crawlo 1.2.8__py3-none-any.whl → 1.3.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of crawlo might be problematic. Click here for more details.

Files changed (221) hide show
  1. crawlo/__init__.py +63 -61
  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 +314 -323
  10. crawlo/commands/startproject.py +436 -436
  11. crawlo/commands/stats.py +187 -187
  12. crawlo/commands/utils.py +186 -186
  13. crawlo/config.py +312 -312
  14. crawlo/config_validator.py +277 -251
  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 -251
  19. crawlo/crawler.py +1097 -1099
  20. crawlo/data/__init__.py +5 -5
  21. crawlo/data/user_agents.py +194 -107
  22. crawlo/downloader/__init__.py +273 -266
  23. crawlo/downloader/aiohttp_downloader.py +226 -228
  24. crawlo/downloader/cffi_downloader.py +245 -256
  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 +45 -43
  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 +136 -136
  50. crawlo/middleware/offsite.py +114 -114
  51. crawlo/middleware/proxy.py +386 -368
  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 -0
  57. crawlo/mode_manager.py +212 -211
  58. crawlo/network/__init__.py +21 -21
  59. crawlo/network/request.py +379 -338
  60. crawlo/network/response.py +359 -359
  61. crawlo/pipelines/__init__.py +21 -21
  62. crawlo/pipelines/bloom_dedup_pipeline.py +157 -157
  63. crawlo/pipelines/console_pipeline.py +39 -39
  64. crawlo/pipelines/csv_pipeline.py +316 -316
  65. crawlo/pipelines/database_dedup_pipeline.py +223 -223
  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 +317 -317
  70. crawlo/pipelines/pipeline_manager.py +74 -62
  71. crawlo/pipelines/redis_dedup_pipeline.py +167 -167
  72. crawlo/project.py +284 -315
  73. crawlo/queue/pqueue.py +37 -37
  74. crawlo/queue/queue_manager.py +379 -378
  75. crawlo/queue/redis_priority_queue.py +306 -306
  76. crawlo/settings/__init__.py +7 -7
  77. crawlo/settings/default_settings.py +216 -220
  78. crawlo/settings/setting_manager.py +175 -122
  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 +261 -288
  89. crawlo/templates/project/settings_distributed.py.tmpl +174 -157
  90. crawlo/templates/project/settings_gentle.py.tmpl +95 -100
  91. crawlo/templates/project/settings_high_performance.py.tmpl +125 -134
  92. crawlo/templates/project/settings_minimal.py.tmpl +30 -0
  93. crawlo/templates/project/settings_simple.py.tmpl +96 -98
  94. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  95. crawlo/templates/run.py.tmpl +47 -47
  96. crawlo/templates/spider/spider.py.tmpl +143 -143
  97. crawlo/tools/__init__.py +200 -182
  98. crawlo/tools/anti_crawler.py +268 -268
  99. crawlo/tools/authenticated_proxy.py +240 -240
  100. crawlo/{cleaners → tools}/data_formatter.py +225 -225
  101. crawlo/tools/data_validator.py +180 -180
  102. crawlo/tools/date_tools.py +290 -36
  103. crawlo/tools/distributed_coordinator.py +388 -387
  104. crawlo/{cleaners → tools}/encoding_converter.py +127 -126
  105. crawlo/tools/request_tools.py +83 -0
  106. crawlo/tools/retry_mechanism.py +224 -221
  107. crawlo/tools/scenario_adapter.py +262 -262
  108. crawlo/{cleaners → tools}/text_cleaner.py +232 -232
  109. crawlo/utils/__init__.py +35 -35
  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 +146 -128
  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-1.2.8.dist-info → crawlo-1.3.0.dist-info}/METADATA +1011 -764
  131. crawlo-1.3.0.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 -237
  137. tests/cleaners_example.py +160 -160
  138. tests/config_validation_demo.py +143 -103
  139. tests/controlled_spider_example.py +205 -205
  140. tests/date_tools_example.py +180 -180
  141. tests/debug_pipelines.py +67 -0
  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 +151 -0
  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 +153 -0
  156. tests/test_config_validator.py +182 -193
  157. tests/test_crawlo_proxy_integration.py +109 -173
  158. tests/test_date_tools.py +123 -123
  159. tests/test_default_header_middleware.py +158 -158
  160. tests/test_distributed.py +65 -0
  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 -357
  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 +185 -0
  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 +73 -0
  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 +112 -0
  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 -153
  213. tests/test_user_agents.py +97 -0
  214. tests/tools_example.py +260 -257
  215. tests/verify_distributed.py +117 -0
  216. crawlo/cleaners/__init__.py +0 -61
  217. crawlo/utils/date_tools.py +0 -290
  218. crawlo-1.2.8.dist-info/RECORD +0 -209
  219. {crawlo-1.2.8.dist-info → crawlo-1.3.0.dist-info}/WHEEL +0 -0
  220. {crawlo-1.2.8.dist-info → crawlo-1.3.0.dist-info}/entry_points.txt +0 -0
  221. {crawlo-1.2.8.dist-info → crawlo-1.3.0.dist-info}/top_level.txt +0 -0
crawlo/commands/stats.py CHANGED
@@ -1,188 +1,188 @@
1
- #!/usr/bin/python
2
- # -*- coding: UTF-8 -*-
3
- """
4
- # @Time : 2025-08-31 22:36
5
- # @Author : crawl-coder
6
- # @Desc : 命令行入口:crawlo stats,查看最近运行的爬虫统计信息。
7
- """
8
- import json
9
- from pathlib import Path
10
- from datetime import datetime
11
- from typing import Dict, Any
12
-
13
- from rich.console import Console
14
- from rich.table import Table
15
- from rich.panel import Panel
16
- from rich.text import Text
17
- from rich import box
18
-
19
- from crawlo.utils.log import get_logger
20
-
21
-
22
- logger = get_logger(__name__)
23
- console = Console()
24
-
25
- # 默认存储目录(相对于项目根目录)
26
- STATS_DIR = "logs/stats"
27
-
28
-
29
- def get_stats_dir() -> Path:
30
- """
31
- 获取统计文件存储目录,优先使用项目根下的 logs/stats/
32
- 如果不在项目中,回退到当前目录
33
- """
34
- current = Path.cwd()
35
- for _ in range(10):
36
- if (current / "crawlo.cfg").exists():
37
- return current / STATS_DIR
38
- if current == current.parent:
39
- break
40
- current = current.parent
41
- return Path.cwd() / STATS_DIR
42
-
43
-
44
- def record_stats(crawler):
45
- """
46
- 【供爬虫运行时调用】记录爬虫结束后的统计信息到 JSON 文件
47
- 需在 Crawler 的 closed 回调中调用
48
- """
49
- spider_name = getattr(crawler.spider, "name", "unknown")
50
- stats = crawler.stats.get_stats() if crawler.stats else {}
51
-
52
- timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
53
- stats_dir = Path(get_stats_dir())
54
- stats_dir.mkdir(parents=True, exist_ok=True)
55
-
56
- filename = stats_dir / f"{spider_name}_{timestamp}.json"
57
- try:
58
- with open(filename, "w", encoding="utf-8") as f:
59
- json.dump({
60
- "spider": spider_name,
61
- "timestamp": datetime.now().isoformat(),
62
- "stats": stats
63
- }, f, ensure_ascii=False, indent=2, default=str)
64
- logger.info(f"📊 爬虫 '{spider_name}' 的统计信息已保存 {filename}")
65
- except Exception as e:
66
- logger.error(f"保存 '{spider_name}' 的统计信息失败: {e}")
67
-
68
-
69
- def load_all_stats() -> Dict[str, list]:
70
- """
71
- 加载所有已保存的统计文件,按 spider name 分组
72
- 返回: {spider_name: [stats_record, ...]}
73
- """
74
- stats_dir = get_stats_dir()
75
- if not stats_dir.exists():
76
- return {}
77
-
78
- result = {}
79
- json_files = sorted(stats_dir.glob("*.json"), key=lambda x: x.stat().st_mtime, reverse=True)
80
-
81
- for file in json_files:
82
- try:
83
- with open(file, "r", encoding="utf-8") as f:
84
- data = json.load(f)
85
- spider_name = data.get("spider", "unknown")
86
- result.setdefault(spider_name, []).append(data)
87
- except Exception as e:
88
- logger.warning(f"加载统计文件 {file} 失败: {e}")
89
- return result
90
-
91
-
92
- def format_value(v: Any) -> str:
93
- """格式化值,防止太长或不可打印"""
94
- if isinstance(v, float):
95
- return f"{v:.4f}"
96
- s = str(v)
97
- if len(s) > 80:
98
- return s[:77] + "..."
99
- return s
100
-
101
-
102
- def display_stats_table(stats_data: dict, title: str = "统计信息"):
103
- """通用函数:用 rich.table 展示统计数据"""
104
- table = Table(title=title, box=box.ROUNDED, show_header=True, header_style="bold magenta")
105
- table.add_column("键", style="cyan", no_wrap=True)
106
- table.add_column("值", style="green")
107
-
108
- for k in sorted(stats_data.keys()):
109
- table.add_row(k, format_value(stats_data[k]))
110
-
111
- console.print(table)
112
-
113
-
114
- def main(args):
115
- """
116
- 主函数:查看统计信息
117
- 用法:
118
- crawlo stats → 显示所有爬虫最近一次运行
119
- crawlo stats myspider → 显示指定爬虫所有历史记录
120
- crawlo stats myspider --all → 显示所有历史(同上)
121
- """
122
- if len(args) > 2:
123
- console.print("[bold red]错误:[/bold red] 用法: [blue]crawlo stats[/blue] [爬虫名称] [--all]")
124
- return 1
125
-
126
- spider_name = None
127
- show_all = False
128
-
129
- if args:
130
- spider_name = args[0]
131
- show_all = "--all" in args or "-a" in args
132
-
133
- all_stats = load_all_stats()
134
-
135
- if not all_stats:
136
- console.print(Panel(
137
- Text.from_markup(
138
- ":chart_with_upwards_trend: [bold]未找到统计信息。[/bold]\n"
139
- "💡 先运行一个爬虫以生成统计信息。\n"
140
- f"📁 统计目录: [cyan]{get_stats_dir()}[/cyan]"
141
- ),
142
- title="📊 统计信息",
143
- border_style="yellow",
144
- padding=(1, 2)
145
- ))
146
- return 0
147
-
148
- # 显示所有爬虫最近一次运行
149
- if not spider_name:
150
- console.print(Panel(
151
- "[bold]最近的爬虫统计信息(上次运行)[/bold]",
152
- title="📊 爬虫统计概览",
153
- border_style="green",
154
- padding=(0, 1)
155
- ))
156
-
157
- for name, runs in all_stats.items():
158
- latest = runs[0]
159
- ts = latest['timestamp'][:19]
160
- console.print(f"🕷️ [bold cyan]{name}[/bold cyan] ([green]{ts}[/green])")
161
- display_stats_table(latest["stats"], title=f"{name} 的统计信息")
162
- console.print() # 空行分隔
163
-
164
- return 0
165
-
166
- # 显示指定爬虫的历史
167
- if spider_name not in all_stats:
168
- console.print(f"[bold red]:cross_mark: 未找到爬虫 '[cyan]{spider_name}[/cyan]' 的统计信息[/bold red]")
169
- available = ', '.join(all_stats.keys())
170
- if available:
171
- console.print(f":bulb: 可用爬虫: [green]{available}[/green]")
172
- return 1
173
-
174
- runs = all_stats[spider_name]
175
- if show_all:
176
- console.print(f":bar_chart: [bold]'[cyan]{spider_name}[/cyan]' 的所有运行记录 ({len(runs)} 次):[/bold]")
177
- else:
178
- runs = runs[:1]
179
- console.print(f":bar_chart: [bold]'[cyan]{spider_name}[/cyan]' 的上次运行:[/bold]")
180
-
181
- for i, run in enumerate(runs, 1):
182
- ts = run['timestamp']
183
- subtitle = f"运行 #{i} · {ts}" if show_all else f"上次运行 · {ts}"
184
- display_stats_table(run["stats"], title=f"{spider_name} 的统计信息 — {subtitle}")
185
- if i < len(runs):
186
- console.print("─" * 60)
187
-
1
+ #!/usr/bin/python
2
+ # -*- coding: UTF-8 -*-
3
+ """
4
+ # @Time : 2025-08-31 22:36
5
+ # @Author : crawl-coder
6
+ # @Desc : 命令行入口:crawlo stats,查看最近运行的爬虫统计信息。
7
+ """
8
+ import json
9
+ from pathlib import Path
10
+ from datetime import datetime
11
+ from typing import Dict, Any
12
+
13
+ from rich.console import Console
14
+ from rich.table import Table
15
+ from rich.panel import Panel
16
+ from rich.text import Text
17
+ from rich import box
18
+
19
+ from crawlo.utils.log import get_logger
20
+
21
+
22
+ logger = get_logger(__name__)
23
+ console = Console()
24
+
25
+ # 默认存储目录(相对于项目根目录)
26
+ STATS_DIR = "logs/stats"
27
+
28
+
29
+ def get_stats_dir() -> Path:
30
+ """
31
+ 获取统计文件存储目录,优先使用项目根下的 logs/stats/
32
+ 如果不在项目中,回退到当前目录
33
+ """
34
+ current = Path.cwd()
35
+ for _ in range(10):
36
+ if (current / "crawlo.cfg").exists():
37
+ return current / STATS_DIR
38
+ if current == current.parent:
39
+ break
40
+ current = current.parent
41
+ return Path.cwd() / STATS_DIR
42
+
43
+
44
+ def record_stats(crawler):
45
+ """
46
+ 【供爬虫运行时调用】记录爬虫结束后的统计信息到 JSON 文件
47
+ 需在 Crawler 的 closed 回调中调用
48
+ """
49
+ spider_name = getattr(crawler.spider, "name", "unknown")
50
+ stats = crawler.stats.get_stats() if crawler.stats else {}
51
+
52
+ timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
53
+ stats_dir = Path(get_stats_dir())
54
+ stats_dir.mkdir(parents=True, exist_ok=True)
55
+
56
+ filename = stats_dir / f"{spider_name}_{timestamp}.json"
57
+ try:
58
+ with open(filename, "w", encoding="utf-8") as f:
59
+ json.dump({
60
+ "spider": spider_name,
61
+ "timestamp": datetime.now().isoformat(),
62
+ "stats": stats
63
+ }, f, ensure_ascii=False, indent=2, default=str)
64
+ logger.info(f"Stats for spider '{spider_name}' saved to {filename}")
65
+ except Exception as e:
66
+ logger.error(f"保存 '{spider_name}' 的统计信息失败: {e}")
67
+
68
+
69
+ def load_all_stats() -> Dict[str, list]:
70
+ """
71
+ 加载所有已保存的统计文件,按 spider name 分组
72
+ 返回: {spider_name: [stats_record, ...]}
73
+ """
74
+ stats_dir = get_stats_dir()
75
+ if not stats_dir.exists():
76
+ return {}
77
+
78
+ result = {}
79
+ json_files = sorted(stats_dir.glob("*.json"), key=lambda x: x.stat().st_mtime, reverse=True)
80
+
81
+ for file in json_files:
82
+ try:
83
+ with open(file, "r", encoding="utf-8") as f:
84
+ data = json.load(f)
85
+ spider_name = data.get("spider", "unknown")
86
+ result.setdefault(spider_name, []).append(data)
87
+ except Exception as e:
88
+ logger.warning(f"加载统计文件 {file} 失败: {e}")
89
+ return result
90
+
91
+
92
+ def format_value(v: Any) -> str:
93
+ """格式化值,防止太长或不可打印"""
94
+ if isinstance(v, float):
95
+ return f"{v:.4f}"
96
+ s = str(v)
97
+ if len(s) > 80:
98
+ return s[:77] + "..."
99
+ return s
100
+
101
+
102
+ def display_stats_table(stats_data: dict, title: str = "统计信息"):
103
+ """通用函数:用 rich.table 展示统计数据"""
104
+ table = Table(title=title, box=box.ROUNDED, show_header=True, header_style="bold magenta")
105
+ table.add_column("键", style="cyan", no_wrap=True)
106
+ table.add_column("值", style="green")
107
+
108
+ for k in sorted(stats_data.keys()):
109
+ table.add_row(k, format_value(stats_data[k]))
110
+
111
+ console.print(table)
112
+
113
+
114
+ def main(args):
115
+ """
116
+ 主函数:查看统计信息
117
+ 用法:
118
+ crawlo stats → 显示所有爬虫最近一次运行
119
+ crawlo stats myspider → 显示指定爬虫所有历史记录
120
+ crawlo stats myspider --all → 显示所有历史(同上)
121
+ """
122
+ if len(args) > 2:
123
+ console.print("[bold red]错误:[/bold red] 用法: [blue]crawlo stats[/blue] [爬虫名称] [--all]")
124
+ return 1
125
+
126
+ spider_name = None
127
+ show_all = False
128
+
129
+ if args:
130
+ spider_name = args[0]
131
+ show_all = "--all" in args or "-a" in args
132
+
133
+ all_stats = load_all_stats()
134
+
135
+ if not all_stats:
136
+ console.print(Panel(
137
+ Text.from_markup(
138
+ "[bold]未找到统计信息。[/bold]\n"
139
+ "先运行一个爬虫以生成统计信息。\n"
140
+ f"统计目录: [cyan]{get_stats_dir()}[/cyan]"
141
+ ),
142
+ title="统计信息",
143
+ border_style="yellow",
144
+ padding=(1, 2)
145
+ ))
146
+ return 0
147
+
148
+ # 显示所有爬虫最近一次运行
149
+ if not spider_name:
150
+ console.print(Panel(
151
+ "[bold]最近的爬虫统计信息(上次运行)[/bold]",
152
+ title="爬虫统计概览",
153
+ border_style="green",
154
+ padding=(0, 1)
155
+ ))
156
+
157
+ for name, runs in all_stats.items():
158
+ latest = runs[0]
159
+ ts = latest['timestamp'][:19]
160
+ console.print(f" [bold cyan]{name}[/bold cyan] ([green]{ts}[/green])")
161
+ display_stats_table(latest["stats"], title=f"{name} 的统计信息")
162
+ console.print() # 空行分隔
163
+
164
+ return 0
165
+
166
+ # 显示指定爬虫的历史
167
+ if spider_name not in all_stats:
168
+ console.print(f"[bold red]未找到爬虫 '[cyan]{spider_name}[/cyan]' 的统计信息[/bold red]")
169
+ available = ', '.join(all_stats.keys())
170
+ if available:
171
+ console.print(f"可用爬虫: [green]{available}[/green]")
172
+ return 1
173
+
174
+ runs = all_stats[spider_name]
175
+ if show_all:
176
+ console.print(f"[bold]'[cyan]{spider_name}[/cyan]' 的所有运行记录 ({len(runs)} 次):[/bold]")
177
+ else:
178
+ runs = runs[:1]
179
+ console.print(f"[bold]'[cyan]{spider_name}[/cyan]' 的上次运行:[/bold]")
180
+
181
+ for i, run in enumerate(runs, 1):
182
+ ts = run['timestamp']
183
+ subtitle = f"运行 #{i} · {ts}" if show_all else f"上次运行 · {ts}"
184
+ display_stats_table(run["stats"], title=f"{spider_name} 的统计信息 — {subtitle}")
185
+ if i < len(runs):
186
+ console.print("─" * 60)
187
+
188
188
  return 0