crawlo 1.3.2__py3-none-any.whl → 1.3.3__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 (219) hide show
  1. crawlo/__init__.py +63 -63
  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 +322 -314
  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 +2 -2
  16. crawlo/core/engine.py +365 -365
  17. crawlo/core/processor.py +40 -40
  18. crawlo/core/scheduler.py +256 -256
  19. crawlo/crawler.py +1166 -1168
  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 +226 -226
  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 +52 -45
  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/filters/__init__.py +154 -154
  40. crawlo/filters/aioredis_filter.py +234 -234
  41. crawlo/filters/memory_filter.py +269 -269
  42. crawlo/items/__init__.py +23 -23
  43. crawlo/items/base.py +21 -21
  44. crawlo/items/fields.py +52 -52
  45. crawlo/items/items.py +104 -104
  46. crawlo/middleware/__init__.py +21 -21
  47. crawlo/middleware/default_header.py +132 -132
  48. crawlo/middleware/download_delay.py +104 -104
  49. crawlo/middleware/middleware_manager.py +135 -135
  50. crawlo/middleware/offsite.py +123 -123
  51. crawlo/middleware/proxy.py +386 -386
  52. crawlo/middleware/request_ignore.py +86 -86
  53. crawlo/middleware/response_code.py +163 -163
  54. crawlo/middleware/response_filter.py +136 -136
  55. crawlo/middleware/retry.py +124 -124
  56. crawlo/middleware/simple_proxy.py +65 -65
  57. crawlo/mode_manager.py +187 -187
  58. crawlo/network/__init__.py +21 -21
  59. crawlo/network/request.py +379 -379
  60. crawlo/network/response.py +359 -359
  61. crawlo/pipelines/__init__.py +21 -21
  62. crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
  63. crawlo/pipelines/console_pipeline.py +39 -39
  64. crawlo/pipelines/csv_pipeline.py +316 -316
  65. crawlo/pipelines/database_dedup_pipeline.py +222 -222
  66. crawlo/pipelines/json_pipeline.py +218 -218
  67. crawlo/pipelines/memory_dedup_pipeline.py +115 -115
  68. crawlo/pipelines/mongo_pipeline.py +131 -131
  69. crawlo/pipelines/mysql_pipeline.py +318 -318
  70. crawlo/pipelines/pipeline_manager.py +75 -75
  71. crawlo/pipelines/redis_dedup_pipeline.py +166 -166
  72. crawlo/project.py +325 -297
  73. crawlo/queue/pqueue.py +37 -37
  74. crawlo/queue/queue_manager.py +379 -379
  75. crawlo/queue/redis_priority_queue.py +306 -306
  76. crawlo/settings/__init__.py +7 -7
  77. crawlo/settings/default_settings.py +225 -225
  78. crawlo/settings/setting_manager.py +198 -198
  79. crawlo/spider/__init__.py +639 -639
  80. crawlo/stats_collector.py +59 -59
  81. crawlo/subscriber.py +129 -129
  82. crawlo/task_manager.py +30 -30
  83. crawlo/templates/crawlo.cfg.tmpl +10 -10
  84. crawlo/templates/project/__init__.py.tmpl +3 -3
  85. crawlo/templates/project/items.py.tmpl +17 -17
  86. crawlo/templates/project/middlewares.py.tmpl +118 -118
  87. crawlo/templates/project/pipelines.py.tmpl +96 -96
  88. crawlo/templates/project/settings.py.tmpl +266 -266
  89. crawlo/templates/project/settings_distributed.py.tmpl +179 -179
  90. crawlo/templates/project/settings_gentle.py.tmpl +60 -60
  91. crawlo/templates/project/settings_high_performance.py.tmpl +130 -130
  92. crawlo/templates/project/settings_minimal.py.tmpl +34 -34
  93. crawlo/templates/project/settings_simple.py.tmpl +101 -101
  94. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  95. crawlo/templates/run.py.tmpl +38 -38
  96. crawlo/templates/spider/spider.py.tmpl +143 -143
  97. crawlo/tools/__init__.py +200 -200
  98. crawlo/tools/anti_crawler.py +268 -268
  99. crawlo/tools/authenticated_proxy.py +240 -240
  100. crawlo/tools/data_formatter.py +225 -225
  101. crawlo/tools/data_validator.py +180 -180
  102. crawlo/tools/date_tools.py +289 -289
  103. crawlo/tools/distributed_coordinator.py +388 -388
  104. crawlo/tools/encoding_converter.py +127 -127
  105. crawlo/tools/request_tools.py +82 -82
  106. crawlo/tools/retry_mechanism.py +224 -224
  107. crawlo/tools/scenario_adapter.py +262 -262
  108. crawlo/tools/text_cleaner.py +232 -232
  109. crawlo/utils/__init__.py +34 -34
  110. crawlo/utils/batch_processor.py +259 -259
  111. crawlo/utils/controlled_spider_mixin.py +439 -439
  112. crawlo/utils/db_helper.py +343 -343
  113. crawlo/utils/enhanced_error_handler.py +356 -356
  114. crawlo/utils/env_config.py +142 -142
  115. crawlo/utils/error_handler.py +123 -123
  116. crawlo/utils/func_tools.py +82 -82
  117. crawlo/utils/large_scale_config.py +286 -286
  118. crawlo/utils/large_scale_helper.py +344 -344
  119. crawlo/utils/log.py +199 -146
  120. crawlo/utils/performance_monitor.py +285 -285
  121. crawlo/utils/queue_helper.py +175 -175
  122. crawlo/utils/redis_connection_pool.py +351 -351
  123. crawlo/utils/redis_key_validator.py +198 -198
  124. crawlo/utils/request.py +267 -267
  125. crawlo/utils/request_serializer.py +218 -218
  126. crawlo/utils/spider_loader.py +61 -61
  127. crawlo/utils/system.py +11 -11
  128. crawlo/utils/tools.py +4 -4
  129. crawlo/utils/url.py +39 -39
  130. {crawlo-1.3.2.dist-info → crawlo-1.3.3.dist-info}/METADATA +1020 -1020
  131. crawlo-1.3.3.dist-info/RECORD +219 -0
  132. examples/__init__.py +7 -7
  133. tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
  134. tests/__init__.py +7 -7
  135. tests/advanced_tools_example.py +275 -275
  136. tests/authenticated_proxy_example.py +107 -107
  137. tests/cleaners_example.py +160 -160
  138. tests/config_validation_demo.py +142 -142
  139. tests/controlled_spider_example.py +205 -205
  140. tests/date_tools_example.py +180 -180
  141. tests/debug_pipelines.py +66 -66
  142. tests/dynamic_loading_example.py +523 -523
  143. tests/dynamic_loading_test.py +104 -104
  144. tests/env_config_example.py +133 -133
  145. tests/error_handling_example.py +171 -171
  146. tests/redis_key_validation_demo.py +130 -130
  147. tests/request_params_example.py +150 -150
  148. tests/response_improvements_example.py +144 -144
  149. tests/test_advanced_tools.py +148 -148
  150. tests/test_all_redis_key_configs.py +145 -145
  151. tests/test_authenticated_proxy.py +141 -141
  152. tests/test_cleaners.py +54 -54
  153. tests/test_comprehensive.py +146 -146
  154. tests/test_config_consistency.py +80 -80
  155. tests/test_config_merge.py +152 -152
  156. tests/test_config_validator.py +182 -182
  157. tests/test_crawlo_proxy_integration.py +108 -108
  158. tests/test_date_tools.py +123 -123
  159. tests/test_default_header_middleware.py +158 -158
  160. tests/test_distributed.py +65 -65
  161. tests/test_double_crawlo_fix.py +207 -207
  162. tests/test_double_crawlo_fix_simple.py +124 -124
  163. tests/test_download_delay_middleware.py +221 -221
  164. tests/test_downloader_proxy_compatibility.py +268 -268
  165. tests/test_dynamic_downloaders_proxy.py +124 -124
  166. tests/test_dynamic_proxy.py +92 -92
  167. tests/test_dynamic_proxy_config.py +146 -146
  168. tests/test_dynamic_proxy_real.py +109 -109
  169. tests/test_edge_cases.py +303 -303
  170. tests/test_enhanced_error_handler.py +270 -270
  171. tests/test_env_config.py +121 -121
  172. tests/test_error_handler_compatibility.py +112 -112
  173. tests/test_final_validation.py +153 -153
  174. tests/test_framework_env_usage.py +103 -103
  175. tests/test_integration.py +169 -169
  176. tests/test_item_dedup_redis_key.py +122 -122
  177. tests/test_mode_consistency.py +51 -51
  178. tests/test_offsite_middleware.py +221 -221
  179. tests/test_parsel.py +29 -29
  180. tests/test_performance.py +327 -327
  181. tests/test_proxy_api.py +264 -264
  182. tests/test_proxy_health_check.py +32 -32
  183. tests/test_proxy_middleware.py +121 -121
  184. tests/test_proxy_middleware_enhanced.py +216 -216
  185. tests/test_proxy_middleware_integration.py +136 -136
  186. tests/test_proxy_middleware_refactored.py +184 -184
  187. tests/test_proxy_providers.py +56 -56
  188. tests/test_proxy_stats.py +19 -19
  189. tests/test_proxy_strategies.py +59 -59
  190. tests/test_queue_manager_double_crawlo.py +173 -173
  191. tests/test_queue_manager_redis_key.py +176 -176
  192. tests/test_random_user_agent.py +72 -72
  193. tests/test_real_scenario_proxy.py +195 -195
  194. tests/test_redis_config.py +28 -28
  195. tests/test_redis_connection_pool.py +294 -294
  196. tests/test_redis_key_naming.py +181 -181
  197. tests/test_redis_key_validator.py +123 -123
  198. tests/test_redis_queue.py +224 -224
  199. tests/test_request_ignore_middleware.py +182 -182
  200. tests/test_request_params.py +111 -111
  201. tests/test_request_serialization.py +70 -70
  202. tests/test_response_code_middleware.py +349 -349
  203. tests/test_response_filter_middleware.py +427 -427
  204. tests/test_response_improvements.py +152 -152
  205. tests/test_retry_middleware.py +241 -241
  206. tests/test_scheduler.py +252 -252
  207. tests/test_scheduler_config_update.py +133 -133
  208. tests/test_simple_response.py +61 -61
  209. tests/test_telecom_spider_redis_key.py +205 -205
  210. tests/test_template_content.py +87 -87
  211. tests/test_template_redis_key.py +134 -134
  212. tests/test_tools.py +159 -159
  213. tests/test_user_agents.py +96 -96
  214. tests/tools_example.py +260 -260
  215. tests/verify_distributed.py +117 -117
  216. crawlo-1.3.2.dist-info/RECORD +0 -219
  217. {crawlo-1.3.2.dist-info → crawlo-1.3.3.dist-info}/WHEEL +0 -0
  218. {crawlo-1.3.2.dist-info → crawlo-1.3.3.dist-info}/entry_points.txt +0 -0
  219. {crawlo-1.3.2.dist-info → crawlo-1.3.3.dist-info}/top_level.txt +0 -0
crawlo/utils/db_helper.py CHANGED
@@ -1,344 +1,344 @@
1
- # -*- coding: utf-8 -*-
2
- import json
3
- import re
4
- import pprint
5
- from typing import Any, Union, List, Dict, Tuple, Optional
6
- from datetime import date, time, datetime
7
-
8
- from crawlo.utils.log import get_logger
9
-
10
- logger = get_logger(__name__)
11
-
12
- # 正则表达式缓存
13
- _REGEXPS: Dict[str, "re.Pattern"] = {}
14
-
15
-
16
- def make_insert_sql(
17
- table: str,
18
- data: Dict[str, Any],
19
- auto_update: bool = False,
20
- update_columns: Tuple = (),
21
- insert_ignore: bool = False,
22
- ) -> str:
23
- """
24
- 生成 MySQL INSERT 或 REPLACE 语句。
25
-
26
- Args:
27
- table (str): 表名
28
- data (dict): 表数据,JSON 格式字典
29
- auto_update (bool): 是否使用 REPLACE INTO(完全覆盖已存在记录)
30
- update_columns (tuple or list): 冲突时需更新的列名;指定后 auto_update 失效
31
- insert_ignore (bool): 是否使用 INSERT IGNORE,忽略重复数据
32
-
33
- Returns:
34
- str: 生成的 SQL 语句
35
- """
36
- keys = [f"`{key}`" for key in data.keys()]
37
- keys_str = list2str(keys).replace("'", "")
38
-
39
- values = [format_sql_value(value) for value in data.values()]
40
- values_str = list2str(values)
41
-
42
- if update_columns:
43
- if not isinstance(update_columns, (tuple, list)):
44
- update_columns = (update_columns,)
45
- update_clause = ", ".join(f"`{key}`=VALUES(`{key}`)" for key in update_columns)
46
- ignore_flag = " IGNORE" if insert_ignore else ""
47
- sql = f"INSERT{ignore_flag} INTO `{table}` {keys_str} VALUES {values_str} ON DUPLICATE KEY UPDATE {update_clause}"
48
-
49
- elif auto_update:
50
- sql = f"REPLACE INTO `{table}` {keys_str} VALUES {values_str}"
51
-
52
- else:
53
- ignore_flag = " IGNORE" if insert_ignore else ""
54
- sql = f"INSERT{ignore_flag} INTO `{table}` {keys_str} VALUES {values_str}"
55
-
56
- return sql.replace("None", "null")
57
-
58
-
59
- def make_update_sql(
60
- table: str,
61
- data: Dict[str, Any],
62
- condition: str,
63
- ) -> str:
64
- """
65
- 生成 MySQL UPDATE 语句。
66
-
67
- Args:
68
- table (str): 表名
69
- data (dict): 更新字段的键值对,键为列名,值为新值
70
- condition (str): WHERE 条件,如 "id = 1"
71
-
72
- Returns:
73
- str: 生成的 SQL 语句
74
- """
75
- key_values: List[str] = []
76
- for key, value in data.items():
77
- formatted_value = format_sql_value(value)
78
- if isinstance(formatted_value, str):
79
- key_values.append(f"`{key}`={repr(formatted_value)}")
80
- elif formatted_value is None:
81
- key_values.append(f"`{key}`=null")
82
- else:
83
- key_values.append(f"`{key}`={formatted_value}")
84
-
85
- key_values_str = ", ".join(key_values)
86
- sql = f"UPDATE `{table}` SET {key_values_str} WHERE {condition}"
87
- return sql
88
-
89
-
90
- def make_batch_sql(
91
- table: str,
92
- datas: List[Dict[str, Any]],
93
- auto_update: bool = False,
94
- update_columns: Tuple = (),
95
- update_columns_value: Tuple = (),
96
- ) -> Optional[Tuple[str, List[List[Any]]]]:
97
- """
98
- 生成批量插入 SQL 及对应值列表。
99
-
100
- 支持 INSERT IGNORE、REPLACE INTO 和 ON DUPLICATE KEY UPDATE。
101
-
102
- Args:
103
- table (str): 表名
104
- datas (list of dict): 数据列表,如 [{'col1': val1}, ...]
105
- auto_update (bool): 使用 REPLACE INTO 替代 INSERT
106
- update_columns (tuple or list): 主键冲突时要更新的列名
107
- update_columns_value (tuple): 更新列对应的固定值,如 ('%s',) 或 ('default',)
108
-
109
- Returns:
110
- tuple[str, list[list]] | None: (SQL语句, 值列表);若数据为空则返回 None
111
- """
112
- if not datas:
113
- return None
114
-
115
- # 提取所有唯一字段名
116
- keys = list({key for data in datas for key in data})
117
- values_list = []
118
-
119
- for data in datas:
120
- if not isinstance(data, dict):
121
- continue # 跳过非字典数据
122
-
123
- row = []
124
- for key in keys:
125
- raw_value = data.get(key)
126
- try:
127
- formatted_value = format_sql_value(raw_value)
128
- row.append(formatted_value)
129
- except Exception as e:
130
- logger.error(f"{key}: {raw_value} (类型: {type(raw_value)}) -> {e}")
131
- values_list.append(row)
132
-
133
- keys_str = ", ".join(f"`{key}`" for key in keys)
134
- placeholders_str = ", ".join(["%s"] * len(keys))
135
-
136
- if update_columns:
137
- if not isinstance(update_columns, (tuple, list)):
138
- update_columns = (update_columns,)
139
-
140
- if update_columns_value:
141
- update_pairs = [
142
- f"`{key}`={value}"
143
- for key, value in zip(update_columns, update_columns_value)
144
- ]
145
- else:
146
- update_pairs = [
147
- f"`{key}`=VALUES(`{key}`)" for key in update_columns
148
- ]
149
- update_clause = ", ".join(update_pairs)
150
- sql = f"INSERT INTO `{table}` ({keys_str}) VALUES ({placeholders_str}) ON DUPLICATE KEY UPDATE {update_clause}"
151
-
152
- elif auto_update:
153
- sql = f"REPLACE INTO `{table}` ({keys_str}) VALUES ({placeholders_str})"
154
-
155
- else:
156
- sql = f"INSERT IGNORE INTO `{table}` ({keys_str}) VALUES ({placeholders_str})"
157
-
158
- return sql, values_list
159
-
160
-
161
- def format_sql_value(value: Any) -> Union[str, int, float, None]:
162
- """
163
- 格式化 SQL 字段值,防止注入并兼容类型。
164
-
165
- 处理字符串、数字、布尔、日期、列表/元组、字典等类型,不可序列化类型抛出异常。
166
-
167
- Args:
168
- value (Any): 待处理的值
169
-
170
- Returns:
171
- str | int | float | None: 格式化后的值,None 表示 SQL 的 NULL
172
- """
173
- if value is None:
174
- return None
175
-
176
- if isinstance(value, str):
177
- return value.strip()
178
-
179
- elif isinstance(value, (list, tuple, dict)):
180
- try:
181
- return json.dumps(value, ensure_ascii=False, default=str)
182
- except Exception as e:
183
- raise ValueError(f"Failed to serialize container to JSON: {value}, error: {e}")
184
-
185
- elif isinstance(value, bool):
186
- return int(value)
187
-
188
- elif isinstance(value, (int, float)):
189
- return value
190
-
191
- elif isinstance(value, (date, time, datetime)):
192
- return str(value)
193
-
194
- else:
195
- raise TypeError(f"Unsupported value type: {type(value)}, value: {value}")
196
-
197
-
198
- def list2str(datas: List[Any]) -> str:
199
- """
200
- 将列表转为 SQL 元组字符串格式。
201
-
202
- 例如:[1, 2] → "(1, 2)",单元素不带逗号:[1] → "(1)"
203
-
204
- Args:
205
- datas (list): 输入列表
206
-
207
- Returns:
208
- str: 对应的元组字符串表示
209
- """
210
- data_str = str(tuple(datas))
211
- return re.sub(r",\)$", ")", data_str)
212
-
213
-
214
- def get_info(
215
- html: Union[str, Any],
216
- regexps: Union[str, List[str]],
217
- allow_repeat: bool = True,
218
- fetch_one: bool = False,
219
- split: Optional[str] = None,
220
- ) -> Union[str, List[str], Tuple]:
221
- """
222
- 从 HTML 文本中提取信息,支持正则匹配和多模式 fallback。
223
-
224
- Args:
225
- html (str): HTML 内容或可转为字符串的类型
226
- regexps (str or list of str): 正则表达式,按顺序尝试匹配
227
- allow_repeat (bool): 是否允许重复结果
228
- fetch_one (bool): 是否只提取第一个匹配项(返回元组)
229
- split (str, optional): 若提供,则将结果用该字符连接成字符串
230
-
231
- Returns:
232
- str | list | tuple: 匹配结果,根据参数返回字符串、列表或元组
233
- """
234
- if isinstance(regexps, str):
235
- regexps = [regexps]
236
-
237
- infos = []
238
- for regex in regexps:
239
- if not regex:
240
- continue
241
-
242
- if regex not in _REGEXPS:
243
- _REGEXPS[regex] = re.compile(regex, re.S)
244
-
245
- if fetch_one:
246
- match = _REGEXPS[regex].search(str(html))
247
- infos = match.groups() if match else ("",)
248
- break
249
- else:
250
- found = _REGEXPS[regex].findall(str(html))
251
- if found:
252
- infos = found
253
- break
254
-
255
- if fetch_one:
256
- return infos[0] if len(infos) == 1 else infos
257
-
258
- if not allow_repeat:
259
- infos = sorted(set(infos), key=infos.index)
260
-
261
- return split.join(infos) if split else infos
262
-
263
-
264
- def get_json(json_str: Union[str, Any]) -> Dict:
265
- """
266
- 安全解析 JSON 字符串,兼容非标准格式(如单引号、缺少引号键)。
267
-
268
- 尝试修复常见格式错误后再解析。
269
-
270
- Args:
271
- json_str (str): JSON 字符串
272
-
273
- Returns:
274
- dict: 解析后的字典,失败返回空字典
275
- """
276
- if not json_str:
277
- return {}
278
-
279
- try:
280
- return json.loads(json_str)
281
- except Exception as e1:
282
- try:
283
- cleaned = json_str.strip().replace("'", '"')
284
- keys = get_info(cleaned, r'(\w+):')
285
- for key in keys:
286
- cleaned = cleaned.replace(f"{key}:", f'"{key}":')
287
- return json.loads(cleaned) if cleaned else {}
288
- except Exception as e2:
289
- logger.error(
290
- f"JSON 解析失败\n"
291
- f"原始内容: {json_str}\n"
292
- f"错误1: {e1}\n"
293
- f"修复后: {cleaned}\n"
294
- f"错误2: {e2}"
295
- )
296
- return {}
297
-
298
-
299
- def dumps_json(
300
- data: Union[str, dict, list, Any],
301
- indent: int = 4,
302
- sort_keys: bool = False,
303
- ensure_ascii: bool = False,
304
- skip_keys: bool = True,
305
- default_repr: bool = False,
306
- ) -> str:
307
- """
308
- 格式化任意对象为可读字符串,优先使用 JSON,失败时降级为 pprint 或 repr。
309
-
310
- 支持自动处理 datetime、ObjectId 等不可序列化类型。
311
-
312
- Args:
313
- data (Any): 输入数据,支持字符串、字典、列表等
314
- indent (int): JSON 缩进空格数
315
- sort_keys (bool): 是否对字典键排序
316
- ensure_ascii (bool): 是否转义非 ASCII 字符(False 可保留中文)
317
- skip_keys (bool): 遇到非法键时是否跳过(而非报错)
318
- default_repr (bool): 是否在最终失败时使用 repr() 降级
319
-
320
- Returns:
321
- str: 格式化后的字符串,适合日志输出或打印
322
- """
323
- try:
324
- if isinstance(data, str):
325
- if not data.strip():
326
- return '""'
327
- data = get_json(data)
328
-
329
- return json.dumps(
330
- data,
331
- ensure_ascii=ensure_ascii,
332
- indent=indent,
333
- skipkeys=skip_keys,
334
- sort_keys=sort_keys,
335
- default=str,
336
- )
337
-
338
- except (UnicodeDecodeError, ValueError, TypeError, OverflowError) as e:
339
- try:
340
- return pprint.pformat(data, indent=indent, width=80, compact=True)
341
- except Exception:
342
- if default_repr:
343
- return repr(data)
1
+ # -*- coding: utf-8 -*-
2
+ import json
3
+ import re
4
+ import pprint
5
+ from typing import Any, Union, List, Dict, Tuple, Optional
6
+ from datetime import date, time, datetime
7
+
8
+ from crawlo.utils.log import get_logger
9
+
10
+ logger = get_logger(__name__)
11
+
12
+ # 正则表达式缓存
13
+ _REGEXPS: Dict[str, "re.Pattern"] = {}
14
+
15
+
16
+ def make_insert_sql(
17
+ table: str,
18
+ data: Dict[str, Any],
19
+ auto_update: bool = False,
20
+ update_columns: Tuple = (),
21
+ insert_ignore: bool = False,
22
+ ) -> str:
23
+ """
24
+ 生成 MySQL INSERT 或 REPLACE 语句。
25
+
26
+ Args:
27
+ table (str): 表名
28
+ data (dict): 表数据,JSON 格式字典
29
+ auto_update (bool): 是否使用 REPLACE INTO(完全覆盖已存在记录)
30
+ update_columns (tuple or list): 冲突时需更新的列名;指定后 auto_update 失效
31
+ insert_ignore (bool): 是否使用 INSERT IGNORE,忽略重复数据
32
+
33
+ Returns:
34
+ str: 生成的 SQL 语句
35
+ """
36
+ keys = [f"`{key}`" for key in data.keys()]
37
+ keys_str = list2str(keys).replace("'", "")
38
+
39
+ values = [format_sql_value(value) for value in data.values()]
40
+ values_str = list2str(values)
41
+
42
+ if update_columns:
43
+ if not isinstance(update_columns, (tuple, list)):
44
+ update_columns = (update_columns,)
45
+ update_clause = ", ".join(f"`{key}`=VALUES(`{key}`)" for key in update_columns)
46
+ ignore_flag = " IGNORE" if insert_ignore else ""
47
+ sql = f"INSERT{ignore_flag} INTO `{table}` {keys_str} VALUES {values_str} ON DUPLICATE KEY UPDATE {update_clause}"
48
+
49
+ elif auto_update:
50
+ sql = f"REPLACE INTO `{table}` {keys_str} VALUES {values_str}"
51
+
52
+ else:
53
+ ignore_flag = " IGNORE" if insert_ignore else ""
54
+ sql = f"INSERT{ignore_flag} INTO `{table}` {keys_str} VALUES {values_str}"
55
+
56
+ return sql.replace("None", "null")
57
+
58
+
59
+ def make_update_sql(
60
+ table: str,
61
+ data: Dict[str, Any],
62
+ condition: str,
63
+ ) -> str:
64
+ """
65
+ 生成 MySQL UPDATE 语句。
66
+
67
+ Args:
68
+ table (str): 表名
69
+ data (dict): 更新字段的键值对,键为列名,值为新值
70
+ condition (str): WHERE 条件,如 "id = 1"
71
+
72
+ Returns:
73
+ str: 生成的 SQL 语句
74
+ """
75
+ key_values: List[str] = []
76
+ for key, value in data.items():
77
+ formatted_value = format_sql_value(value)
78
+ if isinstance(formatted_value, str):
79
+ key_values.append(f"`{key}`={repr(formatted_value)}")
80
+ elif formatted_value is None:
81
+ key_values.append(f"`{key}`=null")
82
+ else:
83
+ key_values.append(f"`{key}`={formatted_value}")
84
+
85
+ key_values_str = ", ".join(key_values)
86
+ sql = f"UPDATE `{table}` SET {key_values_str} WHERE {condition}"
87
+ return sql
88
+
89
+
90
+ def make_batch_sql(
91
+ table: str,
92
+ datas: List[Dict[str, Any]],
93
+ auto_update: bool = False,
94
+ update_columns: Tuple = (),
95
+ update_columns_value: Tuple = (),
96
+ ) -> Optional[Tuple[str, List[List[Any]]]]:
97
+ """
98
+ 生成批量插入 SQL 及对应值列表。
99
+
100
+ 支持 INSERT IGNORE、REPLACE INTO 和 ON DUPLICATE KEY UPDATE。
101
+
102
+ Args:
103
+ table (str): 表名
104
+ datas (list of dict): 数据列表,如 [{'col1': val1}, ...]
105
+ auto_update (bool): 使用 REPLACE INTO 替代 INSERT
106
+ update_columns (tuple or list): 主键冲突时要更新的列名
107
+ update_columns_value (tuple): 更新列对应的固定值,如 ('%s',) 或 ('default',)
108
+
109
+ Returns:
110
+ tuple[str, list[list]] | None: (SQL语句, 值列表);若数据为空则返回 None
111
+ """
112
+ if not datas:
113
+ return None
114
+
115
+ # 提取所有唯一字段名
116
+ keys = list({key for data in datas for key in data})
117
+ values_list = []
118
+
119
+ for data in datas:
120
+ if not isinstance(data, dict):
121
+ continue # 跳过非字典数据
122
+
123
+ row = []
124
+ for key in keys:
125
+ raw_value = data.get(key)
126
+ try:
127
+ formatted_value = format_sql_value(raw_value)
128
+ row.append(formatted_value)
129
+ except Exception as e:
130
+ logger.error(f"{key}: {raw_value} (类型: {type(raw_value)}) -> {e}")
131
+ values_list.append(row)
132
+
133
+ keys_str = ", ".join(f"`{key}`" for key in keys)
134
+ placeholders_str = ", ".join(["%s"] * len(keys))
135
+
136
+ if update_columns:
137
+ if not isinstance(update_columns, (tuple, list)):
138
+ update_columns = (update_columns,)
139
+
140
+ if update_columns_value:
141
+ update_pairs = [
142
+ f"`{key}`={value}"
143
+ for key, value in zip(update_columns, update_columns_value)
144
+ ]
145
+ else:
146
+ update_pairs = [
147
+ f"`{key}`=VALUES(`{key}`)" for key in update_columns
148
+ ]
149
+ update_clause = ", ".join(update_pairs)
150
+ sql = f"INSERT INTO `{table}` ({keys_str}) VALUES ({placeholders_str}) ON DUPLICATE KEY UPDATE {update_clause}"
151
+
152
+ elif auto_update:
153
+ sql = f"REPLACE INTO `{table}` ({keys_str}) VALUES ({placeholders_str})"
154
+
155
+ else:
156
+ sql = f"INSERT IGNORE INTO `{table}` ({keys_str}) VALUES ({placeholders_str})"
157
+
158
+ return sql, values_list
159
+
160
+
161
+ def format_sql_value(value: Any) -> Union[str, int, float, None]:
162
+ """
163
+ 格式化 SQL 字段值,防止注入并兼容类型。
164
+
165
+ 处理字符串、数字、布尔、日期、列表/元组、字典等类型,不可序列化类型抛出异常。
166
+
167
+ Args:
168
+ value (Any): 待处理的值
169
+
170
+ Returns:
171
+ str | int | float | None: 格式化后的值,None 表示 SQL 的 NULL
172
+ """
173
+ if value is None:
174
+ return None
175
+
176
+ if isinstance(value, str):
177
+ return value.strip()
178
+
179
+ elif isinstance(value, (list, tuple, dict)):
180
+ try:
181
+ return json.dumps(value, ensure_ascii=False, default=str)
182
+ except Exception as e:
183
+ raise ValueError(f"Failed to serialize container to JSON: {value}, error: {e}")
184
+
185
+ elif isinstance(value, bool):
186
+ return int(value)
187
+
188
+ elif isinstance(value, (int, float)):
189
+ return value
190
+
191
+ elif isinstance(value, (date, time, datetime)):
192
+ return str(value)
193
+
194
+ else:
195
+ raise TypeError(f"Unsupported value type: {type(value)}, value: {value}")
196
+
197
+
198
+ def list2str(datas: List[Any]) -> str:
199
+ """
200
+ 将列表转为 SQL 元组字符串格式。
201
+
202
+ 例如:[1, 2] → "(1, 2)",单元素不带逗号:[1] → "(1)"
203
+
204
+ Args:
205
+ datas (list): 输入列表
206
+
207
+ Returns:
208
+ str: 对应的元组字符串表示
209
+ """
210
+ data_str = str(tuple(datas))
211
+ return re.sub(r",\)$", ")", data_str)
212
+
213
+
214
+ def get_info(
215
+ html: Union[str, Any],
216
+ regexps: Union[str, List[str]],
217
+ allow_repeat: bool = True,
218
+ fetch_one: bool = False,
219
+ split: Optional[str] = None,
220
+ ) -> Union[str, List[str], Tuple]:
221
+ """
222
+ 从 HTML 文本中提取信息,支持正则匹配和多模式 fallback。
223
+
224
+ Args:
225
+ html (str): HTML 内容或可转为字符串的类型
226
+ regexps (str or list of str): 正则表达式,按顺序尝试匹配
227
+ allow_repeat (bool): 是否允许重复结果
228
+ fetch_one (bool): 是否只提取第一个匹配项(返回元组)
229
+ split (str, optional): 若提供,则将结果用该字符连接成字符串
230
+
231
+ Returns:
232
+ str | list | tuple: 匹配结果,根据参数返回字符串、列表或元组
233
+ """
234
+ if isinstance(regexps, str):
235
+ regexps = [regexps]
236
+
237
+ infos = []
238
+ for regex in regexps:
239
+ if not regex:
240
+ continue
241
+
242
+ if regex not in _REGEXPS:
243
+ _REGEXPS[regex] = re.compile(regex, re.S)
244
+
245
+ if fetch_one:
246
+ match = _REGEXPS[regex].search(str(html))
247
+ infos = match.groups() if match else ("",)
248
+ break
249
+ else:
250
+ found = _REGEXPS[regex].findall(str(html))
251
+ if found:
252
+ infos = found
253
+ break
254
+
255
+ if fetch_one:
256
+ return infos[0] if len(infos) == 1 else infos
257
+
258
+ if not allow_repeat:
259
+ infos = sorted(set(infos), key=infos.index)
260
+
261
+ return split.join(infos) if split else infos
262
+
263
+
264
+ def get_json(json_str: Union[str, Any]) -> Dict:
265
+ """
266
+ 安全解析 JSON 字符串,兼容非标准格式(如单引号、缺少引号键)。
267
+
268
+ 尝试修复常见格式错误后再解析。
269
+
270
+ Args:
271
+ json_str (str): JSON 字符串
272
+
273
+ Returns:
274
+ dict: 解析后的字典,失败返回空字典
275
+ """
276
+ if not json_str:
277
+ return {}
278
+
279
+ try:
280
+ return json.loads(json_str)
281
+ except Exception as e1:
282
+ try:
283
+ cleaned = json_str.strip().replace("'", '"')
284
+ keys = get_info(cleaned, r'(\w+):')
285
+ for key in keys:
286
+ cleaned = cleaned.replace(f"{key}:", f'"{key}":')
287
+ return json.loads(cleaned) if cleaned else {}
288
+ except Exception as e2:
289
+ logger.error(
290
+ f"JSON 解析失败\n"
291
+ f"原始内容: {json_str}\n"
292
+ f"错误1: {e1}\n"
293
+ f"修复后: {cleaned}\n"
294
+ f"错误2: {e2}"
295
+ )
296
+ return {}
297
+
298
+
299
+ def dumps_json(
300
+ data: Union[str, dict, list, Any],
301
+ indent: int = 4,
302
+ sort_keys: bool = False,
303
+ ensure_ascii: bool = False,
304
+ skip_keys: bool = True,
305
+ default_repr: bool = False,
306
+ ) -> str:
307
+ """
308
+ 格式化任意对象为可读字符串,优先使用 JSON,失败时降级为 pprint 或 repr。
309
+
310
+ 支持自动处理 datetime、ObjectId 等不可序列化类型。
311
+
312
+ Args:
313
+ data (Any): 输入数据,支持字符串、字典、列表等
314
+ indent (int): JSON 缩进空格数
315
+ sort_keys (bool): 是否对字典键排序
316
+ ensure_ascii (bool): 是否转义非 ASCII 字符(False 可保留中文)
317
+ skip_keys (bool): 遇到非法键时是否跳过(而非报错)
318
+ default_repr (bool): 是否在最终失败时使用 repr() 降级
319
+
320
+ Returns:
321
+ str: 格式化后的字符串,适合日志输出或打印
322
+ """
323
+ try:
324
+ if isinstance(data, str):
325
+ if not data.strip():
326
+ return '""'
327
+ data = get_json(data)
328
+
329
+ return json.dumps(
330
+ data,
331
+ ensure_ascii=ensure_ascii,
332
+ indent=indent,
333
+ skipkeys=skip_keys,
334
+ sort_keys=sort_keys,
335
+ default=str,
336
+ )
337
+
338
+ except (UnicodeDecodeError, ValueError, TypeError, OverflowError) as e:
339
+ try:
340
+ return pprint.pformat(data, indent=indent, width=80, compact=True)
341
+ except Exception:
342
+ if default_repr:
343
+ return repr(data)
344
344
  return f"<无法序列化的对象: {type(data).__name__}>"