crawlo 1.1.8__py3-none-any.whl → 1.1.9__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.
- crawlo/__init__.py +61 -61
- crawlo/__version__.py +1 -1
- crawlo/cleaners/__init__.py +60 -60
- crawlo/cleaners/data_formatter.py +225 -225
- crawlo/cleaners/encoding_converter.py +125 -125
- crawlo/cleaners/text_cleaner.py +232 -232
- crawlo/cli.py +65 -65
- crawlo/commands/__init__.py +14 -14
- crawlo/commands/check.py +594 -594
- crawlo/commands/genspider.py +151 -151
- crawlo/commands/help.py +132 -132
- crawlo/commands/list.py +155 -155
- crawlo/commands/run.py +292 -292
- crawlo/commands/startproject.py +418 -418
- crawlo/commands/stats.py +188 -188
- crawlo/commands/utils.py +186 -186
- crawlo/config.py +312 -312
- crawlo/config_validator.py +252 -252
- crawlo/core/__init__.py +2 -2
- crawlo/core/engine.py +345 -345
- crawlo/core/processor.py +40 -40
- crawlo/core/scheduler.py +136 -136
- crawlo/crawler.py +1027 -1027
- crawlo/downloader/__init__.py +266 -266
- crawlo/downloader/aiohttp_downloader.py +220 -220
- crawlo/downloader/cffi_downloader.py +256 -256
- crawlo/downloader/httpx_downloader.py +259 -259
- crawlo/downloader/hybrid_downloader.py +213 -213
- crawlo/downloader/playwright_downloader.py +402 -402
- crawlo/downloader/selenium_downloader.py +472 -472
- crawlo/event.py +11 -11
- crawlo/exceptions.py +81 -81
- crawlo/extension/__init__.py +37 -37
- crawlo/extension/health_check.py +141 -141
- crawlo/extension/log_interval.py +57 -57
- crawlo/extension/log_stats.py +81 -81
- crawlo/extension/logging_extension.py +43 -43
- crawlo/extension/memory_monitor.py +104 -104
- crawlo/extension/performance_profiler.py +133 -133
- crawlo/extension/request_recorder.py +107 -107
- crawlo/filters/__init__.py +154 -154
- crawlo/filters/aioredis_filter.py +280 -280
- crawlo/filters/memory_filter.py +269 -269
- crawlo/items/__init__.py +23 -23
- crawlo/items/base.py +21 -21
- crawlo/items/fields.py +53 -53
- crawlo/items/items.py +104 -104
- crawlo/middleware/__init__.py +21 -21
- crawlo/middleware/default_header.py +32 -32
- crawlo/middleware/download_delay.py +28 -28
- crawlo/middleware/middleware_manager.py +135 -135
- crawlo/middleware/proxy.py +272 -272
- crawlo/middleware/request_ignore.py +30 -30
- crawlo/middleware/response_code.py +18 -18
- crawlo/middleware/response_filter.py +26 -26
- crawlo/middleware/retry.py +124 -124
- crawlo/mode_manager.py +211 -211
- crawlo/network/__init__.py +21 -21
- crawlo/network/request.py +338 -338
- crawlo/network/response.py +359 -359
- crawlo/pipelines/__init__.py +21 -21
- crawlo/pipelines/bloom_dedup_pipeline.py +156 -156
- crawlo/pipelines/console_pipeline.py +39 -39
- crawlo/pipelines/csv_pipeline.py +316 -316
- crawlo/pipelines/database_dedup_pipeline.py +224 -224
- crawlo/pipelines/json_pipeline.py +218 -218
- crawlo/pipelines/memory_dedup_pipeline.py +115 -115
- crawlo/pipelines/mongo_pipeline.py +131 -131
- crawlo/pipelines/mysql_pipeline.py +316 -316
- crawlo/pipelines/pipeline_manager.py +61 -61
- crawlo/pipelines/redis_dedup_pipeline.py +167 -167
- crawlo/project.py +187 -187
- crawlo/queue/pqueue.py +37 -37
- crawlo/queue/queue_manager.py +334 -334
- crawlo/queue/redis_priority_queue.py +298 -298
- crawlo/settings/__init__.py +7 -7
- crawlo/settings/default_settings.py +219 -219
- crawlo/settings/setting_manager.py +122 -122
- crawlo/spider/__init__.py +639 -639
- crawlo/stats_collector.py +59 -59
- crawlo/subscriber.py +130 -130
- crawlo/task_manager.py +30 -30
- crawlo/templates/crawlo.cfg.tmpl +10 -10
- crawlo/templates/project/__init__.py.tmpl +3 -3
- crawlo/templates/project/items.py.tmpl +17 -17
- crawlo/templates/project/middlewares.py.tmpl +109 -109
- crawlo/templates/project/pipelines.py.tmpl +96 -96
- crawlo/templates/project/run.py.tmpl +45 -45
- crawlo/templates/project/settings.py.tmpl +326 -326
- crawlo/templates/project/settings_distributed.py.tmpl +119 -119
- crawlo/templates/project/settings_gentle.py.tmpl +94 -94
- crawlo/templates/project/settings_high_performance.py.tmpl +151 -151
- crawlo/templates/project/settings_simple.py.tmpl +68 -68
- crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
- crawlo/templates/spider/spider.py.tmpl +141 -141
- crawlo/tools/__init__.py +182 -182
- crawlo/tools/anti_crawler.py +268 -268
- crawlo/tools/authenticated_proxy.py +240 -240
- crawlo/tools/data_validator.py +180 -180
- crawlo/tools/date_tools.py +35 -35
- crawlo/tools/distributed_coordinator.py +386 -386
- crawlo/tools/retry_mechanism.py +220 -220
- crawlo/tools/scenario_adapter.py +262 -262
- crawlo/utils/__init__.py +35 -35
- crawlo/utils/batch_processor.py +260 -260
- crawlo/utils/controlled_spider_mixin.py +439 -439
- crawlo/utils/date_tools.py +290 -290
- crawlo/utils/db_helper.py +343 -343
- crawlo/utils/enhanced_error_handler.py +359 -359
- crawlo/utils/env_config.py +105 -105
- crawlo/utils/error_handler.py +125 -125
- crawlo/utils/func_tools.py +82 -82
- crawlo/utils/large_scale_config.py +286 -286
- crawlo/utils/large_scale_helper.py +343 -343
- crawlo/utils/log.py +128 -128
- crawlo/utils/performance_monitor.py +284 -284
- crawlo/utils/queue_helper.py +175 -175
- crawlo/utils/redis_connection_pool.py +334 -334
- crawlo/utils/redis_key_validator.py +199 -199
- crawlo/utils/request.py +267 -267
- crawlo/utils/request_serializer.py +219 -219
- crawlo/utils/spider_loader.py +62 -62
- crawlo/utils/system.py +11 -11
- crawlo/utils/tools.py +4 -4
- crawlo/utils/url.py +39 -39
- {crawlo-1.1.8.dist-info → crawlo-1.1.9.dist-info}/METADATA +626 -626
- crawlo-1.1.9.dist-info/RECORD +190 -0
- examples/__init__.py +7 -7
- tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
- tests/__init__.py +7 -7
- tests/advanced_tools_example.py +275 -275
- tests/authenticated_proxy_example.py +236 -236
- tests/cleaners_example.py +160 -160
- tests/config_validation_demo.py +102 -102
- tests/controlled_spider_example.py +205 -205
- tests/date_tools_example.py +180 -180
- tests/dynamic_loading_example.py +523 -523
- tests/dynamic_loading_test.py +104 -104
- tests/env_config_example.py +133 -133
- tests/error_handling_example.py +171 -171
- tests/redis_key_validation_demo.py +130 -130
- tests/response_improvements_example.py +144 -144
- tests/test_advanced_tools.py +148 -148
- tests/test_all_redis_key_configs.py +145 -145
- tests/test_authenticated_proxy.py +141 -141
- tests/test_cleaners.py +54 -54
- tests/test_comprehensive.py +146 -146
- tests/test_config_validator.py +193 -193
- tests/test_date_tools.py +123 -123
- tests/test_double_crawlo_fix.py +207 -207
- tests/test_double_crawlo_fix_simple.py +124 -124
- tests/test_dynamic_downloaders_proxy.py +124 -124
- tests/test_dynamic_proxy.py +92 -92
- tests/test_dynamic_proxy_config.py +146 -146
- tests/test_dynamic_proxy_real.py +109 -109
- tests/test_edge_cases.py +303 -303
- tests/test_enhanced_error_handler.py +270 -270
- tests/test_env_config.py +121 -121
- tests/test_error_handler_compatibility.py +112 -112
- tests/test_final_validation.py +153 -153
- tests/test_framework_env_usage.py +103 -103
- tests/test_integration.py +356 -356
- tests/test_item_dedup_redis_key.py +122 -122
- tests/test_parsel.py +29 -29
- tests/test_performance.py +327 -327
- tests/test_proxy_health_check.py +32 -32
- tests/test_proxy_middleware_integration.py +136 -136
- tests/test_proxy_providers.py +56 -56
- tests/test_proxy_stats.py +19 -19
- tests/test_proxy_strategies.py +59 -59
- tests/test_queue_manager_double_crawlo.py +230 -230
- tests/test_queue_manager_redis_key.py +176 -176
- tests/test_redis_config.py +28 -28
- tests/test_redis_connection_pool.py +294 -294
- tests/test_redis_key_naming.py +181 -181
- tests/test_redis_key_validator.py +123 -123
- tests/test_redis_queue.py +224 -224
- tests/test_request_serialization.py +70 -70
- tests/test_response_improvements.py +152 -152
- tests/test_scheduler.py +241 -241
- tests/test_simple_response.py +61 -61
- tests/test_telecom_spider_redis_key.py +205 -205
- tests/test_template_content.py +87 -87
- tests/test_template_redis_key.py +134 -134
- tests/test_tools.py +153 -153
- tests/tools_example.py +257 -257
- crawlo-1.1.8.dist-info/RECORD +0 -190
- {crawlo-1.1.8.dist-info → crawlo-1.1.9.dist-info}/WHEEL +0 -0
- {crawlo-1.1.8.dist-info → crawlo-1.1.9.dist-info}/entry_points.txt +0 -0
- {crawlo-1.1.8.dist-info → crawlo-1.1.9.dist-info}/top_level.txt +0 -0
|
@@ -0,0 +1,190 @@
|
|
|
1
|
+
crawlo/__init__.py,sha256=1tc6uUDF1yRNU7K_k-Dl6h9FGy7Jp8fdhRsXu9PctFI,1312
|
|
2
|
+
crawlo/__version__.py,sha256=lnHAM_YSOt5TvtAm4ZVs32T0TpsCQ5kOOznnQlur1YE,22
|
|
3
|
+
crawlo/cli.py,sha256=pbd9wR6evB4aHWNrTRG4WW2ScCN5p4kz44eAuohSdR0,2029
|
|
4
|
+
crawlo/config.py,sha256=cQTDYn2VCdlIs3Jb8mGwF6IWqj85BMr6HQaGS3XjZ7g,9535
|
|
5
|
+
crawlo/config_validator.py,sha256=Q2j9rGW2lZiaA1ka5cJWaabPr1W0fwYHzY_gv-qpPyY,9903
|
|
6
|
+
crawlo/crawler.py,sha256=Mjv4WrNduSTXv3hJuSynwEu-MyUhgx2TOMJ913LxkmY,36371
|
|
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=cLHwKW_iupFQ-uTgyl90SFhrYtbpVIdqevMXgPOJpWE,7517
|
|
10
|
+
crawlo/project.py,sha256=FDAwiucebeck5Ftuc7M8mFCRunAyUd49FtKcCAE7R4c,6644
|
|
11
|
+
crawlo/stats_collector.py,sha256=NkO09CB-220qz5rxFcD_dedGfr2VPFrDo4hya0Zh8Qc,1577
|
|
12
|
+
crawlo/subscriber.py,sha256=gioTIqRdEwVG-bwIiQonbk1vWWAqTh9hzVkrqZ1AfP0,5006
|
|
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=172OiAxnX5wwSlszUsyPgMZwAoIbGDTdfhtRz309ilc,22843
|
|
20
|
+
crawlo/commands/genspider.py,sha256=-jGJdfXLsefX_H1ydQ2wirdu6p6wmhClzVXY_0L-1aE,5050
|
|
21
|
+
crawlo/commands/help.py,sha256=EaU2v4A5cFFaUUG_HTp6Hby1p36777oK_OogGnrzBfI,4879
|
|
22
|
+
crawlo/commands/list.py,sha256=yByqQeZBgvjewOKxpnOobpeJ7Hnbs-CWsoyITqZu2ZY,5781
|
|
23
|
+
crawlo/commands/run.py,sha256=LL6P0eGgwCgMWLkGsTWjXDu6Vh74N8vq4m7-PUiNKWc,10751
|
|
24
|
+
crawlo/commands/startproject.py,sha256=aBBR5dNb7R-yEMVMisoKiEA86HUFB_yHa0VgPftDXko,15354
|
|
25
|
+
crawlo/commands/stats.py,sha256=6pAgkEi8MBnCer2rWmKpaTYr1jaM6HeMG9owAvEzJyY,6064
|
|
26
|
+
crawlo/commands/utils.py,sha256=nohMvUU2zLvX0XzXk6KeCNxP0EvSWj9DiVLxM_7tD5o,5106
|
|
27
|
+
crawlo/core/__init__.py,sha256=PnFyJdVNHBoPmV1sW0AHQXijeoSTQ8cMYrbNM1JK8kA,41
|
|
28
|
+
crawlo/core/engine.py,sha256=tWiQGAxK3bhwmq6xgg03gz-hyflGi5jPSI1ML2vrBgE,13139
|
|
29
|
+
crawlo/core/processor.py,sha256=qmCqAeqhwYu-UE86evYesaGt9qpuSIfH-ZIZKcXFCZc,1140
|
|
30
|
+
crawlo/core/scheduler.py,sha256=4RsGl9P0hmXB6crbOwfNr2RLiIUET1h5JFIVKtrqyD0,4953
|
|
31
|
+
crawlo/downloader/__init__.py,sha256=MlstaKfW-WLXNuZs7tb7cG_wG2sQLw2hdWmUjZEIH7c,8299
|
|
32
|
+
crawlo/downloader/aiohttp_downloader.py,sha256=n2qP3Q13lOnvwB7cb3YxNyNKYVHKqofNNg7j9tV9h-E,8400
|
|
33
|
+
crawlo/downloader/cffi_downloader.py,sha256=IpQUqvls4mEYs_UwPvtN2L4uUIujqn-rf03NuZZkMl0,10710
|
|
34
|
+
crawlo/downloader/httpx_downloader.py,sha256=7jfQfvAtfk8yD_mvwUbWLhYOxMM7r1nudiU7m_Jl9wc,12037
|
|
35
|
+
crawlo/downloader/hybrid_downloader.py,sha256=otiIQBJYmzDeY9dB4Qrlu9LSSdJOpZVVae-HnNKBXik,8043
|
|
36
|
+
crawlo/downloader/playwright_downloader.py,sha256=Lnc7k5cXhVnURXSxgZFCYMJkBxLg5F_OE67rtf3G7Ig,16261
|
|
37
|
+
crawlo/downloader/selenium_downloader.py,sha256=vykWifXoSSs61k8BB6PtcTDDBKp5uZ9-rYYFR4_pgSQ,21036
|
|
38
|
+
crawlo/extension/__init__.py,sha256=Sg588p6UhyrwFNTiD2wqGW-i3xgLX6HlLuQPKT7mayE,1526
|
|
39
|
+
crawlo/extension/health_check.py,sha256=IVaaVo_0CcZtf1LoCAYXIBvs3wZ7hdmT6U4-NYWAgP0,5527
|
|
40
|
+
crawlo/extension/log_interval.py,sha256=VCIeNqXcWDnxj4m6l77cjqgRzV8LfsPMb22X0Xc1Vwc,2417
|
|
41
|
+
crawlo/extension/log_stats.py,sha256=Ssxz6R1YpWIj5WJvQ2cJ9F5oR7FUFdj-ITc9lV92SSU,2908
|
|
42
|
+
crawlo/extension/logging_extension.py,sha256=ET6VAu1J2qNMz4NnG1G3zQLRhbsvV7l6xRIuQLE6DaE,1626
|
|
43
|
+
crawlo/extension/memory_monitor.py,sha256=4aszl3C0GMQbqFhGZjZq5iQuXQR1sOz06VHjjEHgkyE,4290
|
|
44
|
+
crawlo/extension/performance_profiler.py,sha256=EPiNuXuPPDU0Jtgy8arYHpr_8ASK13cCI2BytdJnu_I,4899
|
|
45
|
+
crawlo/extension/request_recorder.py,sha256=RC23yzXClnVv9j2ljQvjBkUfWznfnDHsrQejKhE9y5E,4074
|
|
46
|
+
crawlo/filters/__init__.py,sha256=XC_Q4ykZtSNYizYlAcehVwBBNO3lZ2zuWwafzXiuWyQ,4241
|
|
47
|
+
crawlo/filters/aioredis_filter.py,sha256=E8BBvzGJfiLuwEZrlfI3O-jANudizT9xcFWrxxFHpgk,10028
|
|
48
|
+
crawlo/filters/memory_filter.py,sha256=VJO0UFRYGxmV8dj4G1subsQ-FtvPcGLbvd7IVtqXnOs,9260
|
|
49
|
+
crawlo/items/__init__.py,sha256=bqekZrRlDhxfWie0UbCs656TptYseoe9QJ67I4E7Elk,386
|
|
50
|
+
crawlo/items/base.py,sha256=tAYrPJgblp3ZEihDXvappdYc6pGdim6x2_9QSmMKI2o,577
|
|
51
|
+
crawlo/items/fields.py,sha256=wMlakQTsEwyrlLzMt1gI4pScLQZMqd3E1xcfH4dbSqk,1801
|
|
52
|
+
crawlo/items/items.py,sha256=e-3nXI9ckD64vcDxxQiAU6ufbtJMs09gbZQcYjxgwHY,3374
|
|
53
|
+
crawlo/middleware/__init__.py,sha256=ldaGFNbiJnK9Fx12Vdf9fDNfzXxoETtShp5r-vodtw0,549
|
|
54
|
+
crawlo/middleware/default_header.py,sha256=i_Uj07JObyeZFxL7ZAZmvZsHvA1HGtkNab1sA0d-nWI,1067
|
|
55
|
+
crawlo/middleware/download_delay.py,sha256=2M-TchDA7MwyTfYy0Hzh_bW9wlHlpiP-oQlys7crTj0,966
|
|
56
|
+
crawlo/middleware/middleware_manager.py,sha256=j1hkWRFB5rnC5SnB7oXWE5eUNv8blS9krDIDM5fIDs8,6213
|
|
57
|
+
crawlo/middleware/proxy.py,sha256=qLPA9_iualWBdZhIRJJLlSZVMbwOophLEEpzS8yBG5M,11089
|
|
58
|
+
crawlo/middleware/request_ignore.py,sha256=QI2z4fUnJ-4xvPTZAmsL-GqR4RFHS1xq9iDr5KFrMco,997
|
|
59
|
+
crawlo/middleware/response_code.py,sha256=tmef2QVl3JCiTMii6VQkASlOY2OyqmOPoOfNxIK1eF8,659
|
|
60
|
+
crawlo/middleware/response_filter.py,sha256=ep8ZxDlfIefi9YqK8dPASEp5TTDRo9QEY_jMceC411s,837
|
|
61
|
+
crawlo/middleware/retry.py,sha256=-7zpRURugiTTm4QYUSUlbnURD5mcT2Ji0yHvCgY1wGc,4124
|
|
62
|
+
crawlo/network/__init__.py,sha256=BLPERYPo22g1BXrW--wUnlolrdFUmOPjgOB8XQQJlck,397
|
|
63
|
+
crawlo/network/request.py,sha256=63aBgH6H3ZZakBt6b_c-HUKE-c70AHxhggNOzmxjA2g,12295
|
|
64
|
+
crawlo/network/response.py,sha256=EZiG4LjuIb7PxdGou4H-oSOQhec1ZdBRTkO-5fl8JTo,12701
|
|
65
|
+
crawlo/pipelines/__init__.py,sha256=lrdVDjeHLNkA4_MAwI1auk_I9xfeU1SlBWXiammb6lc,616
|
|
66
|
+
crawlo/pipelines/bloom_dedup_pipeline.py,sha256=QQxGFGEoMHN4Vx2kq7G_i1o9pmuXp8clZebilOar3fk,5642
|
|
67
|
+
crawlo/pipelines/console_pipeline.py,sha256=KABkR3J-rqO0Awox7lizxKR2XuHfVhWPiVRgIybwwu4,1248
|
|
68
|
+
crawlo/pipelines/csv_pipeline.py,sha256=6FBT2AoU6iNU-5NfgWRq7-JpF9dK2nBokjxx-y4jIas,12174
|
|
69
|
+
crawlo/pipelines/database_dedup_pipeline.py,sha256=wVBXEGArFR3uxoN7yfJSOarBmtGrJpOqowAqa7OUs98,8000
|
|
70
|
+
crawlo/pipelines/json_pipeline.py,sha256=vlu1nqbD2mtqtExt9cL5nibx1CwJM1RNqd4WGjZRHAY,8367
|
|
71
|
+
crawlo/pipelines/memory_dedup_pipeline.py,sha256=5jeL2jEq7sioYmXlzfkx-LNSbWyChrXeWx8d15YEZOA,3839
|
|
72
|
+
crawlo/pipelines/mongo_pipeline.py,sha256=k7gNqAO-g2MtIfArphC6z5ZzkKVRkBKcv-2ImziPFA0,5706
|
|
73
|
+
crawlo/pipelines/mysql_pipeline.py,sha256=cwgJvRORTRea_Eep2coBaMf3G8PQVTQA1qrnIlDZApc,13480
|
|
74
|
+
crawlo/pipelines/pipeline_manager.py,sha256=vK87pAEmpGR24yl6Cr7ovCKag2oB5mruijfYT8nnG5o,2358
|
|
75
|
+
crawlo/pipelines/redis_dedup_pipeline.py,sha256=sgrBSVdxPWgh8HQxvGsazz1MSyBERJF5jd1yoeYo0lE,6166
|
|
76
|
+
crawlo/queue/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
77
|
+
crawlo/queue/pqueue.py,sha256=yzF900ko2RReVNZtfk_VV3PzSXEUALI6SHf97geuu6s,1058
|
|
78
|
+
crawlo/queue/queue_manager.py,sha256=UxIhyLzVM0HNNzwQ6LvOoCJ-zOcE95gl0ZKpzTz1ybA,12930
|
|
79
|
+
crawlo/queue/redis_priority_queue.py,sha256=RbwKsVxzk31B1VRvyve4vHKe2DesL7K37IZAA31kdd0,12783
|
|
80
|
+
crawlo/settings/__init__.py,sha256=xsukVKn_h2Hopm1Nj-bXkhbfyS62QTTvJi7fhZUwR9M,123
|
|
81
|
+
crawlo/settings/default_settings.py,sha256=cwEIVL294hs7iWVOSfnwA4nuRWjHXJk_Bqgbd37Vmcw,8783
|
|
82
|
+
crawlo/settings/setting_manager.py,sha256=0RYAk07qoJ5WTw_mvV4ECWGS2QNpCnGmBZVTHjqOVIg,3707
|
|
83
|
+
crawlo/spider/__init__.py,sha256=Z_rK23l5yt-DuwJPg8bcqodM_FIs4-iHLaKOimGumcE,20452
|
|
84
|
+
crawlo/templates/crawlo.cfg.tmpl,sha256=9BAmwEibS5Tvy6HIcGXPb0BGeuesmibebmTW0iAEkmo,230
|
|
85
|
+
crawlo/templates/project/__init__.py.tmpl,sha256=f3ETIXw_O6K-lkL6lXM5znMPJW1FZYGFrwDs2BnHcnQ,58
|
|
86
|
+
crawlo/templates/project/items.py.tmpl,sha256=mt1Mm--H2Ouos3r7JPkYh0r33rgYJf1YOMz0OZy8TYs,297
|
|
87
|
+
crawlo/templates/project/middlewares.py.tmpl,sha256=Dyp_tyNgF9U4w1oMAvOAOfSepWsjXWOvH__qQ3BOkSQ,3731
|
|
88
|
+
crawlo/templates/project/pipelines.py.tmpl,sha256=GBHYU0Jx8sKDCdGJp44FMSH7u2slxoFg6a-R9Uwg_-I,2608
|
|
89
|
+
crawlo/templates/project/run.py.tmpl,sha256=KaLhqngKEzKtvDI2KCHe00yFRXnxMwbdq7YoXPR4kEg,1226
|
|
90
|
+
crawlo/templates/project/settings.py.tmpl,sha256=JpK0Zq9TdxwucizUliOSLNYs9KgnFwJuai8GJEGlt6o,11710
|
|
91
|
+
crawlo/templates/project/settings_distributed.py.tmpl,sha256=6xG7ehu86qAXscWOAFbrtXL5mzGNarCgYpbW5LXzExg,4202
|
|
92
|
+
crawlo/templates/project/settings_gentle.py.tmpl,sha256=IPE9H9WqRQWVdj9supFutt9gvypYQRVhRFOwZyYxem0,3226
|
|
93
|
+
crawlo/templates/project/settings_high_performance.py.tmpl,sha256=UNDx9f76kF2je8hE4ZE73wQcLcApjrEzpNLHWp9DvaI,5283
|
|
94
|
+
crawlo/templates/project/settings_simple.py.tmpl,sha256=qk0EnX4xncVBPVlFmqS1yDn56Cz6TBEQhgDdY8TABJ8,2297
|
|
95
|
+
crawlo/templates/project/spiders/__init__.py.tmpl,sha256=j_YKsw6HQMJyqlk3WUouP3bsr-XVxshRoSNakHBc00g,106
|
|
96
|
+
crawlo/templates/spider/spider.py.tmpl,sha256=CzZr8SNzkuEQGA8F11CfMxYvOpwnHOWCG-1MiLqN6D0,4896
|
|
97
|
+
crawlo/tools/__init__.py,sha256=5H6rAhjfNSqRMjjlLDVq-vEJWRFyCO-J6HN2kexnXJU,3671
|
|
98
|
+
crawlo/tools/anti_crawler.py,sha256=MU6KEPT0q85e_-Px8Rmw1fxdwlmOdpXfo0KYVpPlivU,9163
|
|
99
|
+
crawlo/tools/authenticated_proxy.py,sha256=L93WeXajIZ3si8xNcE7bBPv34FvqSyTvVfD78fJAKQE,7032
|
|
100
|
+
crawlo/tools/data_validator.py,sha256=hxPN28YtJDFFLjBBYhDjHmR8ShNTEjgIsv-cmcDKIu8,5310
|
|
101
|
+
crawlo/tools/date_tools.py,sha256=icbx6x08t-Aj8j0jAB-93hDdSpBV9Rd-aaNt4UpyjNA,600
|
|
102
|
+
crawlo/tools/distributed_coordinator.py,sha256=ZN-zYsDPw0JWSBF7oHqL2vpUDgRElkDTVW7TcY1ArcI,12477
|
|
103
|
+
crawlo/tools/retry_mechanism.py,sha256=27iIuLCg1ZHjog6Gcr7dz0APkeTZ5cIlcnZ0pF18ZVA,7801
|
|
104
|
+
crawlo/tools/scenario_adapter.py,sha256=JouFxI3513PRe1ObwHWc72vBvptNpNv0Ew3pRaEKjQQ,9398
|
|
105
|
+
crawlo/utils/__init__.py,sha256=OVjs7qjyd7sn1vrh4MWykO4sMsAPLIWkq-74dQ2Pzak,557
|
|
106
|
+
crawlo/utils/batch_processor.py,sha256=Bim6iSinjFKuKI2c1Ss6PQ1R-zJEvLdVxPiBDTa75z4,8895
|
|
107
|
+
crawlo/utils/controlled_spider_mixin.py,sha256=VjT30pNW_YIgmTD0nb7DDl2D3HvpnAYFzgSgV3fxFN0,16475
|
|
108
|
+
crawlo/utils/date_tools.py,sha256=6zNU23vQ8p3-xHknlIp5airCLOREETaqw4YElyMO_lQ,8907
|
|
109
|
+
crawlo/utils/db_helper.py,sha256=3ib5-agrlwf2t5S_QtLRYH75wvJDlYbRqRmDEbpH5Bo,10559
|
|
110
|
+
crawlo/utils/enhanced_error_handler.py,sha256=qcFR3o2HyEyBQf0n1l6-hSOiFGytYGmhAzseqeidwHA,13906
|
|
111
|
+
crawlo/utils/env_config.py,sha256=Rn5DOUoshtIfCDqWh5CNpTfiXo1bF_zEb0tLo09DLMk,2869
|
|
112
|
+
crawlo/utils/error_handler.py,sha256=v-UVJfIp9k-lOXq5DBukJfE_nb-kv83tlr28RXrIUYQ,4286
|
|
113
|
+
crawlo/utils/func_tools.py,sha256=WUZEGpWMuDDX7g-QySM7iaiC74erW2SSkZoUvDw1NjM,2369
|
|
114
|
+
crawlo/utils/large_scale_config.py,sha256=j7wQ5ty7pQlBRygw2vhRJ7OI19RYBZKPfYMP3WeF2WI,8154
|
|
115
|
+
crawlo/utils/large_scale_helper.py,sha256=JJqcGSI6VaVe3MSL6IWjmCp8XQIu6T4U-BvBLSttr_s,12157
|
|
116
|
+
crawlo/utils/log.py,sha256=A3lPyhD8kD88cV23KOL-_eT8g69xGQ5L1toDB2AO0mc,4005
|
|
117
|
+
crawlo/utils/performance_monitor.py,sha256=mygXJ0FNxHyunb_aQSgmcBv0bkT4ISG5QqlOXANtvlk,9595
|
|
118
|
+
crawlo/utils/queue_helper.py,sha256=xpUUTOqlU1xz2Pb9NKAVGo3AfAO-7Xvx8Lm1q65Dgck,4743
|
|
119
|
+
crawlo/utils/redis_connection_pool.py,sha256=9WprN-HbtYGLhAu0AXjXeHcVbJ9jd3dS3U4e_stdCMY,10331
|
|
120
|
+
crawlo/utils/redis_key_validator.py,sha256=mDqZROAlrnMvKX7ToXdaSjQGfu2J5tpCqo1tQ75n5RA,5637
|
|
121
|
+
crawlo/utils/request.py,sha256=yoLB2rY8d78vgPjIWpdhY5SalIKjyLIvTG_UH6EMdVI,8798
|
|
122
|
+
crawlo/utils/request_serializer.py,sha256=bPoSQqE2ksiMyP3WiPB3w3UqZs4f_LgkAw4Pj0qyBDo,8565
|
|
123
|
+
crawlo/utils/spider_loader.py,sha256=pEDUsYOTGjszA6KgjiMlYN4GS5fP4uakkhcp3JTFFQY,2187
|
|
124
|
+
crawlo/utils/system.py,sha256=HvWV1acxou0Rn0L7pNq4CnV_GWFeU0Tmjy3_nLD8M64,237
|
|
125
|
+
crawlo/utils/tools.py,sha256=5Uv25Wy4m_ndZY0-n-eX-t3PxvaZ6wR3-Wvx-o7_Vrs,271
|
|
126
|
+
crawlo/utils/url.py,sha256=rlgX2VlJv6JvLmCDTsbxzMSXE6R5ZL_0dLEqprsA-JU,1482
|
|
127
|
+
examples/__init__.py,sha256=6i631BPnS_TR_BWUjtjB5CBO-zv9kRkwQTQvSya2wHE,123
|
|
128
|
+
tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md,sha256=HjMZv6RjN1o5D1mfgEydP8Mcc9T_4ScR6lG3xVxs8P8,3346
|
|
129
|
+
tests/__init__.py,sha256=scL1IPVT1iucth7v8ffrjRdeW7QrC_Y7AMmFVMdTY1Y,129
|
|
130
|
+
tests/advanced_tools_example.py,sha256=7nlFLRVMVYzDz_CAdgQa9fJu7o0M6jBMo7PTvUsRbo0,9065
|
|
131
|
+
tests/authenticated_proxy_example.py,sha256=8I8bxAIeYDdsh5JoGIK1nxaKEpIdOFnCtufVLjpuq_o,8241
|
|
132
|
+
tests/cleaners_example.py,sha256=i90lrmno16qSq_qjc6WOVOw1Mx4_vzoBgVeqJYC7Vro,5170
|
|
133
|
+
tests/config_validation_demo.py,sha256=iPe_BWBTa-gRvRrnYYkkRDqyKqLzAhSCoWB_yFSkhrg,3116
|
|
134
|
+
tests/controlled_spider_example.py,sha256=SP_k4mdKPvD1JCPs9UCm68jcy2Frg84vvXv9-14RC6I,7776
|
|
135
|
+
tests/date_tools_example.py,sha256=x_-duqnVZ-Hrk-SaNplIfcIV6W3c6u6MTxW35u1i0F0,4862
|
|
136
|
+
tests/dynamic_loading_example.py,sha256=NI0SCg4lPME0RCcNpDDw1HjErjmCgJntCN0ahAEw61g,18263
|
|
137
|
+
tests/dynamic_loading_test.py,sha256=DYbMrEewerx0VGXixci3p9VYgDDQvCPevA92CNjq1Jo,3309
|
|
138
|
+
tests/env_config_example.py,sha256=sKE8DvMBhM3uy439LpgLHd4wF7MGUrUc-X6E7g9qsz0,4818
|
|
139
|
+
tests/error_handling_example.py,sha256=219H1dOm6TZaQ0tmd1zXZlo0ODcwQSBL7m4jZmCFoCo,5161
|
|
140
|
+
tests/redis_key_validation_demo.py,sha256=z1R7ZW6oiG3T0mSZJfP6FRqp4IsOjgbCPxvPuEL7z0I,4345
|
|
141
|
+
tests/response_improvements_example.py,sha256=wnYGJO6MKj5_jbwKLDlbXu_Dli5XC7vlWdzByi82_5Y,5258
|
|
142
|
+
tests/test_advanced_tools.py,sha256=3R8EfKVyBHEb6FA5TP3ieaWeHZhobVgSx8t3phipCrE,5250
|
|
143
|
+
tests/test_all_redis_key_configs.py,sha256=uMLlgtJ7tglzFO_Xbnwol723Lu6bjyIeHaLHtemphaQ,5660
|
|
144
|
+
tests/test_authenticated_proxy.py,sha256=s4pr5JyBTHYQgRq_IymiVKE08vyW1MwR27pSwrrVLVk,4198
|
|
145
|
+
tests/test_cleaners.py,sha256=7KRAjqXF7lWXe-9Hj_5CSFlbRJ6SB7XyMNuMXx36Jmg,1765
|
|
146
|
+
tests/test_comprehensive.py,sha256=kGNcJ9UkQxysYqvsBu0YxAaPleOvN9_hztLy7ljkfc4,5036
|
|
147
|
+
tests/test_config_validator.py,sha256=eZCnZyh34rpbYbzXMWvQkLNl7gu7_Js0fE7iFatXyB4,6632
|
|
148
|
+
tests/test_date_tools.py,sha256=CQdAmIS6bpAdwQH9ETDH__06l2gGL7EHUQuh7mdTF-A,3930
|
|
149
|
+
tests/test_double_crawlo_fix.py,sha256=t7EZsKIfE49ZL3FM0bu1AZ1hOMygwALUN5UtqDGtLUs,7826
|
|
150
|
+
tests/test_double_crawlo_fix_simple.py,sha256=0OPbW8c71n_oB7pt10rRZi-W9eFCO_JOKTquWdIgTUU,4683
|
|
151
|
+
tests/test_dynamic_downloaders_proxy.py,sha256=PtEW-pnVijeX2yX34UcoXYEY23yTBxb-kyNYh-WDljQ,4326
|
|
152
|
+
tests/test_dynamic_proxy.py,sha256=YL2sghNKG7k27-SaHMh4boNLVBHhfSttUwUqiSsOEX4,3080
|
|
153
|
+
tests/test_dynamic_proxy_config.py,sha256=uYXZ804ULI9qYMF-uNjMbi3L_NGzoMqLJcEZAl7aZ2I,5707
|
|
154
|
+
tests/test_dynamic_proxy_real.py,sha256=DTjP8JnSwBnNZ3Ls1BjDAmt6xSuye_6CxwZ4LBisPTM,3402
|
|
155
|
+
tests/test_edge_cases.py,sha256=fFRL3-ChBylg4e-73L9ZSc3u72dPmSfg3jpAg_6GOGA,10553
|
|
156
|
+
tests/test_enhanced_error_handler.py,sha256=E6HHzqGA6U9frzQvy0iVqFHi6LvRJobRwkFWk37tA10,8435
|
|
157
|
+
tests/test_env_config.py,sha256=nfP4nCG9ZHeJUfxo1JKUmiihYbhSeWx_oNW5mMfDHfQ,4746
|
|
158
|
+
tests/test_error_handler_compatibility.py,sha256=o5JLLLdo25Sl_3hpMx6I2fqSgZFAcnI4E6Ci-KxAxwA,4129
|
|
159
|
+
tests/test_final_validation.py,sha256=fBxf_6YcAEa_HyV_oGAXmmVHY4i6FdA4J6klCmc36hQ,4925
|
|
160
|
+
tests/test_framework_env_usage.py,sha256=HYpTwORXeaJHMffCYAGHGvc_a6ax4lo28xP8BYOaKxk,4098
|
|
161
|
+
tests/test_integration.py,sha256=8Bky_n5fbJDbb2pbKqc6IwJgpV0B9iau84C-PwcbsLA,11321
|
|
162
|
+
tests/test_item_dedup_redis_key.py,sha256=GOmmJ7hdTV_2XifRa_PQDrQpBt7Rnt3ViYNjNpflGgw,3755
|
|
163
|
+
tests/test_parsel.py,sha256=KYskaN_4HBc1XDTltjVo12v1i7JAThB2UIwcWZ-mwbY,672
|
|
164
|
+
tests/test_performance.py,sha256=heeFoS3R9n_t7ri0MyUL8kE0FY9sYJiC7BSQNI2C5HQ,11286
|
|
165
|
+
tests/test_proxy_health_check.py,sha256=xo3QMP1YNw9hu7JDHZOYCUZmFFKLJpHSh4SbxXhCRPQ,1091
|
|
166
|
+
tests/test_proxy_middleware_integration.py,sha256=zcl7fR9Toc-I-stSUTzKZPwcfh3kgrpjI5SbkZ6AVmE,4305
|
|
167
|
+
tests/test_proxy_providers.py,sha256=XwWZCywTYguSsUxSm6fsbaoH1p9dKjqSIx9-sqKZehA,1693
|
|
168
|
+
tests/test_proxy_stats.py,sha256=Til_yksrRz2yBVw-yJi5-36LhNW3vTwpXTm4BdR9PUM,507
|
|
169
|
+
tests/test_proxy_strategies.py,sha256=ZkziozkvZd3KWOQnpHQ8Upd3WpyoX7gN0qFGluNm348,1809
|
|
170
|
+
tests/test_queue_manager_double_crawlo.py,sha256=LYduecvJ93HAU6Ub-tIrGM2pwOUGoCTkpmzBxjpY5tM,9116
|
|
171
|
+
tests/test_queue_manager_redis_key.py,sha256=-dnqs2p50zpf09-Z7vo74s8hLQ6cxXd8WCdHM0l17qM,6278
|
|
172
|
+
tests/test_redis_config.py,sha256=TqzFRojc6esGXjGhUCvSLYQDUTAgEJsty9vRVuNraMU,893
|
|
173
|
+
tests/test_redis_connection_pool.py,sha256=ORBU0k-6htQ2VVfyQkqTKVLGQWX04XRxdEGsZKeerQA,9177
|
|
174
|
+
tests/test_redis_key_naming.py,sha256=ojHhBED2DEf0VzqQgtzefygSn6hZiBhPFyVUBs_4rdI,6776
|
|
175
|
+
tests/test_redis_key_validator.py,sha256=kud0AhnS_6NP9s8G5HB5L9rob5rv2W6WLy6ypHYQDbk,4304
|
|
176
|
+
tests/test_redis_queue.py,sha256=o6xViXxJcdx-1eMcG3vhAQEIm8h346HnZb7JXs7ZjwM,6622
|
|
177
|
+
tests/test_request_serialization.py,sha256=8sVdppAsohJ5u-m1WvablCndwL-M_36YPLdGKwgeznM,2289
|
|
178
|
+
tests/test_response_improvements.py,sha256=zvbkTkWhgdlFYtRu_ckgq6wGDGwpe_PTECYqpLDM3BU,5876
|
|
179
|
+
tests/test_scheduler.py,sha256=-FOkTWzaMdr6yfO1Msu74hI_GgSfD7iRxO-cFA-9Iyk,7442
|
|
180
|
+
tests/test_simple_response.py,sha256=6RYOBRzAtyNvJ9a5JVTNubM-rvxnuX8jQOvq3sUZxwo,1488
|
|
181
|
+
tests/test_telecom_spider_redis_key.py,sha256=R581J-kvjh4CpDCCIZKPnV0vY6MvtkvTzmSIbwhXSXs,7470
|
|
182
|
+
tests/test_template_content.py,sha256=5QAnhKZFDKg-_uFryllLMpCk3a1nCS44hMmYfXm8gWk,2878
|
|
183
|
+
tests/test_template_redis_key.py,sha256=U6L5HtnDyGp3s6-O4F_yG2Q2nNIGTqB_Q-ESv2EMeOU,4812
|
|
184
|
+
tests/test_tools.py,sha256=IWiu9JGV-5Ow0ivFtiDw62REht-8Hn7NfyR9rnYSlbU,5113
|
|
185
|
+
tests/tools_example.py,sha256=MfVBYemKvHs6MUbydgrJfhiGnygp5dRoIE-eIXCOR7M,7669
|
|
186
|
+
crawlo-1.1.9.dist-info/METADATA,sha256=i3EFNboqsUyzh_CSajaNfJajxlwq-uiP7iDkjMCTQjg,25548
|
|
187
|
+
crawlo-1.1.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
|
188
|
+
crawlo-1.1.9.dist-info/entry_points.txt,sha256=5HoVoTSPxI8SCa5B7pQYxLSrkOdiunyO9tqNsLMv52g,43
|
|
189
|
+
crawlo-1.1.9.dist-info/top_level.txt,sha256=keG_67pbZ_wZL2dmDRA9RMaNHTaV_x_oxZ9DKNgwvR0,22
|
|
190
|
+
crawlo-1.1.9.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
|
+
"""
|