crawlo 1.3.5__py3-none-any.whl → 1.3.6__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 (289) hide show
  1. crawlo/__init__.py +87 -87
  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 +341 -341
  10. crawlo/commands/startproject.py +436 -436
  11. crawlo/commands/stats.py +187 -187
  12. crawlo/commands/utils.py +196 -196
  13. crawlo/config.py +312 -312
  14. crawlo/config_validator.py +277 -277
  15. crawlo/core/__init__.py +45 -45
  16. crawlo/core/engine.py +439 -439
  17. crawlo/core/processor.py +40 -40
  18. crawlo/core/scheduler.py +257 -257
  19. crawlo/crawler.py +638 -638
  20. crawlo/data/__init__.py +5 -5
  21. crawlo/data/user_agents.py +194 -194
  22. crawlo/downloader/__init__.py +273 -273
  23. crawlo/downloader/aiohttp_downloader.py +228 -228
  24. crawlo/downloader/cffi_downloader.py +245 -245
  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 +61 -61
  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 +103 -103
  42. crawlo/factories/registry.py +84 -84
  43. crawlo/filters/__init__.py +154 -154
  44. crawlo/filters/aioredis_filter.py +257 -257
  45. crawlo/filters/memory_filter.py +269 -269
  46. crawlo/framework.py +292 -291
  47. crawlo/initialization/__init__.py +39 -39
  48. crawlo/initialization/built_in.py +425 -425
  49. crawlo/initialization/context.py +141 -141
  50. crawlo/initialization/core.py +193 -193
  51. crawlo/initialization/phases.py +148 -148
  52. crawlo/initialization/registry.py +145 -145
  53. crawlo/items/__init__.py +23 -23
  54. crawlo/items/base.py +23 -23
  55. crawlo/items/fields.py +52 -52
  56. crawlo/items/items.py +104 -104
  57. crawlo/logging/__init__.py +37 -37
  58. crawlo/logging/config.py +96 -96
  59. crawlo/logging/factory.py +128 -128
  60. crawlo/logging/manager.py +111 -111
  61. crawlo/middleware/__init__.py +21 -21
  62. crawlo/middleware/default_header.py +132 -132
  63. crawlo/middleware/download_delay.py +104 -104
  64. crawlo/middleware/middleware_manager.py +135 -135
  65. crawlo/middleware/offsite.py +123 -123
  66. crawlo/middleware/proxy.py +386 -386
  67. crawlo/middleware/request_ignore.py +86 -86
  68. crawlo/middleware/response_code.py +163 -163
  69. crawlo/middleware/response_filter.py +136 -136
  70. crawlo/middleware/retry.py +124 -124
  71. crawlo/middleware/simple_proxy.py +65 -65
  72. crawlo/mode_manager.py +212 -212
  73. crawlo/network/__init__.py +21 -21
  74. crawlo/network/request.py +379 -379
  75. crawlo/network/response.py +359 -359
  76. crawlo/pipelines/__init__.py +21 -21
  77. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  78. crawlo/pipelines/console_pipeline.py +39 -39
  79. crawlo/pipelines/csv_pipeline.py +316 -316
  80. crawlo/pipelines/database_dedup_pipeline.py +222 -222
  81. crawlo/pipelines/json_pipeline.py +218 -218
  82. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  83. crawlo/pipelines/mongo_pipeline.py +131 -131
  84. crawlo/pipelines/mysql_pipeline.py +325 -325
  85. crawlo/pipelines/pipeline_manager.py +76 -76
  86. crawlo/pipelines/redis_dedup_pipeline.py +166 -166
  87. crawlo/project.py +327 -327
  88. crawlo/queue/pqueue.py +42 -42
  89. crawlo/queue/queue_manager.py +503 -503
  90. crawlo/queue/redis_priority_queue.py +326 -326
  91. crawlo/settings/__init__.py +7 -7
  92. crawlo/settings/default_settings.py +321 -321
  93. crawlo/settings/setting_manager.py +214 -214
  94. crawlo/spider/__init__.py +657 -657
  95. crawlo/stats_collector.py +73 -73
  96. crawlo/subscriber.py +129 -129
  97. crawlo/task_manager.py +138 -138
  98. crawlo/templates/crawlo.cfg.tmpl +10 -10
  99. crawlo/templates/project/__init__.py.tmpl +3 -3
  100. crawlo/templates/project/items.py.tmpl +17 -17
  101. crawlo/templates/project/middlewares.py.tmpl +118 -118
  102. crawlo/templates/project/pipelines.py.tmpl +96 -96
  103. crawlo/templates/project/settings.py.tmpl +167 -167
  104. crawlo/templates/project/settings_distributed.py.tmpl +166 -166
  105. crawlo/templates/project/settings_gentle.py.tmpl +166 -166
  106. crawlo/templates/project/settings_high_performance.py.tmpl +167 -167
  107. crawlo/templates/project/settings_minimal.py.tmpl +65 -65
  108. crawlo/templates/project/settings_simple.py.tmpl +164 -164
  109. crawlo/templates/project/spiders/__init__.py.tmpl +9 -9
  110. crawlo/templates/run.py.tmpl +34 -34
  111. crawlo/templates/spider/spider.py.tmpl +143 -143
  112. crawlo/templates/spiders_init.py.tmpl +9 -9
  113. crawlo/tools/__init__.py +200 -200
  114. crawlo/tools/anti_crawler.py +268 -268
  115. crawlo/tools/authenticated_proxy.py +240 -240
  116. crawlo/tools/data_formatter.py +225 -225
  117. crawlo/tools/data_validator.py +180 -180
  118. crawlo/tools/date_tools.py +289 -289
  119. crawlo/tools/distributed_coordinator.py +388 -388
  120. crawlo/tools/encoding_converter.py +127 -127
  121. crawlo/tools/network_diagnostic.py +364 -364
  122. crawlo/tools/request_tools.py +82 -82
  123. crawlo/tools/retry_mechanism.py +224 -224
  124. crawlo/tools/scenario_adapter.py +262 -262
  125. crawlo/tools/text_cleaner.py +232 -232
  126. crawlo/utils/__init__.py +34 -34
  127. crawlo/utils/batch_processor.py +259 -259
  128. crawlo/utils/class_loader.py +25 -25
  129. crawlo/utils/controlled_spider_mixin.py +439 -439
  130. crawlo/utils/db_helper.py +343 -343
  131. crawlo/utils/enhanced_error_handler.py +356 -356
  132. crawlo/utils/env_config.py +142 -142
  133. crawlo/utils/error_handler.py +165 -165
  134. crawlo/utils/func_tools.py +82 -82
  135. crawlo/utils/large_scale_config.py +286 -286
  136. crawlo/utils/large_scale_helper.py +344 -344
  137. crawlo/utils/log.py +79 -79
  138. crawlo/utils/performance_monitor.py +285 -285
  139. crawlo/utils/queue_helper.py +175 -175
  140. crawlo/utils/redis_connection_pool.py +388 -388
  141. crawlo/utils/redis_key_validator.py +198 -198
  142. crawlo/utils/request.py +267 -267
  143. crawlo/utils/request_serializer.py +225 -225
  144. crawlo/utils/spider_loader.py +61 -61
  145. crawlo/utils/system.py +11 -11
  146. crawlo/utils/tools.py +4 -4
  147. crawlo/utils/url.py +39 -39
  148. {crawlo-1.3.5.dist-info → crawlo-1.3.6.dist-info}/METADATA +1126 -1126
  149. crawlo-1.3.6.dist-info/RECORD +290 -0
  150. examples/__init__.py +7 -7
  151. tests/__init__.py +7 -7
  152. tests/advanced_tools_example.py +275 -275
  153. tests/authenticated_proxy_example.py +106 -106
  154. tests/baidu_performance_test.py +108 -108
  155. tests/baidu_test.py +59 -59
  156. tests/cleaners_example.py +160 -160
  157. tests/comprehensive_framework_test.py +212 -212
  158. tests/comprehensive_test.py +81 -81
  159. tests/comprehensive_testing_summary.md +186 -186
  160. tests/config_validation_demo.py +142 -142
  161. tests/controlled_spider_example.py +205 -205
  162. tests/date_tools_example.py +180 -180
  163. tests/debug_configure.py +69 -69
  164. tests/debug_framework_logger.py +84 -84
  165. tests/debug_log_config.py +126 -126
  166. tests/debug_log_levels.py +63 -63
  167. tests/debug_pipelines.py +66 -66
  168. tests/detailed_log_test.py +233 -233
  169. tests/distributed_test.py +66 -66
  170. tests/distributed_test_debug.py +76 -76
  171. tests/dynamic_loading_example.py +523 -523
  172. tests/dynamic_loading_test.py +104 -104
  173. tests/env_config_example.py +133 -133
  174. tests/error_handling_example.py +171 -171
  175. tests/final_comprehensive_test.py +151 -151
  176. tests/final_log_test.py +260 -260
  177. tests/final_validation_test.py +182 -182
  178. tests/fix_log_test.py +142 -142
  179. tests/framework_performance_test.py +202 -202
  180. tests/log_buffering_test.py +111 -111
  181. tests/log_generation_timing_test.py +153 -153
  182. tests/optimized_performance_test.py +211 -211
  183. tests/performance_comparison.py +245 -245
  184. tests/queue_blocking_test.py +113 -113
  185. tests/queue_test.py +89 -89
  186. tests/redis_key_validation_demo.py +130 -130
  187. tests/request_params_example.py +150 -150
  188. tests/response_improvements_example.py +144 -144
  189. tests/scrapy_comparison/ofweek_scrapy.py +138 -138
  190. tests/scrapy_comparison/scrapy_test.py +133 -133
  191. tests/simple_command_test.py +119 -119
  192. tests/simple_crawlo_test.py +127 -127
  193. tests/simple_log_test.py +57 -57
  194. tests/simple_log_test2.py +137 -137
  195. tests/simple_optimization_test.py +128 -128
  196. tests/simple_queue_type_test.py +42 -0
  197. tests/simple_spider_test.py +49 -49
  198. tests/simple_test.py +47 -47
  199. tests/spider_log_timing_test.py +177 -177
  200. tests/test_advanced_tools.py +148 -148
  201. tests/test_all_commands.py +230 -230
  202. tests/test_all_redis_key_configs.py +145 -145
  203. tests/test_authenticated_proxy.py +141 -141
  204. tests/test_batch_processor.py +178 -178
  205. tests/test_cleaners.py +54 -54
  206. tests/test_component_factory.py +174 -174
  207. tests/test_comprehensive.py +146 -146
  208. tests/test_config_consistency.py +80 -80
  209. tests/test_config_merge.py +152 -152
  210. tests/test_config_validator.py +182 -182
  211. tests/test_controlled_spider_mixin.py +79 -79
  212. tests/test_crawlo_proxy_integration.py +108 -108
  213. tests/test_date_tools.py +123 -123
  214. tests/test_default_header_middleware.py +158 -158
  215. tests/test_distributed.py +65 -65
  216. tests/test_double_crawlo_fix.py +207 -207
  217. tests/test_double_crawlo_fix_simple.py +124 -124
  218. tests/test_download_delay_middleware.py +221 -221
  219. tests/test_downloader_proxy_compatibility.py +268 -268
  220. tests/test_dynamic_downloaders_proxy.py +124 -124
  221. tests/test_dynamic_proxy.py +92 -92
  222. tests/test_dynamic_proxy_config.py +146 -146
  223. tests/test_dynamic_proxy_real.py +109 -109
  224. tests/test_edge_cases.py +303 -303
  225. tests/test_enhanced_error_handler.py +270 -270
  226. tests/test_enhanced_error_handler_comprehensive.py +245 -245
  227. tests/test_env_config.py +121 -121
  228. tests/test_error_handler_compatibility.py +112 -112
  229. tests/test_factories.py +252 -252
  230. tests/test_final_validation.py +153 -153
  231. tests/test_framework_env_usage.py +103 -103
  232. tests/test_framework_logger.py +66 -66
  233. tests/test_framework_startup.py +64 -64
  234. tests/test_get_component_logger.py +83 -83
  235. tests/test_integration.py +169 -169
  236. tests/test_item_dedup_redis_key.py +122 -122
  237. tests/test_large_scale_config.py +112 -112
  238. tests/test_large_scale_helper.py +235 -235
  239. tests/test_logging_system.py +282 -282
  240. tests/test_mode_change.py +72 -72
  241. tests/test_mode_consistency.py +51 -51
  242. tests/test_offsite_middleware.py +221 -221
  243. tests/test_parsel.py +29 -29
  244. tests/test_performance.py +327 -327
  245. tests/test_performance_monitor.py +115 -115
  246. tests/test_proxy_api.py +264 -264
  247. tests/test_proxy_health_check.py +32 -32
  248. tests/test_proxy_middleware.py +121 -121
  249. tests/test_proxy_middleware_enhanced.py +216 -216
  250. tests/test_proxy_middleware_integration.py +136 -136
  251. tests/test_proxy_middleware_refactored.py +184 -184
  252. tests/test_proxy_providers.py +56 -56
  253. tests/test_proxy_stats.py +19 -19
  254. tests/test_proxy_strategies.py +59 -59
  255. tests/test_queue_empty_check.py +41 -41
  256. tests/test_queue_manager_double_crawlo.py +173 -173
  257. tests/test_queue_manager_redis_key.py +176 -176
  258. tests/test_queue_type.py +107 -0
  259. tests/test_random_user_agent.py +72 -72
  260. tests/test_real_scenario_proxy.py +195 -195
  261. tests/test_redis_config.py +28 -28
  262. tests/test_redis_connection_pool.py +294 -294
  263. tests/test_redis_key_naming.py +181 -181
  264. tests/test_redis_key_validator.py +123 -123
  265. tests/test_redis_queue.py +224 -224
  266. tests/test_request_ignore_middleware.py +182 -182
  267. tests/test_request_params.py +111 -111
  268. tests/test_request_serialization.py +70 -70
  269. tests/test_response_code_middleware.py +349 -349
  270. tests/test_response_filter_middleware.py +427 -427
  271. tests/test_response_improvements.py +152 -152
  272. tests/test_retry_middleware.py +241 -241
  273. tests/test_scheduler.py +252 -252
  274. tests/test_scheduler_config_update.py +133 -133
  275. tests/test_simple_response.py +61 -61
  276. tests/test_telecom_spider_redis_key.py +205 -205
  277. tests/test_template_content.py +87 -87
  278. tests/test_template_redis_key.py +134 -134
  279. tests/test_tools.py +159 -159
  280. tests/test_user_agents.py +96 -96
  281. tests/tools_example.py +260 -260
  282. tests/untested_features_report.md +138 -138
  283. tests/verify_debug.py +51 -51
  284. tests/verify_distributed.py +117 -117
  285. tests/verify_log_fix.py +111 -111
  286. crawlo-1.3.5.dist-info/RECORD +0 -288
  287. {crawlo-1.3.5.dist-info → crawlo-1.3.6.dist-info}/WHEEL +0 -0
  288. {crawlo-1.3.5.dist-info → crawlo-1.3.6.dist-info}/entry_points.txt +0 -0
  289. {crawlo-1.3.5.dist-info → crawlo-1.3.6.dist-info}/top_level.txt +0 -0
crawlo/utils/request.py CHANGED
@@ -1,267 +1,267 @@
1
- #!/usr/bin/python
2
- # -*- coding:UTF-8 -*-
3
- """
4
- # @Time : 2025-07-08 08:55
5
- # @Author : crawl-coder
6
- # @Desc : None
7
- """
8
- import importlib
9
- import json
10
- import hashlib
11
- from typing import Any, Optional, Iterable, Union, Dict
12
- from w3lib.url import canonicalize_url
13
-
14
- from crawlo import Request
15
-
16
-
17
- def to_bytes(data: Any, encoding: str = 'utf-8') -> bytes:
18
- """
19
- 将各种类型统一转换为 bytes。
20
-
21
- Args:
22
- data: 要转换的数据,支持 str, bytes, dict, int, float, bool, None 等类型
23
- encoding: 字符串编码格式,默认为 'utf-8'
24
-
25
- Returns:
26
- bytes: 转换后的字节数据
27
-
28
- Raises:
29
- TypeError: 当数据类型无法转换时
30
- UnicodeEncodeError: 当编码失败时
31
- ValueError: 当 JSON 序列化失败时
32
-
33
- Examples:
34
- >>> to_bytes("hello")
35
- b'hello'
36
- >>> to_bytes({"key": "value"})
37
- b'{"key": "value"}'
38
- >>> to_bytes(123)
39
- b'123'
40
- >>> to_bytes(None)
41
- b'null'
42
- """
43
- # 预检查编码参数
44
- if not isinstance(encoding, str):
45
- raise TypeError(f"encoding must be str, not {type(encoding).__name__}")
46
-
47
- try:
48
- if isinstance(data, bytes):
49
- return data
50
- elif isinstance(data, str):
51
- return data.encode(encoding)
52
- elif isinstance(data, dict):
53
- return json.dumps(data, sort_keys=True, ensure_ascii=False, separators=(',', ':')).encode(encoding)
54
- elif isinstance(data, (int, float, bool)):
55
- return str(data).encode(encoding)
56
- elif data is None:
57
- return b'null'
58
- elif hasattr(data, '__str__'):
59
- # 处理其他可转换为字符串的对象
60
- return str(data).encode(encoding)
61
- else:
62
- raise TypeError(
63
- f"`data` must be str, dict, bytes, int, float, bool, or None, "
64
- f"not {type(data).__name__}"
65
- )
66
- except (UnicodeEncodeError, ValueError) as e:
67
- raise type(e)(f"Failed to convert {type(data).__name__} to bytes: {str(e)}") from e
68
-
69
-
70
- def request_fingerprint(
71
- request: Request,
72
- include_headers: Optional[Iterable[Union[bytes, str]]] = None
73
- ) -> str:
74
- """
75
- 生成请求指纹,基于方法、标准化 URL、body 和可选的 headers。
76
- 使用 SHA256 哈希算法以提高安全性。
77
-
78
- :param request: Request 对象(需包含 method, url, body, headers)
79
- :param include_headers: 指定要参与指纹计算的 header 名称列表(str 或 bytes)
80
- :return: 请求指纹(hex string)
81
- """
82
- hash_func = hashlib.sha256()
83
-
84
- # 基本字段
85
- hash_func.update(to_bytes(request.method))
86
- hash_func.update(to_bytes(canonicalize_url(request.url)))
87
- hash_func.update(request.body or b'')
88
-
89
- # 处理 headers
90
- if include_headers:
91
- headers = request.headers # 假设 headers 是类似字典或 MultiDict 的结构
92
- for header_name in include_headers:
93
- name_bytes = to_bytes(header_name).lower() # 统一转为小写进行匹配
94
- value = b''
95
-
96
- # 兼容 headers 的访问方式(如 MultiDict 或 dict)
97
- if hasattr(headers, 'get_all'):
98
- # 如 scrapy.http.Headers 的 get_all 方法
99
- values = headers.get_all(name_bytes)
100
- value = b';'.join(values) if values else b''
101
- elif hasattr(headers, '__getitem__'):
102
- # 如普通 dict
103
- try:
104
- raw_value = headers[name_bytes]
105
- if isinstance(raw_value, list):
106
- value = b';'.join(to_bytes(v) for v in raw_value)
107
- else:
108
- value = to_bytes(raw_value)
109
- except (KeyError, TypeError):
110
- value = b''
111
- else:
112
- value = b''
113
-
114
- hash_func.update(name_bytes + b':' + value)
115
-
116
- return hash_func.hexdigest()
117
-
118
-
119
- def set_request(request: Request, priority: int) -> None:
120
- request.meta['depth'] = request.meta.setdefault('depth', 0) + 1
121
- if priority:
122
- request.priority -= request.meta['depth'] * priority
123
-
124
-
125
- def request_to_dict(request: Request, spider=None) -> Dict[str, Any]:
126
- """
127
- 将 Request 对象转换为可 JSON 序列化的字典。
128
-
129
- Args:
130
- request: 要序列化的 Request 对象
131
- spider: 可选,用于辅助序列化(如回调函数的归属)
132
-
133
- Returns:
134
- 包含 Request 所有关键信息的字典
135
- """
136
- # 基础属性
137
- d = {
138
- 'url': request.url,
139
- 'method': request.method,
140
- 'headers': dict(request.headers),
141
- 'body': request.body,
142
- 'meta': request.meta.copy(), # 复制一份
143
- 'flags': request.flags.copy(),
144
- 'cb_kwargs': request.cb_kwargs.copy(),
145
- }
146
-
147
- # 1. 处理 callback
148
- # 不能直接序列化函数,所以存储其路径
149
- if callable(request.callback):
150
- d['_callback'] = _get_function_path(request.callback)
151
-
152
- # 2. 处理 errback
153
- if callable(request.errback):
154
- d['_errback'] = _get_function_path(request.errback)
155
-
156
- # 3. 记录原始类名,以便反序列化时创建正确的实例
157
- d['_class'] = request.__class__.__module__ + '.' + request.__class__.__name__
158
-
159
- # 4. 特殊处理 FormRequest
160
- # 如果是 FormRequest,需要保存 formdata
161
- if isinstance(request, Request):
162
- if hasattr(request, 'formdata'):
163
- d['formdata'] = request.formdata
164
-
165
- return d
166
-
167
-
168
- def request_from_dict(d: Dict[str, Any], spider=None) -> Request:
169
- """
170
- 从字典重建 Request 对象。
171
-
172
- Args:
173
- d: 由 request_to_dict 生成的字典
174
- spider: 可选,用于解析回调函数
175
-
176
- Returns:
177
- 重建的 Request 对象
178
- """
179
- # 1. 获取类名并动态导入
180
- cls_path = d.pop('_class', None)
181
- if cls_path:
182
- module_path, cls_name = cls_path.rsplit('.', 1)
183
- module = importlib.import_module(module_path)
184
- cls = getattr(module, cls_name)
185
- else:
186
- cls = Request # 默认为 Request
187
-
188
- # 2. 提取回调函数
189
- callback_path = d.pop('_callback', None)
190
- callback = _get_function_from_path(callback_path, spider) if callback_path else None
191
-
192
- # 3. 提取错误回调
193
- errback_path = d.pop('_errback', None)
194
- errback = _get_function_from_path(errback_path, spider) if errback_path else None
195
-
196
- # 4. 提取特殊字段
197
- formdata = d.pop('formdata', None)
198
-
199
- # 5. 创建 Request 实例
200
- # 注意:body 和 formdata 不能同时存在
201
- if formdata is not None and cls is FormRequest:
202
- # 如果是 FormRequest 且有 formdata,优先使用 formdata
203
- request = FormRequest(
204
- url=d['url'],
205
- method=d.get('method', 'GET'),
206
- headers=d.get('headers', {}),
207
- formdata=formdata,
208
- callback=callback,
209
- errback=errback,
210
- meta=d.get('meta', {}),
211
- flags=d.get('flags', []),
212
- cb_kwargs=d.get('cb_kwargs', {}),
213
- )
214
- else:
215
- # 普通 Request 或没有 formdata 的情况
216
- request = cls(
217
- url=d['url'],
218
- method=d.get('method', 'GET'),
219
- headers=d.get('headers', {}),
220
- body=d.get('body'),
221
- callback=callback,
222
- errback=errback,
223
- meta=d.get('meta', {}),
224
- flags=d.get('flags', []),
225
- cb_kwargs=d.get('cb_kwargs', {}),
226
- )
227
-
228
- return request
229
-
230
-
231
- def _get_function_path(func: callable) -> str:
232
- """
233
- 获取函数的模块路径,如 'myproject.spiders.my_spider.parse'
234
- """
235
- if hasattr(func, '__wrapped__'):
236
- # 处理被装饰的函数
237
- func = func.__wrapped__
238
- module = func.__module__
239
- if module is None or module == str.__class__.__module__:
240
- raise ValueError(f"无法序列化内置函数或lambda: {func}")
241
- return f"{module}.{func.__qualname__}"
242
-
243
-
244
- def _get_function_from_path(path: str, spider=None) -> Optional[callable]:
245
- """
246
- 从路径字符串获取函数对象。
247
- 如果函数是 spider 的方法,会尝试绑定到 spider 实例。
248
- """
249
- try:
250
- module_path, func_name = path.rsplit('.', 1)
251
- module = importlib.import_module(module_path)
252
-
253
- # 逐级获取属性,支持 nested functions
254
- func = module
255
- for attr in func_name.split('.'):
256
- func = getattr(func, attr)
257
-
258
- # 如果 spider 存在,并且 func 是 spider 的方法
259
- if spider and hasattr(spider, func.__name__):
260
- spider_method = getattr(spider, func.__name__)
261
- if spider_method is func:
262
- return spider_method # 返回绑定的方法
263
-
264
- return func
265
- except Exception as e:
266
- raise ValueError(f"无法从路径 '{path}' 加载函数: {e}")
267
-
1
+ #!/usr/bin/python
2
+ # -*- coding:UTF-8 -*-
3
+ """
4
+ # @Time : 2025-07-08 08:55
5
+ # @Author : crawl-coder
6
+ # @Desc : None
7
+ """
8
+ import importlib
9
+ import json
10
+ import hashlib
11
+ from typing import Any, Optional, Iterable, Union, Dict
12
+ from w3lib.url import canonicalize_url
13
+
14
+ from crawlo import Request
15
+
16
+
17
+ def to_bytes(data: Any, encoding: str = 'utf-8') -> bytes:
18
+ """
19
+ 将各种类型统一转换为 bytes。
20
+
21
+ Args:
22
+ data: 要转换的数据,支持 str, bytes, dict, int, float, bool, None 等类型
23
+ encoding: 字符串编码格式,默认为 'utf-8'
24
+
25
+ Returns:
26
+ bytes: 转换后的字节数据
27
+
28
+ Raises:
29
+ TypeError: 当数据类型无法转换时
30
+ UnicodeEncodeError: 当编码失败时
31
+ ValueError: 当 JSON 序列化失败时
32
+
33
+ Examples:
34
+ >>> to_bytes("hello")
35
+ b'hello'
36
+ >>> to_bytes({"key": "value"})
37
+ b'{"key": "value"}'
38
+ >>> to_bytes(123)
39
+ b'123'
40
+ >>> to_bytes(None)
41
+ b'null'
42
+ """
43
+ # 预检查编码参数
44
+ if not isinstance(encoding, str):
45
+ raise TypeError(f"encoding must be str, not {type(encoding).__name__}")
46
+
47
+ try:
48
+ if isinstance(data, bytes):
49
+ return data
50
+ elif isinstance(data, str):
51
+ return data.encode(encoding)
52
+ elif isinstance(data, dict):
53
+ return json.dumps(data, sort_keys=True, ensure_ascii=False, separators=(',', ':')).encode(encoding)
54
+ elif isinstance(data, (int, float, bool)):
55
+ return str(data).encode(encoding)
56
+ elif data is None:
57
+ return b'null'
58
+ elif hasattr(data, '__str__'):
59
+ # 处理其他可转换为字符串的对象
60
+ return str(data).encode(encoding)
61
+ else:
62
+ raise TypeError(
63
+ f"`data` must be str, dict, bytes, int, float, bool, or None, "
64
+ f"not {type(data).__name__}"
65
+ )
66
+ except (UnicodeEncodeError, ValueError) as e:
67
+ raise type(e)(f"Failed to convert {type(data).__name__} to bytes: {str(e)}") from e
68
+
69
+
70
+ def request_fingerprint(
71
+ request: Request,
72
+ include_headers: Optional[Iterable[Union[bytes, str]]] = None
73
+ ) -> str:
74
+ """
75
+ 生成请求指纹,基于方法、标准化 URL、body 和可选的 headers。
76
+ 使用 SHA256 哈希算法以提高安全性。
77
+
78
+ :param request: Request 对象(需包含 method, url, body, headers)
79
+ :param include_headers: 指定要参与指纹计算的 header 名称列表(str 或 bytes)
80
+ :return: 请求指纹(hex string)
81
+ """
82
+ hash_func = hashlib.sha256()
83
+
84
+ # 基本字段
85
+ hash_func.update(to_bytes(request.method))
86
+ hash_func.update(to_bytes(canonicalize_url(request.url)))
87
+ hash_func.update(request.body or b'')
88
+
89
+ # 处理 headers
90
+ if include_headers:
91
+ headers = request.headers # 假设 headers 是类似字典或 MultiDict 的结构
92
+ for header_name in include_headers:
93
+ name_bytes = to_bytes(header_name).lower() # 统一转为小写进行匹配
94
+ value = b''
95
+
96
+ # 兼容 headers 的访问方式(如 MultiDict 或 dict)
97
+ if hasattr(headers, 'get_all'):
98
+ # 如 scrapy.http.Headers 的 get_all 方法
99
+ values = headers.get_all(name_bytes)
100
+ value = b';'.join(values) if values else b''
101
+ elif hasattr(headers, '__getitem__'):
102
+ # 如普通 dict
103
+ try:
104
+ raw_value = headers[name_bytes]
105
+ if isinstance(raw_value, list):
106
+ value = b';'.join(to_bytes(v) for v in raw_value)
107
+ else:
108
+ value = to_bytes(raw_value)
109
+ except (KeyError, TypeError):
110
+ value = b''
111
+ else:
112
+ value = b''
113
+
114
+ hash_func.update(name_bytes + b':' + value)
115
+
116
+ return hash_func.hexdigest()
117
+
118
+
119
+ def set_request(request: Request, priority: int) -> None:
120
+ request.meta['depth'] = request.meta.setdefault('depth', 0) + 1
121
+ if priority:
122
+ request.priority -= request.meta['depth'] * priority
123
+
124
+
125
+ def request_to_dict(request: Request, spider=None) -> Dict[str, Any]:
126
+ """
127
+ 将 Request 对象转换为可 JSON 序列化的字典。
128
+
129
+ Args:
130
+ request: 要序列化的 Request 对象
131
+ spider: 可选,用于辅助序列化(如回调函数的归属)
132
+
133
+ Returns:
134
+ 包含 Request 所有关键信息的字典
135
+ """
136
+ # 基础属性
137
+ d = {
138
+ 'url': request.url,
139
+ 'method': request.method,
140
+ 'headers': dict(request.headers),
141
+ 'body': request.body,
142
+ 'meta': request.meta.copy(), # 复制一份
143
+ 'flags': request.flags.copy(),
144
+ 'cb_kwargs': request.cb_kwargs.copy(),
145
+ }
146
+
147
+ # 1. 处理 callback
148
+ # 不能直接序列化函数,所以存储其路径
149
+ if callable(request.callback):
150
+ d['_callback'] = _get_function_path(request.callback)
151
+
152
+ # 2. 处理 errback
153
+ if callable(request.errback):
154
+ d['_errback'] = _get_function_path(request.errback)
155
+
156
+ # 3. 记录原始类名,以便反序列化时创建正确的实例
157
+ d['_class'] = request.__class__.__module__ + '.' + request.__class__.__name__
158
+
159
+ # 4. 特殊处理 FormRequest
160
+ # 如果是 FormRequest,需要保存 formdata
161
+ if isinstance(request, Request):
162
+ if hasattr(request, 'formdata'):
163
+ d['formdata'] = request.formdata
164
+
165
+ return d
166
+
167
+
168
+ def request_from_dict(d: Dict[str, Any], spider=None) -> Request:
169
+ """
170
+ 从字典重建 Request 对象。
171
+
172
+ Args:
173
+ d: 由 request_to_dict 生成的字典
174
+ spider: 可选,用于解析回调函数
175
+
176
+ Returns:
177
+ 重建的 Request 对象
178
+ """
179
+ # 1. 获取类名并动态导入
180
+ cls_path = d.pop('_class', None)
181
+ if cls_path:
182
+ module_path, cls_name = cls_path.rsplit('.', 1)
183
+ module = importlib.import_module(module_path)
184
+ cls = getattr(module, cls_name)
185
+ else:
186
+ cls = Request # 默认为 Request
187
+
188
+ # 2. 提取回调函数
189
+ callback_path = d.pop('_callback', None)
190
+ callback = _get_function_from_path(callback_path, spider) if callback_path else None
191
+
192
+ # 3. 提取错误回调
193
+ errback_path = d.pop('_errback', None)
194
+ errback = _get_function_from_path(errback_path, spider) if errback_path else None
195
+
196
+ # 4. 提取特殊字段
197
+ formdata = d.pop('formdata', None)
198
+
199
+ # 5. 创建 Request 实例
200
+ # 注意:body 和 formdata 不能同时存在
201
+ if formdata is not None and cls is FormRequest:
202
+ # 如果是 FormRequest 且有 formdata,优先使用 formdata
203
+ request = FormRequest(
204
+ url=d['url'],
205
+ method=d.get('method', 'GET'),
206
+ headers=d.get('headers', {}),
207
+ formdata=formdata,
208
+ callback=callback,
209
+ errback=errback,
210
+ meta=d.get('meta', {}),
211
+ flags=d.get('flags', []),
212
+ cb_kwargs=d.get('cb_kwargs', {}),
213
+ )
214
+ else:
215
+ # 普通 Request 或没有 formdata 的情况
216
+ request = cls(
217
+ url=d['url'],
218
+ method=d.get('method', 'GET'),
219
+ headers=d.get('headers', {}),
220
+ body=d.get('body'),
221
+ callback=callback,
222
+ errback=errback,
223
+ meta=d.get('meta', {}),
224
+ flags=d.get('flags', []),
225
+ cb_kwargs=d.get('cb_kwargs', {}),
226
+ )
227
+
228
+ return request
229
+
230
+
231
+ def _get_function_path(func: callable) -> str:
232
+ """
233
+ 获取函数的模块路径,如 'myproject.spiders.my_spider.parse'
234
+ """
235
+ if hasattr(func, '__wrapped__'):
236
+ # 处理被装饰的函数
237
+ func = func.__wrapped__
238
+ module = func.__module__
239
+ if module is None or module == str.__class__.__module__:
240
+ raise ValueError(f"无法序列化内置函数或lambda: {func}")
241
+ return f"{module}.{func.__qualname__}"
242
+
243
+
244
+ def _get_function_from_path(path: str, spider=None) -> Optional[callable]:
245
+ """
246
+ 从路径字符串获取函数对象。
247
+ 如果函数是 spider 的方法,会尝试绑定到 spider 实例。
248
+ """
249
+ try:
250
+ module_path, func_name = path.rsplit('.', 1)
251
+ module = importlib.import_module(module_path)
252
+
253
+ # 逐级获取属性,支持 nested functions
254
+ func = module
255
+ for attr in func_name.split('.'):
256
+ func = getattr(func, attr)
257
+
258
+ # 如果 spider 存在,并且 func 是 spider 的方法
259
+ if spider and hasattr(spider, func.__name__):
260
+ spider_method = getattr(spider, func.__name__)
261
+ if spider_method is func:
262
+ return spider_method # 返回绑定的方法
263
+
264
+ return func
265
+ except Exception as e:
266
+ raise ValueError(f"无法从路径 '{path}' 加载函数: {e}")
267
+