crawlo 1.4.6__py3-none-any.whl → 1.4.7__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 +90 -89
- crawlo/__version__.py +1 -1
- crawlo/cli.py +75 -75
- crawlo/commands/__init__.py +14 -14
- crawlo/commands/check.py +594 -594
- crawlo/commands/genspider.py +186 -186
- crawlo/commands/help.py +140 -138
- crawlo/commands/list.py +155 -155
- crawlo/commands/run.py +379 -341
- crawlo/commands/startproject.py +460 -460
- crawlo/commands/stats.py +187 -187
- crawlo/commands/utils.py +196 -196
- crawlo/config.py +320 -312
- crawlo/config_validator.py +277 -277
- crawlo/core/__init__.py +52 -52
- crawlo/core/engine.py +451 -438
- crawlo/core/processor.py +47 -47
- crawlo/core/scheduler.py +290 -291
- crawlo/crawler.py +698 -657
- crawlo/data/__init__.py +5 -5
- crawlo/data/user_agents.py +194 -194
- crawlo/downloader/__init__.py +280 -276
- crawlo/downloader/aiohttp_downloader.py +233 -233
- crawlo/downloader/cffi_downloader.py +250 -247
- crawlo/downloader/httpx_downloader.py +265 -259
- crawlo/downloader/hybrid_downloader.py +212 -212
- crawlo/downloader/playwright_downloader.py +425 -402
- crawlo/downloader/selenium_downloader.py +486 -472
- crawlo/event.py +45 -11
- crawlo/exceptions.py +215 -82
- crawlo/extension/__init__.py +65 -64
- crawlo/extension/health_check.py +141 -141
- crawlo/extension/log_interval.py +94 -94
- crawlo/extension/log_stats.py +70 -70
- crawlo/extension/logging_extension.py +53 -61
- crawlo/extension/memory_monitor.py +104 -104
- crawlo/extension/performance_profiler.py +133 -133
- crawlo/extension/request_recorder.py +107 -107
- crawlo/factories/__init__.py +27 -27
- crawlo/factories/base.py +68 -68
- crawlo/factories/crawler.py +104 -103
- crawlo/factories/registry.py +84 -84
- crawlo/factories/utils.py +135 -0
- crawlo/filters/__init__.py +170 -153
- crawlo/filters/aioredis_filter.py +348 -264
- crawlo/filters/memory_filter.py +261 -276
- crawlo/framework.py +306 -292
- crawlo/initialization/__init__.py +44 -44
- crawlo/initialization/built_in.py +391 -434
- crawlo/initialization/context.py +141 -141
- crawlo/initialization/core.py +240 -194
- crawlo/initialization/phases.py +230 -149
- crawlo/initialization/registry.py +143 -145
- crawlo/initialization/utils.py +49 -0
- crawlo/interfaces.py +23 -23
- crawlo/items/__init__.py +23 -23
- crawlo/items/base.py +23 -23
- crawlo/items/fields.py +52 -52
- crawlo/items/items.py +104 -104
- crawlo/logging/__init__.py +42 -46
- crawlo/logging/config.py +277 -197
- crawlo/logging/factory.py +175 -171
- crawlo/logging/manager.py +104 -112
- crawlo/middleware/__init__.py +87 -24
- crawlo/middleware/default_header.py +132 -132
- crawlo/middleware/download_delay.py +104 -104
- crawlo/middleware/middleware_manager.py +142 -142
- crawlo/middleware/offsite.py +123 -123
- crawlo/middleware/proxy.py +209 -209
- crawlo/middleware/request_ignore.py +86 -86
- crawlo/middleware/response_code.py +150 -150
- crawlo/middleware/response_filter.py +136 -136
- crawlo/middleware/retry.py +124 -124
- crawlo/mode_manager.py +287 -253
- crawlo/network/__init__.py +21 -21
- crawlo/network/request.py +375 -379
- crawlo/network/response.py +569 -664
- crawlo/pipelines/__init__.py +53 -22
- crawlo/pipelines/base_pipeline.py +452 -0
- crawlo/pipelines/bloom_dedup_pipeline.py +146 -146
- crawlo/pipelines/console_pipeline.py +39 -39
- crawlo/pipelines/csv_pipeline.py +316 -316
- crawlo/pipelines/database_dedup_pipeline.py +197 -197
- crawlo/pipelines/json_pipeline.py +218 -218
- crawlo/pipelines/memory_dedup_pipeline.py +105 -105
- crawlo/pipelines/mongo_pipeline.py +140 -132
- crawlo/pipelines/mysql_pipeline.py +469 -476
- crawlo/pipelines/pipeline_manager.py +100 -100
- crawlo/pipelines/redis_dedup_pipeline.py +155 -156
- crawlo/project.py +347 -347
- crawlo/queue/__init__.py +10 -0
- crawlo/queue/pqueue.py +38 -38
- crawlo/queue/queue_manager.py +591 -525
- crawlo/queue/redis_priority_queue.py +519 -370
- crawlo/settings/__init__.py +7 -7
- crawlo/settings/default_settings.py +284 -277
- crawlo/settings/setting_manager.py +219 -219
- crawlo/spider/__init__.py +657 -657
- crawlo/stats_collector.py +81 -81
- crawlo/subscriber.py +129 -129
- crawlo/task_manager.py +138 -138
- crawlo/templates/crawlo.cfg.tmpl +10 -10
- crawlo/templates/project/__init__.py.tmpl +2 -4
- crawlo/templates/project/items.py.tmpl +13 -17
- crawlo/templates/project/middlewares.py.tmpl +38 -38
- crawlo/templates/project/pipelines.py.tmpl +35 -36
- crawlo/templates/project/settings.py.tmpl +109 -111
- crawlo/templates/project/settings_distributed.py.tmpl +156 -159
- crawlo/templates/project/settings_gentle.py.tmpl +170 -176
- crawlo/templates/project/settings_high_performance.py.tmpl +171 -177
- crawlo/templates/project/settings_minimal.py.tmpl +98 -100
- crawlo/templates/project/settings_simple.py.tmpl +168 -174
- crawlo/templates/project/spiders/__init__.py.tmpl +9 -9
- crawlo/templates/run.py.tmpl +23 -23
- crawlo/templates/spider/spider.py.tmpl +32 -40
- crawlo/templates/spiders_init.py.tmpl +5 -10
- crawlo/tools/__init__.py +86 -189
- crawlo/tools/date_tools.py +289 -289
- crawlo/tools/distributed_coordinator.py +384 -384
- crawlo/tools/scenario_adapter.py +262 -262
- crawlo/tools/text_cleaner.py +232 -232
- crawlo/utils/__init__.py +50 -50
- crawlo/utils/batch_processor.py +276 -259
- crawlo/utils/config_manager.py +442 -0
- crawlo/utils/controlled_spider_mixin.py +439 -439
- crawlo/utils/db_helper.py +250 -250
- crawlo/utils/error_handler.py +410 -410
- crawlo/utils/fingerprint.py +121 -121
- crawlo/utils/func_tools.py +82 -82
- crawlo/utils/large_scale_helper.py +344 -344
- crawlo/utils/leak_detector.py +335 -0
- crawlo/utils/log.py +79 -79
- crawlo/utils/misc.py +81 -81
- crawlo/utils/mongo_connection_pool.py +157 -0
- crawlo/utils/mysql_connection_pool.py +197 -0
- crawlo/utils/performance_monitor.py +285 -285
- crawlo/utils/queue_helper.py +175 -175
- crawlo/utils/redis_checker.py +91 -0
- crawlo/utils/redis_connection_pool.py +578 -388
- crawlo/utils/redis_key_validator.py +198 -198
- crawlo/utils/request.py +278 -256
- crawlo/utils/request_serializer.py +225 -225
- crawlo/utils/resource_manager.py +337 -0
- crawlo/utils/selector_helper.py +137 -137
- crawlo/utils/singleton.py +70 -0
- crawlo/utils/spider_loader.py +201 -201
- crawlo/utils/text_helper.py +94 -94
- crawlo/utils/{url.py → url_utils.py} +39 -39
- crawlo-1.4.7.dist-info/METADATA +689 -0
- crawlo-1.4.7.dist-info/RECORD +347 -0
- examples/__init__.py +7 -7
- tests/__init__.py +7 -7
- tests/advanced_tools_example.py +217 -275
- tests/authenticated_proxy_example.py +110 -110
- tests/baidu_performance_test.py +108 -108
- tests/baidu_test.py +59 -59
- tests/bug_check_test.py +250 -250
- tests/cleaners_example.py +160 -160
- tests/comprehensive_framework_test.py +212 -212
- tests/comprehensive_test.py +81 -81
- tests/comprehensive_testing_summary.md +186 -186
- tests/config_validation_demo.py +142 -142
- tests/controlled_spider_example.py +205 -205
- tests/date_tools_example.py +180 -180
- tests/debug_configure.py +69 -69
- tests/debug_framework_logger.py +84 -84
- tests/debug_log_config.py +126 -126
- tests/debug_log_levels.py +63 -63
- tests/debug_pipelines.py +66 -66
- tests/detailed_log_test.py +233 -233
- tests/direct_selector_helper_test.py +96 -96
- tests/distributed_dedup_test.py +467 -0
- tests/distributed_test.py +66 -66
- tests/distributed_test_debug.py +76 -76
- tests/dynamic_loading_example.py +523 -523
- tests/dynamic_loading_test.py +104 -104
- tests/error_handling_example.py +171 -171
- tests/explain_mysql_update_behavior.py +76 -76
- tests/final_comprehensive_test.py +151 -151
- tests/final_log_test.py +260 -260
- tests/final_validation_test.py +182 -182
- tests/fix_log_test.py +142 -142
- tests/framework_performance_test.py +202 -202
- tests/log_buffering_test.py +111 -111
- tests/log_generation_timing_test.py +153 -153
- tests/monitor_redis_dedup.sh +72 -0
- tests/ofweek_scrapy/ofweek_scrapy/items.py +12 -12
- tests/ofweek_scrapy/ofweek_scrapy/middlewares.py +100 -100
- tests/ofweek_scrapy/ofweek_scrapy/pipelines.py +13 -13
- tests/ofweek_scrapy/ofweek_scrapy/settings.py +84 -84
- tests/ofweek_scrapy/scrapy.cfg +11 -11
- tests/optimized_performance_test.py +211 -211
- tests/performance_comparison.py +244 -244
- tests/queue_blocking_test.py +113 -113
- tests/queue_test.py +89 -89
- tests/redis_key_validation_demo.py +130 -130
- tests/request_params_example.py +150 -150
- tests/response_improvements_example.py +144 -144
- tests/scrapy_comparison/ofweek_scrapy.py +138 -138
- tests/scrapy_comparison/scrapy_test.py +133 -133
- tests/simple_cli_test.py +55 -0
- tests/simple_command_test.py +119 -119
- tests/simple_crawlo_test.py +126 -126
- tests/simple_follow_test.py +38 -38
- tests/simple_log_test2.py +137 -137
- tests/simple_optimization_test.py +128 -128
- tests/simple_queue_type_test.py +41 -41
- tests/simple_response_selector_test.py +94 -94
- tests/simple_selector_helper_test.py +154 -154
- tests/simple_selector_test.py +207 -207
- tests/simple_spider_test.py +49 -49
- tests/simple_url_test.py +73 -73
- tests/simulate_mysql_update_test.py +139 -139
- tests/spider_log_timing_test.py +177 -177
- tests/test_advanced_tools.py +148 -148
- tests/test_all_commands.py +230 -230
- tests/test_all_pipeline_fingerprints.py +133 -133
- tests/test_all_redis_key_configs.py +145 -145
- tests/test_asyncmy_usage.py +56 -56
- tests/test_batch_processor.py +178 -178
- tests/test_cleaners.py +54 -54
- tests/test_cli_arguments.py +119 -0
- tests/test_component_factory.py +174 -174
- tests/test_config_consistency.py +80 -80
- tests/test_config_merge.py +152 -152
- tests/test_config_validator.py +182 -182
- tests/test_controlled_spider_mixin.py +79 -79
- tests/test_crawler_process_import.py +38 -38
- tests/test_crawler_process_spider_modules.py +47 -47
- tests/test_crawlo_proxy_integration.py +114 -114
- tests/test_date_tools.py +123 -123
- tests/test_dedup_fix.py +220 -220
- tests/test_dedup_pipeline_consistency.py +124 -124
- tests/test_default_header_middleware.py +313 -313
- tests/test_distributed.py +65 -65
- tests/test_double_crawlo_fix.py +204 -204
- tests/test_double_crawlo_fix_simple.py +124 -124
- tests/test_download_delay_middleware.py +221 -221
- tests/test_downloader_proxy_compatibility.py +272 -272
- tests/test_edge_cases.py +305 -305
- tests/test_encoding_core.py +56 -56
- tests/test_encoding_detection.py +126 -126
- tests/test_enhanced_error_handler.py +270 -270
- tests/test_enhanced_error_handler_comprehensive.py +245 -245
- tests/test_error_handler_compatibility.py +112 -112
- tests/test_factories.py +252 -252
- tests/test_factory_compatibility.py +196 -196
- tests/test_final_validation.py +153 -153
- tests/test_fingerprint_consistency.py +135 -135
- tests/test_fingerprint_simple.py +51 -51
- tests/test_get_component_logger.py +83 -83
- tests/test_hash_performance.py +99 -99
- tests/test_integration.py +169 -169
- tests/test_item_dedup_redis_key.py +122 -122
- tests/test_large_scale_helper.py +235 -235
- tests/test_logging_enhancements.py +374 -374
- tests/test_logging_final.py +184 -184
- tests/test_logging_integration.py +312 -312
- tests/test_logging_system.py +282 -282
- tests/test_middleware_debug.py +141 -141
- tests/test_mode_consistency.py +51 -51
- tests/test_multi_directory.py +67 -67
- tests/test_multiple_spider_modules.py +80 -80
- tests/test_mysql_pipeline_config.py +164 -164
- tests/test_mysql_pipeline_error.py +98 -98
- tests/test_mysql_pipeline_init_log.py +82 -82
- tests/test_mysql_pipeline_integration.py +132 -132
- tests/test_mysql_pipeline_refactor.py +143 -143
- tests/test_mysql_pipeline_refactor_simple.py +85 -85
- tests/test_mysql_pipeline_robustness.py +195 -195
- tests/test_mysql_pipeline_types.py +88 -88
- tests/test_mysql_update_columns.py +93 -93
- tests/test_offsite_middleware.py +244 -244
- tests/test_offsite_middleware_simple.py +203 -203
- tests/test_optimized_selector_naming.py +100 -100
- tests/test_parsel.py +29 -29
- tests/test_performance.py +327 -327
- tests/test_performance_monitor.py +115 -115
- tests/test_pipeline_fingerprint_consistency.py +86 -86
- tests/test_priority_behavior.py +211 -211
- tests/test_priority_consistency.py +151 -151
- tests/test_priority_consistency_fixed.py +249 -249
- tests/test_proxy_health_check.py +32 -32
- tests/test_proxy_middleware.py +217 -217
- tests/test_proxy_middleware_enhanced.py +212 -212
- tests/test_proxy_middleware_integration.py +142 -142
- tests/test_proxy_middleware_refactored.py +207 -207
- tests/test_proxy_only.py +83 -83
- tests/test_proxy_providers.py +56 -56
- tests/test_proxy_stats.py +19 -19
- tests/test_proxy_strategies.py +59 -59
- tests/test_proxy_with_downloader.py +152 -152
- tests/test_queue_empty_check.py +41 -41
- tests/test_queue_manager_double_crawlo.py +173 -173
- tests/test_queue_manager_redis_key.py +179 -179
- tests/test_queue_naming.py +154 -154
- tests/test_queue_type.py +106 -106
- tests/test_queue_type_redis_config_consistency.py +130 -130
- tests/test_random_headers_default.py +322 -322
- tests/test_random_headers_necessity.py +308 -308
- tests/test_random_user_agent.py +72 -72
- 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_redis_queue_name_fix.py +175 -175
- tests/test_redis_queue_type_fallback.py +129 -129
- tests/test_request_ignore_middleware.py +182 -182
- tests/test_request_params.py +111 -111
- tests/test_request_serialization.py +70 -70
- tests/test_response_code_middleware.py +349 -349
- tests/test_response_filter_middleware.py +427 -427
- tests/test_response_follow.py +104 -104
- tests/test_response_improvements.py +152 -152
- tests/test_response_selector_methods.py +92 -92
- tests/test_response_url_methods.py +70 -70
- tests/test_response_urljoin.py +86 -86
- tests/test_retry_middleware.py +333 -333
- tests/test_retry_middleware_realistic.py +273 -273
- tests/test_scheduler.py +252 -252
- tests/test_scheduler_config_update.py +133 -133
- tests/test_scrapy_style_encoding.py +112 -112
- tests/test_selector_helper.py +100 -100
- tests/test_selector_optimizations.py +146 -146
- tests/test_simple_response.py +61 -61
- tests/test_spider_loader.py +49 -49
- tests/test_spider_loader_comprehensive.py +69 -69
- tests/test_spider_modules.py +84 -84
- tests/test_spiders/test_spider.py +9 -9
- 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 +159 -159
- tests/test_user_agent_randomness.py +176 -176
- tests/test_user_agents.py +96 -96
- tests/untested_features_report.md +138 -138
- tests/verify_debug.py +51 -51
- tests/verify_distributed.py +117 -117
- tests/verify_log_fix.py +111 -111
- tests/verify_mysql_warnings.py +109 -109
- crawlo/logging/async_handler.py +0 -181
- crawlo/logging/monitor.py +0 -153
- crawlo/logging/sampler.py +0 -167
- crawlo/tools/authenticated_proxy.py +0 -241
- crawlo/tools/data_formatter.py +0 -226
- crawlo/tools/data_validator.py +0 -181
- crawlo/tools/encoding_converter.py +0 -127
- crawlo/tools/network_diagnostic.py +0 -365
- crawlo/tools/request_tools.py +0 -83
- crawlo/tools/retry_mechanism.py +0 -224
- crawlo/utils/env_config.py +0 -143
- crawlo/utils/large_scale_config.py +0 -287
- crawlo/utils/system.py +0 -11
- crawlo/utils/tools.py +0 -5
- crawlo-1.4.6.dist-info/METADATA +0 -329
- crawlo-1.4.6.dist-info/RECORD +0 -361
- tests/env_config_example.py +0 -134
- tests/ofweek_scrapy/ofweek_scrapy/spiders/ofweek_spider.py +0 -162
- tests/test_authenticated_proxy.py +0 -142
- tests/test_comprehensive.py +0 -147
- tests/test_dynamic_downloaders_proxy.py +0 -125
- tests/test_dynamic_proxy.py +0 -93
- tests/test_dynamic_proxy_config.py +0 -147
- tests/test_dynamic_proxy_real.py +0 -110
- tests/test_env_config.py +0 -122
- tests/test_framework_env_usage.py +0 -104
- tests/test_large_scale_config.py +0 -113
- tests/test_proxy_api.py +0 -265
- tests/test_real_scenario_proxy.py +0 -196
- tests/tools_example.py +0 -261
- {crawlo-1.4.6.dist-info → crawlo-1.4.7.dist-info}/WHEEL +0 -0
- {crawlo-1.4.6.dist-info → crawlo-1.4.7.dist-info}/entry_points.txt +0 -0
- {crawlo-1.4.6.dist-info → crawlo-1.4.7.dist-info}/top_level.txt +0 -0
crawlo-1.4.6.dist-info/METADATA
DELETED
|
@@ -1,329 +0,0 @@
|
|
|
1
|
-
Metadata-Version: 2.4
|
|
2
|
-
Name: crawlo
|
|
3
|
-
Version: 1.4.6
|
|
4
|
-
Summary: Crawlo 是一款基于异步IO的高性能Python爬虫框架,支持分布式抓取。
|
|
5
|
-
Home-page: https://github.com/crawl-coder/Crawlo.git
|
|
6
|
-
Author: crawl-coder
|
|
7
|
-
Author-email: crawlo@qq.com
|
|
8
|
-
License: MIT
|
|
9
|
-
Classifier: Programming Language :: Python :: 3
|
|
10
|
-
Classifier: License :: OSI Approved :: MIT License
|
|
11
|
-
Classifier: Operating System :: OS Independent
|
|
12
|
-
Requires-Python: >=3.6
|
|
13
|
-
Description-Content-Type: text/markdown
|
|
14
|
-
Requires-Dist: aiohttp>=3.12.14
|
|
15
|
-
Requires-Dist: aiomysql>=0.2.0
|
|
16
|
-
Requires-Dist: aioredis>=2.0.1
|
|
17
|
-
Requires-Dist: asyncmy>=0.2.10
|
|
18
|
-
Requires-Dist: cssselect>=1.2.0
|
|
19
|
-
Requires-Dist: dateparser>=1.2.2
|
|
20
|
-
Requires-Dist: httpx[http2]>=0.27.0
|
|
21
|
-
Requires-Dist: curl-cffi>=0.13.0
|
|
22
|
-
Requires-Dist: lxml>=5.2.1
|
|
23
|
-
Requires-Dist: motor>=3.7.0
|
|
24
|
-
Requires-Dist: parsel>=1.9.1
|
|
25
|
-
Requires-Dist: pydantic>=2.11.7
|
|
26
|
-
Requires-Dist: pymongo>=4.11
|
|
27
|
-
Requires-Dist: PyMySQL>=1.1.1
|
|
28
|
-
Requires-Dist: python-dateutil>=2.9.0.post0
|
|
29
|
-
Requires-Dist: redis>=6.2.0
|
|
30
|
-
Requires-Dist: requests>=2.32.4
|
|
31
|
-
Requires-Dist: six>=1.17.0
|
|
32
|
-
Requires-Dist: ujson>=5.9.0
|
|
33
|
-
Requires-Dist: urllib3>=2.5.0
|
|
34
|
-
Requires-Dist: w3lib>=2.1.2
|
|
35
|
-
Requires-Dist: rich>=14.1.0
|
|
36
|
-
Requires-Dist: astor>=0.8.1
|
|
37
|
-
Requires-Dist: watchdog>=6.0.0
|
|
38
|
-
Provides-Extra: render
|
|
39
|
-
Requires-Dist: webdriver-manager>=4.0.0; extra == "render"
|
|
40
|
-
Requires-Dist: playwright; extra == "render"
|
|
41
|
-
Requires-Dist: selenium>=3.141.0; extra == "render"
|
|
42
|
-
Provides-Extra: all
|
|
43
|
-
Requires-Dist: bitarray>=1.5.3; extra == "all"
|
|
44
|
-
Requires-Dist: PyExecJS>=1.5.1; extra == "all"
|
|
45
|
-
Requires-Dist: pymongo>=3.10.1; extra == "all"
|
|
46
|
-
Requires-Dist: redis-py-cluster>=2.1.0; extra == "all"
|
|
47
|
-
Requires-Dist: webdriver-manager>=4.0.0; extra == "all"
|
|
48
|
-
Requires-Dist: playwright; extra == "all"
|
|
49
|
-
Requires-Dist: selenium>=3.141.0; extra == "all"
|
|
50
|
-
|
|
51
|
-
# Crawlo 爬虫框架
|
|
52
|
-
|
|
53
|
-
Crawlo 是一个高性能、可扩展的 Python 爬虫框架,支持单机和分布式部署。
|
|
54
|
-
|
|
55
|
-
## 特性
|
|
56
|
-
|
|
57
|
-
- 高性能异步爬取
|
|
58
|
-
- 支持多种下载器 (aiohttp, httpx, curl-cffi)
|
|
59
|
-
- 内置数据清洗和验证
|
|
60
|
-
- 分布式爬取支持
|
|
61
|
-
- 灵活的中间件系统
|
|
62
|
-
- 强大的配置管理系统
|
|
63
|
-
- 详细的日志记录和监控
|
|
64
|
-
- Windows 和 Linux 兼容
|
|
65
|
-
|
|
66
|
-
## 安装
|
|
67
|
-
|
|
68
|
-
```bash
|
|
69
|
-
pip install crawlo
|
|
70
|
-
```
|
|
71
|
-
|
|
72
|
-
或者从源码安装:
|
|
73
|
-
|
|
74
|
-
```bash
|
|
75
|
-
git clone git@github.com:crawl-coder/Crawlo.git
|
|
76
|
-
cd crawlo
|
|
77
|
-
pip install -r requirements.txt
|
|
78
|
-
pip install .
|
|
79
|
-
```
|
|
80
|
-
|
|
81
|
-
## 快速开始
|
|
82
|
-
|
|
83
|
-
```python
|
|
84
|
-
from crawlo import Spider
|
|
85
|
-
|
|
86
|
-
class MySpider(Spider):
|
|
87
|
-
name = 'example'
|
|
88
|
-
|
|
89
|
-
def parse(self, response):
|
|
90
|
-
# 解析逻辑
|
|
91
|
-
pass
|
|
92
|
-
|
|
93
|
-
# 运行爬虫
|
|
94
|
-
# crawlo run example
|
|
95
|
-
```
|
|
96
|
-
|
|
97
|
-
## Response 对象功能
|
|
98
|
-
|
|
99
|
-
Crawlo 框架对 Response 对象进行了增强,提供了更多便捷方法:
|
|
100
|
-
|
|
101
|
-
### URL 处理
|
|
102
|
-
|
|
103
|
-
使用 Response 对象封装的 URL 处理方法可以方便地处理各种 URL 操作,无需手动导入 `urllib.parse` 中的函数:
|
|
104
|
-
|
|
105
|
-
```python
|
|
106
|
-
class MySpider(Spider):
|
|
107
|
-
def parse(self, response):
|
|
108
|
-
# 1. 处理相对URL和绝对URL
|
|
109
|
-
absolute_url = response.urljoin('/relative/path')
|
|
110
|
-
|
|
111
|
-
# 2. 解析URL组件
|
|
112
|
-
parsed = response.urlparse() # 解析当前响应URL
|
|
113
|
-
scheme = parsed.scheme
|
|
114
|
-
domain = parsed.netloc
|
|
115
|
-
path = parsed.path
|
|
116
|
-
|
|
117
|
-
# 3. 解析查询参数
|
|
118
|
-
query_params = response.parse_qs() # 解析当前URL的查询参数
|
|
119
|
-
|
|
120
|
-
# 4. 编码查询参数
|
|
121
|
-
new_query = response.urlencode({'key': 'value', 'name': '测试'})
|
|
122
|
-
|
|
123
|
-
# 5. URL编码/解码
|
|
124
|
-
encoded = response.quote('hello world 你好')
|
|
125
|
-
decoded = response.unquote(encoded)
|
|
126
|
-
|
|
127
|
-
# 6. 移除URL片段
|
|
128
|
-
url_without_fragment, fragment = response.urldefrag('http://example.com/path#section')
|
|
129
|
-
|
|
130
|
-
yield Request(url=absolute_url, callback=self.parse_detail)
|
|
131
|
-
```
|
|
132
|
-
|
|
133
|
-
### 编码检测优化
|
|
134
|
-
|
|
135
|
-
Crawlo 框架参考 Scrapy 的设计模式对 Response 对象的编码检测功能进行了优化,提供了更准确和可靠的编码检测:
|
|
136
|
-
|
|
137
|
-
```python
|
|
138
|
-
class MySpider(Spider):
|
|
139
|
-
def parse(self, response):
|
|
140
|
-
# 自动检测响应编码
|
|
141
|
-
encoding = response.encoding
|
|
142
|
-
|
|
143
|
-
# 获取声明的编码(Request编码 > BOM > HTTP头部 > HTML meta标签)
|
|
144
|
-
declared_encoding = response._declared_encoding()
|
|
145
|
-
|
|
146
|
-
# 响应文本已自动使用正确的编码解码
|
|
147
|
-
text = response.text
|
|
148
|
-
|
|
149
|
-
# 处理解码后的内容
|
|
150
|
-
# ...
|
|
151
|
-
```
|
|
152
|
-
|
|
153
|
-
编码检测优先级:
|
|
154
|
-
1. Request 中指定的编码
|
|
155
|
-
2. BOM 字节顺序标记
|
|
156
|
-
3. HTTP Content-Type 头部
|
|
157
|
-
4. HTML meta 标签声明
|
|
158
|
-
5. 内容自动检测
|
|
159
|
-
6. 默认编码 (utf-8)
|
|
160
|
-
|
|
161
|
-
### 选择器方法优化
|
|
162
|
-
|
|
163
|
-
Crawlo 框架对 Response 对象的选择器方法进行了优化,提供了更便捷的数据提取功能,方法命名更加直观和统一:
|
|
164
|
-
|
|
165
|
-
```python
|
|
166
|
-
class MySpider(Spider):
|
|
167
|
-
def parse(self, response):
|
|
168
|
-
# 1. 提取单个元素文本(支持CSS和XPath)
|
|
169
|
-
title = response.extract_text('title') # CSS选择器
|
|
170
|
-
title = response.extract_text('//title') # XPath选择器
|
|
171
|
-
|
|
172
|
-
# 2. 提取多个元素文本
|
|
173
|
-
paragraphs = response.extract_texts('.content p') # CSS选择器
|
|
174
|
-
paragraphs = response.extract_texts('//div[@class="content"]//p') # XPath选择器
|
|
175
|
-
|
|
176
|
-
# 3. 提取单个元素属性
|
|
177
|
-
link_href = response.extract_attr('a', 'href') # CSS选择器
|
|
178
|
-
link_href = response.extract_attr('//a[@class="link"]', 'href') # XPath选择器
|
|
179
|
-
|
|
180
|
-
# 4. 提取多个元素属性
|
|
181
|
-
all_links = response.extract_attrs('a', 'href') # CSS选择器
|
|
182
|
-
all_links = response.extract_attrs('//a[@class="link"]', 'href') # XPath选择器
|
|
183
|
-
|
|
184
|
-
yield {
|
|
185
|
-
'title': title,
|
|
186
|
-
'paragraphs': paragraphs,
|
|
187
|
-
'links': all_links
|
|
188
|
-
}
|
|
189
|
-
```
|
|
190
|
-
|
|
191
|
-
所有选择器方法都采用了简洁直观的命名风格,便于记忆和使用。
|
|
192
|
-
|
|
193
|
-
### 工具模块
|
|
194
|
-
|
|
195
|
-
Crawlo 框架提供了丰富的工具模块,用于处理各种常见任务。选择器相关的辅助函数现在位于 `crawlo.utils.selector_helper` 模块中:
|
|
196
|
-
|
|
197
|
-
```python
|
|
198
|
-
from crawlo.utils import (
|
|
199
|
-
extract_text,
|
|
200
|
-
extract_texts,
|
|
201
|
-
extract_attr,
|
|
202
|
-
extract_attrs,
|
|
203
|
-
is_xpath
|
|
204
|
-
)
|
|
205
|
-
|
|
206
|
-
# 在自定义代码中使用这些工具函数
|
|
207
|
-
title_elements = response.css('title')
|
|
208
|
-
title_text = extract_text(title_elements)
|
|
209
|
-
|
|
210
|
-
li_elements = response.css('.list li')
|
|
211
|
-
li_texts = extract_texts(li_elements)
|
|
212
|
-
|
|
213
|
-
link_elements = response.css('.link')
|
|
214
|
-
link_href = extract_attr(link_elements, 'href')
|
|
215
|
-
|
|
216
|
-
all_links = response.css('a')
|
|
217
|
-
all_hrefs = extract_attrs(all_links, 'href')
|
|
218
|
-
```
|
|
219
|
-
|
|
220
|
-
## 日志系统
|
|
221
|
-
|
|
222
|
-
Crawlo 拥有一个功能强大的日志系统,支持多种配置选项:
|
|
223
|
-
|
|
224
|
-
### 基本配置
|
|
225
|
-
|
|
226
|
-
```python
|
|
227
|
-
from crawlo.logging import configure_logging, get_logger
|
|
228
|
-
|
|
229
|
-
# 配置日志系统
|
|
230
|
-
configure_logging(
|
|
231
|
-
LOG_LEVEL='INFO',
|
|
232
|
-
LOG_FILE='logs/app.log',
|
|
233
|
-
LOG_MAX_BYTES=10*1024*1024, # 10MB
|
|
234
|
-
LOG_BACKUP_COUNT=5
|
|
235
|
-
)
|
|
236
|
-
|
|
237
|
-
# 获取logger
|
|
238
|
-
logger = get_logger('my_module')
|
|
239
|
-
logger.info('这是一条日志消息')
|
|
240
|
-
```
|
|
241
|
-
|
|
242
|
-
### 高级配置
|
|
243
|
-
|
|
244
|
-
```python
|
|
245
|
-
# 分别配置控制台和文件日志级别
|
|
246
|
-
configure_logging(
|
|
247
|
-
LOG_LEVEL='INFO',
|
|
248
|
-
LOG_CONSOLE_LEVEL='WARNING', # 控制台只显示WARNING及以上级别
|
|
249
|
-
LOG_FILE_LEVEL='DEBUG', # 文件记录DEBUG及以上级别
|
|
250
|
-
LOG_FILE='logs/app.log',
|
|
251
|
-
LOG_INCLUDE_THREAD_ID=True, # 包含线程ID
|
|
252
|
-
LOG_INCLUDE_PROCESS_ID=True # 包含进程ID
|
|
253
|
-
)
|
|
254
|
-
|
|
255
|
-
# 模块特定日志级别
|
|
256
|
-
configure_logging(
|
|
257
|
-
LOG_LEVEL='WARNING',
|
|
258
|
-
LOG_LEVELS={
|
|
259
|
-
'my_module.debug': 'DEBUG',
|
|
260
|
-
'my_module.info': 'INFO'
|
|
261
|
-
}
|
|
262
|
-
)
|
|
263
|
-
```
|
|
264
|
-
|
|
265
|
-
### 性能监控
|
|
266
|
-
|
|
267
|
-
```python
|
|
268
|
-
from crawlo.logging import get_monitor
|
|
269
|
-
|
|
270
|
-
# 启用日志性能监控
|
|
271
|
-
monitor = get_monitor()
|
|
272
|
-
monitor.enable_monitoring()
|
|
273
|
-
|
|
274
|
-
# 获取性能报告
|
|
275
|
-
report = monitor.get_performance_report()
|
|
276
|
-
print(report)
|
|
277
|
-
```
|
|
278
|
-
|
|
279
|
-
### 日志采样
|
|
280
|
-
|
|
281
|
-
```python
|
|
282
|
-
from crawlo.logging import get_sampler
|
|
283
|
-
|
|
284
|
-
# 设置采样率(只记录30%的日志)
|
|
285
|
-
sampler = get_sampler()
|
|
286
|
-
sampler.set_sample_rate('my_module', 0.3)
|
|
287
|
-
|
|
288
|
-
# 设置速率限制(每秒最多100条日志)
|
|
289
|
-
sampler.set_rate_limit('my_module', 100)
|
|
290
|
-
```
|
|
291
|
-
|
|
292
|
-
## Windows 兼容性说明
|
|
293
|
-
|
|
294
|
-
在 Windows 系统上使用日志轮转功能时,可能会遇到文件锁定问题。为了解决这个问题,建议安装 `concurrent-log-handler` 库:
|
|
295
|
-
|
|
296
|
-
```bash
|
|
297
|
-
pip install concurrent-log-handler
|
|
298
|
-
```
|
|
299
|
-
|
|
300
|
-
Crawlo 框架会自动检测并使用这个库来提供更好的 Windows 兼容性。
|
|
301
|
-
|
|
302
|
-
如果未安装 `concurrent-log-handler`,在 Windows 上运行时可能会出现以下错误:
|
|
303
|
-
```
|
|
304
|
-
PermissionError: [WinError 32] 另一个程序正在使用此文件,进程无法访问。
|
|
305
|
-
```
|
|
306
|
-
|
|
307
|
-
## 爬虫自动发现
|
|
308
|
-
|
|
309
|
-
Crawlo 框架支持通过 `SPIDER_MODULES` 配置自动发现和加载爬虫,类似于 Scrapy 的机制:
|
|
310
|
-
|
|
311
|
-
```python
|
|
312
|
-
# settings.py
|
|
313
|
-
SPIDER_MODULES = [
|
|
314
|
-
'myproject.spiders',
|
|
315
|
-
'myproject.more_spiders',
|
|
316
|
-
]
|
|
317
|
-
|
|
318
|
-
SPIDER_LOADER_WARN_ONLY = True # 加载错误时只警告不报错
|
|
319
|
-
```
|
|
320
|
-
|
|
321
|
-
框架会自动扫描配置的模块目录,发现并注册其中的爬虫类。
|
|
322
|
-
|
|
323
|
-
## 文档
|
|
324
|
-
|
|
325
|
-
请查看 [文档](https://your-docs-url.com) 获取更多信息。
|
|
326
|
-
|
|
327
|
-
## 许可证
|
|
328
|
-
|
|
329
|
-
MIT
|