crawlo 1.2.6__py3-none-any.whl → 1.2.8__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 (209) 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 +75 -88
  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 +138 -144
  12. crawlo/commands/list.py +155 -155
  13. crawlo/commands/run.py +323 -323
  14. crawlo/commands/startproject.py +436 -436
  15. crawlo/commands/stats.py +187 -187
  16. crawlo/commands/utils.py +186 -186
  17. crawlo/config.py +312 -312
  18. crawlo/config_validator.py +251 -251
  19. crawlo/core/__init__.py +2 -2
  20. crawlo/core/engine.py +365 -356
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +251 -239
  23. crawlo/crawler.py +1099 -1110
  24. crawlo/data/__init__.py +5 -5
  25. crawlo/data/user_agents.py +107 -107
  26. crawlo/downloader/__init__.py +266 -266
  27. crawlo/downloader/aiohttp_downloader.py +228 -221
  28. crawlo/downloader/cffi_downloader.py +256 -256
  29. crawlo/downloader/httpx_downloader.py +259 -259
  30. crawlo/downloader/hybrid_downloader.py +212 -212
  31. crawlo/downloader/playwright_downloader.py +402 -402
  32. crawlo/downloader/selenium_downloader.py +472 -472
  33. crawlo/event.py +11 -11
  34. crawlo/exceptions.py +81 -81
  35. crawlo/extension/__init__.py +39 -38
  36. crawlo/extension/health_check.py +141 -141
  37. crawlo/extension/log_interval.py +57 -57
  38. crawlo/extension/log_stats.py +81 -81
  39. crawlo/extension/logging_extension.py +43 -43
  40. crawlo/extension/memory_monitor.py +104 -104
  41. crawlo/extension/performance_profiler.py +133 -133
  42. crawlo/extension/request_recorder.py +107 -107
  43. crawlo/filters/__init__.py +154 -154
  44. crawlo/filters/aioredis_filter.py +234 -234
  45. crawlo/filters/memory_filter.py +269 -269
  46. crawlo/items/__init__.py +23 -23
  47. crawlo/items/base.py +21 -21
  48. crawlo/items/fields.py +52 -52
  49. crawlo/items/items.py +104 -104
  50. crawlo/middleware/__init__.py +21 -21
  51. crawlo/middleware/default_header.py +131 -131
  52. crawlo/middleware/download_delay.py +104 -104
  53. crawlo/middleware/middleware_manager.py +136 -135
  54. crawlo/middleware/offsite.py +114 -114
  55. crawlo/middleware/proxy.py +367 -367
  56. crawlo/middleware/request_ignore.py +86 -86
  57. crawlo/middleware/response_code.py +163 -163
  58. crawlo/middleware/response_filter.py +136 -136
  59. crawlo/middleware/retry.py +124 -124
  60. crawlo/mode_manager.py +211 -211
  61. crawlo/network/__init__.py +21 -21
  62. crawlo/network/request.py +338 -338
  63. crawlo/network/response.py +359 -359
  64. crawlo/pipelines/__init__.py +21 -21
  65. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  66. crawlo/pipelines/console_pipeline.py +39 -39
  67. crawlo/pipelines/csv_pipeline.py +316 -316
  68. crawlo/pipelines/database_dedup_pipeline.py +222 -222
  69. crawlo/pipelines/json_pipeline.py +218 -218
  70. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  71. crawlo/pipelines/mongo_pipeline.py +131 -131
  72. crawlo/pipelines/mysql_pipeline.py +317 -317
  73. crawlo/pipelines/pipeline_manager.py +62 -61
  74. crawlo/pipelines/redis_dedup_pipeline.py +166 -165
  75. crawlo/project.py +314 -279
  76. crawlo/queue/pqueue.py +37 -37
  77. crawlo/queue/queue_manager.py +377 -376
  78. crawlo/queue/redis_priority_queue.py +306 -306
  79. crawlo/settings/__init__.py +7 -7
  80. crawlo/settings/default_settings.py +219 -215
  81. crawlo/settings/setting_manager.py +122 -122
  82. crawlo/spider/__init__.py +639 -639
  83. crawlo/stats_collector.py +59 -59
  84. crawlo/subscriber.py +129 -129
  85. crawlo/task_manager.py +30 -30
  86. crawlo/templates/crawlo.cfg.tmpl +10 -10
  87. crawlo/templates/project/__init__.py.tmpl +3 -3
  88. crawlo/templates/project/items.py.tmpl +17 -17
  89. crawlo/templates/project/middlewares.py.tmpl +118 -118
  90. crawlo/templates/project/pipelines.py.tmpl +96 -96
  91. crawlo/templates/project/settings.py.tmpl +288 -288
  92. crawlo/templates/project/settings_distributed.py.tmpl +157 -157
  93. crawlo/templates/project/settings_gentle.py.tmpl +100 -100
  94. crawlo/templates/project/settings_high_performance.py.tmpl +134 -134
  95. crawlo/templates/project/settings_simple.py.tmpl +98 -98
  96. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  97. crawlo/templates/run.py.tmpl +47 -45
  98. crawlo/templates/spider/spider.py.tmpl +143 -143
  99. crawlo/tools/__init__.py +182 -182
  100. crawlo/tools/anti_crawler.py +268 -268
  101. crawlo/tools/authenticated_proxy.py +240 -240
  102. crawlo/tools/data_validator.py +180 -180
  103. crawlo/tools/date_tools.py +35 -35
  104. crawlo/tools/distributed_coordinator.py +386 -386
  105. crawlo/tools/retry_mechanism.py +220 -220
  106. crawlo/tools/scenario_adapter.py +262 -262
  107. crawlo/utils/__init__.py +35 -35
  108. crawlo/utils/batch_processor.py +259 -259
  109. crawlo/utils/controlled_spider_mixin.py +439 -439
  110. crawlo/utils/date_tools.py +290 -290
  111. crawlo/utils/db_helper.py +343 -343
  112. crawlo/utils/enhanced_error_handler.py +356 -356
  113. crawlo/utils/env_config.py +143 -106
  114. crawlo/utils/error_handler.py +123 -123
  115. crawlo/utils/func_tools.py +82 -82
  116. crawlo/utils/large_scale_config.py +286 -286
  117. crawlo/utils/large_scale_helper.py +344 -344
  118. crawlo/utils/log.py +128 -128
  119. crawlo/utils/performance_monitor.py +285 -285
  120. crawlo/utils/queue_helper.py +175 -175
  121. crawlo/utils/redis_connection_pool.py +351 -351
  122. crawlo/utils/redis_key_validator.py +198 -198
  123. crawlo/utils/request.py +267 -267
  124. crawlo/utils/request_serializer.py +218 -218
  125. crawlo/utils/spider_loader.py +61 -61
  126. crawlo/utils/system.py +11 -11
  127. crawlo/utils/tools.py +4 -4
  128. crawlo/utils/url.py +39 -39
  129. {crawlo-1.2.6.dist-info → crawlo-1.2.8.dist-info}/METADATA +764 -764
  130. crawlo-1.2.8.dist-info/RECORD +209 -0
  131. examples/__init__.py +7 -7
  132. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  133. tests/__init__.py +7 -7
  134. tests/advanced_tools_example.py +275 -275
  135. tests/authenticated_proxy_example.py +236 -236
  136. tests/cleaners_example.py +160 -160
  137. tests/config_validation_demo.py +102 -102
  138. tests/controlled_spider_example.py +205 -205
  139. tests/date_tools_example.py +180 -180
  140. tests/dynamic_loading_example.py +523 -523
  141. tests/dynamic_loading_test.py +104 -104
  142. tests/env_config_example.py +133 -133
  143. tests/error_handling_example.py +171 -171
  144. tests/redis_key_validation_demo.py +130 -130
  145. tests/response_improvements_example.py +144 -144
  146. tests/test_advanced_tools.py +148 -148
  147. tests/test_all_redis_key_configs.py +145 -145
  148. tests/test_authenticated_proxy.py +141 -141
  149. tests/test_cleaners.py +54 -54
  150. tests/test_comprehensive.py +146 -146
  151. tests/test_config_consistency.py +81 -0
  152. tests/test_config_validator.py +193 -193
  153. tests/test_crawlo_proxy_integration.py +172 -172
  154. tests/test_date_tools.py +123 -123
  155. tests/test_default_header_middleware.py +158 -158
  156. tests/test_double_crawlo_fix.py +207 -207
  157. tests/test_double_crawlo_fix_simple.py +124 -124
  158. tests/test_download_delay_middleware.py +221 -221
  159. tests/test_downloader_proxy_compatibility.py +268 -268
  160. tests/test_dynamic_downloaders_proxy.py +124 -124
  161. tests/test_dynamic_proxy.py +92 -92
  162. tests/test_dynamic_proxy_config.py +146 -146
  163. tests/test_dynamic_proxy_real.py +109 -109
  164. tests/test_edge_cases.py +303 -303
  165. tests/test_enhanced_error_handler.py +270 -270
  166. tests/test_env_config.py +121 -121
  167. tests/test_error_handler_compatibility.py +112 -112
  168. tests/test_final_validation.py +153 -153
  169. tests/test_framework_env_usage.py +103 -103
  170. tests/test_integration.py +356 -356
  171. tests/test_item_dedup_redis_key.py +122 -122
  172. tests/test_mode_consistency.py +52 -0
  173. tests/test_offsite_middleware.py +221 -221
  174. tests/test_parsel.py +29 -29
  175. tests/test_performance.py +327 -327
  176. tests/test_proxy_api.py +264 -264
  177. tests/test_proxy_health_check.py +32 -32
  178. tests/test_proxy_middleware.py +121 -121
  179. tests/test_proxy_middleware_enhanced.py +216 -216
  180. tests/test_proxy_middleware_integration.py +136 -136
  181. tests/test_proxy_providers.py +56 -56
  182. tests/test_proxy_stats.py +19 -19
  183. tests/test_proxy_strategies.py +59 -59
  184. tests/test_queue_manager_double_crawlo.py +173 -173
  185. tests/test_queue_manager_redis_key.py +176 -176
  186. tests/test_real_scenario_proxy.py +195 -195
  187. tests/test_redis_config.py +28 -28
  188. tests/test_redis_connection_pool.py +294 -294
  189. tests/test_redis_key_naming.py +181 -181
  190. tests/test_redis_key_validator.py +123 -123
  191. tests/test_redis_queue.py +224 -224
  192. tests/test_request_ignore_middleware.py +182 -182
  193. tests/test_request_serialization.py +70 -70
  194. tests/test_response_code_middleware.py +349 -349
  195. tests/test_response_filter_middleware.py +427 -427
  196. tests/test_response_improvements.py +152 -152
  197. tests/test_retry_middleware.py +241 -241
  198. tests/test_scheduler.py +252 -241
  199. tests/test_scheduler_config_update.py +134 -0
  200. tests/test_simple_response.py +61 -61
  201. tests/test_telecom_spider_redis_key.py +205 -205
  202. tests/test_template_content.py +87 -87
  203. tests/test_template_redis_key.py +134 -134
  204. tests/test_tools.py +153 -153
  205. tests/tools_example.py +257 -257
  206. crawlo-1.2.6.dist-info/RECORD +0 -206
  207. {crawlo-1.2.6.dist-info → crawlo-1.2.8.dist-info}/WHEEL +0 -0
  208. {crawlo-1.2.6.dist-info → crawlo-1.2.8.dist-info}/entry_points.txt +0 -0
  209. {crawlo-1.2.6.dist-info → crawlo-1.2.8.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
+