crawlo 1.4.0__py3-none-any.whl → 1.4.2__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 (45) hide show
  1. crawlo/__init__.py +9 -4
  2. crawlo/__version__.py +1 -1
  3. crawlo/core/__init__.py +8 -2
  4. crawlo/core/scheduler.py +2 -2
  5. crawlo/downloader/aiohttp_downloader.py +7 -2
  6. crawlo/extension/log_interval.py +44 -7
  7. crawlo/initialization/__init__.py +6 -2
  8. crawlo/middleware/middleware_manager.py +1 -1
  9. crawlo/mode_manager.py +13 -7
  10. crawlo/pipelines/bloom_dedup_pipeline.py +5 -15
  11. crawlo/pipelines/database_dedup_pipeline.py +5 -8
  12. crawlo/pipelines/memory_dedup_pipeline.py +5 -15
  13. crawlo/pipelines/redis_dedup_pipeline.py +2 -15
  14. crawlo/project.py +18 -7
  15. crawlo/settings/default_settings.py +114 -150
  16. crawlo/settings/setting_manager.py +14 -9
  17. crawlo/tools/distributed_coordinator.py +4 -8
  18. crawlo/utils/fingerprint.py +123 -0
  19. {crawlo-1.4.0.dist-info → crawlo-1.4.2.dist-info}/METADATA +1 -1
  20. {crawlo-1.4.0.dist-info → crawlo-1.4.2.dist-info}/RECORD +45 -29
  21. examples/test_project/__init__.py +7 -0
  22. examples/test_project/run.py +35 -0
  23. examples/test_project/test_project/__init__.py +4 -0
  24. examples/test_project/test_project/items.py +18 -0
  25. examples/test_project/test_project/middlewares.py +119 -0
  26. examples/test_project/test_project/pipelines.py +97 -0
  27. examples/test_project/test_project/settings.py +170 -0
  28. examples/test_project/test_project/spiders/__init__.py +10 -0
  29. examples/test_project/test_project/spiders/of_week_dis.py +144 -0
  30. tests/debug_framework_logger.py +1 -1
  31. tests/debug_log_levels.py +1 -1
  32. tests/test_all_pipeline_fingerprints.py +134 -0
  33. tests/test_default_header_middleware.py +242 -87
  34. tests/test_fingerprint_consistency.py +136 -0
  35. tests/test_fingerprint_simple.py +52 -0
  36. tests/test_framework_logger.py +1 -1
  37. tests/test_framework_startup.py +1 -1
  38. tests/test_hash_performance.py +100 -0
  39. tests/test_mode_change.py +1 -1
  40. tests/test_offsite_middleware.py +185 -162
  41. tests/test_offsite_middleware_simple.py +204 -0
  42. tests/test_pipeline_fingerprint_consistency.py +87 -0
  43. {crawlo-1.4.0.dist-info → crawlo-1.4.2.dist-info}/WHEEL +0 -0
  44. {crawlo-1.4.0.dist-info → crawlo-1.4.2.dist-info}/entry_points.txt +0 -0
  45. {crawlo-1.4.0.dist-info → crawlo-1.4.2.dist-info}/top_level.txt +0 -0
@@ -1,5 +1,5 @@
1
- crawlo/__init__.py,sha256=rCeDq1OoX6mmcBxuK60eUpEp1cIg5T8Zgic3FUQAOkA,2318
2
- crawlo/__version__.py,sha256=EyMGX1ADFzN6XVXHWbJUtKPONYKeFkvWoKIFPDDB2I8,22
1
+ crawlo/__init__.py,sha256=WD-F_HxUb9ad2v7J_yipTK4wwENCzIYwa7AF14eL4sg,2288
2
+ crawlo/__version__.py,sha256=Gom1_ABKKkZoIghfDiYvSntLG2OKXC64sJD2Xm8bUKc,22
3
3
  crawlo/cli.py,sha256=OXprmcTUbFK02ptw_Gq8Gk4-ZCU-WEMJgzU1ztgP6Bk,2327
4
4
  crawlo/config.py,sha256=dNoNyTkXLe2msQ7bZx3YTQItk1m49nIg5-g89FQDNwE,9486
5
5
  crawlo/config_validator.py,sha256=gsiLqf5swWd9ISDvoLqCdG7iSXr-ZdBPD4iT6ug1ua4,11239
@@ -7,8 +7,8 @@ crawlo/crawler.py,sha256=E83JhClOe58XVX1ma0f-HAF1BJ7Ej9Zs0w51ERs3fgA,26348
7
7
  crawlo/event.py,sha256=7-y6HNv_EIJSYQNzsj0mVK-Gg4ON3wdQeMdQjfFJPlw,313
8
8
  crawlo/exceptions.py,sha256=sMay0wnWLfc_FXWslqxm60qz6b66LXs3EdN_w8ygE9k,1166
9
9
  crawlo/framework.py,sha256=1RVBwj_VBzfJiMB3lq6XcfFHCjRBHyT4D_T2X4fU_6g,9166
10
- crawlo/mode_manager.py,sha256=JP8_jkH2p9LMg1-g1e05PhSggSvt4jO_oO2h51pLVYQ,7399
11
- crawlo/project.py,sha256=DooXmO0nmcHPVRsnDBTE0dOrX-KOqnJe6A0s_-qOxRI,12147
10
+ crawlo/mode_manager.py,sha256=j5Kez-KwZQWbEWeYlyUZov18kk8ZRQFYEBUzbkIc-DY,7549
11
+ crawlo/project.py,sha256=LofpNMP1D5AHMe987jfgkSFTjRmrfF5zUBkXl6Cvp3U,12730
12
12
  crawlo/stats_collector.py,sha256=copzmfWTArYZCkMeZJsJfJcdC36s7_LM88hxAYttoeE,2306
13
13
  crawlo/subscriber.py,sha256=D3hzE7Pc_zJjc-zR7lct5pt32bz6LsDYeC8uHlS4Hso,4986
14
14
  crawlo/task_manager.py,sha256=a9JWpqiozFEhReH4PwD9HsDs050HERwi9X9LNGdOp0E,5828
@@ -21,14 +21,14 @@ crawlo/commands/run.py,sha256=gQ14PN3ZxsRNapRsyGZ4qdhbqzh70EnuS2YPaIUA8q0,12828
21
21
  crawlo/commands/startproject.py,sha256=aqKRJarKqTf5XjJnGXwjRpp0uYF16LreFbwwQLGpK-0,16070
22
22
  crawlo/commands/stats.py,sha256=8wTubR1RQ1JPTlpOKArcGcQ39bM-0cuH27lDpndnwPQ,6014
23
23
  crawlo/commands/utils.py,sha256=Psfu2tKrmDloMq0WnfXLaxx0lJFitMZ-FWS3HAIrziQ,5382
24
- crawlo/core/__init__.py,sha256=nikMDqFwnDfE8ugqwAIfycBtIqIVZpeprjEYW-H5Dkw,1272
24
+ crawlo/core/__init__.py,sha256=Mcf4BKnjz-AP72eLCSh5ryLoZchxJnr7Jqv0W_OpkiI,1278
25
25
  crawlo/core/engine.py,sha256=0l7TVNf2R8EHJAZ4ktj71j-qysrq84cYqf_7LEzzYJM,19096
26
26
  crawlo/core/processor.py,sha256=wO6DMU-Azr0yaMLJw8LSTG19a6ZAvPuT3J7wNLfbpu4,1577
27
- crawlo/core/scheduler.py,sha256=By1JB0iukcss5j0nrj1rq1Lk-VmmUHIiGl0RLCH9YUs,12630
27
+ crawlo/core/scheduler.py,sha256=C2V23SIm1VGdi3A41TThB3zE99QFxTnsJp4SDOvSaBE,12561
28
28
  crawlo/data/__init__.py,sha256=8MgDxcMhx-emFARcLAw_ODOZNz0neYBcx7kEbzothd8,116
29
29
  crawlo/data/user_agents.py,sha256=6V34lYHREWV5ZR5wH-1pCnr1Y3ZYC7iMLfC6vZHyhZQ,9697
30
30
  crawlo/downloader/__init__.py,sha256=PB8oluLFMX2PBmeb3NBKkM6GaceX0ujFId8t2URy1ks,8624
31
- crawlo/downloader/aiohttp_downloader.py,sha256=rkCgEfX_s7w-cRK2ZoX43Unt9C7pPPYP64q22ShJMso,9107
31
+ crawlo/downloader/aiohttp_downloader.py,sha256=nlsq2CE-NcmT7nsNEENWC66YlWDx_JzS-eA-P2cvw_Q,9323
32
32
  crawlo/downloader/cffi_downloader.py,sha256=BpA1q6Udz7sSXJ0gX94xGnzy8cdgK-vlr_Q6YA4QIxE,10243
33
33
  crawlo/downloader/httpx_downloader.py,sha256=7jfQfvAtfk8yD_mvwUbWLhYOxMM7r1nudiU7m_Jl9wc,12037
34
34
  crawlo/downloader/hybrid_downloader.py,sha256=4SzOPEwBlSZVzUAWR3DyxMx2Tsx15YrpBvQS4it4Vps,8028
@@ -36,7 +36,7 @@ crawlo/downloader/playwright_downloader.py,sha256=Lnc7k5cXhVnURXSxgZFCYMJkBxLg5F
36
36
  crawlo/downloader/selenium_downloader.py,sha256=B_0muNi-GQ_hgoYHcf7wgu01V68q7xKnSh-0kzlUiio,21036
37
37
  crawlo/extension/__init__.py,sha256=7HxWQKBuiVphZUBLIBVCtIjgFIbzTa5QDOQp6WH4HhU,2923
38
38
  crawlo/extension/health_check.py,sha256=0GveZgUtFwjYEKlm3qbwIvCmb4FR0qrIKc8cEF1yQV8,5516
39
- crawlo/extension/log_interval.py,sha256=VCIeNqXcWDnxj4m6l77cjqgRzV8LfsPMb22X0Xc1Vwc,2417
39
+ crawlo/extension/log_interval.py,sha256=gWCcUCvMzpmx1IE_HvUGAvhfUIqd-UjARNNQLqvjyow,4403
40
40
  crawlo/extension/log_stats.py,sha256=X90Y_E6USAdm55yvRN5t59HNLmyN9QMKglhbPPxtehA,2382
41
41
  crawlo/extension/logging_extension.py,sha256=8KT-WJRK5tocS2kBOiSquree53L11qD1vLg-P8ob40U,2354
42
42
  crawlo/extension/memory_monitor.py,sha256=4aszl3C0GMQbqFhGZjZq5iQuXQR1sOz06VHjjEHgkyE,4290
@@ -49,7 +49,7 @@ crawlo/factories/registry.py,sha256=LrtH7wMGQ2ZrswxnHDM9s43ckJ1isJKL7R8uyMQ8hCc,
49
49
  crawlo/filters/__init__.py,sha256=XC_Q4ykZtSNYizYlAcehVwBBNO3lZ2zuWwafzXiuWyQ,4241
50
50
  crawlo/filters/aioredis_filter.py,sha256=ZEApX23-S-7ruO_TSTKI0Noh8SEwjdZznf8TySeEtbQ,9255
51
51
  crawlo/filters/memory_filter.py,sha256=mO4oBPV5_uAiBQF3a16tU5tcD8244dOjKoNX_MU8cEw,9292
52
- crawlo/initialization/__init__.py,sha256=Y7pLI5MDiAgG1NuRvkIhwzaE6438_2ZP5jK317utgUQ,1084
52
+ crawlo/initialization/__init__.py,sha256=ML9fKhttJC3TRAtp5n9MTevLBH-vdPUXwKihQdxEUlE,1088
53
53
  crawlo/initialization/built_in.py,sha256=EkZIPBrqsvFf0CuBL6POk2IJiDFf8q30eRGMqcL2N8M,15333
54
54
  crawlo/initialization/context.py,sha256=SL2ge47EmyLHzB5yldISA-xr__ZOV1xnQP_-1RF5v0Y,4722
55
55
  crawlo/initialization/core.py,sha256=ZR6veRDkKU5erQGXGKzgX6TU2_i6YkWsuFUeWnOEVjo,6679
@@ -66,7 +66,7 @@ crawlo/logging/manager.py,sha256=hbdwyFGnnyRFrVDXoqzHs8oERx72NHrf7KqwCf4oPc4,307
66
66
  crawlo/middleware/__init__.py,sha256=ldaGFNbiJnK9Fx12Vdf9fDNfzXxoETtShp5r-vodtw0,549
67
67
  crawlo/middleware/default_header.py,sha256=wQ7BrUHd-hRosFoKsReV9hwNNr_jwK6V0ZfxL6MOGrk,5032
68
68
  crawlo/middleware/download_delay.py,sha256=zt9R5g2HWErWA_MAOnGcw_D8l6HD769Kyaw-Hv-vcTc,3438
69
- crawlo/middleware/middleware_manager.py,sha256=bQuIxn-i2oud-0hDkv890sa3YvNMbuJIR8zuAmIdLKA,6289
69
+ crawlo/middleware/middleware_manager.py,sha256=1-qeqlyjBDvLhojt8aOT-EASe9gCcwzJ2q53iRagOHI,6280
70
70
  crawlo/middleware/offsite.py,sha256=FIWZvkkzlDJfvQc7Ud7BdfDZ78Sa85qlEEwAR76hSBk,4559
71
71
  crawlo/middleware/proxy.py,sha256=NquB6tqHAgHs3-2_1_5220kJYfjNG5JyHRJyo_2j4wo,15636
72
72
  crawlo/middleware/request_ignore.py,sha256=xcyZ1c7r_HhbzR3r9pfjsLGW7L7FBVeYvlNt8cpP2wY,2577
@@ -78,23 +78,23 @@ crawlo/network/__init__.py,sha256=BLPERYPo22g1BXrW--wUnlolrdFUmOPjgOB8XQQJlck,39
78
78
  crawlo/network/request.py,sha256=9kV-gqb_d6aCsSBAwyzxnP9a70cAViwX8qvpyYV7Ym4,13799
79
79
  crawlo/network/response.py,sha256=EZiG4LjuIb7PxdGou4H-oSOQhec1ZdBRTkO-5fl8JTo,12701
80
80
  crawlo/pipelines/__init__.py,sha256=lrdVDjeHLNkA4_MAwI1auk_I9xfeU1SlBWXiammb6lc,616
81
- crawlo/pipelines/bloom_dedup_pipeline.py,sha256=AIejBxWpRWg2SSYuMPmPy2VrG_FhFmjXYaAcRhuF7h0,5677
81
+ crawlo/pipelines/bloom_dedup_pipeline.py,sha256=yNs7ON4icJK0nDGpDyZzghbPyf350bMEi1gOn4r_ya8,5317
82
82
  crawlo/pipelines/console_pipeline.py,sha256=KABkR3J-rqO0Awox7lizxKR2XuHfVhWPiVRgIybwwu4,1248
83
83
  crawlo/pipelines/csv_pipeline.py,sha256=6FBT2AoU6iNU-5NfgWRq7-JpF9dK2nBokjxx-y4jIas,12174
84
- crawlo/pipelines/database_dedup_pipeline.py,sha256=qQ6w0eoGcUB26VO1lgI8GFhVjERG-GZhg5UCTYKyovg,7135
84
+ crawlo/pipelines/database_dedup_pipeline.py,sha256=EfX_y9JiqD5EissBZNWfDYJavMcCYQ72swzfe7RsNZc,7099
85
85
  crawlo/pipelines/json_pipeline.py,sha256=vlu1nqbD2mtqtExt9cL5nibx1CwJM1RNqd4WGjZRHAY,8367
86
- crawlo/pipelines/memory_dedup_pipeline.py,sha256=9KuUA1S0uHWSB3qJntPdg9ifPdRXwc8ju4j9tWe8qTo,3853
86
+ crawlo/pipelines/memory_dedup_pipeline.py,sha256=sHoihpQiMZ7teiH4Ctl8OIPJs1x1bRRgzdy89JXFm7U,3493
87
87
  crawlo/pipelines/mongo_pipeline.py,sha256=k7gNqAO-g2MtIfArphC6z5ZzkKVRkBKcv-2ImziPFA0,5706
88
88
  crawlo/pipelines/mysql_pipeline.py,sha256=_oRfIvlEiOsTKkr4v-yPTcL8nG9O9coRmke2ZSkkKII,13871
89
89
  crawlo/pipelines/pipeline_manager.py,sha256=BX17CU9JK2xJeIdzQ4FeK7kwpwew1k-BEVMk9oviqTQ,3682
90
- crawlo/pipelines/redis_dedup_pipeline.py,sha256=6fkHt7O-R2TTMlULgxyqPdyKBjsRzYh_GL-Juye4ZQ0,6410
90
+ crawlo/pipelines/redis_dedup_pipeline.py,sha256=zNk7WJxtgWNfRzKnyxOM2OyfsKhPNsOmy_8IGT1iZi0,5921
91
91
  crawlo/queue/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
92
92
  crawlo/queue/pqueue.py,sha256=j2ISmyays5t1tuI36xM6EcELwSpq2xIjAScSBWSRZms,1220
93
93
  crawlo/queue/queue_manager.py,sha256=JfkjtOD04e_OZZvEEvp3O_W3lfGXhHslZHrCgw90amY,20693
94
94
  crawlo/queue/redis_priority_queue.py,sha256=Evmo514OFL0a7Xu2SdCiz6klFUGH1gmjlxCc01vX1tQ,15400
95
95
  crawlo/settings/__init__.py,sha256=xsukVKn_h2Hopm1Nj-bXkhbfyS62QTTvJi7fhZUwR9M,123
96
- crawlo/settings/default_settings.py,sha256=LReJ11Wm8wh1z2GHgGRBYH6Tpq6_CkRd8QZ4dKRCqI0,13220
97
- crawlo/settings/setting_manager.py,sha256=AWPvvhOGo04Yv_q3jqEMyzhEpbxOX_Wr8tSHmI2sUnA,8109
96
+ crawlo/settings/default_settings.py,sha256=BBJkTYe2ViIuGzr6KtWnJRDe0Yj6dkcBo56VxDeJIkE,12552
97
+ crawlo/settings/setting_manager.py,sha256=hfmZfRcCQjTCSFWOelrzsIjLBIGDPmy_vlWDm6rhHeM,8376
98
98
  crawlo/spider/__init__.py,sha256=oi9LEYq9xaCSjktAIRUgjpGQQI7rTtN61ESdHeWb1x4,21224
99
99
  crawlo/templates/crawlo.cfg.tmpl,sha256=9BAmwEibS5Tvy6HIcGXPb0BGeuesmibebmTW0iAEkmo,230
100
100
  crawlo/templates/run.py.tmpl,sha256=j8xRI4IEI_YiDFvMyfYG0XD2GgBM9eXgSqpvBniferU,927
@@ -117,7 +117,7 @@ crawlo/tools/authenticated_proxy.py,sha256=L93WeXajIZ3si8xNcE7bBPv34FvqSyTvVfD78
117
117
  crawlo/tools/data_formatter.py,sha256=NEj3NqPiyG67V6qDgn2KNj9VNHWOLNwX-7p_nad0znc,7583
118
118
  crawlo/tools/data_validator.py,sha256=hxPN28YtJDFFLjBBYhDjHmR8ShNTEjgIsv-cmcDKIu8,5310
119
119
  crawlo/tools/date_tools.py,sha256=jjP5xA0-aDgm9UIK1RG2qaNagBzHFQ-BBDMo_YzSlLQ,8906
120
- crawlo/tools/distributed_coordinator.py,sha256=Au20nZ4qUiAZUD2A1yfwD3soaHADpkEZt1hRyegp6M4,12323
120
+ crawlo/tools/distributed_coordinator.py,sha256=eUAQudIaz96WGIPVJxF_W0BOKDpRBX3ZmPLsDmiBKXM,12190
121
121
  crawlo/tools/encoding_converter.py,sha256=7P9Z7J1ALw_PPNApmjFsHZDpRxgxzduiViluenlSLEU,4043
122
122
  crawlo/tools/network_diagnostic.py,sha256=92diB7Ppo_TKGDYCRLzy7uvQMGApgGLwv7P5w4OpCms,12649
123
123
  crawlo/tools/request_tools.py,sha256=CjyFBtRQf_vFjQhaVwgHSGai4ZaWS8IIaF1flSfJxDs,2338
@@ -132,6 +132,7 @@ crawlo/utils/db_helper.py,sha256=3ib5-agrlwf2t5S_QtLRYH75wvJDlYbRqRmDEbpH5Bo,105
132
132
  crawlo/utils/enhanced_error_handler.py,sha256=hj5AElt3ajfqnP4csQnEfEnzkbIep9k65DNQiCbmTFo,13858
133
133
  crawlo/utils/env_config.py,sha256=HbZOEKkeQ0FMdZYJu9SgmSNEmfPJrmAzA7lHu5Du1DA,3937
134
134
  crawlo/utils/error_handler.py,sha256=nDfDA99q2sirE2pe7OT2bcA54GqUiAYgtdAh38uFEX4,5290
135
+ crawlo/utils/fingerprint.py,sha256=5XTH8ma0HSHc8arvre_sVv2g0Unxte1KLScmf3bHPDA,3565
135
136
  crawlo/utils/func_tools.py,sha256=WUZEGpWMuDDX7g-QySM7iaiC74erW2SSkZoUvDw1NjM,2369
136
137
  crawlo/utils/large_scale_config.py,sha256=j7wQ5ty7pQlBRygw2vhRJ7OI19RYBZKPfYMP3WeF2WI,8154
137
138
  crawlo/utils/large_scale_helper.py,sha256=Kxdy3WMuqjzQTyCc6z4xEYxXDi4xnYKJzsVwaBYZrrg,12108
@@ -147,6 +148,15 @@ crawlo/utils/system.py,sha256=HvWV1acxou0Rn0L7pNq4CnV_GWFeU0Tmjy3_nLD8M64,237
147
148
  crawlo/utils/tools.py,sha256=5Uv25Wy4m_ndZY0-n-eX-t3PxvaZ6wR3-Wvx-o7_Vrs,271
148
149
  crawlo/utils/url.py,sha256=rlgX2VlJv6JvLmCDTsbxzMSXE6R5ZL_0dLEqprsA-JU,1482
149
150
  examples/__init__.py,sha256=6i631BPnS_TR_BWUjtjB5CBO-zv9kRkwQTQvSya2wHE,123
151
+ examples/test_project/__init__.py,sha256=sBO0-NPkGiKKO44U9OYknIdkPGKgJGn7ne2M7v_YOSU,129
152
+ examples/test_project/run.py,sha256=5kADlYJYVp2seoxM5KPCX8qwSB-YzyLf-SGm66FcvyQ,919
153
+ examples/test_project/test_project/__init__.py,sha256=-8hHXHKxttgUB58mL95faujZIsubNXuA_0-VzU-Mmy8,54
154
+ examples/test_project/test_project/items.py,sha256=f4GN_2OChAdDI0zunbWIA6dpP7ou6ySt4mY98GGZzos,293
155
+ examples/test_project/test_project/middlewares.py,sha256=qh_UvYaxH_mK1h8oNL405NQ2SYLEWAKs7r9Fyw-Jw5M,4152
156
+ examples/test_project/test_project/pipelines.py,sha256=k1Z4M5StwGF4eHW8JoLCNLSVi57FiAxRRO-ABFynJ1k,2600
157
+ examples/test_project/test_project/settings.py,sha256=Aidvz43WZYu7LAJ3N9gXdpddWCP_656kIJGJMe7J4NA,6946
158
+ examples/test_project/test_project/spiders/__init__.py,sha256=tWZ6jEMrDw1KoRBw12F54srI1-YX7RNYe0dtU4OP0aQ,203
159
+ examples/test_project/test_project/spiders/of_week_dis.py,sha256=zKulqu_lc7NS0ewDh_MCttwpXMBp0P2fPostkxxM3Xc,5035
150
160
  tests/__init__.py,sha256=scL1IPVT1iucth7v8ffrjRdeW7QrC_Y7AMmFVMdTY1Y,129
151
161
  tests/advanced_tools_example.py,sha256=7nlFLRVMVYzDz_CAdgQa9fJu7o0M6jBMo7PTvUsRbo0,9065
152
162
  tests/authenticated_proxy_example.py,sha256=rsLmILsrf9PpR77ekGi8KpB1dAYZdF26hlxkBjm4rSQ,2913
@@ -160,9 +170,9 @@ tests/config_validation_demo.py,sha256=5MzW5P7ZX6xoMW_zC6XmIA50KWMTu0iB5H2hTe42S
160
170
  tests/controlled_spider_example.py,sha256=SP_k4mdKPvD1JCPs9UCm68jcy2Frg84vvXv9-14RC6I,7776
161
171
  tests/date_tools_example.py,sha256=x_-duqnVZ-Hrk-SaNplIfcIV6W3c6u6MTxW35u1i0F0,4862
162
172
  tests/debug_configure.py,sha256=E-6Djz8kk7tf2pzEqrGdekW2W20vrJeZN7iNm9ArWKk,2144
163
- tests/debug_framework_logger.py,sha256=l2OX6igGu-pCUGrlwdWqcenqSSK9wMDheZ47XhEUqPg,3341
173
+ tests/debug_framework_logger.py,sha256=lAxT1esheIyNtgjXf6VJj8Lv0TNw5KUHdjaKHTYrF7Q,3329
164
174
  tests/debug_log_config.py,sha256=F5MrUmpkaD9Dc1eSbajaOrw3nKo9Sp55BTnNxmQkUWc,3588
165
- tests/debug_log_levels.py,sha256=yPyKRNwz9kNWU1QMVLRD989Wh2sb6CrH4GAsMO0PHW8,2117
175
+ tests/debug_log_levels.py,sha256=39ugttR13gfotsS3I4XVoWRRjTXPpLtuJOyU8V_ijEs,2105
166
176
  tests/debug_pipelines.py,sha256=VpUmoYlt6Ci7foIGuQIotUu42xp6TzoA1cBDeagBzDk,2098
167
177
  tests/detailed_log_test.py,sha256=M6yXjQypKmIjihgTSBffkgOzC7Nn0_4ZdQLrBN-L8i0,7268
168
178
  tests/distributed_test.py,sha256=qZpFAMQTFcg0KUEdp2RUpkuYauSCf4C3lbbosyIDqgw,1759
@@ -197,6 +207,7 @@ tests/simple_test.py,sha256=kzMspCmfJxdnAIXXJv9tmDW1gpodkD9pznW5vA_gL84,1211
197
207
  tests/spider_log_timing_test.py,sha256=ngZQ_v3o9oHYcs_BtZgxH1N-N2tZUDPu-cnTnsHEpP8,5396
198
208
  tests/test_advanced_tools.py,sha256=3R8EfKVyBHEb6FA5TP3ieaWeHZhobVgSx8t3phipCrE,5250
199
209
  tests/test_all_commands.py,sha256=yGPw8zMrB5Z5w5LkaymSzKRLOcZsBPBXLvllCkgEY4I,7488
210
+ tests/test_all_pipeline_fingerprints.py,sha256=4dtn-APwK2JIg-c4J-7u9J1PF9L_pdMh4CmIyVP266I,5175
200
211
  tests/test_all_redis_key_configs.py,sha256=SGoip8M7oB2LNWC_31aJ4ECcDRmx0psr7i7DGzuaH7c,5565
201
212
  tests/test_authenticated_proxy.py,sha256=s4pr5JyBTHYQgRq_IymiVKE08vyW1MwR27pSwrrVLVk,4198
202
213
  tests/test_batch_processor.py,sha256=gMPoQcnUMm2-G_d7Zt9QnrRjCx1urzT31tYqoFNEklc,7034
@@ -210,7 +221,7 @@ tests/test_controlled_spider_mixin.py,sha256=7t6VGWr6Hxw0xtIFyToLH8_deSagUtsdqSJ
210
221
  tests/test_crawlo_proxy_integration.py,sha256=SvdBuZjS6N2vuvFkTnc59U5n3dHV3E4dmFayxtmjCm4,2625
211
222
  tests/test_date_tools.py,sha256=CQdAmIS6bpAdwQH9ETDH__06l2gGL7EHUQuh7mdTF-A,3930
212
223
  tests/test_dedup_fix.py,sha256=9rFzzsDJKQbFaohzKJAlqo3Mm4wFy8-wAm3fWmw8jb4,8568
213
- tests/test_default_header_middleware.py,sha256=7kpONSsGMsmWgTX2pCpseme54_-82Baak0xVz6gclJk,5845
224
+ tests/test_default_header_middleware.py,sha256=5zYSZmUR_02UChFZfoCqurabNdAZLy7t4yNZ8I7Bw8E,12813
214
225
  tests/test_distributed.py,sha256=RQHUpDfRNG2x_1Cdr9DLk25IBcgapm_u0xSBMObE0Xc,1725
215
226
  tests/test_double_crawlo_fix.py,sha256=E5NxWHnQkwRTIrJGoag8G29fZqVMnsN6eCPuv17gGq0,7652
216
227
  tests/test_double_crawlo_fix_simple.py,sha256=MlWUqo51kOQ7Gu6Neoler8FVyRs0jpmQWoORHMBENz0,4644
@@ -227,21 +238,26 @@ tests/test_env_config.py,sha256=nfP4nCG9ZHeJUfxo1JKUmiihYbhSeWx_oNW5mMfDHfQ,4746
227
238
  tests/test_error_handler_compatibility.py,sha256=o5JLLLdo25Sl_3hpMx6I2fqSgZFAcnI4E6Ci-KxAxwA,4129
228
239
  tests/test_factories.py,sha256=vXI8tx42iuBivCKQoY2kH7G6c0i_QCmCq77krEgQiGU,8613
229
240
  tests/test_final_validation.py,sha256=aAiWLzhDCcv-GEXg9sauaVIfq5rz3s2vm67Gk2_lmBI,4813
241
+ tests/test_fingerprint_consistency.py,sha256=LI0hDokBtW5OJ6kwn9-x1WiiS_euBqXGNsD1iwngBhQ,4821
242
+ tests/test_fingerprint_simple.py,sha256=H-8C-ae8TDx29BY9xQGQzZXbpk6szj-kWK8zknR1jwk,1575
230
243
  tests/test_framework_env_usage.py,sha256=HYpTwORXeaJHMffCYAGHGvc_a6ax4lo28xP8BYOaKxk,4098
231
- tests/test_framework_logger.py,sha256=HNkOlyA-dQKEdE6H4VaUHfF3aeVkKRoISSr53Hw90qQ,2506
232
- tests/test_framework_startup.py,sha256=I0zUfJUjkM7JgUBChO2w9cIL-tDJwUHdzKm3QjuEEJM,2215
244
+ tests/test_framework_logger.py,sha256=RBwf0aOV1TibMqOajg-KYiq_Oe7gxLfvRAurpyY4rnI,2494
245
+ tests/test_framework_startup.py,sha256=zvpzWwozMxGaCfdEER9A2qJuMYytW5mg3q4T86mJ6to,2203
233
246
  tests/test_get_component_logger.py,sha256=f7nmmSGxoD1i3d17FlSicOmMGLTcyJxcujoS5eJFbAI,2202
247
+ tests/test_hash_performance.py,sha256=pHJpxF09JCCxk_32hRGXx221ySQROCx2OK7Yk6-B1bk,3112
234
248
  tests/test_integration.py,sha256=OCkjyv76Wop7CrXEko6rfoDsIK6SESA18KgCaTwL7Q4,4670
235
249
  tests/test_item_dedup_redis_key.py,sha256=QxLuXHUx0xqT6y7lQzOWcrLkRui7Qs7C6NgRvjzIypA,3720
236
250
  tests/test_large_scale_config.py,sha256=wyeMOMjGYhbZ6mrcnLH3Eh6GfspJwhavwWoyOy1y90c,4184
237
251
  tests/test_large_scale_helper.py,sha256=spvL0MPyXMAUDpzI2fY6-OQdSxOHtgJ1yuSUIbydyHY,8136
238
252
  tests/test_logging_system.py,sha256=_LRdgprZFrChA26JJgkjVyf6S6qRIyi6BRajK13l_Q8,8924
239
- tests/test_mode_change.py,sha256=kh5C4ut7T5dZ8b2dDot4RbLWMXJidv4FHzuTIgDxMBI,2605
253
+ tests/test_mode_change.py,sha256=zNVdmvFOeKD6LMVnCwjtrIyhTw95n1ZQJPjNhOanUHw,2593
240
254
  tests/test_mode_consistency.py,sha256=YJXf0SqAYVnFXy8eeBLC-zGTFAyO2fnsR4qLB76gZts,1225
241
- tests/test_offsite_middleware.py,sha256=L5YT9ZqcQwBunUv0Ddj-sLZcW4IMlAlgaJCwICHFWxI,7543
255
+ tests/test_offsite_middleware.py,sha256=K5NREsWwpJda4OWgf9J4NXIqpbG9jNlgpbALevuGLzc,10358
256
+ tests/test_offsite_middleware_simple.py,sha256=CVBS7dvjpJ_fWBae7t9GtAQF_etn0U_cZ4UQFdu8eh8,7715
242
257
  tests/test_parsel.py,sha256=KYskaN_4HBc1XDTltjVo12v1i7JAThB2UIwcWZ-mwbY,672
243
258
  tests/test_performance.py,sha256=gOJ1EpU9uGynIxETLAroe98OA4QPcX1wchCDJoO41Kc,11130
244
259
  tests/test_performance_monitor.py,sha256=5oEHPJfjZXdtDK2nW_2MuGbOFgTTZyEhLapV9Ug1iHY,4072
260
+ tests/test_pipeline_fingerprint_consistency.py,sha256=WV-1UC6PSXb43B5ATyRDSjW9FcHSBMmHDCFFJwQqE_s,2761
245
261
  tests/test_proxy_api.py,sha256=dVqGElyL3K0_9IqkXzn7Ka2jSuhvYfR1BfZgyVukNM0,10749
246
262
  tests/test_proxy_health_check.py,sha256=xo3QMP1YNw9hu7JDHZOYCUZmFFKLJpHSh4SbxXhCRPQ,1091
247
263
  tests/test_proxy_middleware.py,sha256=qm2B0lepBZqzUpXNi4t1gjrQxUV4MQ2wvpmcaYV6O5A,3900
@@ -286,8 +302,8 @@ tests/verify_distributed.py,sha256=krnYYA5Qx9xXDMWc9YF5DxPSplGvawDg2n0l-3CAqoM,3
286
302
  tests/verify_log_fix.py,sha256=TD7M1R22NxLqQPufvgE-H33u9tUjyz-rSR2ayIXozRU,4225
287
303
  tests/scrapy_comparison/ofweek_scrapy.py,sha256=2Hvpi6DRTubUxBy6RyJApQxMQONPLc1zWjKTQO_i5U4,5652
288
304
  tests/scrapy_comparison/scrapy_test.py,sha256=5sw7jOHhaTmQ8bsUd1TiolAUTRQYQOe-f49HPfysqbI,5466
289
- crawlo-1.4.0.dist-info/METADATA,sha256=WIambmjeZxudgM_Ej7lv8CKd1EyoQ4f-Z4CugfsHTkY,33235
290
- crawlo-1.4.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
291
- crawlo-1.4.0.dist-info/entry_points.txt,sha256=5HoVoTSPxI8SCa5B7pQYxLSrkOdiunyO9tqNsLMv52g,43
292
- crawlo-1.4.0.dist-info/top_level.txt,sha256=keG_67pbZ_wZL2dmDRA9RMaNHTaV_x_oxZ9DKNgwvR0,22
293
- crawlo-1.4.0.dist-info/RECORD,,
305
+ crawlo-1.4.2.dist-info/METADATA,sha256=IwT9XfhtTQOUvMyKss9cne9PjX5RuWpiOkwMVu6zV6c,33235
306
+ crawlo-1.4.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
307
+ crawlo-1.4.2.dist-info/entry_points.txt,sha256=5HoVoTSPxI8SCa5B7pQYxLSrkOdiunyO9tqNsLMv52g,43
308
+ crawlo-1.4.2.dist-info/top_level.txt,sha256=keG_67pbZ_wZL2dmDRA9RMaNHTaV_x_oxZ9DKNgwvR0,22
309
+ crawlo-1.4.2.dist-info/RECORD,,
@@ -0,0 +1,7 @@
1
+ #!/usr/bin/python
2
+ # -*- coding:UTF-8 -*-
3
+ """
4
+ # @Time : 2025-09-27 23:36
5
+ # @Author : crawl-coder
6
+ # @Desc : None
7
+ """
@@ -0,0 +1,35 @@
1
+ #!/usr/bin/env python3
2
+ # -*- coding: UTF-8 -*-
3
+ """
4
+ test_project 项目运行脚本
5
+ ============================
6
+ 基于 Crawlo 框架的简化爬虫启动器。
7
+
8
+ 框架会自动处理爬虫模块的导入和注册,用户无需手动导入。
9
+ 只需指定spider_modules参数,框架会自动扫描并导入所有爬虫。
10
+ """
11
+ import sys
12
+ import asyncio
13
+
14
+ from crawlo.crawler import CrawlerProcess
15
+
16
+
17
+ def main():
18
+ """主函数:运行爬虫"""
19
+ try:
20
+ # 指定爬虫模块路径,框架会自动导入并注册所有爬虫
21
+ spider_modules = ['test_project.spiders']
22
+ process = CrawlerProcess(spider_modules=spider_modules)
23
+
24
+ # TODO 运行指定的爬虫
25
+ asyncio.run(process.crawl('of_week_dis'))
26
+
27
+ except Exception as e:
28
+ print(f"❌ 运行失败: {e}")
29
+ import traceback
30
+ traceback.print_exc()
31
+ sys.exit(1)
32
+
33
+
34
+ if __name__ == '__main__':
35
+ main()
@@ -0,0 +1,4 @@
1
+ # -*- coding: UTF-8 -*-
2
+ """
3
+ test_project 项目包
4
+ """
@@ -0,0 +1,18 @@
1
+ # -*- coding: UTF-8 -*-
2
+ """
3
+ test_project.items
4
+ ======================
5
+ 定义你抓取的数据结构。
6
+ """
7
+
8
+ from crawlo.items import Item, Field
9
+
10
+
11
+ class ExampleItem(Item):
12
+ """
13
+ 一个示例数据项。
14
+ """
15
+ id = Field()
16
+ # price = Field()
17
+ # description = Field()
18
+ pass
@@ -0,0 +1,119 @@
1
+ # -*- coding: UTF-8 -*-
2
+ """
3
+ test_project.middlewares
4
+ ============================
5
+ 自定义中间件,用于在请求/响应/异常处理过程中插入自定义逻辑。
6
+
7
+ 这是一个简单的示例中间件,您可以根据需要添加更多中间件。
8
+ """
9
+
10
+ import random
11
+ from crawlo import Request, Response
12
+ from crawlo.utils.log import get_logger
13
+
14
+
15
+ class ExampleMiddleware:
16
+ """
17
+ 示例中间件,演示如何处理请求、响应和异常。
18
+
19
+ 此中间件会:
20
+ 1. 为请求添加随机 User-Agent
21
+ 2. 记录请求和响应信息
22
+ 3. 处理异常情况
23
+ """
24
+
25
+ def __init__(self):
26
+ self.logger = get_logger(self.__class__.__name__)
27
+ self.user_agents = [
28
+ 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36',
29
+ 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/136.0.0.0 Safari/537.36',
30
+ 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:135.0) Gecko/20100101 Firefox/135.0',
31
+ 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:135.0) Gecko/20100101 Firefox/135.0',
32
+ ]
33
+
34
+ def process_request(self, request, spider):
35
+ """
36
+ 在请求被下载器执行前调用。
37
+
38
+ Args:
39
+ request: 请求对象
40
+ spider: 爬虫实例
41
+
42
+ Returns:
43
+ None: 继续处理请求
44
+ Response: 返回响应对象(短路处理)
45
+ Request: 返回新请求对象(替换原请求)
46
+ """
47
+ # 为请求添加随机 User-Agent
48
+ if 'User-Agent' not in request.headers:
49
+ ua = random.choice(self.user_agents)
50
+ request.headers['User-Agent'] = ua
51
+ self.logger.debug(f"为请求 {request.url} 设置 User-Agent: {ua[:50]}...")
52
+
53
+ return None
54
+
55
+ def process_response(self, request, response, spider):
56
+ """
57
+ 在响应被 Spider 处理前调用。
58
+
59
+ Args:
60
+ request: 原始请求对象
61
+ response: 响应对象
62
+ spider: 爬虫实例
63
+
64
+ Returns:
65
+ Response: 处理后的响应对象
66
+ """
67
+ # 记录响应信息
68
+ self.logger.info(f"收到响应: {request.url} - 状态码: {response.status_code}")
69
+
70
+ # 可以在这里处理特殊状态码
71
+ if response.status_code == 403:
72
+ self.logger.warning(f"访问被拒绝: {request.url}")
73
+
74
+ return response
75
+
76
+ def process_exception(self, request, exception, spider):
77
+ """
78
+ 在下载或处理过程中发生异常时调用。
79
+
80
+ Args:
81
+ request: 请求对象
82
+ exception: 异常对象
83
+ spider: 爬虫实例
84
+
85
+ Returns:
86
+ None: 异常将继续传播
87
+ Response: 返回响应对象(处理异常)
88
+ Request: 返回新请求对象(重试请求)
89
+ """
90
+ self.logger.error(f"请求异常: {request.url} - {exception}")
91
+ return None
92
+
93
+
94
+ # ======================== 使用说明 ========================
95
+ #
96
+ # 在 settings.py 中启用中间件:
97
+ # MIDDLEWARES = [
98
+ # 'test_project.middlewares.ExampleMiddleware',
99
+ # ]
100
+ #
101
+ # 您可以根据需要添加更多中间件,例如:
102
+ # 1. 请求处理中间件(修改请求头、设置代理等)
103
+ # 2. 响应处理中间件(解析、过滤等)
104
+ # 3. 异常处理中间件(重试、记录等)
105
+ #
106
+ # 每个中间件可以实现以下方法:
107
+ # - process_request: 处理请求
108
+ # - process_response: 处理响应
109
+ # - process_exception: 处理异常
110
+ #
111
+ # 注意:Crawlo框架提供了许多内置中间件,您可以直接使用:
112
+ # - DownloadDelayMiddleware: 控制请求延迟
113
+ # - ResponseCodeMiddleware: 处理HTTP状态码并记录统计信息
114
+ # - ResponseFilterMiddleware: 过滤特定状态码的响应
115
+ # - DefaultHeaderMiddleware: 添加默认请求头
116
+ # - ProxyMiddleware: 设置代理
117
+ # - RetryMiddleware: 处理重试逻辑
118
+ # - OffsiteMiddleware: 过滤站外请求
119
+ # ======================== 使用说明 ========================
@@ -0,0 +1,97 @@
1
+ # -*- coding: UTF-8 -*-
2
+ """
3
+ test_project.pipelines
4
+ ==========================
5
+ 数据管道,用于处理 Spider 返回的 Item。
6
+ 例如:清理、验证、去重、保存到数据库等。
7
+
8
+ 这是一个简单的示例管道,您可以根据需要添加更多管道。
9
+ """
10
+
11
+ from datetime import datetime
12
+ from crawlo.exceptions import DropItem
13
+ from crawlo.utils.log import get_logger
14
+
15
+
16
+ class ExamplePipeline:
17
+ """
18
+ 示例管道,演示如何处理数据项。
19
+
20
+ 此管道会:
21
+ 1. 验证必要字段
22
+ 2. 清理数据
23
+ 3. 添加时间戳
24
+ 4. 记录处理日志
25
+ """
26
+
27
+ def __init__(self):
28
+ self.logger = get_logger(self.__class__.__name__)
29
+ self.item_count = 0
30
+
31
+ def process_item(self, item, spider):
32
+ """
33
+ 处理数据项。
34
+
35
+ Args:
36
+ item: 要处理的数据项
37
+ spider: 爬虫实例
38
+
39
+ Returns:
40
+ 处理后的数据项
41
+
42
+ Raises:
43
+ DropItem: 如果数据项无效则抛出此异常
44
+ """
45
+ # 验证必要字段
46
+ if not item.get('title') or not item.get('url'):
47
+ raise DropItem("缺少必要字段: title 或 url")
48
+
49
+ # 数据清理
50
+ item['title'] = str(item['title']).strip()
51
+
52
+ # 添加处理时间戳
53
+ item['processed_at'] = datetime.now().isoformat()
54
+
55
+ # 计数器
56
+ self.item_count += 1
57
+
58
+ # 记录日志
59
+ self.logger.info(f"处理第 {self.item_count} 个数据项: {item['title']}")
60
+
61
+ return item
62
+
63
+ def open_spider(self, spider):
64
+ """
65
+ 爬虫启动时调用。
66
+
67
+ Args:
68
+ spider: 爬虫实例
69
+ """
70
+ self.logger.info(f"管道已启动,准备处理爬虫 '{spider.name}' 的数据")
71
+
72
+ def close_spider(self, spider):
73
+ """
74
+ 爬虫关闭时调用。
75
+
76
+ Args:
77
+ spider: 爬虫实例
78
+ """
79
+ self.logger.info(f"管道已关闭,共处理了 {self.item_count} 个数据项")
80
+
81
+
82
+ # ======================== 使用说明 ========================
83
+ #
84
+ # 在 settings.py 中启用管道:
85
+ # PIPELINES = [
86
+ # 'test_project.pipelines.ExamplePipeline',
87
+ # ]
88
+ #
89
+ # 您可以根据需要添加更多管道,例如:
90
+ # 1. 数据验证管道
91
+ # 2. 去重管道
92
+ # 3. 数据存储管道(数据库、文件等)
93
+ # 4. 数据转换管道
94
+ #
95
+ # 每个管道都应该实现 process_item 方法,
96
+ # 可选实现 open_spider 和 close_spider 方法。
97
+ # ======================== 使用说明 ========================
@@ -0,0 +1,170 @@
1
+ # -*- coding: UTF-8 -*-
2
+ """
3
+ test_project 项目配置文件(分布式版)
4
+ =============================
5
+ 基于 Crawlo 框架的分布式爬虫项目配置。
6
+ 适合大规模数据采集和多节点部署。
7
+ """
8
+
9
+ import os
10
+
11
+ # ============================== 项目基本信息 ==============================
12
+ PROJECT_NAME = 'test_project'
13
+
14
+ # ============================== 运行模式 ==============================
15
+ RUN_MODE = 'distributed'
16
+
17
+ # ============================== 并发配置 ==============================
18
+ CONCURRENCY = 16
19
+ MAX_RUNNING_SPIDERS = 5
20
+ DOWNLOAD_DELAY = 1.0
21
+
22
+ # ============================== 下载器配置 ==============================
23
+ # 可选下载器:
24
+ # DOWNLOADER = 'crawlo.downloader.aiohttp_downloader.AioHttpDownloader'
25
+ # DOWNLOADER = 'crawlo.downloader.httpx_downloader.HttpXDownloader'
26
+ # DOWNLOADER = 'crawlo.downloader.cffi_downloader.CurlCffiDownloader'
27
+ DOWNLOADER = 'crawlo.downloader.aiohttp_downloader.AioHttpDownloader'
28
+
29
+ # ============================== 队列配置 ==============================
30
+ QUEUE_TYPE = 'redis'
31
+ # 当使用Redis队列时,可自定义队列名称
32
+ # 队列名称遵循统一命名规范: crawlo:{PROJECT_NAME}:queue:requests
33
+ # SCHEDULER_QUEUE_NAME = f'crawlo:{PROJECT_NAME}:queue:requests'
34
+
35
+ # ============================== 去重过滤器 ==============================
36
+ FILTER_CLASS = 'crawlo.filters.aioredis_filter.AioRedisFilter'
37
+
38
+ # ============================== 默认去重管道 ==============================
39
+ DEFAULT_DEDUP_PIPELINE = 'crawlo.pipelines.redis_dedup_pipeline.RedisDedupPipeline'
40
+
41
+ # ============================== 爬虫模块配置 ==============================
42
+ SPIDER_MODULES = ['test_project.spiders']
43
+
44
+ # ============================== 中间件 ==============================
45
+ # MIDDLEWARES = [
46
+ # 'crawlo.middleware.simple_proxy.SimpleProxyMiddleware',
47
+ # ]
48
+
49
+ # ============================== 默认请求头配置 ==============================
50
+ # 为DefaultHeaderMiddleware配置默认请求头
51
+ DEFAULT_REQUEST_HEADERS = {
52
+ 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
53
+ 'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
54
+ 'Accept-Encoding': 'gzip, deflate, br',
55
+ }
56
+
57
+ # ============================== 允许的域名 ==============================
58
+ # 为OffsiteMiddleware配置允许的域名
59
+ # ALLOWED_DOMAINS = ['example.com']
60
+
61
+ # ============================== 数据管道 ==============================
62
+ # PIPELINES = [
63
+ # 'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline', # MySQL 存储(使用asyncmy异步库)
64
+ # ]
65
+
66
+ # ============================== 扩展组件 ==============================
67
+ # EXTENSIONS = [
68
+ # 'crawlo.extension.log_interval.LogIntervalExtension',
69
+ # 'crawlo.extension.log_stats.LogStats',
70
+ # 'crawlo.extension.logging_extension.CustomLoggerExtension',
71
+ # ]
72
+
73
+ # ============================== 日志配置 ==============================
74
+ LOG_LEVEL = 'INFO'
75
+ LOG_FILE = 'logs/test_project.log'
76
+ LOG_ENCODING = 'utf-8' # 明确指定日志文件编码
77
+ STATS_DUMP = True
78
+
79
+ # ============================== 输出配置 ==============================
80
+ OUTPUT_DIR = 'output'
81
+
82
+ # ============================== Redis配置 ==============================
83
+ REDIS_HOST = os.getenv('REDIS_HOST', '127.0.0.1')
84
+ REDIS_PORT = int(os.getenv('REDIS_PORT', 6379))
85
+ REDIS_PASSWORD = os.getenv('REDIS_PASSWORD', '')
86
+ REDIS_DB = int(os.getenv('REDIS_DB', 0))
87
+
88
+ # 根据是否有密码生成 URL
89
+ if REDIS_PASSWORD:
90
+ REDIS_URL = f'redis://:{REDIS_PASSWORD}@{REDIS_HOST}:{REDIS_PORT}/{REDIS_DB}'
91
+ else:
92
+ REDIS_URL = f'redis://{REDIS_HOST}:{REDIS_PORT}/{REDIS_DB}'
93
+
94
+ # ============================== MySQL配置 ==============================
95
+ MYSQL_HOST = os.getenv('MYSQL_HOST', '127.0.0.1')
96
+ MYSQL_PORT = int(os.getenv('MYSQL_PORT', 3306))
97
+ MYSQL_USER = os.getenv('MYSQL_USER', 'root')
98
+ MYSQL_PASSWORD = os.getenv('MYSQL_PASSWORD', '123456')
99
+ MYSQL_DB = os.getenv('MYSQL_DB', 'test_project')
100
+ MYSQL_TABLE = 'test_project_data'
101
+ MYSQL_BATCH_SIZE = 100
102
+ MYSQL_USE_BATCH = True # 是否启用批量插入
103
+
104
+ # ============================== MongoDB配置 ==============================
105
+ MONGO_URI = os.getenv('MONGO_URI', 'mongodb://localhost:27017')
106
+ MONGO_DATABASE = 'test_project_db'
107
+ MONGO_COLLECTION = 'test_project_items'
108
+ MONGO_MAX_POOL_SIZE = 200
109
+ MONGO_MIN_POOL_SIZE = 20
110
+ MONGO_BATCH_SIZE = 100 # 批量插入条数
111
+ MONGO_USE_BATCH = True # 是否启用批量插入
112
+
113
+ # ============================== 代理配置 ==============================
114
+ # 代理功能默认不启用,如需使用请在项目配置文件中启用并配置相关参数
115
+ PROXY_ENABLED = False # 是否启用代理
116
+
117
+ # 简化版代理配置(适用于SimpleProxyMiddleware)
118
+ PROXY_LIST = [] # 代理列表,例如: ["http://proxy1:8080", "http://proxy2:8080"]
119
+
120
+ # 高级代理配置(适用于ProxyMiddleware)
121
+ PROXY_API_URL = "" # 代理获取接口(请替换为真实地址)
122
+
123
+ # 代理提取方式(支持字段路径或函数)
124
+ # 示例: "proxy" 适用于 {"proxy": "http://1.1.1.1:8080"}
125
+ # 示例: "data.proxy" 适用于 {"data": {"proxy": "http://1.1.1.1:8080"}}
126
+ PROXY_EXTRACTOR = "proxy"
127
+
128
+ # 代理刷新控制
129
+ PROXY_REFRESH_INTERVAL = 60 # 代理刷新间隔(秒)
130
+ PROXY_API_TIMEOUT = 10 # 请求代理 API 超时时间
131
+
132
+ # ============================== Curl-Cffi 特有配置 ==============================
133
+ # 浏览器指纹模拟(仅 CurlCffi 下载器有效)
134
+ CURL_BROWSER_TYPE = "chrome" # 可选: chrome, edge, safari, firefox 或版本如 chrome136
135
+
136
+ # 自定义浏览器版本映射(可覆盖默认行为)
137
+ CURL_BROWSER_VERSION_MAP = {
138
+ "chrome": "chrome136",
139
+ "edge": "edge101",
140
+ "safari": "safari184",
141
+ "firefox": "firefox135",
142
+ }
143
+
144
+ # ============================== 下载器优化配置 ==============================
145
+ # 下载器健康检查
146
+ DOWNLOADER_HEALTH_CHECK = True # 是否启用下载器健康检查
147
+ HEALTH_CHECK_INTERVAL = 60 # 健康检查间隔(秒)
148
+
149
+ # 请求统计配置
150
+ REQUEST_STATS_ENABLED = True # 是否启用请求统计
151
+ STATS_RESET_ON_START = False # 启动时是否重置统计
152
+
153
+ # HttpX 下载器专用配置
154
+ HTTPX_HTTP2 = True # 是否启用HTTP/2支持
155
+ HTTPX_FOLLOW_REDIRECTS = True # 是否自动跟随重定向
156
+
157
+ # AioHttp 下载器专用配置
158
+ AIOHTTP_AUTO_DECOMPRESS = True # 是否自动解压响应
159
+ AIOHTTP_FORCE_CLOSE = False # 是否强制关闭连接
160
+
161
+ # 通用优化配置
162
+ CONNECTION_TTL_DNS_CACHE = 300 # DNS缓存TTL(秒)
163
+ CONNECTION_KEEPALIVE_TIMEOUT = 15 # Keep-Alive超时(秒)
164
+
165
+ # ============================== 内存监控配置 ==============================
166
+ # 内存监控扩展默认不启用,如需使用请在项目配置文件中启用
167
+ MEMORY_MONITOR_ENABLED = False # 是否启用内存监控
168
+ MEMORY_MONITOR_INTERVAL = 60 # 内存监控检查间隔(秒)
169
+ MEMORY_WARNING_THRESHOLD = 80.0 # 内存使用率警告阈值(百分比)
170
+ MEMORY_CRITICAL_THRESHOLD = 90.0 # 内存使用率严重阈值(百分比)