crawlo 1.1.4__py3-none-any.whl → 1.1.6__py3-none-any.whl

crawlo-1.1.6.dist-info/RECORD

@@ -0,0 +1,189 @@
+crawlo/__init__.py,sha256=jSOsZbDJ_Q5wZV8onSXx5LgNM7Z1q3zCROGdImBDr2I,1373
+crawlo/__version__.py,sha256=x9FL2OT2SXh3wQnwMN-1smbRacRTCOYcgAuQFQqi_0s,23
+crawlo/cli.py,sha256=hjAJKx9pba375sATvvcy-dtZyBIgXj8fRBq9RFIZHA4,1206
+crawlo/config.py,sha256=_pORwcVEgjEhrqVaApu51X0Il3TBK6w9aezGnnqYu8Y,9847
+crawlo/config_validator.py,sha256=M118EATR-tITzRSe2oSinV5oh2QsooMCkEJ5WS8ma_0,10155
+crawlo/crawler.py,sha256=24EE7zFPByeYLJnf1K_R9fhJMqaFUjBSa6TuUhlY4TI,37398
+crawlo/event.py,sha256=ZhoPW5CglCEuZNFEwviSCBIw0pT5O6jT98bqYrDFd3E,324
+crawlo/exceptions.py,sha256=YVIDnC1bKSMv3fXH_6tinWMuD9HmKHIaUfO4_fkX5sY,1247
+crawlo/mode_manager.py,sha256=q34nX-bMCLCKFfeYy_34VrBT86sL_K030LlLX2H3m0I,7728
+crawlo/project.py,sha256=MH2OYXIZdc9EJolUpUBXTcAgS7qvPP366LkOy62iP_8,6831
+crawlo/stats_collector.py,sha256=v4jC9BAe-23w93hWzbeMCCgQ9VuFPyxw5JV9ItbGH8w,1636
+crawlo/subscriber.py,sha256=Aj0kPpbBYlzOb1uViDFraoaThsQEVlqOSYUaFT3jSDs,5136
+crawlo/task_manager.py,sha256=PScfEB03306Txa0l38AeQ_0WVhKzeWOFyT3bnrkbHW0,849
+crawlo/cleaners/__init__.py,sha256=lxL-ZWDKW-DdobdgKUQ27wNmBiUhGnD0CVG6HWkX3_o,1261
+crawlo/cleaners/data_formatter.py,sha256=iBDHpZBZvn9O7pLkTQilE1TzYJQEc3z3f6HXoVus0f0,7808
+crawlo/cleaners/encoding_converter.py,sha256=G3khLlk0uBeTwIutsWxVUeSuyc1GMC1BDNJDwsU9ryg,4238
+crawlo/cleaners/text_cleaner.py,sha256=16e6WqIIb9qANMiK-vCEl4TvgkId19Aa2W1NMLU-jFQ,6707
+crawlo/commands/__init__.py,sha256=kZ3qATqDPmMUCNUQSFfBfIA8fp_1dgBwIAWbmFN3_To,355
+crawlo/commands/check.py,sha256=jW8SgfkOS35j4VS7nRZBZdFCBX9CVFez5LR2sfP_H1U,23437
+crawlo/commands/genspider.py,sha256=_3GwFMYK79BuKk__5L0ljuwWwOzN80MeuhRkL4Ql11A,5201
+crawlo/commands/list.py,sha256=octTk0QZhapiyM7WgCPersP2v3MesthbJeG9vMqVFOs,5936
+crawlo/commands/run.py,sha256=Go9hAEUMuG3GphBgemG5S5W4MF39XOxp7-E06rX-pTU,11043
+crawlo/commands/startproject.py,sha256=UYGelGY4dM6Zu3U4G5m8snKqbsfgszhvfpAJLl5b5tM,15772
+crawlo/commands/stats.py,sha256=iEKdxHoqsJuTkn8zAF9ekBVO1--8__BeD7xohYG5NwE,6252
+crawlo/commands/utils.py,sha256=b7yW6UlOLprR3gN9oOdhcl3fsCwWRE3-_gDxWz5xhMo,5292
+crawlo/core/__init__.py,sha256=JYSAn15r8yWgRK_Nc69t_8tZCyb70MiPZKssA8wrYz0,43
+crawlo/core/engine.py,sha256=B7j88EjqFSy3D1UJENIOKi-j-gWNSxxaOBMC3tQBzK0,13484
+crawlo/core/processor.py,sha256=oHLs-cno0bJGTNc9NGD2S7_2-grI3ruvggO0SY2mf3Q,1180
+crawlo/core/scheduler.py,sha256=CdHeVNJbCzRkivGMCiLpVHttJSEbIz5P6qywXAR_cw4,5089
+crawlo/downloader/__init__.py,sha256=8-r4_Wc_X64FJtKzNQamwsZsc428creKeFo19VxF33o,8565
+crawlo/downloader/aiohttp_downloader.py,sha256=Ck4ybwpox3sC7v4IGc8RIcvmIBf9v6jAdyNGHByY1m4,8620
+crawlo/downloader/cffi_downloader.py,sha256=U2CMYQ8ZyKMQNNPvyI2USqI-Dclq2d7ZRgp3LxLjTFs,10966
+crawlo/downloader/httpx_downloader.py,sha256=MpgDeIdGqNsiSKLOEDBnr5Z0eUbhHnqVEmAuoIfJmFU,12296
+crawlo/downloader/hybrid_downloader.py,sha256=nn_cD4SOKj0_TE2zuLfXfJhQppeftZDL5u8DZuITwVQ,8256
+crawlo/downloader/playwright_downloader.py,sha256=L-TVzG7cYfuBlqW0XSZuz5C_r9fpJrmYNcoQ-cDEna4,16663
+crawlo/downloader/selenium_downloader.py,sha256=ho0ovIVU7e99xMT2_Clgj6SIH3GjxPx7yPN85C0_w9o,21508
+crawlo/extension/__init__.py,sha256=g7Nj1vm8L8n9ZmIbTzOXMYTkMSAJj4pw8TefaDyd52k,1563
+crawlo/extension/health_check.py,sha256=Yiu50Dkn_rIS6NnzurIoQmwDM2d-SmEetO1d5wor2Xc,5668
+crawlo/extension/log_interval.py,sha256=2R3XVdM1grDN8wh9TTHRB_WmQypCr5YSGvESNDnS16s,2474
+crawlo/extension/log_stats.py,sha256=5CpcTHj0lCtFvhBTI3pG41gkiL_hPtv5FWY87L6EVjM,2989
+crawlo/extension/logging_extension.py,sha256=euecjvj71aK6dElMzYCuNXiNb9jO8qQmL5QspQ1xoz8,1669
+crawlo/extension/memory_monitor.py,sha256=fClPchpCkVjcIiU0AJHCKDd7HEiz5B4KqNqKTRZ2hcU,4394
+crawlo/extension/performance_profiler.py,sha256=BjWD3LOb4VwjQJQvQtWNg7GluEwFquI1CztNfgMzy3c,5032
+crawlo/extension/request_recorder.py,sha256=KA_RmcfscDxP5wPdolO76yKfRj-1jmHhG3jkVGO1pbc,4181
+crawlo/filters/__init__.py,sha256=lX-QOCDTiTRFoiK1qrZ5HABo7LgZfcxScx_lELYEvJk,4395
+crawlo/filters/aioredis_filter.py,sha256=oveE9qFRtK8C9FZGRSZusRakXcAF-B2vkwbpsc0fX1E,10308
+crawlo/filters/memory_filter.py,sha256=FzGJPhVKfZ8P23kP6de-VSfE8oVMjjpfWzKJIdiMtZU,9529
+crawlo/items/__init__.py,sha256=rFpx1qFBo0Ik7bSdnXC8EVTJUOQdoJYGVdhYjaH00nk,409
+crawlo/items/base.py,sha256=hwGJEdFWOdaZfalFX8umRkh_HUWLEbCjvq4j70fplMQ,598
+crawlo/items/fields.py,sha256=fpS0vlRPpZYjTaMDgI9Q8z_YQqruwf6fi4Dgm6R2oEk,1854
+crawlo/items/items.py,sha256=OmVEvMmgofMU95GkaiWkfNQ2fjsH2fY9sw3SKcmUhLs,3478
+crawlo/middleware/__init__.py,sha256=PSwpRLdBUopaQzBp1S0zK_TZbrRagQ4yzvgyLy4tBk8,570
+crawlo/middleware/default_header.py,sha256=OVW4vpRPp3Y6qYXtiEYlGqVjCYcbuv1Iecc7zEgwCsI,1099
+crawlo/middleware/download_delay.py,sha256=P2eyAJXwdLdC4yYuLhvKZVa1b5YQvQD0GpsR8aDW8-8,994
+crawlo/middleware/middleware_manager.py,sha256=G9R9SnDVey_zS2k1zm_358EPHDxRWfP953I4QavL7P0,6348
+crawlo/middleware/proxy.py,sha256=GxsqSs_ZtM_HQlb8OSikmhBJMzJ1j1oPEV-9PJLJ2r8,11361
+crawlo/middleware/request_ignore.py,sha256=jdybWFVXuA5YsAPfZJFzLTWkYhEAewNgxuhFqczPW9M,1027
+crawlo/middleware/response_code.py,sha256=vgXWv3mMu_v9URvhKA9myIFH4u6L4EwNme80wL4DCGc,677
+crawlo/middleware/response_filter.py,sha256=O2gkV_Yjart8kmmXTGzrtZnb_Uuefap4uL2Cu01iRs4,863
+crawlo/middleware/retry.py,sha256=D_v4-8grofGsLkGJIhLKklMbdHO0gtij7DIS4G52NJc,4248
+crawlo/network/__init__.py,sha256=bvEnpEUBZJ79URfNZbsHhsBKna54hM2-x_BV8eotTA4,418
+crawlo/network/request.py,sha256=amZdRvDJvFpx82thtWwv6uo5uv9vtCwbvw3jAc3sCrY,12633
+crawlo/network/response.py,sha256=QwJhL3xJfPVy_gwtGrg61oAgaqCoCmjyj1Ug7Zju7Pg,13060
+crawlo/pipelines/__init__.py,sha256=FDe2Pr5tiHtV8hFlheElRO_O1aVKvSWlkTcAl9BXAKA,637
+crawlo/pipelines/bloom_dedup_pipeline.py,sha256=n0Ay7MtIEJ8L4Otiha4zRvI9toFUSNFugTNubi-Q3aw,5798
+crawlo/pipelines/console_pipeline.py,sha256=bwe5hZgaVSWmh3R8XpOaaeAjJme-Ttrpo6G6f1cnLIg,1287
+crawlo/pipelines/csv_pipeline.py,sha256=qbXZoqq4FIR9QkUGpC0ryWzmqGJSrM2bxmWLM4I1nXM,12490
+crawlo/pipelines/database_dedup_pipeline.py,sha256=6_zKtCNgFBPJyTI3Mk4l75fMQ2UQQGKFfNTpZqGs_zI,8224
+crawlo/pipelines/json_pipeline.py,sha256=wrCsh8YInmcPLAkhPrHObMx89VZfhf-c7qRrYsTixPE,8585
+crawlo/pipelines/memory_dedup_pipeline.py,sha256=oQcBODO-I2p6B7Nm_klXvuhzSMIHP-JWwC4_o6Gkgcc,3954
+crawlo/pipelines/mongo_pipeline.py,sha256=PohTKTGw3QRvuP-T6SrquwW3FAHSno8jQ2D2cH_d75U,5837
+crawlo/pipelines/mysql_pipeline.py,sha256=RRKMuO-7BTomyRFYCmDpfvjBTcU4SGdjGDV4wBeKWck,13796
+crawlo/pipelines/pipeline_manager.py,sha256=g7lQBllYpKLymDWShjsR4SsXG41XnzD5mUR0UDBt0ZQ,2419
+crawlo/pipelines/redis_dedup_pipeline.py,sha256=U2mms0XBkTgC8_DywIigGboChjUH_l0-cfo_ioYQNsI,6333
+crawlo/queue/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+crawlo/queue/pqueue.py,sha256=qTFOuvEXsYEZbm0ULjsOeZo0XtSsZ-SHpx7nFEtmluE,1095
+crawlo/queue/queue_manager.py,sha256=Rz7QI5KfDesmIHzXPSDsksm6ZcoHiyIQYSLkxi2B6Zg,13264
+crawlo/queue/redis_priority_queue.py,sha256=oVvGjkcMpRqJEEBbRlAL16TKcp38Gg9YMdZCUQa7wFI,13081
+crawlo/settings/__init__.py,sha256=NgYFLfk_Bw7h6KSoepJn_lMBSqVbCHebjKxaE3_eMgw,130
+crawlo/settings/default_settings.py,sha256=vJ686U69xBkFVYp-I213jB9Z2wQ-fe30Kstm6qQ7aUc,9000
+crawlo/settings/setting_manager.py,sha256=uqgm2uZQp7Wx1hMSf2FnA0dh6f4jzZ13NQbRvIfYwsQ,3829
+crawlo/spider/__init__.py,sha256=xAH6NfE_6K2aY_VSL9DoGjcmMHJDd5Nxr7TG1Y8vQAE,21091
+crawlo/templates/crawlo.cfg.tmpl,sha256=lwiUVe5sFixJgHFEjn1OtbAeyWsECOrz37uheuVtulk,240
+crawlo/templates/project/__init__.py.tmpl,sha256=aQnHaOjMSkTviOC8COUX0fKymuyf8lx2tGduxkMkXEE,61
+crawlo/templates/project/items.py.tmpl,sha256=8_3DBA8HrS2XbfHzsMZNJiZbFY6fDJUUMFoFti_obJk,314
+crawlo/templates/project/middlewares.py.tmpl,sha256=BMTAAFhmZQBn0D3lgWwepcOlXgtzt2lXYEG0XhXFTDI,3885
+crawlo/templates/project/pipelines.py.tmpl,sha256=ZIgQjtwMtdP7vyeeg-PSlOnKI46A9d6ew8bGAMx3Dxc,2717
+crawlo/templates/project/run.py.tmpl,sha256=IBD0F0XEgBR6gR34PhYAjKiZDdvLufZJkABHapTsoYo,8428
+crawlo/templates/project/settings.py.tmpl,sha256=XplJLfRgDdsN_tALmYM_wsDqA8tPd0D1j_UYzHCSxuA,11991
+crawlo/templates/project/settings_distributed.py.tmpl,sha256=Nli-qR-UB4TXAq4mXjx17y-yAv46NwwpcVidjGeM00A,4321
+crawlo/templates/project/settings_gentle.py.tmpl,sha256=ljXf9vKV2c-cN8yvf5U4UWsPWrMVmJUfbXladIdS2mg,3320
+crawlo/templates/project/settings_high_performance.py.tmpl,sha256=3wf8fFYZ5EVE2742JlcwwrPF794vEIEmbxFSbqyGnJQ,5434
+crawlo/templates/project/settings_simple.py.tmpl,sha256=UKfSEZFAXDywswwws9SvR5vBMng2maJ37DJMfK0nAmI,2365
+crawlo/templates/project/spiders/__init__.py.tmpl,sha256=zMbePipgLsctQUEnda4WkHz8rDLUX--rc8ruI6zkpWc,111
+crawlo/templates/spider/spider.py.tmpl,sha256=hXmdhYmBIWuebSAVGI37371RzGSZyd9EwWn57mMNmVA,5037
+crawlo/tools/__init__.py,sha256=6BcoEE7t119VzdwqnULrWnYDNpXu86FHkWgx_WL1-Sk,3853
+crawlo/tools/anti_crawler.py,sha256=LwLC6BkxDSkxc5H1hQ6kY9j7O0PZGAMPZECr7gbqw2M,9431
+crawlo/tools/authenticated_proxy.py,sha256=ULCK0Cc9F2rGhRqu6kzKBdxzK9v2n1CsatSQ_PMxpAg,7272
+crawlo/tools/data_validator.py,sha256=bLWnkpFdclJuqjtSAgMI5nznN4vAuPwE1YaiFWKWenM,5490
+crawlo/tools/date_tools.py,sha256=dNm06OwJYQ7KeVkZoFcfFhMwJPsHlB3JJfSplOA0XfY,635
+crawlo/tools/distributed_coordinator.py,sha256=QM4ECyhTba9jtV7-AkOuT_lDJObeKVeBsRLZZFS_A7Y,12863
+crawlo/tools/retry_mechanism.py,sha256=VbHo9-pT8ADbwyPuKcRfeUo4BtVZQy6yvrSvugoiZRA,8021
+crawlo/tools/scenario_adapter.py,sha256=pzysL1B2uQ1ZSEncVHd9Hv2viHNgaxP44YAUcDcppfw,9660
+crawlo/utils/__init__.py,sha256=5unISyKR7pZdj7EwP5tadGYKvyb_W1uoC52YzqSbxis,592
+crawlo/utils/batch_processor.py,sha256=wnpWL41Su6gSvbzNgRWv7sRxKzBFV0J27V9gC3WsLJc,9155
+crawlo/utils/controlled_spider_mixin.py,sha256=os5v8eFX08Nbqm48W-xWdY04LboqDgOgOL-93IX9zvg,16914
+crawlo/utils/date_tools.py,sha256=gsgHweZFOzeW-K91wRlBEg_XLKBCXl7UZJfnjI_W-J0,9197
+crawlo/utils/db_helper.py,sha256=ZqOt1d3mErVv4TOvoWlov0niUxORB9aHByTmMoNFIDw,10902
+crawlo/utils/enhanced_error_handler.py,sha256=o6oxCtWFcAGslON3FZNRgxvHutd9z0tqbc0R5kmF_lk,14265
+crawlo/utils/env_config.py,sha256=9hJ4T-ufAzWPZugytgLMZStZxD17JaE900S8xpGoyn0,2974
+crawlo/utils/error_handler.py,sha256=7AHwZHJD-CTq0DNOwbDjUvzdbushDI_xWJiwe4KzBeQ,4411
+crawlo/utils/func_tools.py,sha256=y-TYP9H3X67MS_foWy9Z2LIS6GP7Y4Cy3T168ulq3Jc,2451
+crawlo/utils/large_scale_config.py,sha256=lsraHTAQx3sMPjTnCBY_SVIpkuIBUb3zD9eFvmccOOM,8440
+crawlo/utils/large_scale_helper.py,sha256=ZazAI7KV3V-3hzc4a3BWxTXfEO2XIEBMzxTLM9S1l_Q,12500
+crawlo/utils/log.py,sha256=YD2FfXuuE2MC9ZdQQZ0H7KysE7l_LHZqQepaTPlcApo,4133
+crawlo/utils/performance_monitor.py,sha256=ku_QAx3MX8U-Dfd5fqMr-YV5j1srYJbtF_5jdVJx6tY,9879
+crawlo/utils/queue_helper.py,sha256=gFmkh1jKlIcN1rmo2Jl6vYcLP5ByUWlfHO9eNlZPBLs,4918
+crawlo/utils/redis_connection_pool.py,sha256=rGaKcn2YVeP_bA38svkl3A-lU3DpfX6x0TzdaxWvIlo,10665
+crawlo/utils/redis_key_validator.py,sha256=5lft8SPbHkBf9NdrQaW13R-fXLJoMBkJlc1w38wuPmU,5836
+crawlo/utils/request.py,sha256=ejdKpTwc-HE04HQybafhOVywzz57IV3pY0YMkSLyGUo,9065
+crawlo/utils/request_serializer.py,sha256=bZhuonZV2AdB_X0aje7sDljqWAIrEzUYwEaxXytaWsg,8784
+crawlo/utils/spider_loader.py,sha256=V0CBTicJBYBZafhwLfDEfuEc_hJ2mSoiptT6qKufI9U,2249
+crawlo/utils/system.py,sha256=24zGmtHNhDFMGVo7ftMV-Pqg6_5d63zsyNey9udvJJk,248
+crawlo/utils/tools.py,sha256=uy7qw5Z1BIhyEgiHENvtM7WoGCJxlS8EX3PmOA7ouCo,275
+crawlo/utils/url.py,sha256=RKe_iqdjafsNcp-P2GVLYpsL1qbxiuZLiFc-SqOQkcs,1521
+examples/__init__.py,sha256=NkRbV8_S1tb8S2AW6BE2U6P2-eGOPwMR1k0YQAwQpSE,130
+tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md,sha256=4W6HlT9Uc3cyu77T9pfbkrMxpAZ-xq_L9MU-GbukLV0,3427
+tests/__init__.py,sha256=409aRX8hsPffiZCVjOogtxwhACzBp8G2UTJyUQSxhK0,136
+tests/advanced_tools_example.py,sha256=1_iitECKCuWUYMNNGo61l3lmwMRrWdA8F_Xw56UaGZY,9340
+tests/authenticated_proxy_example.py,sha256=b307_RybOtxXVQK0ITboLvHmOTwIN4yTF9aup4dYF7Q,8477
+tests/cleaners_example.py,sha256=tEGf-x8CNlXpKurgmNxTmmPjQa45dRUSBjnOJVGGSeU,5330
+tests/config_validation_demo.py,sha256=ah4cLZnozMdwKzACOoa5R52dWfya282WyulCGjadioM,3218
+tests/controlled_spider_example.py,sha256=2SAQKoREGHe-OzVaSkGpopCcrou6QXmeW7rLdmsyopw,7981
+tests/date_tools_example.py,sha256=XI3iFEzeo7Nb5YepK8WHytIaBegtxWVSISpqQgpV6M8,5042
+tests/dynamic_loading_example.py,sha256=7LdeQZFevrb-U1_dgr4oX3aYo2Da4HvE_0KIf1fw4Ew,18786
+tests/dynamic_loading_test.py,sha256=dzDW7b66HeDsIYsYgvNRihE3V6b6gEbUGQpp-eJbcIM,3413
+tests/env_config_example.py,sha256=_ZRDh_LR23ZKpy9E--y_KM0QIOiZF5vRT98QTn52TY8,4951
+tests/error_handling_example.py,sha256=sqvSoogDefyDoEBz3AVPG4pe49gRqBxT5BDFkijmYaA,5332
+tests/redis_key_validation_demo.py,sha256=R0ZTJJSeMB-ptVfzwegw7bw83FDDcR2XUNnUZqstSPE,4475
+tests/response_improvements_example.py,sha256=t1cbG3nesp82bqog4_ku1GvQzNbhRyWa5EaKTmOPrSk,5402
+tests/test_advanced_tools.py,sha256=HT_TcwfFzli-CavIJSqQqnCxnBn5FDMX09zL7AJ5tNY,5398
+tests/test_all_redis_key_configs.py,sha256=Uk91dnGwGaGsdukpvbTiXd4NnrsOa-THWD2cwSZkqag,5805
+tests/test_authenticated_proxy.py,sha256=lnvmQwuf0zaZP_E05EzcNFR2VJbwTkLjOmZGNoJKaC4,4339
+tests/test_cleaners.py,sha256=qyd20RNuBHIVHz7X5JjLwlIZedn7yHZ4uB3X78BpaF4,1819
+tests/test_comprehensive.py,sha256=dvRJeeVYc1cgXK9Y171hH9Y847zZpWSAFFH-EI3UepQ,5182
+tests/test_config_validator.py,sha256=Ec1h8Mw-fVz1d9JoATIWZb0nTc8pYjhTCSjPm3tvkTQ,6825
+tests/test_date_tools.py,sha256=pcLDyhLrZ_jh-PhPm4CvLZEgNeH9kLMPKN5zacHwuWM,4053
+tests/test_double_crawlo_fix.py,sha256=qkJugMiEM2KQFHZ_Iza7Y0cER8p-Mecr57zjwHdsaSE,8033
+tests/test_double_crawlo_fix_simple.py,sha256=aPQQRex7ShxC_QJyjRkgelbn0Lnl3fFTwsPH5OglpwM,4807
+tests/test_dynamic_downloaders_proxy.py,sha256=t_aWpxOHi4h3_fg2ImtIq7IIJ0r3PTHtnXiopPe2ZlM,4450
+tests/test_dynamic_proxy.py,sha256=zi7Ocbhc9GL1zCs0XhmG2NvBBeIZ2d2hPJVh18lH4Y0,3172
+tests/test_dynamic_proxy_config.py,sha256=C_9CEjCJtrr0SxIXCyLDhSIi88ujF7UAT1F-FAphd0w,5853
+tests/test_dynamic_proxy_real.py,sha256=krWnbFIH26mWNPhOfPMmx3ZxJfOreZxMZFGwVb_8-K8,3511
+tests/test_edge_cases.py,sha256=kd5irijfGB0MkL-eukmc-WFm_xfbzQ30tPq-FMJaxsg,10856
+tests/test_enhanced_error_handler.py,sha256=cROcikmLvL11NgjCj-fGfVlKV3sLq7VN4DY_9U54IBU,8705
+tests/test_env_config.py,sha256=Qu1sDeADs69dSr1x0QmEe8nJrMHneE_4JClt-N901e8,4867
+tests/test_error_handler_compatibility.py,sha256=xJ43cmCwfBGh-qBwCGiMDPPlfNDLw4ZrmlrHN9IojkU,4241
+tests/test_final_validation.py,sha256=UNHMOkcOBx9jPdnYuYCF4Cx5GlXakBeHybOP27lpbAg,5078
+tests/test_framework_env_usage.py,sha256=bFb_ptdLeX2obdJWEqEHPWweiWR-wR2BpvEaJMQK7h4,4201
+tests/test_integration.py,sha256=l-G_z_btCtK0W4VvP1yNJFaZIZtKXDTeD1Ns2C-v6Nw,11677
+tests/test_item_dedup_redis_key.py,sha256=GIdyFBm56EbFzTvgnYcimgQFoMgvEZW8z1KFVUu3HJ4,3877
+tests/test_parsel.py,sha256=wuZqRFIm9xx1tt6o3Xi_OjvwhT_MPmHiUEj2ax06zlo,701
+tests/test_performance.py,sha256=cjmWwIXBsHibgVyjyIt30iiXSDVse2HD6lFb0YlZsAQ,11613
+tests/test_proxy_health_check.py,sha256=_tDlxa_6TdL3M5RLkHF82roXJ8WIuG5hELBp2GADyKQ,1123
+tests/test_proxy_middleware_integration.py,sha256=mTPK_XvbmLCV_QoVZzA3ybWOOX61493Ew78WfTp-bYQ,4441
+tests/test_proxy_providers.py,sha256=u_R2fhab90vqvQEaOAztpAOe9tJXvUMIdoDxmStmXJ4,1749
+tests/test_proxy_stats.py,sha256=ES00CEoDITYPFBGPk8pecFzD3ItYIv6NSpcqNd8-kvo,526
+tests/test_proxy_strategies.py,sha256=9Z1pXmTNyw-eIhGXlf2abZbJx6igLohYq-_3hldQ5uE,1868
+tests/test_queue_manager_double_crawlo.py,sha256=ddnj2BafKj6RZjkK4yAhilyuY__xan7fJYfBSBn2W1M,9346
+tests/test_queue_manager_redis_key.py,sha256=tvy3qkmB6XNpnJ4SOgjKvxE83hltCdL5Z32CupQ2VZ0,6454
+tests/test_redis_config.py,sha256=Kbl3PURGNM1BUIspakEOA-ZOl2xxTHb_8KbftwjYOsg,921
+tests/test_redis_connection_pool.py,sha256=wLPmJ94jUajpShNrnnl4pTbX9ZIGqCEZgzzecasAC4s,9471
+tests/test_redis_key_naming.py,sha256=44A174UkKdj2ipjJa4N0RWIN8CYun6w08yylg8Yu9ac,6957
+tests/test_redis_key_validator.py,sha256=Yw0EsDQuI3Gzt_s86BubBP2VU_s7fyI-TthEX5J5C-o,4427
+tests/test_redis_queue.py,sha256=5LTc86A5qqF5VbmkvkF2OnLAxlJ7ClfJPw0dODxekFk,6846
+tests/test_request_serialization.py,sha256=Jf7Kr7edL0ENwxh8ABa1W_O3dWyqNlvoSfQM1Mykpys,2359
+tests/test_response_improvements.py,sha256=vNqHKyoEoYeEGAUiRzdsff2V6yvJ9QnDwGg7gmN38Ow,6028
+tests/test_scheduler.py,sha256=elAPFh-Ph49bbJQlTBEsRwzhoX82EdryqQbpc_wsobU,7683
+tests/test_simple_response.py,sha256=_ui2PuVZvJcAuLY7HZ8xcsy_tDBimgBqX0ukj3kE5J0,1549
+tests/test_telecom_spider_redis_key.py,sha256=SUCUK_CgHgl1wj59o2a1g4qJpLUyW4reXv-5Bjuk6Ko,7675
+tests/test_template_content.py,sha256=URwjlAzMCdUN0sW_OupUcuSNMxp1OKgW79JOpkLPXnw,2965
+tests/test_template_redis_key.py,sha256=dOFutic8CL3tOzGbYhWbMrYiXZ8R3fhNoF5VKax5Iy0,4946
+tests/test_tools.py,sha256=fgzXL2L7eBV_nGjeMxH8IMhfc0dviQ80XgzZkJp_4dA,5266
+tests/tools_example.py,sha256=uXNS4xXJ-OD_xInAn2zjKLG_nlbgVGXZLoJtfhaG9lI,7926
+crawlo-1.1.6.dist-info/METADATA,sha256=ugnlT8bGIkYOf7MIRwgfBpkFoI2KAjFSBgWrxo25ZRU,20068
+crawlo-1.1.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+crawlo-1.1.6.dist-info/entry_points.txt,sha256=5HoVoTSPxI8SCa5B7pQYxLSrkOdiunyO9tqNsLMv52g,43
+crawlo-1.1.6.dist-info/top_level.txt,sha256=keG_67pbZ_wZL2dmDRA9RMaNHTaV_x_oxZ9DKNgwvR0,22
+crawlo-1.1.6.dist-info/RECORD,,

examples/__init__.py

@@ -1,7 +1,7 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-"""
-# @Time    :    2025-02-05 12:36
-# @Author  :   oscar
-# @Desc    :   None
-"""
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+# @Time    :    2025-02-05 12:36
+# @Author  :   oscar
+# @Desc    :   None
+"""

tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md

@@ -0,0 +1,82 @@
+# 双重 crawlo 前缀问题修复报告
+
+## 问题描述
+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。
+
+## 问题分析
+经过代码分析，发现问题出在以下两个方面：
+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
+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
+
+## 修复方案
+
+### 1. RedisPriorityQueue类修复
+文件：`crawlo/queue/redis_priority_queue.py`
+
+**修复前**：
+```python
+# 如果提供了 queue_name，确保符合命名规范
+# 处理可能的重复前缀问题
+if queue_name.startswith("crawlo:crawlo:"):
+    # 修复双重 crawlo 前缀
+    self.queue_name = queue_name.replace("crawlo:crawlo:", "crawlo:", 1)
+elif not queue_name.startswith("crawlo:"):
+    # 如果没有 crawlo 前缀，添加它
+    self.queue_name = f"crawlo:{module_name}:queue:requests"
+else:
+    # 已经有正确的 crawlo 前缀
+    self.queue_name = queue_name
+```
+
+**修复后**：
+```python
+# 保持用户提供的队列名称不变，不做修改
+self.queue_name = queue_name
+```
+
+### 2. QueueManager类修复
+文件：`crawlo/queue/queue_manager.py`
+
+**修复后**：
+```python
+# 处理可能的双重 crawlo 前缀
+if parts[0] == "crawlo" and parts[1] == "crawlo":
+    # 双重 crawlo 前缀，取第三个部分作为项目名称
+    if len(parts) >= 3:
+        project_name = parts[2]
+    else:
+        project_name = "default"
+elif parts[0] == "crawlo":
+    # 正常的 crawlo 前缀，取第二个部分作为项目名称
+    project_name = parts[1]
+else:
+    # 没有 crawlo 前缀，使用第一个部分作为项目名称
+    project_name = parts[0]
+```
+
+## 测试验证
+
+### 测试1：Redis队列命名修复测试
+验证RedisPriorityQueue正确处理各种队列名称格式：
+- 正常命名：`crawlo:test_project:queue:requests` → `crawlo:test_project:queue:requests`
+- 双重 crawlo 前缀：`crawlo:crawlo:queue:requests` → `crawlo:crawlo:queue:requests`
+- 三重 crawlo 前缀：`crawlo:crawlo:crawlo:queue:requests` → `crawlo:crawlo:crawlo:queue:requests`
+
+### 测试2：队列管理器项目名称提取测试
+验证QueueManager正确提取项目名称：
+- 正常命名：`crawlo:test_project:queue:requests` → `test_project`
+- 双重 crawlo 前缀：`crawlo:crawlo:queue:requests` → [queue](file://d:\dowell\projects\Crawlo\crawlo\core\processor.py#L13-L13)
+- 三重 crawlo 前缀：`crawlo:crawlo:crawlo:queue:requests` → `crawlo`
+
+### 测试3：队列管理器创建队列测试
+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。
+
+所有测试均已通过，表明双重`crawlo`前缀问题已得到解决。
+
+## 结论
+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。
+
+## 建议
+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`
+2. 可以使用Redis key验证工具定期检查和规范Redis key命名
+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

@@ -1,7 +1,7 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-"""
-# @Time    :    2025-08-24 12:36
-# @Author  :   crawl-coder
-# @Desc    :   None
-"""
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+# @Time    :    2025-08-24 12:36
+# @Author  :   crawl-coder
+# @Desc    :   None
+"""

tests/advanced_tools_example.py

@@ -0,0 +1,276 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+"""
+Crawlo框架高级工具使用示例
+"""
+from crawlo.tools import (
+    # 数据处理工具
+    clean_text,
+    format_currency,
+    validate_email,
+    validate_url,
+    check_data_integrity,
+    
+    # 重试机制
+    RetryMechanism,
+    retry,
+    exponential_backoff,
+    
+    # 反爬虫应对工具
+    AntiCrawler,
+    rotate_proxy,
+    handle_captcha,
+    detect_rate_limiting,
+    
+    # 带认证代理工具
+    AuthenticatedProxy,
+    create_proxy_config,
+    format_proxy_for_request,
+    
+    # 分布式协调工具
+    generate_pagination_tasks,
+    distribute_tasks,
+    DistributedCoordinator
+)
+
+
+def demo_data_processing_tools():
+    """演示数据处理工具的使用"""
+    print("=== 数据处理工具演示 ===\n")
+    
+    # 数据清洗
+    dirty_text = "<p>这是一个&nbsp;<b>测试</b>&amp;文本</p>"
+    clean_result = clean_text(dirty_text)
+    print(f"清洗文本: {dirty_text} -> {clean_result}")
+    
+    # 数据格式化
+    price = 1234.567
+    formatted_price = format_currency(price, "¥", 2)
+    print(f"格式化货币: {price} -> {formatted_price}")
+    
+    # 字段验证
+    email = "test@example.com"
+    is_valid_email = validate_email(email)
+    print(f"验证邮箱: {email} -> {'有效' if is_valid_email else '无效'}")
+    
+    url = "https://example.com"
+    is_valid_url = validate_url(url)
+    print(f"验证URL: {url} -> {'有效' if is_valid_url else '无效'}")
+    
+    # 数据完整性检查
+    data = {
+        "name": "张三",
+        "email": "test@example.com",
+        "phone": "13812345678"
+    }
+    required_fields = ["name", "email", "phone", "address"]
+    integrity_result = check_data_integrity(data, required_fields)
+    print(f"数据完整性检查: {integrity_result}")
+    
+    print()
+
+
+def demo_retry_mechanism():
+    """演示重试机制的使用"""
+    print("=== 重试机制演示 ===\n")
+    
+    # 指数退避
+    for attempt in range(5):
+        delay = exponential_backoff(attempt)
+        print(f"重试次数 {attempt}: 延迟 {delay:.2f} 秒")
+    
+    # 重试装饰器示例
+    @retry(max_retries=3)
+    def unreliable_function():
+        import random
+        if random.random() < 0.7:  # 70%概率失败
+            raise ConnectionError("网络连接失败")
+        return "成功执行"
+    
+    try:
+        result = unreliable_function()
+        print(f"函数执行结果: {result}")
+    except Exception as e:
+        print(f"函数执行失败: {e}")
+    
+    print()
+
+
+def demo_anti_crawler_tools():
+    """演示反爬虫应对工具的使用"""
+    print("=== 反爬虫应对工具演示 ===\n")
+    
+    # 反爬虫工具
+    anti_crawler = AntiCrawler()
+    
+    # 获取随机User-Agent
+    user_agent = anti_crawler.get_random_user_agent()
+    print(f"随机User-Agent: {user_agent[:50]}...")
+    
+    # 轮换代理
+    proxy = anti_crawler.rotate_proxy()
+    print(f"轮换代理: {proxy}")
+    
+    # 检测验证码
+    response_with_captcha = "请输入验证码进行验证"
+    has_captcha = anti_crawler.handle_captcha(response_with_captcha)
+    print(f"检测验证码: {response_with_captcha} -> {'需要验证码' if has_captcha else '无需验证码'}")
+    
+    # 检测频率限制
+    status_code = 429  # Too Many Requests
+    response_headers = {"Retry-After": "60"}
+    is_rate_limited = anti_crawler.detect_rate_limiting(status_code, response_headers)
+    print(f"检测频率限制: 状态码{status_code} -> {'被限制' if is_rate_limited else '未限制'}")
+    
+    print()
+
+
+def demo_authenticated_proxy_tools():
+    """演示带认证代理工具的使用"""
+    print("=== 带认证代理工具演示 ===\n")
+    
+    # 不同类型的代理URL
+    proxy_urls = [
+        "http://user:pass@proxy1.example.com:8080",  # 带认证HTTP代理
+        "https://username:password@proxy2.example.com:443",  # 带认证HTTPS代理
+        "http://proxy3.example.com:8080"  # 不带认证代理
+    ]
+    
+    for proxy_url in proxy_urls:
+        print(f"处理代理: {proxy_url}")
+        
+        # 创建代理对象
+        proxy = AuthenticatedProxy(proxy_url)
+        
+        # 为不同下载器格式化代理配置
+        for downloader in ["aiohttp", "httpx", "curl_cffi"]:
+            config = create_proxy_config(proxy_url)
+            formatted = format_proxy_for_request(config, downloader)
+            print(f"  {downloader}格式: {formatted}")
+        
+        print()
+
+
+def demo_distributed_coordinator_tools():
+    """演示分布式协调工具的使用"""
+    print("=== 分布式协调工具演示 ===\n")
+    
+    # 生成分页任务
+    base_url = "https://example.com/products"
+    pagination_tasks = generate_pagination_tasks(base_url, 1, 5)
+    print(f"生成分页任务 ({len(pagination_tasks)} 个):")
+    for i, task in enumerate(pagination_tasks[:3]):  # 只显示前3个
+        print(f"  {i+1}. {task}")
+    if len(pagination_tasks) > 3:
+        print(f"  ... 还有 {len(pagination_tasks) - 3} 个任务")
+    
+    # 任务分发
+    tasks = list(range(1, 21))  # 20个任务
+    distributed = distribute_tasks(tasks, 4)  # 分发给4个工作节点
+    print(f"\n任务分发 (20个任务分发给4个工作节点):")
+    for i, worker_tasks in enumerate(distributed):
+        print(f"  工作节点 {i+1}: {len(worker_tasks)} 个任务 -> {worker_tasks}")
+    
+    # 分布式协调器
+    coordinator = DistributedCoordinator()
+    cluster_info = coordinator.get_cluster_info()
+    print(f"\n集群信息: {cluster_info}")
+    
+    print()
+
+
+def demo_in_spider():
+    """演示在爬虫中使用高级工具"""
+    print("=== 在爬虫中使用高级工具 ===\n")
+    print("在爬虫项目中，您可以这样使用高级工具:")
+    print("""
+import asyncio
+from crawlo import Spider, Request
+from crawlo.tools import (
+    clean_text,
+    validate_email,
+    AntiCrawler,
+    DistributedCoordinator,
+    retry,
+    AuthenticatedProxy
+)
+
+class AdvancedSpider(Spider):
+    def __init__(self):
+        super().__init__()
+        self.anti_crawler = AntiCrawler()
+        self.coordinator = DistributedCoordinator()
+        # 代理列表
+        self.proxy_urls = [
+            "http://user1:pass1@proxy1.example.com:8080",
+            "http://user2:pass2@proxy2.example.com:8080",
+            "http://proxy3.example.com:8080"  # 不带认证
+        ]
+    
+    def start_requests(self):
+        # 生成分页任务
+        base_url = "https://api.example.com/products"
+        pagination_tasks = self.coordinator.generate_pagination_tasks(base_url, 1, 100)
+        
+        for i, url in enumerate(pagination_tasks):
+            # 轮换使用代理
+            proxy_url = self.proxy_urls[i % len(self.proxy_urls)]
+            proxy = AuthenticatedProxy(proxy_url)
+            
+            request = Request(url, callback=self.parse)
+            
+            # 根据下载器类型设置代理
+            downloader_type = self.crawler.settings.get("DOWNLOADER_TYPE", "aiohttp")
+            if downloader_type == "aiohttp":
+                request.proxy = proxy.clean_url
+                auth = proxy.get_auth_credentials()
+                if auth:
+                    request.meta["proxy_auth"] = auth
+            elif downloader_type == "httpx":
+                request.proxy = proxy.clean_url
+            elif downloader_type == "curl_cffi":
+                request.proxy = proxy.proxy_dict
+                auth_header = proxy.get_auth_header()
+                if auth_header:
+                    request.headers["Proxy-Authorization"] = auth_header
+            
+            yield request
+    
+    @retry(max_retries=3)
+    async def parse(self, response):
+        # 检查是否遇到验证码
+        if self.anti_crawler.handle_captcha(response.text):
+            # 处理验证码逻辑
+            print("遇到验证码，需要处理")
+            return
+            
+        # 提取数据
+        products = response.css('.product-item')
+        for product in products:
+            name = product.css('.product-name::text').get()
+            price_text = product.css('.price::text').get()
+            email = product.css('.contact-email::text').get()
+            
+            # 数据清洗和验证
+            clean_name = clean_text(name) if name else None
+            clean_price = clean_text(price_text) if price_text else None
+            is_valid_email = validate_email(email) if email else False
+            
+            # 检查数据是否重复
+            if not await self.coordinator.is_duplicate({"name": clean_name, "price": clean_price}):
+                # 添加到去重集合
+                await self.coordinator.add_to_dedup({"name": clean_name, "price": clean_price})
+                
+                # 处理产品数据...
+                pass
+    """)
+
+
+if __name__ == '__main__':
+    # 运行演示
+    demo_data_processing_tools()
+    demo_retry_mechanism()
+    demo_anti_crawler_tools()
+    demo_authenticated_proxy_tools()
+    demo_distributed_coordinator_tools()
+    demo_in_spider()