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/__init__.py CHANGED
@@ -1,64 +1,64 @@
1
- #!/usr/bin/python
2
- # -*- coding: UTF-8 -*-
3
- """
4
- Crawlo - 一个异步爬虫框架
5
- """
6
- from crawlo.spider import Spider
7
- from crawlo.items import Item, Field
8
- from crawlo.network.request import Request
9
- from crawlo.network.response import Response
10
- from crawlo.downloader import DownloaderBase
11
- from crawlo.middleware import BaseMiddleware
12
- from crawlo.utils import (
13
- TimeUtils,
14
- parse_time,
15
- format_time,
16
- time_diff,
17
- to_timestamp,
18
- to_datetime,
19
- now,
20
- to_timezone,
21
- to_utc,
22
- to_local,
23
- from_timestamp_with_tz
24
- )
25
- from crawlo import tools
26
-
27
- # 为了向后兼容,从tools中导入cleaners相关的功能
28
- import crawlo.tools as cleaners
29
-
30
- # 版本号:优先从元数据读取
31
- try:
32
- from importlib.metadata import version
33
- __version__ = version("crawlo")
34
- except Exception:
35
- # 开发模式下可能未安装,回退到 __version__.py 或 dev
36
- try:
37
- from crawlo.__version__ import __version__
38
- except ImportError:
39
- __version__ = "dev"
40
-
41
- # 定义对外 API
42
- __all__ = [
43
- 'Spider',
44
- 'Item',
45
- 'Field',
46
- 'Request',
47
- 'Response',
48
- 'DownloaderBase',
49
- 'BaseMiddleware',
50
- 'TimeUtils',
51
- 'parse_time',
52
- 'format_time',
53
- 'time_diff',
54
- 'to_timestamp',
55
- 'to_datetime',
56
- 'now',
57
- 'to_timezone',
58
- 'to_utc',
59
- 'to_local',
60
- 'from_timestamp_with_tz',
61
- 'cleaners',
62
- 'tools',
63
- '__version__',
1
+ #!/usr/bin/python
2
+ # -*- coding: UTF-8 -*-
3
+ """
4
+ Crawlo - 一个异步爬虫框架
5
+ """
6
+ from crawlo.spider import Spider
7
+ from crawlo.items import Item, Field
8
+ from crawlo.network.request import Request
9
+ from crawlo.network.response import Response
10
+ from crawlo.downloader import DownloaderBase
11
+ from crawlo.middleware import BaseMiddleware
12
+ from crawlo.utils import (
13
+ TimeUtils,
14
+ parse_time,
15
+ format_time,
16
+ time_diff,
17
+ to_timestamp,
18
+ to_datetime,
19
+ now,
20
+ to_timezone,
21
+ to_utc,
22
+ to_local,
23
+ from_timestamp_with_tz
24
+ )
25
+ from crawlo import tools
26
+
27
+ # 为了向后兼容,从tools中导入cleaners相关的功能
28
+ import crawlo.tools as cleaners
29
+
30
+ # 版本号:优先从元数据读取
31
+ try:
32
+ from importlib.metadata import version
33
+ __version__ = version("crawlo")
34
+ except Exception:
35
+ # 开发模式下可能未安装,回退到 __version__.py 或 dev
36
+ try:
37
+ from crawlo.__version__ import __version__
38
+ except ImportError:
39
+ __version__ = "dev"
40
+
41
+ # 定义对外 API
42
+ __all__ = [
43
+ 'Spider',
44
+ 'Item',
45
+ 'Field',
46
+ 'Request',
47
+ 'Response',
48
+ 'DownloaderBase',
49
+ 'BaseMiddleware',
50
+ 'TimeUtils',
51
+ 'parse_time',
52
+ 'format_time',
53
+ 'time_diff',
54
+ 'to_timestamp',
55
+ 'to_datetime',
56
+ 'now',
57
+ 'to_timezone',
58
+ 'to_utc',
59
+ 'to_local',
60
+ 'from_timestamp_with_tz',
61
+ 'cleaners',
62
+ 'tools',
63
+ '__version__',
64
64
  ]
crawlo/__version__.py CHANGED
@@ -1 +1 @@
1
- __version__ = '1.3.2'
1
+ __version__ = '1.3.3'
crawlo/cli.py CHANGED
@@ -1,76 +1,76 @@
1
- # crawlo/cli.py
2
- # !/usr/bin/python
3
- # -*- coding: UTF-8 -*-
4
- import sys
5
- import argparse
6
- from crawlo.commands import get_commands
7
- from crawlo.utils.env_config import get_version
8
-
9
-
10
- def main():
11
- # 获取框架版本号
12
- VERSION = get_version()
13
-
14
- # 获取所有可用命令
15
- commands = get_commands()
16
-
17
- # 创建主解析器
18
- parser = argparse.ArgumentParser(
19
- description="Crawlo: A lightweight web crawler framework.",
20
- usage="crawlo <command> [options]",
21
- add_help=False # 禁用默认帮助,我们自己处理
22
- )
23
-
24
- # 添加帮助参数
25
- parser.add_argument('-h', '--help', action='store_true', help='显示帮助信息')
26
- parser.add_argument('-v', '--version', action='store_true', help='显示版本信息')
27
- parser.add_argument('command', nargs='?', help='可用命令: ' + ', '.join(commands.keys()))
28
-
29
- # 解析已知参数
30
- args, unknown = parser.parse_known_args()
31
-
32
- # 处理版本参数
33
- if args.version:
34
- print(f"Crawlo {VERSION}")
35
- sys.exit(0)
36
-
37
- # 处理帮助参数
38
- if args.help or (args.command is None and not unknown):
39
- # 导入并运行帮助命令
40
- try:
41
- module = __import__(commands['help'], fromlist=['main'])
42
- sys.exit(module.main([]))
43
- except ImportError as e:
44
- print(f"Failed to load help command: {e}")
45
- sys.exit(1)
46
- except Exception as e:
47
- print(f"Help command failed: {e}")
48
- sys.exit(1)
49
-
50
- # 检查命令是否存在
51
- if args.command not in commands:
52
- print(f"Unknown command: {args.command}")
53
- print(f"Available commands: {', '.join(commands.keys())}")
54
- # 显示帮助信息
55
- try:
56
- module = __import__(commands['help'], fromlist=['main'])
57
- module.main([])
58
- except:
59
- pass
60
- sys.exit(1)
61
-
62
- # 动态导入并执行命令
63
- try:
64
- module = __import__(commands[args.command], fromlist=['main'])
65
- # 将未知参数传递给子命令
66
- sys.exit(module.main(unknown))
67
- except ImportError as e:
68
- print(f"Failed to load command '{args.command}': {e}")
69
- sys.exit(1)
70
- except Exception as e:
71
- print(f"Command '{args.command}' failed: {e}")
72
- sys.exit(1)
73
-
74
-
75
- if __name__ == '__main__':
1
+ # crawlo/cli.py
2
+ # !/usr/bin/python
3
+ # -*- coding: UTF-8 -*-
4
+ import sys
5
+ import argparse
6
+ from crawlo.commands import get_commands
7
+ from crawlo.utils.env_config import get_version
8
+
9
+
10
+ def main():
11
+ # 获取框架版本号
12
+ VERSION = get_version()
13
+
14
+ # 获取所有可用命令
15
+ commands = get_commands()
16
+
17
+ # 创建主解析器
18
+ parser = argparse.ArgumentParser(
19
+ description="Crawlo: A lightweight web crawler framework.",
20
+ usage="crawlo <command> [options]",
21
+ add_help=False # 禁用默认帮助,我们自己处理
22
+ )
23
+
24
+ # 添加帮助参数
25
+ parser.add_argument('-h', '--help', action='store_true', help='显示帮助信息')
26
+ parser.add_argument('-v', '--version', action='store_true', help='显示版本信息')
27
+ parser.add_argument('command', nargs='?', help='可用命令: ' + ', '.join(commands.keys()))
28
+
29
+ # 解析已知参数
30
+ args, unknown = parser.parse_known_args()
31
+
32
+ # 处理版本参数
33
+ if args.version:
34
+ print(f"Crawlo {VERSION}")
35
+ sys.exit(0)
36
+
37
+ # 处理帮助参数
38
+ if args.help or (args.command is None and not unknown):
39
+ # 导入并运行帮助命令
40
+ try:
41
+ module = __import__(commands['help'], fromlist=['main'])
42
+ sys.exit(module.main([]))
43
+ except ImportError as e:
44
+ print(f"Failed to load help command: {e}")
45
+ sys.exit(1)
46
+ except Exception as e:
47
+ print(f"Help command failed: {e}")
48
+ sys.exit(1)
49
+
50
+ # 检查命令是否存在
51
+ if args.command not in commands:
52
+ print(f"Unknown command: {args.command}")
53
+ print(f"Available commands: {', '.join(commands.keys())}")
54
+ # 显示帮助信息
55
+ try:
56
+ module = __import__(commands['help'], fromlist=['main'])
57
+ module.main([])
58
+ except:
59
+ pass
60
+ sys.exit(1)
61
+
62
+ # 动态导入并执行命令
63
+ try:
64
+ module = __import__(commands[args.command], fromlist=['main'])
65
+ # 将未知参数传递给子命令
66
+ sys.exit(module.main(unknown))
67
+ except ImportError as e:
68
+ print(f"Failed to load command '{args.command}': {e}")
69
+ sys.exit(1)
70
+ except Exception as e:
71
+ print(f"Command '{args.command}' failed: {e}")
72
+ sys.exit(1)
73
+
74
+
75
+ if __name__ == '__main__':
76
76
  main()
@@ -1,15 +1,15 @@
1
- #!/usr/bin/python
2
- # -*- coding:UTF-8 -*-
3
-
4
- _commands = {
5
- 'startproject': 'crawlo.commands.startproject',
6
- 'genspider': 'crawlo.commands.genspider',
7
- 'run': 'crawlo.commands.run',
8
- 'check': 'crawlo.commands.check',
9
- 'list': 'crawlo.commands.list',
10
- 'stats': 'crawlo.commands.stats',
11
- 'help': 'crawlo.commands.help'
12
- }
13
-
14
- def get_commands():
1
+ #!/usr/bin/python
2
+ # -*- coding:UTF-8 -*-
3
+
4
+ _commands = {
5
+ 'startproject': 'crawlo.commands.startproject',
6
+ 'genspider': 'crawlo.commands.genspider',
7
+ 'run': 'crawlo.commands.run',
8
+ 'check': 'crawlo.commands.check',
9
+ 'list': 'crawlo.commands.list',
10
+ 'stats': 'crawlo.commands.stats',
11
+ 'help': 'crawlo.commands.help'
12
+ }
13
+
14
+ def get_commands():
15
15
  return _commands