector_test.py +207 -207
  212. tests/simple_spider_test.py +49 -49
  213. tests/simple_url_test.py +73 -73
  214. tests/simulate_mysql_update_test.py +139 -139
  215. tests/spider_log_timing_test.py +177 -177
  216. tests/test_advanced_tools.py +148 -148
  217. tests/test_all_commands.py +230 -230
  218. tests/test_all_pipeline_fingerprints.py +133 -133
  219. tests/test_all_redis_key_configs.py +145 -145
  220. tests/test_asyncmy_usage.py +56 -56
  221. tests/test_batch_processor.py +178 -178
  222. tests/test_cleaners.py +54 -54
  223. tests/test_cli_arguments.py +118 -118
  224. tests/test_component_factory.py +174 -174
  225. tests/test_config_consistency.py +80 -80
  226. tests/test_config_merge.py +152 -152
  227. tests/test_config_validator.py +182 -182
  228. tests/test_controlled_spider_mixin.py +79 -79
  229. tests/test_crawler_process_import.py +38 -38
  230. tests/test_crawler_process_spider_modules.py +47 -47
  231. tests/test_crawlo_proxy_integration.py +114 -114
  232. tests/test_date_tools.py +123 -123
  233. tests/test_dedup_fix.py +220 -220
  234. tests/test_dedup_pipeline_consistency.py +124 -124
  235. tests/test_default_header_middleware.py +313 -313
  236. tests/test_distributed.py +65 -65
  237. tests/test_double_crawlo_fix.py +204 -204
  238. tests/test_double_crawlo_fix_simple.py +124 -124
  239. tests/test_download_delay_middleware.py +221 -221
  240. tests/test_downloader_proxy_compatibility.py +272 -272
  241. tests/test_edge_cases.py +305 -305
  242. tests/test_encoding_core.py +56 -56
  243. tests/test_encoding_detection.py +126 -126
  244. tests/test_enhanced_error_handler.py +270 -270
  245. tests/test_enhanced_error_handler_comprehensive.py +245 -245
  246. tests/test_error_handler_compatibility.py +112 -112
  247. tests/test_factories.py +252 -252
  248. tests/test_factory_compatibility.py +196 -196
  249. tests/test_final_validation.py +153 -153
  250. tests/test_fingerprint_consistency.py +135 -135
  251. tests/test_fingerprint_simple.py +51 -51
  252. tests/test_get_component_logger.py +83 -83
  253. tests/test_hash_performance.py +99 -99
  254. tests/test_integration.py +169 -169
  255. tests/test_item_dedup_redis_key.py +122 -122
  256. tests/test_large_scale_helper.py +235 -235
  257. tests/test_logging_enhancements.py +374 -374
  258. tests/test_logging_final.py +184 -184
  259. tests/test_logging_integration.py +312 -312
  260. tests/test_logging_system.py +282 -282
  261. tests/test_middleware_debug.py +141 -141
  262. tests/test_mode_consistency.py +51 -51
  263. tests/test_multi_directory.py +67 -67
  264. tests/test_multiple_spider_modules.py +80 -80
  265. tests/test_mysql_pipeline_config.py +164 -164
  266. tests/test_mysql_pipeline_error.py +98 -98
  267. tests/test_mysql_pipeline_init_log.py +82 -82
  268. tests/test_mysql_pipeline_integration.py +132 -132
  269. tests/test_mysql_pipeline_refactor.py +143 -143
  270. tests/test_mysql_pipeline_refactor_simple.py +85 -85
  271. tests/test_mysql_pipeline_robustness.py +195 -195
  272. tests/test_mysql_pipeline_types.py +88 -88
  273. tests/test_mysql_update_columns.py +93 -93
  274. tests/test_offsite_middleware.py +244 -244
  275. tests/test_offsite_middleware_simple.py +203 -203
  276. tests/test_optimized_selector_naming.py +100 -100
  277. tests/test_parsel.py +29 -29
  278. tests/test_performance.py +327 -327
  279. tests/test_performance_monitor.py +115 -115
  280. tests/test_pipeline_fingerprint_consistency.py +86 -86
  281. tests/test_priority_behavior.py +211 -211
  282. tests/test_priority_consistency.py +151 -151
  283. tests/test_priority_consistency_fixed.py +249 -249
  284. tests/test_proxy_health_check.py +32 -32
  285. tests/test_proxy_middleware.py +217 -217
  286. tests/test_proxy_middleware_enhanced.py +212 -212
  287. tests/test_proxy_middleware_integration.py +142 -142
  288. tests/test_proxy_middleware_refactored.py +207 -207
  289. tests/test_proxy_only.py +83 -83
  290. tests/test_proxy_providers.py +56 -56
  291. tests/test_proxy_stats.py +19 -19
  292. tests/test_proxy_strategies.py +59 -59
  293. tests/test_proxy_with_downloader.py +152 -152
  294. tests/test_queue_empty_check.py +41 -41
  295. tests/test_queue_manager_double_crawlo.py +173 -173
  296. tests/test_queue_manager_redis_key.py +179 -179
  297. tests/test_queue_naming.py +154 -154
  298. tests/test_queue_type.py +106 -106
  299. tests/test_queue_type_redis_config_consistency.py +130 -130
  300. tests/test_random_headers_default.py +322 -322
  301. tests/test_random_headers_necessity.py +308 -308
  302. tests/test_random_user_agent.py +72 -72
  303. tests/test_redis_config.py +28 -28
  304. tests/test_redis_connection_pool.py +294 -294
  305. tests/test_redis_key_naming.py +181 -181
  306. tests/test_redis_key_validator.py +123 -123
  307. tests/test_redis_queue.py +224 -224
  308. tests/test_redis_queue_name_fix.py +175 -175
  309. tests/test_redis_queue_type_fallback.py +129 -129
  310. tests/test_request_ignore_middleware.py +182 -182
  311. tests/test_request_params.py +111 -111
  312. tests/test_request_serialization.py +70 -70
  313. tests/test_response_code_middleware.py +349 -349
  314. tests/test_response_filter_middleware.py +427 -427
  315. tests/test_response_follow.py +104 -104
  316. tests/test_response_improvements.py +152 -152
  317. tests/test_response_selector_methods.py +92 -92
  318. tests/test_response_url_methods.py +70 -70
  319. tests/test_response_urljoin.py +86 -86
  320. tests/test_retry_middleware.py +333 -333
  321. tests/test_retry_middleware_realistic.py +273 -273
  322. tests/test_scheduler.py +252 -252
  323. tests/test_scheduler_config_update.py +133 -133
  324. tests/test_scrapy_style_encoding.py +112 -112
  325. tests/test_selector_helper.py +100 -100
  326. tests/test_selector_optimizations.py +146 -146
  327. tests/test_simple_response.py +61 -61
  328. tests/test_spider_loader.py +49 -49
  329. tests/test_spider_loader_comprehensive.py +69 -69
  330. tests/test_spider_modules.py +84 -84
  331. tests/test_spiders/test_spider.py +9 -9
  332. tests/test_telecom_spider_redis_key.py +205 -205
  333. tests/test_template_content.py +87 -87
  334. tests/test_template_redis_key.py +134 -134
  335. tests/test_tools.py +159 -159
  336. tests/test_user_agent_randomness.py +176 -176
  337. tests/test_user_agents.py +96 -96
  338. tests/untested_features_report.md +138 -138
  339. tests/verify_debug.py +51 -51
  340. tests/verify_distributed.py +117 -117
  341. tests/verify_log_fix.py +111 -111
  342. tests/verify_mysql_warnings.py +109 -109
  343. crawlo/utils/log.py +0 -80
  344. crawlo/utils/url_utils.py +0 -40
  345. crawlo-1.4.7.dist-info/RECORD +0 -347
  346. {crawlo-1.4.7.dist-info → crawlo-1.4.8.dist-info}/WHEEL +0 -0
  347. {crawlo-1.4.7.dist-info → crawlo-1.4.8.dist-info}/entry_points.txt +0 -0
  348. {crawlo-1.4.7.dist-info → crawlo-1.4.8.dist-info}/top_level.txt +0 -0
crawlo/network/request.py CHANGED
@@ -1,376 +1,408 @@
1
- #!/usr/bin/python
2
- # -*- coding: UTF-8 -*-
3
- """
4
- HTTP Request 封装模块
5
- ====================
6
- 提供功能完善的HTTP请求封装,支持:
7
- - JSON/表单数据自动处理
8
- - GET请求参数处理
9
- - 优先级排序机制
10
- - 安全的深拷贝操作
11
- - 灵活的请求配置
12
- """
13
- import json
14
- from copy import deepcopy
15
- from enum import IntEnum
16
- from w3lib.url import safe_url_string
17
- from urllib.parse import urlencode, urlparse, urlunparse, parse_qsl
18
- from typing import Dict, Optional, Callable, Union, Any, TypeVar, List
19
-
20
- from crawlo.utils.url_utils import escape_ajax
21
-
22
-
23
- _Request = TypeVar("_Request", bound="Request")
24
-
25
-
26
- class RequestPriority(IntEnum):
27
- """
28
- 请求优先级枚举。
29
-
30
- 数值越小,优先级越高。使用 IntEnum 确保可以直接当作整数使用。
31
-
32
- Examples:
33
- >>> request = Request(url, priority=RequestPriority.HIGH)
34
- >>> request.priority = RequestPriority.URGENT
35
- """
36
- URGENT = -200 # 紧急任务
37
- HIGH = -100 # 高优先级
38
- NORMAL = 0 # 正常优先级(默认)
39
- LOW = 100 # 低优先级
40
- BACKGROUND = 200 # 后台任务
41
-
42
-
43
- class Request:
44
- """
45
- 封装一个 HTTP 请求对象,用于爬虫框架中表示一个待抓取的请求任务。
46
- 支持 JSON、表单、GET参数、原始 body 提交,自动处理 Content-Type 与编码。
47
- 不支持文件上传(multipart/form-data),保持轻量。
48
- """
49
-
50
- __slots__ = (
51
- '_url',
52
- '_meta',
53
- 'callback',
54
- 'cb_kwargs',
55
- 'err_back',
56
- 'headers',
57
- 'body',
58
- 'method',
59
- 'cookies',
60
- 'priority',
61
- 'encoding',
62
- 'dont_filter',
63
- 'timeout',
64
- 'proxy',
65
- 'allow_redirects',
66
- 'auth',
67
- 'verify',
68
- 'flags',
69
- '_json_body',
70
- '_form_data',
71
- '_params',
72
- 'use_dynamic_loader',
73
- 'dynamic_loader_options'
74
- )
75
-
76
- def __init__(
77
- self,
78
- url: str,
79
- callback: Optional[Callable] = None,
80
- err_back: Optional[Callable] = None,
81
- method: Optional[str] = 'GET',
82
- headers: Optional[Dict[str, str]] = None,
83
- body: Optional[Union[bytes, str, Dict[Any, Any]]] = None,
84
- form_data: Optional[Dict[str, Any]] = None,
85
- json_body: Optional[Dict[str, Any]] = None,
86
- params: Optional[Dict[str, Any]] = None,
87
- cb_kwargs: Optional[Dict[str, Any]] = None,
88
- cookies: Optional[Dict[str, str]] = None,
89
- meta: Optional[Dict[str, Any]] = None,
90
- priority: int = RequestPriority.NORMAL,
91
- dont_filter: bool = False,
92
- timeout: Optional[float] = None,
93
- proxy: Optional[str] = None,
94
- allow_redirects: bool = True,
95
- auth: Optional[tuple] = None,
96
- verify: bool = True,
97
- flags: Optional[List[str]] = None,
98
- encoding: str = 'utf-8',
99
- # 动态加载相关参数
100
- use_dynamic_loader: bool = False,
101
- dynamic_loader_options: Optional[Dict[str, Any]] = None
102
- ):
103
- """
104
- 初始化请求对象。
105
-
106
- :param url: 请求 URL(必须)
107
- :param callback: 成功回调函数
108
- :param err_back: 错误回调函数
109
- :param method: HTTP 方法,默认 GET
110
- :param headers: 请求头
111
- :param body: 原始请求体(bytes/str),若为 dict 且未使用 json_body/form_data,则自动转为 JSON
112
- :param form_data: 表单数据,POST请求时自动转为 application/x-www-form-urlencoded
113
- :param json_body: JSON 数据,自动序列化并设置 Content-Type
114
- :param params: GET请求参数,会自动附加到URL上
115
- :param cb_kwargs: 传递给 callback 的额外参数
116
- :param cookies: Cookies 字典
117
- :param meta: 元数据(跨中间件传递数据)
118
- :param priority: 优先级(数值越小越优先)
119
- :param dont_filter: 是否跳过去重
120
- :param timeout: 超时时间(秒)
121
- :param proxy: 代理地址,如 http://127.0.0.1:8080
122
- :param allow_redirects: 是否允许重定向
123
- :param auth: 认证元组 (username, password)
124
- :param verify: 是否验证 SSL 证书
125
- :param flags: 标记(用于调试或分类)
126
- :param encoding: 字符编码,默认 utf-8
127
- """
128
- self.callback = callback
129
- self.err_back = err_back
130
- self.method = str(method).upper()
131
- self.headers = headers or {}
132
- self.cookies = cookies or {}
133
- self.priority = -priority # 用于排序:值越小优先级越高
134
-
135
- # 安全处理 meta,移除 logger 后再 deepcopy
136
- self._meta = self._safe_deepcopy_meta(meta) if meta is not None else {}
137
-
138
- self.timeout = self._meta.get('download_timeout', timeout)
139
- self.proxy = proxy
140
- self.allow_redirects = allow_redirects
141
- self.auth = auth
142
- self.verify = verify
143
- self.flags = flags or []
144
- self.encoding = encoding
145
- self.cb_kwargs = cb_kwargs or {}
146
- self.body = body
147
- # 保存高层语义参数(用于 copy)
148
- self._json_body = json_body
149
- self._form_data = form_data
150
- self._params = params
151
-
152
- # 动态加载相关属性
153
- self.use_dynamic_loader = use_dynamic_loader
154
- self.dynamic_loader_options = dynamic_loader_options or {}
155
-
156
- # 处理GET参数
157
- if params is not None and self.method == 'GET':
158
- # 将GET参数附加到URL上
159
- self._url = self._add_params_to_url(url, params)
160
- else:
161
- self._url = url
162
-
163
- # 构建 body
164
- if json_body is not None:
165
- if 'Content-Type' not in self.headers:
166
- self.headers['Content-Type'] = 'application/json'
167
- self.body = json.dumps(json_body, ensure_ascii=False).encode(encoding)
168
- if self.method == 'GET':
169
- self.method = 'POST'
170
-
171
- elif form_data is not None:
172
- if self.method == 'GET':
173
- # 对于GET请求,将form_data作为GET参数处理
174
- self._url = self._add_params_to_url(self._url, form_data)
175
- else:
176
- # 对于POST等请求,将form_data作为请求体处理
177
- if 'Content-Type' not in self.headers:
178
- self.headers['Content-Type'] = 'application/x-www-form-urlencoded'
179
- query_str = urlencode(form_data)
180
- self.body = query_str.encode(encoding) # 显式编码为 bytes
181
-
182
-
183
- else:
184
- # 处理原始 body
185
- if isinstance(self.body, dict):
186
- if 'Content-Type' not in self.headers:
187
- self.headers['Content-Type'] = 'application/json'
188
- self.body = json.dumps(self.body, ensure_ascii=False).encode(encoding)
189
- elif isinstance(self.body, str):
190
- self.body = self.body.encode(encoding)
191
-
192
- self.dont_filter = dont_filter
193
- self._set_url(self._url)
194
-
195
- @staticmethod
196
- def _add_params_to_url(url: str, params: Dict[str, Any]) -> str:
197
- """将参数添加到URL中"""
198
- if not params:
199
- return url
200
-
201
- # 解析URL
202
- parsed = urlparse(url)
203
- # 解析现有查询参数
204
- query_params = parse_qsl(parsed.query, keep_blank_values=True)
205
- # 添加新参数
206
- for key, value in params.items():
207
- query_params.append((str(key), str(value)))
208
- # 重新构建查询字符串
209
- new_query = urlencode(query_params)
210
- # 构建新的URL
211
- return urlunparse((
212
- parsed.scheme,
213
- parsed.netloc,
214
- parsed.path,
215
- parsed.params,
216
- new_query,
217
- parsed.fragment
218
- ))
219
-
220
- @staticmethod
221
- def _safe_deepcopy_meta(meta: Dict[str, Any]) -> Dict[str, Any]:
222
- """安全地 deepcopy meta,移除 logger 后再复制"""
223
- import logging
224
-
225
- def clean_logger_recursive(obj: Any) -> Any:
226
- """递归移除 logger 对象"""
227
- if isinstance(obj, logging.Logger):
228
- return None
229
- elif isinstance(obj, dict):
230
- cleaned = {}
231
- for k, v in obj.items():
232
- if not (k == 'logger' or isinstance(v, logging.Logger)):
233
- cleaned[k] = clean_logger_recursive(v)
234
- return cleaned
235
- elif isinstance(obj, (list, tuple)):
236
- cleaned_list = []
237
- for item in obj:
238
- cleaned_item = clean_logger_recursive(item)
239
- if cleaned_item is not None:
240
- cleaned_list.append(cleaned_item)
241
- return type(obj)(cleaned_list)
242
- else:
243
- return obj
244
-
245
- # 先清理 logger,再 deepcopy
246
- cleaned_meta = clean_logger_recursive(meta)
247
- # 确保返回字典类型
248
- if not isinstance(cleaned_meta, dict):
249
- return {}
250
- return deepcopy(cleaned_meta)
251
-
252
- def copy(self: _Request) -> _Request:
253
- """
254
- 创建当前请求的副本,保留所有高层语义(json_body/form_data/params)。
255
- """
256
- return type(self)(
257
- url=self.url,
258
- callback=self.callback,
259
- method=self.method,
260
- headers=self.headers.copy(),
261
- body=None, # 由 form_data/json_body/params 重新生成
262
- form_data=self._form_data,
263
- json_body=self._json_body,
264
- params=self._params,
265
- cb_kwargs=deepcopy(self.cb_kwargs),
266
- err_back=self.err_back,
267
- cookies=self.cookies.copy(),
268
- meta=deepcopy(self._meta),
269
- priority=-self.priority,
270
- dont_filter=self.dont_filter,
271
- timeout=self.timeout,
272
- proxy=self.proxy,
273
- allow_redirects=self.allow_redirects,
274
- auth=self.auth,
275
- verify=self.verify,
276
- flags=self.flags.copy(),
277
- encoding=self.encoding,
278
- use_dynamic_loader=self.use_dynamic_loader,
279
- dynamic_loader_options=deepcopy(self.dynamic_loader_options)
280
- )
281
-
282
- def set_meta(self, key: str, value: Any) -> 'Request':
283
- """设置 meta 中的某个键值,支持链式调用。"""
284
- self._meta[key] = value
285
- return self
286
-
287
- def add_header(self, key: str, value: str) -> 'Request':
288
- """添加请求头,支持链式调用。"""
289
- self.headers[key] = value
290
- return self
291
-
292
- def add_headers(self, headers: Dict[str, str]) -> 'Request':
293
- """批量添加请求头,支持链式调用。"""
294
- self.headers.update(headers)
295
- return self
296
-
297
- def set_proxy(self, proxy: str) -> 'Request':
298
- """设置代理,支持链式调用。"""
299
- self.proxy = proxy
300
- return self
301
-
302
- def set_timeout(self, timeout: float) -> 'Request':
303
- """设置超时时间,支持链式调用。"""
304
- self.timeout = timeout
305
- return self
306
-
307
- def add_flag(self, flag: str) -> 'Request':
308
- """添加标记,支持链式调用。"""
309
- if flag not in self.flags:
310
- self.flags.append(flag)
311
- return self
312
-
313
- def remove_flag(self, flag: str) -> 'Request':
314
- """移除标记,支持链式调用。"""
315
- if flag in self.flags:
316
- self.flags.remove(flag)
317
- return self
318
-
319
- def set_dynamic_loader(self, use_dynamic: bool = True, options: Optional[Dict[str, Any]] = None) -> 'Request':
320
- """设置使用动态加载器,支持链式调用。"""
321
- self.use_dynamic_loader = use_dynamic
322
- if options:
323
- self.dynamic_loader_options = options
324
- # 同时在meta中设置标记,供混合下载器使用
325
- self._meta['use_dynamic_loader'] = use_dynamic
326
- return self
327
-
328
- def set_protocol_loader(self) -> 'Request':
329
- """强制使用协议加载器,支持链式调用。"""
330
- self.use_dynamic_loader = False
331
- self._meta['use_dynamic_loader'] = False
332
- self._meta['use_protocol_loader'] = True
333
- return self
334
-
335
- def _set_url(self, url: str) -> None:
336
- """安全设置 URL,确保格式正确。"""
337
- if not isinstance(url, str):
338
- raise TypeError(f"Request url 必须为字符串,当前类型: {type(url).__name__}")
339
-
340
- if not url.strip():
341
- raise ValueError("URL 不能为空")
342
-
343
- # 检查危险的 URL scheme
344
- dangerous_schemes = ['file://', 'ftp://', 'javascript:', 'data:']
345
- if any(url.lower().startswith(scheme) for scheme in dangerous_schemes):
346
- raise ValueError(f"URL scheme 不安全: {url[:20]}...")
347
-
348
- s = safe_url_string(url, self.encoding)
349
- escaped_url = escape_ajax(s)
350
-
351
- if not escaped_url.startswith(('http://', 'https://')):
352
- raise ValueError(f"URL 缺少 HTTP(S) scheme: {escaped_url[:50]}...")
353
-
354
- # 检查 URL 长度
355
- if len(escaped_url) > 8192: # 大多数服务器支持的最大 URL 长度
356
- raise ValueError(f"URL 过长 (超过 8192 字符): {len(escaped_url)} 字符")
357
-
358
- self._url = escaped_url
359
-
360
- @property
361
- def url(self) -> str:
362
- return self._url
363
-
364
- @property
365
- def meta(self) -> Dict[str, Any]:
366
- return self._meta
367
-
368
- def __str__(self) -> str:
369
- return f'<Request url={self.url} method={self.method}>'
370
-
371
- def __repr__(self) -> str:
372
- return str(self)
373
-
374
- def __lt__(self, other: _Request) -> bool:
375
- """用于按优先级排序"""
376
- return self.priority < other.priority
1
+ #!/usr/bin/python
2
+ # -*- coding: UTF-8 -*-
3
+ """
4
+ HTTP Request 封装模块
5
+ ====================
6
+ 提供功能完善的HTTP请求封装,支持:
7
+ - JSON/表单数据自动处理
8
+ - GET请求参数处理
9
+ - 优先级排序机制
10
+ - 安全的深拷贝操作
11
+ - 灵活的请求配置
12
+ """
13
+ import json
14
+ from copy import deepcopy
15
+ from enum import IntEnum
16
+ from urllib.parse import urldefrag, urlencode, urlparse, urlunparse, parse_qsl
17
+ from w3lib.url import safe_url_string, add_or_replace_parameter
18
+ from typing import Dict, Optional, Callable, Union, Any, TypeVar, List
19
+
20
+
21
+
22
+
23
+ _Request = TypeVar("_Request", bound="Request")
24
+
25
+
26
+ class RequestPriority(IntEnum):
27
+ """
28
+ 请求优先级枚举。
29
+
30
+ 数值越小,优先级越高。使用 IntEnum 确保可以直接当作整数使用。
31
+
32
+ Examples:
33
+ >>> request = Request(url, priority=RequestPriority.HIGH)
34
+ >>> request.priority = RequestPriority.URGENT
35
+ """
36
+ URGENT = -200 # 紧急任务
37
+ HIGH = -100 # 高优先级
38
+ NORMAL = 0 # 正常优先级(默认)
39
+ LOW = 100 # 低优先级
40
+ BACKGROUND = 200 # 后台任务
41
+
42
+
43
+ class Request:
44
+ """
45
+ 封装一个 HTTP 请求对象,用于爬虫框架中表示一个待抓取的请求任务。
46
+ 支持 JSON、表单、GET参数、原始 body 提交,自动处理 Content-Type 与编码。
47
+ 不支持文件上传(multipart/form-data),保持轻量。
48
+ """
49
+
50
+ __slots__ = (
51
+ '_url',
52
+ '_meta',
53
+ 'callback',
54
+ 'cb_kwargs',
55
+ 'err_back',
56
+ 'headers',
57
+ 'body',
58
+ 'method',
59
+ 'cookies',
60
+ 'priority',
61
+ 'encoding',
62
+ 'dont_filter',
63
+ 'timeout',
64
+ 'proxy',
65
+ 'allow_redirects',
66
+ 'auth',
67
+ 'verify',
68
+ 'flags',
69
+ '_json_body',
70
+ '_form_data',
71
+ '_params',
72
+ 'use_dynamic_loader',
73
+ 'dynamic_loader_options'
74
+ )
75
+
76
+ def __init__(
77
+ self,
78
+ url: str,
79
+ callback: Optional[Callable] = None,
80
+ err_back: Optional[Callable] = None,
81
+ method: Optional[str] = 'GET',
82
+ headers: Optional[Dict[str, str]] = None,
83
+ body: Optional[Union[bytes, str, Dict[Any, Any]]] = None,
84
+ form_data: Optional[Dict[str, Any]] = None,
85
+ json_body: Optional[Dict[str, Any]] = None,
86
+ params: Optional[Dict[str, Any]] = None,
87
+ cb_kwargs: Optional[Dict[str, Any]] = None,
88
+ cookies: Optional[Dict[str, str]] = None,
89
+ meta: Optional[Dict[str, Any]] = None,
90
+ priority: int = RequestPriority.NORMAL,
91
+ dont_filter: bool = False,
92
+ timeout: Optional[float] = None,
93
+ proxy: Optional[str] = None,
94
+ allow_redirects: bool = True,
95
+ auth: Optional[tuple] = None,
96
+ verify: bool = True,
97
+ flags: Optional[List[str]] = None,
98
+ encoding: str = 'utf-8',
99
+ # 动态加载相关参数
100
+ use_dynamic_loader: bool = False,
101
+ dynamic_loader_options: Optional[Dict[str, Any]] = None
102
+ ):
103
+ """
104
+ 初始化请求对象。
105
+
106
+ :param url: 请求 URL(必须)
107
+ :param callback: 成功回调函数
108
+ :param err_back: 错误回调函数
109
+ :param method: HTTP 方法,默认 GET
110
+ :param headers: 请求头
111
+ :param body: 原始请求体(bytes/str),若为 dict 且未使用 json_body/form_data,则自动转为 JSON
112
+ :param form_data: 表单数据,POST请求时自动转为 application/x-www-form-urlencoded
113
+ :param json_body: JSON 数据,自动序列化并设置 Content-Type
114
+ :param params: GET请求参数,会自动附加到URL上
115
+ :param cb_kwargs: 传递给 callback 的额外参数
116
+ :param cookies: Cookies 字典
117
+ :param meta: 元数据(跨中间件传递数据)
118
+ :param priority: 优先级(数值越小越优先)
119
+ :param dont_filter: 是否跳过去重
120
+ :param timeout: 超时时间(秒)
121
+ :param proxy: 代理地址,如 http://127.0.0.1:8080
122
+ :param allow_redirects: 是否允许重定向
123
+ :param auth: 认证元组 (username, password)
124
+ :param verify: 是否验证 SSL 证书
125
+ :param flags: 标记(用于调试或分类)
126
+ :param encoding: 字符编码,默认 utf-8
127
+ """
128
+ self.callback = callback
129
+ self.err_back = err_back
130
+ self.method = str(method).upper()
131
+ self.headers = headers or {}
132
+ self.cookies = cookies or {}
133
+ self.priority = -priority # 用于排序:值越小优先级越高
134
+
135
+ # 安全处理 meta,移除 logger 后再 deepcopy
136
+ self._meta = self._safe_deepcopy_meta(meta) if meta is not None else {}
137
+
138
+ self.timeout = self._meta.get('download_timeout', timeout)
139
+ self.proxy = proxy
140
+ self.allow_redirects = allow_redirects
141
+ self.auth = auth
142
+ self.verify = verify
143
+ self.flags = flags or []
144
+ self.encoding = encoding
145
+ self.cb_kwargs = cb_kwargs or {}
146
+ self.body = body
147
+ # 保存高层语义参数(用于 copy)
148
+ self._json_body = json_body
149
+ self._form_data = form_data
150
+ self._params = params
151
+
152
+ # 动态加载相关属性
153
+ self.use_dynamic_loader = use_dynamic_loader
154
+ self.dynamic_loader_options = dynamic_loader_options or {}
155
+
156
+ # 处理GET参数
157
+ if params is not None and self.method == 'GET':
158
+ # 将GET参数附加到URL上
159
+ self._url = self._add_params_to_url(url, params)
160
+ else:
161
+ self._url = url
162
+
163
+ # 构建 body
164
+ if json_body is not None:
165
+ if 'Content-Type' not in self.headers:
166
+ self.headers['Content-Type'] = 'application/json'
167
+ self.body = json.dumps(json_body, ensure_ascii=False).encode(encoding)
168
+ if self.method == 'GET':
169
+ self.method = 'POST'
170
+
171
+ elif form_data is not None:
172
+ if self.method == 'GET':
173
+ # 对于GET请求,将form_data作为GET参数处理
174
+ self._url = self._add_params_to_url(self._url, form_data)
175
+ else:
176
+ # 对于POST等请求,将form_data作为请求体处理
177
+ if 'Content-Type' not in self.headers:
178
+ self.headers['Content-Type'] = 'application/x-www-form-urlencoded'
179
+ query_str = urlencode(form_data)
180
+ self.body = query_str.encode(encoding) # 显式编码为 bytes
181
+
182
+
183
+ else:
184
+ # 处理原始 body
185
+ if isinstance(self.body, dict):
186
+ if 'Content-Type' not in self.headers:
187
+ self.headers['Content-Type'] = 'application/json'
188
+ self.body = json.dumps(self.body, ensure_ascii=False).encode(encoding)
189
+ elif isinstance(self.body, str):
190
+ self.body = self.body.encode(encoding)
191
+
192
+ self.dont_filter = dont_filter
193
+ self._set_url(self._url)
194
+
195
+ @staticmethod
196
+ def _add_params_to_url(url: str, params: Dict[str, Any]) -> str:
197
+ """将参数添加到URL中"""
198
+ if not params:
199
+ return url
200
+
201
+ # 解析URL
202
+ parsed = urlparse(url)
203
+ # 解析现有查询参数
204
+ query_params = parse_qsl(parsed.query, keep_blank_values=True)
205
+ # 添加新参数
206
+ for key, value in params.items():
207
+ query_params.append((str(key), str(value)))
208
+ # 重新构建查询字符串
209
+ new_query = urlencode(query_params)
210
+ # 构建新的URL
211
+ return urlunparse((
212
+ parsed.scheme,
213
+ parsed.netloc,
214
+ parsed.path,
215
+ parsed.params,
216
+ new_query,
217
+ parsed.fragment
218
+ ))
219
+
220
+ @staticmethod
221
+ def _safe_deepcopy_meta(meta: Dict[str, Any]) -> Dict[str, Any]:
222
+ """安全地 deepcopy meta,移除 logger 后再复制"""
223
+ import logging
224
+
225
+ def clean_logger_recursive(obj: Any) -> Any:
226
+ """递归移除 logger 对象"""
227
+ if isinstance(obj, logging.Logger):
228
+ return None
229
+ elif isinstance(obj, dict):
230
+ cleaned = {}
231
+ for k, v in obj.items():
232
+ if not (k == 'logger' or isinstance(v, logging.Logger)):
233
+ cleaned[k] = clean_logger_recursive(v)
234
+ return cleaned
235
+ elif isinstance(obj, (list, tuple)):
236
+ cleaned_list = []
237
+ for item in obj:
238
+ cleaned_item = clean_logger_recursive(item)
239
+ if cleaned_item is not None:
240
+ cleaned_list.append(cleaned_item)
241
+ return type(obj)(cleaned_list)
242
+ else:
243
+ return obj
244
+
245
+ # 先清理 logger,再 deepcopy
246
+ cleaned_meta = clean_logger_recursive(meta)
247
+ # 确保返回字典类型
248
+ if not isinstance(cleaned_meta, dict):
249
+ return {}
250
+ return deepcopy(cleaned_meta)
251
+
252
+ def copy(self: _Request) -> _Request:
253
+ """
254
+ 创建当前请求的副本,保留所有高层语义(json_body/form_data/params)。
255
+ """
256
+ return type(self)(
257
+ url=self.url,
258
+ callback=self.callback,
259
+ method=self.method,
260
+ headers=self.headers.copy(),
261
+ body=None, # 由 form_data/json_body/params 重新生成
262
+ form_data=self._form_data,
263
+ json_body=self._json_body,
264
+ params=self._params,
265
+ cb_kwargs=deepcopy(self.cb_kwargs),
266
+ err_back=self.err_back,
267
+ cookies=self.cookies.copy(),
268
+ meta=deepcopy(self._meta),
269
+ priority=-self.priority,
270
+ dont_filter=self.dont_filter,
271
+ timeout=self.timeout,
272
+ proxy=self.proxy,
273
+ allow_redirects=self.allow_redirects,
274
+ auth=self.auth,
275
+ verify=self.verify,
276
+ flags=self.flags.copy(),
277
+ encoding=self.encoding,
278
+ use_dynamic_loader=self.use_dynamic_loader,
279
+ dynamic_loader_options=deepcopy(self.dynamic_loader_options)
280
+ )
281
+
282
+ def set_meta(self, key: str, value: Any) -> 'Request':
283
+ """设置 meta 中的某个键值,支持链式调用。"""
284
+ self._meta[key] = value
285
+ return self
286
+
287
+ def add_header(self, key: str, value: str) -> 'Request':
288
+ """添加请求头,支持链式调用。"""
289
+ self.headers[key] = value
290
+ return self
291
+
292
+ def add_headers(self, headers: Dict[str, str]) -> 'Request':
293
+ """批量添加请求头,支持链式调用。"""
294
+ self.headers.update(headers)
295
+ return self
296
+
297
+ def set_proxy(self, proxy: str) -> 'Request':
298
+ """设置代理,支持链式调用。"""
299
+ self.proxy = proxy
300
+ return self
301
+
302
+ def set_timeout(self, timeout: float) -> 'Request':
303
+ """设置超时时间,支持链式调用。"""
304
+ self.timeout = timeout
305
+ return self
306
+
307
+ def add_flag(self, flag: str) -> 'Request':
308
+ """添加标记,支持链式调用。"""
309
+ if flag not in self.flags:
310
+ self.flags.append(flag)
311
+ return self
312
+
313
+ def remove_flag(self, flag: str) -> 'Request':
314
+ """移除标记,支持链式调用。"""
315
+ if flag in self.flags:
316
+ self.flags.remove(flag)
317
+ return self
318
+
319
+ def set_dynamic_loader(self, use_dynamic: bool = True, options: Optional[Dict[str, Any]] = None) -> 'Request':
320
+ """设置使用动态加载器,支持链式调用。"""
321
+ self.use_dynamic_loader = use_dynamic
322
+ if options:
323
+ self.dynamic_loader_options = options
324
+ # 同时在meta中设置标记,供混合下载器使用
325
+ self._meta['use_dynamic_loader'] = use_dynamic
326
+ return self
327
+
328
+ def set_protocol_loader(self) -> 'Request':
329
+ """强制使用协议加载器,支持链式调用。"""
330
+ self.use_dynamic_loader = False
331
+ self._meta['use_dynamic_loader'] = False
332
+ self._meta['use_protocol_loader'] = True
333
+ return self
334
+
335
+ def _set_url(self, url: str) -> None:
336
+ """安全设置 URL,确保格式正确。"""
337
+ if not isinstance(url, str):
338
+ raise TypeError(f"Request url 必须为字符串,当前类型: {type(url).__name__}")
339
+
340
+ if not url.strip():
341
+ raise ValueError("URL 不能为空")
342
+
343
+ # 检查危险的 URL scheme
344
+ dangerous_schemes = ['file://', 'ftp://', 'javascript:', 'data:']
345
+ if any(url.lower().startswith(scheme) for scheme in dangerous_schemes):
346
+ raise ValueError(f"URL scheme 不安全: {url[:20]}...")
347
+
348
+ s = safe_url_string(url, self.encoding)
349
+ escaped_url = escape_ajax(s)
350
+
351
+ if not escaped_url.startswith(('http://', 'https://')):
352
+ raise ValueError(f"URL 缺少 HTTP(S) scheme: {escaped_url[:50]}...")
353
+
354
+ # 检查 URL 长度
355
+ if len(escaped_url) > 8192: # 大多数服务器支持的最大 URL 长度
356
+ raise ValueError(f"URL 过长 (超过 8192 字符): {len(escaped_url)} 字符")
357
+
358
+ self._url = escaped_url
359
+
360
+ @property
361
+ def url(self) -> str:
362
+ return self._url
363
+
364
+ @property
365
+ def meta(self) -> Dict[str, Any]:
366
+ return self._meta
367
+
368
+ def __str__(self) -> str:
369
+ return f'<Request url={self.url} method={self.method}>'
370
+
371
+ def __repr__(self) -> str:
372
+ return str(self)
373
+
374
+ def __lt__(self, other: _Request) -> bool:
375
+ """用于按优先级排序"""
376
+ return self.priority < other.priority
377
+
378
+ def escape_ajax(url: str) -> str:
379
+ """
380
+ 根据Google AJAX爬取规范转换URL(处理哈希片段#!):
381
+ https://developers.google.com/webmasters/ajax-crawling/docs/getting-started
382
+
383
+ 规则说明:
384
+ 1. 仅当URL包含 `#!` 时才转换(表示这是AJAX可爬取页面)
385
+ 2. 将 `#!key=value` 转换为 `?_escaped_fragment_=key%3Dvalue`
386
+ 3. 保留原始查询参数(如果有)
387
+
388
+ 示例:
389
+ >>> escape_ajax("www.example.com/ajax.html#!key=value")
390
+ 'www.example.com/ajax.html?_escaped_fragment_=key%3Dvalue'
391
+ >>> escape_ajax("www.example.com/ajax.html?k1=v1#!key=value")
392
+ 'www.example.com/ajax.html?k1=v1&_escaped_fragment_=key%3Dvalue'
393
+ >>> escape_ajax("www.example.com/ajax.html#!")
394
+ 'www.example.com/ajax.html?_escaped_fragment_='
395
+
396
+ 非AJAX可爬取的URL(无#!)原样返回:
397
+ >>> escape_ajax("www.example.com/ajax.html#normal")
398
+ 'www.example.com/ajax.html#normal'
399
+ """
400
+ # 分离URL的基础部分和哈希片段
401
+ de_frag, frag = urldefrag(url)
402
+
403
+ # 仅处理以"!"开头的哈希片段(Google规范)
404
+ if not frag.startswith("!"):
405
+ return url # 不符合规则则原样返回
406
+
407
+ # 调用辅助函数添加 `_escaped_fragment_` 参数
408
+ return add_or_replace_parameter(de_frag, "_escaped_fragment_", frag[1:])