crawlo 1.2.3__py3-none-any.whl → 1.2.5__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 (222) 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 +88 -81
  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 +144 -142
  12. crawlo/commands/list.py +155 -155
  13. crawlo/commands/run.py +323 -292
  14. crawlo/commands/startproject.py +436 -417
  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 +354 -354
  21. crawlo/core/processor.py +40 -40
  22. crawlo/core/scheduler.py +143 -143
  23. crawlo/crawler.py +1110 -1027
  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 +220 -220
  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 +37 -37
  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 +280 -280
  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 +135 -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 +61 -61
  74. crawlo/pipelines/redis_dedup_pipeline.py +165 -165
  75. crawlo/project.py +279 -187
  76. crawlo/queue/pqueue.py +37 -37
  77. crawlo/queue/queue_manager.py +337 -337
  78. crawlo/queue/redis_priority_queue.py +298 -298
  79. crawlo/settings/__init__.py +7 -7
  80. crawlo/settings/default_settings.py +217 -226
  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 +324 -325
  92. crawlo/templates/project/settings_distributed.py.tmpl +154 -121
  93. crawlo/templates/project/settings_gentle.py.tmpl +127 -94
  94. crawlo/templates/project/settings_high_performance.py.tmpl +149 -151
  95. crawlo/templates/project/settings_simple.py.tmpl +102 -68
  96. crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
  97. crawlo/templates/{project/run.py.tmpl → 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 +105 -105
  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 +334 -334
  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-1.2.3.dist-info → crawlo-1.2.5.dist-info}/METADATA +764 -692
  130. crawlo-1.2.5.dist-info/RECORD +206 -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_validator.py +193 -193
  152. tests/test_crawlo_proxy_integration.py +172 -172
  153. tests/test_date_tools.py +123 -123
  154. tests/test_default_header_middleware.py +158 -158
  155. tests/test_double_crawlo_fix.py +207 -207
  156. tests/test_double_crawlo_fix_simple.py +124 -124
  157. tests/test_download_delay_middleware.py +221 -221
  158. tests/test_downloader_proxy_compatibility.py +268 -268
  159. tests/test_dynamic_downloaders_proxy.py +124 -124
  160. tests/test_dynamic_proxy.py +92 -92
  161. tests/test_dynamic_proxy_config.py +146 -146
  162. tests/test_dynamic_proxy_real.py +109 -109
  163. tests/test_edge_cases.py +303 -303
  164. tests/test_enhanced_error_handler.py +270 -270
  165. tests/test_env_config.py +121 -121
  166. tests/test_error_handler_compatibility.py +112 -112
  167. tests/test_final_validation.py +153 -153
  168. tests/test_framework_env_usage.py +103 -103
  169. tests/test_integration.py +356 -356
  170. tests/test_item_dedup_redis_key.py +122 -122
  171. tests/test_offsite_middleware.py +221 -221
  172. tests/test_parsel.py +29 -29
  173. tests/test_performance.py +327 -327
  174. tests/test_proxy_api.py +264 -264
  175. tests/test_proxy_health_check.py +32 -32
  176. tests/test_proxy_middleware.py +121 -121
  177. tests/test_proxy_middleware_enhanced.py +216 -216
  178. tests/test_proxy_middleware_integration.py +136 -136
  179. tests/test_proxy_providers.py +56 -56
  180. tests/test_proxy_stats.py +19 -19
  181. tests/test_proxy_strategies.py +59 -59
  182. tests/test_queue_manager_double_crawlo.py +173 -173
  183. tests/test_queue_manager_redis_key.py +176 -176
  184. tests/test_real_scenario_proxy.py +195 -195
  185. tests/test_redis_config.py +28 -28
  186. tests/test_redis_connection_pool.py +294 -294
  187. tests/test_redis_key_naming.py +181 -181
  188. tests/test_redis_key_validator.py +123 -123
  189. tests/test_redis_queue.py +224 -224
  190. tests/test_request_ignore_middleware.py +182 -182
  191. tests/test_request_serialization.py +70 -70
  192. tests/test_response_code_middleware.py +349 -349
  193. tests/test_response_filter_middleware.py +427 -427
  194. tests/test_response_improvements.py +152 -152
  195. tests/test_retry_middleware.py +241 -241
  196. tests/test_scheduler.py +241 -241
  197. tests/test_simple_response.py +61 -61
  198. tests/test_telecom_spider_redis_key.py +205 -205
  199. tests/test_template_content.py +87 -87
  200. tests/test_template_redis_key.py +134 -134
  201. tests/test_tools.py +153 -153
  202. tests/tools_example.py +257 -257
  203. crawlo-1.2.3.dist-info/RECORD +0 -222
  204. examples/aiohttp_settings.py +0 -42
  205. examples/curl_cffi_settings.py +0 -41
  206. examples/default_header_middleware_example.py +0 -107
  207. examples/default_header_spider_example.py +0 -129
  208. examples/download_delay_middleware_example.py +0 -160
  209. examples/httpx_settings.py +0 -42
  210. examples/multi_downloader_proxy_example.py +0 -81
  211. examples/offsite_middleware_example.py +0 -55
  212. examples/offsite_spider_example.py +0 -107
  213. examples/proxy_spider_example.py +0 -166
  214. examples/request_ignore_middleware_example.py +0 -51
  215. examples/request_ignore_spider_example.py +0 -99
  216. examples/response_code_middleware_example.py +0 -52
  217. examples/response_filter_middleware_example.py +0 -67
  218. examples/tong_hua_shun_settings.py +0 -62
  219. examples/tong_hua_shun_spider.py +0 -170
  220. {crawlo-1.2.3.dist-info → crawlo-1.2.5.dist-info}/WHEEL +0 -0
  221. {crawlo-1.2.3.dist-info → crawlo-1.2.5.dist-info}/entry_points.txt +0 -0
  222. {crawlo-1.2.3.dist-info → crawlo-1.2.5.dist-info}/top_level.txt +0 -0
@@ -0,0 +1,206 @@
1
+ crawlo/__init__.py,sha256=1tc6uUDF1yRNU7K_k-Dl6h9FGy7Jp8fdhRsXu9PctFI,1312
2
+ crawlo/__version__.py,sha256=jBmZf3HLbiQlWiolOsAA6J5-BbxXD2bqFqEqDH3lfqo,22
3
+ crawlo/cli.py,sha256=8OD2us3YYG55AMTm_3YmHiZ8_Plokkx6p2DVR7w0JGs,2872
4
+ crawlo/config.py,sha256=zbFn2HfcbDcD1QOSgNOB9kjw12UDb7zo4Y7RLcJJirQ,9506
5
+ crawlo/config_validator.py,sha256=eQWrSY4xNnbDgwAmPOENyMb0wb3rdzOL55yBCKmpIak,9883
6
+ crawlo/crawler.py,sha256=KPVgLpDJIZ0k3-U9CtrYgvnLatFG9eYPdjUtqoPBHXU,40305
7
+ crawlo/event.py,sha256=7-y6HNv_EIJSYQNzsj0mVK-Gg4ON3wdQeMdQjfFJPlw,313
8
+ crawlo/exceptions.py,sha256=sMay0wnWLfc_FXWslqxm60qz6b66LXs3EdN_w8ygE9k,1166
9
+ crawlo/mode_manager.py,sha256=UpaY3qhyWYnZpNFdqyeD4VJXPZYXAKJ7VxWc5Fy6tqo,7517
10
+ crawlo/project.py,sha256=E8HRs-LNDQB62sVrYS3mnC6pLLQ_RcPTahWgHbj-vKU,10553
11
+ crawlo/stats_collector.py,sha256=NkO09CB-220qz5rxFcD_dedGfr2VPFrDo4hya0Zh8Qc,1577
12
+ crawlo/subscriber.py,sha256=D3hzE7Pc_zJjc-zR7lct5pt32bz6LsDYeC8uHlS4Hso,4986
13
+ crawlo/task_manager.py,sha256=19InAxS9oJ9EMj20Aw2urN-v6BeC22dkgPuW-B9-4UI,819
14
+ crawlo/cleaners/__init__.py,sha256=DVD4W09aJF-ih8vYx3DPZaXIE18MTEM36uo1SnqLMLk,1201
15
+ crawlo/cleaners/data_formatter.py,sha256=NEj3NqPiyG67V6qDgn2KNj9VNHWOLNwX-7p_nad0znc,7583
16
+ crawlo/cleaners/encoding_converter.py,sha256=uWyZMHJxC2y5cBRg8LnrBAYV3X4ESrkmKVE2ho8s1FY,4113
17
+ crawlo/cleaners/text_cleaner.py,sha256=WDcQdvoyaY3tSxYa7EdS6BGvZNggoJbfyE662Y8TiL8,6475
18
+ crawlo/commands/__init__.py,sha256=QbhGAmItiwVrtlTr9UUbEJMegLJo-SdzaKX2PUhBgfI,378
19
+ crawlo/commands/check.py,sha256=hpNkeLYym3D1Fz4pwu8RPN0DbUp_mjuhX3mw6TznYo8,22849
20
+ crawlo/commands/genspider.py,sha256=NAeXmfb9ElLOuLc4F2xIzuG779KvAAesy3EZa_QxqR8,4991
21
+ crawlo/commands/help.py,sha256=pHp0m6QBF4NZnZncPBxOLRlJQXJZQsztlyn5euFD9po,5186
22
+ crawlo/commands/list.py,sha256=VR4AWrOiLQgw2t6u8dm9uxsCoCPzX36_6XeTs3tzcQk,5772
23
+ crawlo/commands/run.py,sha256=-5psh1ui0zJmHjmzkSo8Tnl99B1e4Rz90lk0Ak-2SuA,12236
24
+ crawlo/commands/startproject.py,sha256=8tMokyCBN4nEpWjAca3NQorU5t8WR5ffBQZ7eyvUWpA,16260
25
+ crawlo/commands/stats.py,sha256=fCNk7ix6v9PrscC-wKQl6ddA4xaQLogrN_1SNEj66tk,6128
26
+ crawlo/commands/utils.py,sha256=3nP8bMgPH36ELqg1ilzPhHS873ncNvZNxOEDYY4uDm4,5087
27
+ crawlo/core/__init__.py,sha256=PnFyJdVNHBoPmV1sW0AHQXijeoSTQ8cMYrbNM1JK8kA,41
28
+ crawlo/core/engine.py,sha256=c65vwIPrwDzFvec2f1QJ2_hikBjj-CYjTGkYrjnWxto,13724
29
+ crawlo/core/processor.py,sha256=qmCqAeqhwYu-UE86evYesaGt9qpuSIfH-ZIZKcXFCZc,1140
30
+ crawlo/core/scheduler.py,sha256=ONdbmcjGyUoOhnXsO2pmTGU6no1RxTEM5FDDcthGLGA,5219
31
+ crawlo/data/__init__.py,sha256=8MgDxcMhx-emFARcLAw_ODOZNz0neYBcx7kEbzothd8,116
32
+ crawlo/data/user_agents.py,sha256=Zpm9nhP1Q3CVLtRGRBmpMFYW8qP-GxlDBeAOWF_2ad0,4698
33
+ crawlo/downloader/__init__.py,sha256=MlstaKfW-WLXNuZs7tb7cG_wG2sQLw2hdWmUjZEIH7c,8299
34
+ crawlo/downloader/aiohttp_downloader.py,sha256=n2qP3Q13lOnvwB7cb3YxNyNKYVHKqofNNg7j9tV9h-E,8400
35
+ crawlo/downloader/cffi_downloader.py,sha256=IpQUqvls4mEYs_UwPvtN2L4uUIujqn-rf03NuZZkMl0,10710
36
+ crawlo/downloader/httpx_downloader.py,sha256=7jfQfvAtfk8yD_mvwUbWLhYOxMM7r1nudiU7m_Jl9wc,12037
37
+ crawlo/downloader/hybrid_downloader.py,sha256=4SzOPEwBlSZVzUAWR3DyxMx2Tsx15YrpBvQS4it4Vps,8028
38
+ crawlo/downloader/playwright_downloader.py,sha256=Lnc7k5cXhVnURXSxgZFCYMJkBxLg5F_OE67rtf3G7Ig,16261
39
+ crawlo/downloader/selenium_downloader.py,sha256=B_0muNi-GQ_hgoYHcf7wgu01V68q7xKnSh-0kzlUiio,21036
40
+ crawlo/extension/__init__.py,sha256=Sg588p6UhyrwFNTiD2wqGW-i3xgLX6HlLuQPKT7mayE,1526
41
+ crawlo/extension/health_check.py,sha256=0GveZgUtFwjYEKlm3qbwIvCmb4FR0qrIKc8cEF1yQV8,5516
42
+ crawlo/extension/log_interval.py,sha256=VCIeNqXcWDnxj4m6l77cjqgRzV8LfsPMb22X0Xc1Vwc,2417
43
+ crawlo/extension/log_stats.py,sha256=Ssxz6R1YpWIj5WJvQ2cJ9F5oR7FUFdj-ITc9lV92SSU,2908
44
+ crawlo/extension/logging_extension.py,sha256=ET6VAu1J2qNMz4NnG1G3zQLRhbsvV7l6xRIuQLE6DaE,1626
45
+ crawlo/extension/memory_monitor.py,sha256=4aszl3C0GMQbqFhGZjZq5iQuXQR1sOz06VHjjEHgkyE,4290
46
+ crawlo/extension/performance_profiler.py,sha256=EPiNuXuPPDU0Jtgy8arYHpr_8ASK13cCI2BytdJnu_I,4899
47
+ crawlo/extension/request_recorder.py,sha256=RC23yzXClnVv9j2ljQvjBkUfWznfnDHsrQejKhE9y5E,4074
48
+ crawlo/filters/__init__.py,sha256=XC_Q4ykZtSNYizYlAcehVwBBNO3lZ2zuWwafzXiuWyQ,4241
49
+ crawlo/filters/aioredis_filter.py,sha256=E8BBvzGJfiLuwEZrlfI3O-jANudizT9xcFWrxxFHpgk,10028
50
+ crawlo/filters/memory_filter.py,sha256=VJO0UFRYGxmV8dj4G1subsQ-FtvPcGLbvd7IVtqXnOs,9260
51
+ crawlo/items/__init__.py,sha256=bqekZrRlDhxfWie0UbCs656TptYseoe9QJ67I4E7Elk,386
52
+ crawlo/items/base.py,sha256=tAYrPJgblp3ZEihDXvappdYc6pGdim6x2_9QSmMKI2o,577
53
+ crawlo/items/fields.py,sha256=jCG0-PS8mVO48lP_ioTZCQCa0vjP5Sfv-sAyvYQqr-s,1800
54
+ crawlo/items/items.py,sha256=e-3nXI9ckD64vcDxxQiAU6ufbtJMs09gbZQcYjxgwHY,3374
55
+ crawlo/middleware/__init__.py,sha256=ldaGFNbiJnK9Fx12Vdf9fDNfzXxoETtShp5r-vodtw0,549
56
+ crawlo/middleware/default_header.py,sha256=wetlmUcT1gUso3O9NXY7b6-zfzwkIFaT7F3fXFnEr0k,5217
57
+ crawlo/middleware/download_delay.py,sha256=zt9R5g2HWErWA_MAOnGcw_D8l6HD769Kyaw-Hv-vcTc,3438
58
+ crawlo/middleware/middleware_manager.py,sha256=j1hkWRFB5rnC5SnB7oXWE5eUNv8blS9krDIDM5fIDs8,6213
59
+ crawlo/middleware/offsite.py,sha256=b3BMwNKGR41YGJGHt1S0H7yXujEkztVvonUQGO05hoM,4026
60
+ crawlo/middleware/proxy.py,sha256=JjXQsXqNK-VAR5_TBx7tcD9NpzIP2n1y57HyYjgBSzg,15239
61
+ crawlo/middleware/request_ignore.py,sha256=xcyZ1c7r_HhbzR3r9pfjsLGW7L7FBVeYvlNt8cpP2wY,2577
62
+ crawlo/middleware/response_code.py,sha256=-Aa9Mm9nJN-WdddN7iTanJRMA83_LYYgSEz3XLQGvMo,4934
63
+ crawlo/middleware/response_filter.py,sha256=6VBUe04mu8C7XxmOak6XyhGMWZPYEm3AMo5Kt_r1SXY,4248
64
+ crawlo/middleware/retry.py,sha256=HxeIf7DibeLCpZ_y4rNARWMyzlrsdq5UR2CaFZInA3s,4124
65
+ crawlo/network/__init__.py,sha256=BLPERYPo22g1BXrW--wUnlolrdFUmOPjgOB8XQQJlck,397
66
+ crawlo/network/request.py,sha256=63aBgH6H3ZZakBt6b_c-HUKE-c70AHxhggNOzmxjA2g,12295
67
+ crawlo/network/response.py,sha256=EZiG4LjuIb7PxdGou4H-oSOQhec1ZdBRTkO-5fl8JTo,12701
68
+ crawlo/pipelines/__init__.py,sha256=lrdVDjeHLNkA4_MAwI1auk_I9xfeU1SlBWXiammb6lc,616
69
+ crawlo/pipelines/bloom_dedup_pipeline.py,sha256=QQxGFGEoMHN4Vx2kq7G_i1o9pmuXp8clZebilOar3fk,5642
70
+ crawlo/pipelines/console_pipeline.py,sha256=KABkR3J-rqO0Awox7lizxKR2XuHfVhWPiVRgIybwwu4,1248
71
+ crawlo/pipelines/csv_pipeline.py,sha256=6FBT2AoU6iNU-5NfgWRq7-JpF9dK2nBokjxx-y4jIas,12174
72
+ crawlo/pipelines/database_dedup_pipeline.py,sha256=TOCT-1fUnaR9YWt71Njwm-6OdvgRlvcnsfTbHU83h5I,7960
73
+ crawlo/pipelines/json_pipeline.py,sha256=vlu1nqbD2mtqtExt9cL5nibx1CwJM1RNqd4WGjZRHAY,8367
74
+ crawlo/pipelines/memory_dedup_pipeline.py,sha256=o6XIjaih4jsfd7997M2n_qyDA9rbWwevAFc-MPQKJlA,3828
75
+ crawlo/pipelines/mongo_pipeline.py,sha256=k7gNqAO-g2MtIfArphC6z5ZzkKVRkBKcv-2ImziPFA0,5706
76
+ crawlo/pipelines/mysql_pipeline.py,sha256=G2DMhdh0ihBBolIul4YVTDz2JbrZGJauDtWF-gqRW0w,13473
77
+ crawlo/pipelines/pipeline_manager.py,sha256=vK87pAEmpGR24yl6Cr7ovCKag2oB5mruijfYT8nnG5o,2358
78
+ crawlo/pipelines/redis_dedup_pipeline.py,sha256=QCHybXm7E-AoqeIaI1ZoFJIoeOB9B6DDlShxpgTyaFg,6164
79
+ crawlo/queue/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
80
+ crawlo/queue/pqueue.py,sha256=yzF900ko2RReVNZtfk_VV3PzSXEUALI6SHf97geuu6s,1058
81
+ crawlo/queue/queue_manager.py,sha256=_oO5Taqj5WTSKtj9UuLrGZcWxMg2liqaa-kceXyF4GI,12874
82
+ crawlo/queue/redis_priority_queue.py,sha256=RbwKsVxzk31B1VRvyve4vHKe2DesL7K37IZAA31kdd0,12783
83
+ crawlo/settings/__init__.py,sha256=xsukVKn_h2Hopm1Nj-bXkhbfyS62QTTvJi7fhZUwR9M,123
84
+ crawlo/settings/default_settings.py,sha256=FnytMOyx4bpzfLkdbppBTkkKn12bxYuWBShVMnXF7RE,8875
85
+ crawlo/settings/setting_manager.py,sha256=0RYAk07qoJ5WTw_mvV4ECWGS2QNpCnGmBZVTHjqOVIg,3707
86
+ crawlo/spider/__init__.py,sha256=Z_rK23l5yt-DuwJPg8bcqodM_FIs4-iHLaKOimGumcE,20452
87
+ crawlo/templates/crawlo.cfg.tmpl,sha256=9BAmwEibS5Tvy6HIcGXPb0BGeuesmibebmTW0iAEkmo,230
88
+ crawlo/templates/run.py.tmpl,sha256=v_g-LQMYJ6pC8TZgyWj0yB2yTTKrwy9lEJufAYCXyxY,1228
89
+ crawlo/templates/project/__init__.py.tmpl,sha256=f3ETIXw_O6K-lkL6lXM5znMPJW1FZYGFrwDs2BnHcnQ,58
90
+ crawlo/templates/project/items.py.tmpl,sha256=mt1Mm--H2Ouos3r7JPkYh0r33rgYJf1YOMz0OZy8TYs,297
91
+ crawlo/templates/project/middlewares.py.tmpl,sha256=T67p8j0laL4NJJ_3xzPM9yivgZRjTEMiEtEWLPwbkmw,4160
92
+ crawlo/templates/project/pipelines.py.tmpl,sha256=GBHYU0Jx8sKDCdGJp44FMSH7u2slxoFg6a-R9Uwg_-I,2608
93
+ crawlo/templates/project/settings.py.tmpl,sha256=DFXWWMo88KQyvg-VVEURyEfEd5EEpAdTrehbUaK0FEM,12661
94
+ crawlo/templates/project/settings_distributed.py.tmpl,sha256=wqrQjQuydhnP8O1xs-8g5txu42aV5YVC4QHVhvpc1-c,5691
95
+ crawlo/templates/project/settings_gentle.py.tmpl,sha256=7UTZe8JqA1SUKozlxiGjxgWsakzIhKAtPvU7EfB28wQ,4759
96
+ crawlo/templates/project/settings_high_performance.py.tmpl,sha256=LzswtNUV6Iw0ewWfnM2FXt2aHNJtUOceXSrg8HBy2mY,5264
97
+ crawlo/templates/project/settings_simple.py.tmpl,sha256=ifn0VhDv8ZGcsahdzhHol18ATwUoq-B2lfbFeJk-ISk,3760
98
+ crawlo/templates/project/spiders/__init__.py.tmpl,sha256=j_YKsw6HQMJyqlk3WUouP3bsr-XVxshRoSNakHBc00g,106
99
+ crawlo/templates/spider/spider.py.tmpl,sha256=jMhzyxpIpV_KigB-pmN-5mGMiYtu4mfQIOvpZcCGGJI,5055
100
+ crawlo/tools/__init__.py,sha256=5H6rAhjfNSqRMjjlLDVq-vEJWRFyCO-J6HN2kexnXJU,3671
101
+ crawlo/tools/anti_crawler.py,sha256=MU6KEPT0q85e_-Px8Rmw1fxdwlmOdpXfo0KYVpPlivU,9163
102
+ crawlo/tools/authenticated_proxy.py,sha256=L93WeXajIZ3si8xNcE7bBPv34FvqSyTvVfD78fJAKQE,7032
103
+ crawlo/tools/data_validator.py,sha256=hxPN28YtJDFFLjBBYhDjHmR8ShNTEjgIsv-cmcDKIu8,5310
104
+ crawlo/tools/date_tools.py,sha256=icbx6x08t-Aj8j0jAB-93hDdSpBV9Rd-aaNt4UpyjNA,600
105
+ crawlo/tools/distributed_coordinator.py,sha256=ZN-zYsDPw0JWSBF7oHqL2vpUDgRElkDTVW7TcY1ArcI,12477
106
+ crawlo/tools/retry_mechanism.py,sha256=27iIuLCg1ZHjog6Gcr7dz0APkeTZ5cIlcnZ0pF18ZVA,7801
107
+ crawlo/tools/scenario_adapter.py,sha256=JouFxI3513PRe1ObwHWc72vBvptNpNv0Ew3pRaEKjQQ,9398
108
+ crawlo/utils/__init__.py,sha256=OVjs7qjyd7sn1vrh4MWykO4sMsAPLIWkq-74dQ2Pzak,557
109
+ crawlo/utils/batch_processor.py,sha256=_J-dKj98csB9LdhTBHh_dKvV4OzHiP22-5OWxavDglQ,8883
110
+ crawlo/utils/controlled_spider_mixin.py,sha256=Re-9ASOUFPUyg5xfBZlTGYlEQi8t9UEH0jMI7WdlLho,16470
111
+ crawlo/utils/date_tools.py,sha256=6zNU23vQ8p3-xHknlIp5airCLOREETaqw4YElyMO_lQ,8907
112
+ crawlo/utils/db_helper.py,sha256=3ib5-agrlwf2t5S_QtLRYH75wvJDlYbRqRmDEbpH5Bo,10559
113
+ crawlo/utils/enhanced_error_handler.py,sha256=hj5AElt3ajfqnP4csQnEfEnzkbIep9k65DNQiCbmTFo,13858
114
+ crawlo/utils/env_config.py,sha256=T1TXO8iyrtMWK1H9legSmjOA6ybXKGp5o735gGEK4ao,2852
115
+ crawlo/utils/error_handler.py,sha256=q6NqHxjYrKdswfmhshMYMmfBIr0M2YWPYxts4ScHl4Y,4244
116
+ crawlo/utils/func_tools.py,sha256=WUZEGpWMuDDX7g-QySM7iaiC74erW2SSkZoUvDw1NjM,2369
117
+ crawlo/utils/large_scale_config.py,sha256=j7wQ5ty7pQlBRygw2vhRJ7OI19RYBZKPfYMP3WeF2WI,8154
118
+ crawlo/utils/large_scale_helper.py,sha256=HpcoyBTu8SZnQnS_F3dAL8WpQX5Xahe50H0ORtHX4e8,12133
119
+ crawlo/utils/log.py,sha256=A3lPyhD8kD88cV23KOL-_eT8g69xGQ5L1toDB2AO0mc,4005
120
+ crawlo/utils/performance_monitor.py,sha256=5B8d0Pjy8K2z_Gh6zhBdC-Hl6ldy55MDro30-wnE2mw,9576
121
+ crawlo/utils/queue_helper.py,sha256=xpUUTOqlU1xz2Pb9NKAVGo3AfAO-7Xvx8Lm1q65Dgck,4743
122
+ crawlo/utils/redis_connection_pool.py,sha256=_wHEpC0hhEftN51z4F5z11sdvMjCP8VBysk9t4PoRxI,10310
123
+ crawlo/utils/redis_key_validator.py,sha256=-efQ44FaxrQdhbN3xT23M7O7a6L3IayumObNH3A_Nuc,5627
124
+ crawlo/utils/request.py,sha256=yoLB2rY8d78vgPjIWpdhY5SalIKjyLIvTG_UH6EMdVI,8798
125
+ crawlo/utils/request_serializer.py,sha256=oCGsLC_-Do7EuIREMQE01gINRtM0cC9X2JbW6ykkV74,8536
126
+ crawlo/utils/spider_loader.py,sha256=WK9gL99sOeIrFC-a0Y10lygtryQR7-wfdGks-uwMYTM,2172
127
+ crawlo/utils/system.py,sha256=HvWV1acxou0Rn0L7pNq4CnV_GWFeU0Tmjy3_nLD8M64,237
128
+ crawlo/utils/tools.py,sha256=5Uv25Wy4m_ndZY0-n-eX-t3PxvaZ6wR3-Wvx-o7_Vrs,271
129
+ crawlo/utils/url.py,sha256=rlgX2VlJv6JvLmCDTsbxzMSXE6R5ZL_0dLEqprsA-JU,1482
130
+ examples/__init__.py,sha256=6i631BPnS_TR_BWUjtjB5CBO-zv9kRkwQTQvSya2wHE,123
131
+ tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md,sha256=HjMZv6RjN1o5D1mfgEydP8Mcc9T_4ScR6lG3xVxs8P8,3346
132
+ tests/__init__.py,sha256=scL1IPVT1iucth7v8ffrjRdeW7QrC_Y7AMmFVMdTY1Y,129
133
+ tests/advanced_tools_example.py,sha256=7nlFLRVMVYzDz_CAdgQa9fJu7o0M6jBMo7PTvUsRbo0,9065
134
+ tests/authenticated_proxy_example.py,sha256=8I8bxAIeYDdsh5JoGIK1nxaKEpIdOFnCtufVLjpuq_o,8241
135
+ tests/cleaners_example.py,sha256=i90lrmno16qSq_qjc6WOVOw1Mx4_vzoBgVeqJYC7Vro,5170
136
+ tests/config_validation_demo.py,sha256=iPe_BWBTa-gRvRrnYYkkRDqyKqLzAhSCoWB_yFSkhrg,3116
137
+ tests/controlled_spider_example.py,sha256=SP_k4mdKPvD1JCPs9UCm68jcy2Frg84vvXv9-14RC6I,7776
138
+ tests/date_tools_example.py,sha256=x_-duqnVZ-Hrk-SaNplIfcIV6W3c6u6MTxW35u1i0F0,4862
139
+ tests/dynamic_loading_example.py,sha256=NI0SCg4lPME0RCcNpDDw1HjErjmCgJntCN0ahAEw61g,18263
140
+ tests/dynamic_loading_test.py,sha256=DYbMrEewerx0VGXixci3p9VYgDDQvCPevA92CNjq1Jo,3309
141
+ tests/env_config_example.py,sha256=sKE8DvMBhM3uy439LpgLHd4wF7MGUrUc-X6E7g9qsz0,4818
142
+ tests/error_handling_example.py,sha256=219H1dOm6TZaQ0tmd1zXZlo0ODcwQSBL7m4jZmCFoCo,5161
143
+ tests/redis_key_validation_demo.py,sha256=z1R7ZW6oiG3T0mSZJfP6FRqp4IsOjgbCPxvPuEL7z0I,4345
144
+ tests/response_improvements_example.py,sha256=wnYGJO6MKj5_jbwKLDlbXu_Dli5XC7vlWdzByi82_5Y,5258
145
+ tests/test_advanced_tools.py,sha256=3R8EfKVyBHEb6FA5TP3ieaWeHZhobVgSx8t3phipCrE,5250
146
+ tests/test_all_redis_key_configs.py,sha256=uMLlgtJ7tglzFO_Xbnwol723Lu6bjyIeHaLHtemphaQ,5660
147
+ tests/test_authenticated_proxy.py,sha256=s4pr5JyBTHYQgRq_IymiVKE08vyW1MwR27pSwrrVLVk,4198
148
+ tests/test_cleaners.py,sha256=7KRAjqXF7lWXe-9Hj_5CSFlbRJ6SB7XyMNuMXx36Jmg,1765
149
+ tests/test_comprehensive.py,sha256=kGNcJ9UkQxysYqvsBu0YxAaPleOvN9_hztLy7ljkfc4,5036
150
+ tests/test_config_validator.py,sha256=eZCnZyh34rpbYbzXMWvQkLNl7gu7_Js0fE7iFatXyB4,6632
151
+ tests/test_crawlo_proxy_integration.py,sha256=pfMui3QGgEyq9CIigX3MT2Ezk414MMRLcYXN3j2LALc,5404
152
+ tests/test_date_tools.py,sha256=CQdAmIS6bpAdwQH9ETDH__06l2gGL7EHUQuh7mdTF-A,3930
153
+ tests/test_default_header_middleware.py,sha256=7kpONSsGMsmWgTX2pCpseme54_-82Baak0xVz6gclJk,5845
154
+ tests/test_double_crawlo_fix.py,sha256=t7EZsKIfE49ZL3FM0bu1AZ1hOMygwALUN5UtqDGtLUs,7826
155
+ tests/test_double_crawlo_fix_simple.py,sha256=0OPbW8c71n_oB7pt10rRZi-W9eFCO_JOKTquWdIgTUU,4683
156
+ tests/test_download_delay_middleware.py,sha256=Va79gsH_8BVrVVLA8gSwFEbrRJ7qwJMCC1cDJN6il_0,8886
157
+ tests/test_downloader_proxy_compatibility.py,sha256=s3EBAk4J13VgpSXpksU__PMVUgaANuKSmibtSpQUZ3s,8647
158
+ tests/test_dynamic_downloaders_proxy.py,sha256=PtEW-pnVijeX2yX34UcoXYEY23yTBxb-kyNYh-WDljQ,4326
159
+ tests/test_dynamic_proxy.py,sha256=YL2sghNKG7k27-SaHMh4boNLVBHhfSttUwUqiSsOEX4,3080
160
+ tests/test_dynamic_proxy_config.py,sha256=uYXZ804ULI9qYMF-uNjMbi3L_NGzoMqLJcEZAl7aZ2I,5707
161
+ tests/test_dynamic_proxy_real.py,sha256=DTjP8JnSwBnNZ3Ls1BjDAmt6xSuye_6CxwZ4LBisPTM,3402
162
+ tests/test_edge_cases.py,sha256=fFRL3-ChBylg4e-73L9ZSc3u72dPmSfg3jpAg_6GOGA,10553
163
+ tests/test_enhanced_error_handler.py,sha256=E6HHzqGA6U9frzQvy0iVqFHi6LvRJobRwkFWk37tA10,8435
164
+ tests/test_env_config.py,sha256=nfP4nCG9ZHeJUfxo1JKUmiihYbhSeWx_oNW5mMfDHfQ,4746
165
+ tests/test_error_handler_compatibility.py,sha256=o5JLLLdo25Sl_3hpMx6I2fqSgZFAcnI4E6Ci-KxAxwA,4129
166
+ tests/test_final_validation.py,sha256=fBxf_6YcAEa_HyV_oGAXmmVHY4i6FdA4J6klCmc36hQ,4925
167
+ tests/test_framework_env_usage.py,sha256=HYpTwORXeaJHMffCYAGHGvc_a6ax4lo28xP8BYOaKxk,4098
168
+ tests/test_integration.py,sha256=8Bky_n5fbJDbb2pbKqc6IwJgpV0B9iau84C-PwcbsLA,11321
169
+ tests/test_item_dedup_redis_key.py,sha256=GOmmJ7hdTV_2XifRa_PQDrQpBt7Rnt3ViYNjNpflGgw,3755
170
+ tests/test_offsite_middleware.py,sha256=L5YT9ZqcQwBunUv0Ddj-sLZcW4IMlAlgaJCwICHFWxI,7543
171
+ tests/test_parsel.py,sha256=KYskaN_4HBc1XDTltjVo12v1i7JAThB2UIwcWZ-mwbY,672
172
+ tests/test_performance.py,sha256=heeFoS3R9n_t7ri0MyUL8kE0FY9sYJiC7BSQNI2C5HQ,11286
173
+ tests/test_proxy_api.py,sha256=vzDzwhzINSSD1S73ESTpszfPQt1spzY0tKgxtFD_A4w,10765
174
+ tests/test_proxy_health_check.py,sha256=xo3QMP1YNw9hu7JDHZOYCUZmFFKLJpHSh4SbxXhCRPQ,1091
175
+ tests/test_proxy_middleware.py,sha256=qm2B0lepBZqzUpXNi4t1gjrQxUV4MQ2wvpmcaYV6O5A,3900
176
+ tests/test_proxy_middleware_enhanced.py,sha256=YQRZs4bniU2CR-eKRc-sS4zZ6cjdSHwijUWL0T4Tq1w,6819
177
+ tests/test_proxy_middleware_integration.py,sha256=zcl7fR9Toc-I-stSUTzKZPwcfh3kgrpjI5SbkZ6AVmE,4305
178
+ tests/test_proxy_providers.py,sha256=XwWZCywTYguSsUxSm6fsbaoH1p9dKjqSIx9-sqKZehA,1693
179
+ tests/test_proxy_stats.py,sha256=Til_yksrRz2yBVw-yJi5-36LhNW3vTwpXTm4BdR9PUM,507
180
+ tests/test_proxy_strategies.py,sha256=ZkziozkvZd3KWOQnpHQ8Upd3WpyoX7gN0qFGluNm348,1809
181
+ tests/test_queue_manager_double_crawlo.py,sha256=pdoWUFgjfiPGCsuCypUaxMzicXPQnKpZqVh1o4LuaSM,6822
182
+ tests/test_queue_manager_redis_key.py,sha256=-dnqs2p50zpf09-Z7vo74s8hLQ6cxXd8WCdHM0l17qM,6278
183
+ tests/test_real_scenario_proxy.py,sha256=TrReMTPQwysEYh7406U1BX5QJd5z2M82vSjx4TT2q6s,8295
184
+ tests/test_redis_config.py,sha256=TqzFRojc6esGXjGhUCvSLYQDUTAgEJsty9vRVuNraMU,893
185
+ tests/test_redis_connection_pool.py,sha256=ORBU0k-6htQ2VVfyQkqTKVLGQWX04XRxdEGsZKeerQA,9177
186
+ tests/test_redis_key_naming.py,sha256=ojHhBED2DEf0VzqQgtzefygSn6hZiBhPFyVUBs_4rdI,6776
187
+ tests/test_redis_key_validator.py,sha256=kud0AhnS_6NP9s8G5HB5L9rob5rv2W6WLy6ypHYQDbk,4304
188
+ tests/test_redis_queue.py,sha256=o6xViXxJcdx-1eMcG3vhAQEIm8h346HnZb7JXs7ZjwM,6622
189
+ tests/test_request_ignore_middleware.py,sha256=8_2E6JU27eOWI3iHeh3YscLnp3SIHaubWdA477Ki6PE,6047
190
+ tests/test_request_serialization.py,sha256=8sVdppAsohJ5u-m1WvablCndwL-M_36YPLdGKwgeznM,2289
191
+ tests/test_response_code_middleware.py,sha256=EAPHsNN3J4ShJ5UfpzcZpOPjDvYgYJgcpNxpRgpQBaE,11844
192
+ tests/test_response_filter_middleware.py,sha256=yVXl7LYxKxziGQg-YpdbVc6CVhmfmNOAZ86SaEVfMyI,15900
193
+ tests/test_response_improvements.py,sha256=zvbkTkWhgdlFYtRu_ckgq6wGDGwpe_PTECYqpLDM3BU,5876
194
+ tests/test_retry_middleware.py,sha256=g7QPDDLaX7hu3jqlWbDsjfuCbQXisTvs7YrcMLmn1Hw,7856
195
+ tests/test_scheduler.py,sha256=-FOkTWzaMdr6yfO1Msu74hI_GgSfD7iRxO-cFA-9Iyk,7442
196
+ tests/test_simple_response.py,sha256=6RYOBRzAtyNvJ9a5JVTNubM-rvxnuX8jQOvq3sUZxwo,1488
197
+ tests/test_telecom_spider_redis_key.py,sha256=R581J-kvjh4CpDCCIZKPnV0vY6MvtkvTzmSIbwhXSXs,7470
198
+ tests/test_template_content.py,sha256=5QAnhKZFDKg-_uFryllLMpCk3a1nCS44hMmYfXm8gWk,2878
199
+ tests/test_template_redis_key.py,sha256=U6L5HtnDyGp3s6-O4F_yG2Q2nNIGTqB_Q-ESv2EMeOU,4812
200
+ tests/test_tools.py,sha256=IWiu9JGV-5Ow0ivFtiDw62REht-8Hn7NfyR9rnYSlbU,5113
201
+ tests/tools_example.py,sha256=MfVBYemKvHs6MUbydgrJfhiGnygp5dRoIE-eIXCOR7M,7669
202
+ crawlo-1.2.5.dist-info/METADATA,sha256=NPGU5IbQFGu8iNyapjE3faSy_A84yHeI9gzjuGv1PbE,19185
203
+ crawlo-1.2.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
204
+ crawlo-1.2.5.dist-info/entry_points.txt,sha256=5HoVoTSPxI8SCa5B7pQYxLSrkOdiunyO9tqNsLMv52g,43
205
+ crawlo-1.2.5.dist-info/top_level.txt,sha256=keG_67pbZ_wZL2dmDRA9RMaNHTaV_x_oxZ9DKNgwvR0,22
206
+ crawlo-1.2.5.dist-info/RECORD,,
examples/__init__.py CHANGED
@@ -1,7 +1,7 @@
1
- #!/usr/bin/python
2
- # -*- coding:UTF-8 -*-
3
- """
4
- # @Time : 2025-02-05 12:36
5
- # @Author : oscar
6
- # @Desc : None
7
- """
1
+ #!/usr/bin/python
2
+ # -*- coding:UTF-8 -*-
3
+ """
4
+ # @Time : 2025-02-05 12:36
5
+ # @Author : oscar
6
+ # @Desc : None
7
+ """
@@ -1,82 +1,82 @@
1
- # 双重 crawlo 前缀问题修复报告
2
-
3
- ## 问题描述
4
- 用户在使用分布式爬虫时发现Redis key中出现了双重`crawlo`前缀,例如`crawlo:crawlo:queue:processing:data`。这导致了Redis key命名不一致和潜在的混淆问题。
5
-
6
- ## 问题分析
7
- 经过代码分析,发现问题出在以下两个方面:
8
- 1. RedisPriorityQueue类在处理队列名称时会自动修改用户提供的队列名称
9
- 2. QueueManager类在提取项目名称时没有正确处理双重`crawlo`前缀的情况
10
-
11
- ## 修复方案
12
-
13
- ### 1. RedisPriorityQueue类修复
14
- 文件:`crawlo/queue/redis_priority_queue.py`
15
-
16
- **修复前**:
17
- ```python
18
- # 如果提供了 queue_name,确保符合命名规范
19
- # 处理可能的重复前缀问题
20
- if queue_name.startswith("crawlo:crawlo:"):
21
- # 修复双重 crawlo 前缀
22
- self.queue_name = queue_name.replace("crawlo:crawlo:", "crawlo:", 1)
23
- elif not queue_name.startswith("crawlo:"):
24
- # 如果没有 crawlo 前缀,添加它
25
- self.queue_name = f"crawlo:{module_name}:queue:requests"
26
- else:
27
- # 已经有正确的 crawlo 前缀
28
- self.queue_name = queue_name
29
- ```
30
-
31
- **修复后**:
32
- ```python
33
- # 保持用户提供的队列名称不变,不做修改
34
- self.queue_name = queue_name
35
- ```
36
-
37
- ### 2. QueueManager类修复
38
- 文件:`crawlo/queue/queue_manager.py`
39
-
40
- **修复后**:
41
- ```python
42
- # 处理可能的双重 crawlo 前缀
43
- if parts[0] == "crawlo" and parts[1] == "crawlo":
44
- # 双重 crawlo 前缀,取第三个部分作为项目名称
45
- if len(parts) >= 3:
46
- project_name = parts[2]
47
- else:
48
- project_name = "default"
49
- elif parts[0] == "crawlo":
50
- # 正常的 crawlo 前缀,取第二个部分作为项目名称
51
- project_name = parts[1]
52
- else:
53
- # 没有 crawlo 前缀,使用第一个部分作为项目名称
54
- project_name = parts[0]
55
- ```
56
-
57
- ## 测试验证
58
-
59
- ### 测试1:Redis队列命名修复测试
60
- 验证RedisPriorityQueue正确处理各种队列名称格式:
61
- - 正常命名:`crawlo:test_project:queue:requests` → `crawlo:test_project:queue:requests`
62
- - 双重 crawlo 前缀:`crawlo:crawlo:queue:requests` → `crawlo:crawlo:queue:requests`
63
- - 三重 crawlo 前缀:`crawlo:crawlo:crawlo:queue:requests` → `crawlo:crawlo:crawlo:queue:requests`
64
-
65
- ### 测试2:队列管理器项目名称提取测试
66
- 验证QueueManager正确提取项目名称:
67
- - 正常命名:`crawlo:test_project:queue:requests` → `test_project`
68
- - 双重 crawlo 前缀:`crawlo:crawlo:queue:requests` → [queue](file://d:\dowell\projects\Crawlo\crawlo\core\processor.py#L13-L13)
69
- - 三重 crawlo 前缀:`crawlo:crawlo:crawlo:queue:requests` → `crawlo`
70
-
71
- ### 测试3:队列管理器创建队列测试
72
- 验证整个流程的正确性,确保队列名称在传递过程中保持一致。
73
-
74
- 所有测试均已通过,表明双重`crawlo`前缀问题已得到解决。
75
-
76
- ## 结论
77
- 通过以上修复,我们成功解决了Redis key中出现双重`crawlo`前缀的问题。现在Redis队列名称将保持用户配置的一致性,processing和failed队列也会相应地保持相同的前缀结构。
78
-
79
- ## 建议
80
- 1. 建议用户在项目配置中使用标准的队列名称格式,如`crawlo:{project_name}:queue:requests`
81
- 2. 可以使用Redis key验证工具定期检查和规范Redis key命名
1
+ # 双重 crawlo 前缀问题修复报告
2
+
3
+ ## 问题描述
4
+ 用户在使用分布式爬虫时发现Redis key中出现了双重`crawlo`前缀,例如`crawlo:crawlo:queue:processing:data`。这导致了Redis key命名不一致和潜在的混淆问题。
5
+
6
+ ## 问题分析
7
+ 经过代码分析,发现问题出在以下两个方面:
8
+ 1. RedisPriorityQueue类在处理队列名称时会自动修改用户提供的队列名称
9
+ 2. QueueManager类在提取项目名称时没有正确处理双重`crawlo`前缀的情况
10
+
11
+ ## 修复方案
12
+
13
+ ### 1. RedisPriorityQueue类修复
14
+ 文件:`crawlo/queue/redis_priority_queue.py`
15
+
16
+ **修复前**:
17
+ ```python
18
+ # 如果提供了 queue_name,确保符合命名规范
19
+ # 处理可能的重复前缀问题
20
+ if queue_name.startswith("crawlo:crawlo:"):
21
+ # 修复双重 crawlo 前缀
22
+ self.queue_name = queue_name.replace("crawlo:crawlo:", "crawlo:", 1)
23
+ elif not queue_name.startswith("crawlo:"):
24
+ # 如果没有 crawlo 前缀,添加它
25
+ self.queue_name = f"crawlo:{module_name}:queue:requests"
26
+ else:
27
+ # 已经有正确的 crawlo 前缀
28
+ self.queue_name = queue_name
29
+ ```
30
+
31
+ **修复后**:
32
+ ```python
33
+ # 保持用户提供的队列名称不变,不做修改
34
+ self.queue_name = queue_name
35
+ ```
36
+
37
+ ### 2. QueueManager类修复
38
+ 文件:`crawlo/queue/queue_manager.py`
39
+
40
+ **修复后**:
41
+ ```python
42
+ # 处理可能的双重 crawlo 前缀
43
+ if parts[0] == "crawlo" and parts[1] == "crawlo":
44
+ # 双重 crawlo 前缀,取第三个部分作为项目名称
45
+ if len(parts) >= 3:
46
+ project_name = parts[2]
47
+ else:
48
+ project_name = "default"
49
+ elif parts[0] == "crawlo":
50
+ # 正常的 crawlo 前缀,取第二个部分作为项目名称
51
+ project_name = parts[1]
52
+ else:
53
+ # 没有 crawlo 前缀,使用第一个部分作为项目名称
54
+ project_name = parts[0]
55
+ ```
56
+
57
+ ## 测试验证
58
+
59
+ ### 测试1:Redis队列命名修复测试
60
+ 验证RedisPriorityQueue正确处理各种队列名称格式:
61
+ - 正常命名:`crawlo:test_project:queue:requests` → `crawlo:test_project:queue:requests`
62
+ - 双重 crawlo 前缀:`crawlo:crawlo:queue:requests` → `crawlo:crawlo:queue:requests`
63
+ - 三重 crawlo 前缀:`crawlo:crawlo:crawlo:queue:requests` → `crawlo:crawlo:crawlo:queue:requests`
64
+
65
+ ### 测试2:队列管理器项目名称提取测试
66
+ 验证QueueManager正确提取项目名称:
67
+ - 正常命名:`crawlo:test_project:queue:requests` → `test_project`
68
+ - 双重 crawlo 前缀:`crawlo:crawlo:queue:requests` → [queue](file://d:\dowell\projects\Crawlo\crawlo\core\processor.py#L13-L13)
69
+ - 三重 crawlo 前缀:`crawlo:crawlo:crawlo:queue:requests` → `crawlo`
70
+
71
+ ### 测试3:队列管理器创建队列测试
72
+ 验证整个流程的正确性,确保队列名称在传递过程中保持一致。
73
+
74
+ 所有测试均已通过,表明双重`crawlo`前缀问题已得到解决。
75
+
76
+ ## 结论
77
+ 通过以上修复,我们成功解决了Redis key中出现双重`crawlo`前缀的问题。现在Redis队列名称将保持用户配置的一致性,processing和failed队列也会相应地保持相同的前缀结构。
78
+
79
+ ## 建议
80
+ 1. 建议用户在项目配置中使用标准的队列名称格式,如`crawlo:{project_name}:queue:requests`
81
+ 2. 可以使用Redis key验证工具定期检查和规范Redis key命名
82
82
  3. 如果需要统一的命名规范,可以在项目初始化时明确指定队列名称
tests/__init__.py CHANGED
@@ -1,7 +1,7 @@
1
- #!/usr/bin/python
2
- # -*- coding:UTF-8 -*-
3
- """
4
- # @Time : 2025-08-24 12:36
5
- # @Author : crawl-coder
6
- # @Desc : None
7
- """
1
+ #!/usr/bin/python
2
+ # -*- coding:UTF-8 -*-
3
+ """
4
+ # @Time : 2025-08-24 12:36
5
+ # @Author : crawl-coder
6
+ # @Desc : None
7
+ """