crawlo 1.4.1__py3-none-any.whl → 1.4.3__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 +93 -93
- 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 +151 -151
- crawlo/commands/help.py +138 -138
- crawlo/commands/list.py +155 -155
- crawlo/commands/run.py +341 -341
- crawlo/commands/startproject.py +436 -436
- crawlo/commands/stats.py +187 -187
- crawlo/commands/utils.py +196 -196
- crawlo/config.py +312 -312
- crawlo/config_validator.py +277 -277
- crawlo/core/__init__.py +52 -52
- crawlo/core/engine.py +438 -439
- crawlo/core/processor.py +47 -47
- crawlo/core/scheduler.py +291 -257
- crawlo/crawler.py +650 -650
- crawlo/data/__init__.py +5 -5
- crawlo/data/user_agents.py +194 -194
- crawlo/downloader/__init__.py +273 -273
- crawlo/downloader/aiohttp_downloader.py +233 -228
- crawlo/downloader/cffi_downloader.py +245 -245
- crawlo/downloader/httpx_downloader.py +259 -259
- crawlo/downloader/hybrid_downloader.py +212 -212
- 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 +63 -63
- 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 +61 -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 +103 -103
- crawlo/factories/registry.py +84 -84
- crawlo/filters/__init__.py +154 -154
- crawlo/filters/aioredis_filter.py +257 -257
- crawlo/filters/memory_filter.py +269 -269
- crawlo/framework.py +292 -292
- crawlo/initialization/__init__.py +44 -44
- crawlo/initialization/built_in.py +425 -425
- crawlo/initialization/context.py +141 -141
- crawlo/initialization/core.py +193 -193
- crawlo/initialization/phases.py +148 -148
- crawlo/initialization/registry.py +145 -145
- 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 +45 -37
- crawlo/logging/async_handler.py +181 -0
- crawlo/logging/config.py +196 -96
- crawlo/logging/factory.py +171 -128
- crawlo/logging/manager.py +111 -111
- crawlo/logging/monitor.py +153 -0
- crawlo/logging/sampler.py +167 -0
- crawlo/middleware/__init__.py +21 -21
- crawlo/middleware/default_header.py +132 -132
- crawlo/middleware/download_delay.py +104 -104
- crawlo/middleware/middleware_manager.py +135 -135
- crawlo/middleware/offsite.py +123 -123
- crawlo/middleware/proxy.py +386 -386
- 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/middleware/simple_proxy.py +65 -65
- crawlo/mode_manager.py +219 -219
- crawlo/network/__init__.py +21 -21
- crawlo/network/request.py +379 -379
- crawlo/network/response.py +359 -359
- crawlo/pipelines/__init__.py +21 -21
- 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 +131 -131
- crawlo/pipelines/mysql_pipeline.py +325 -325
- crawlo/pipelines/pipeline_manager.py +100 -84
- crawlo/pipelines/redis_dedup_pipeline.py +156 -156
- crawlo/project.py +349 -338
- crawlo/queue/pqueue.py +42 -42
- crawlo/queue/queue_manager.py +526 -522
- crawlo/queue/redis_priority_queue.py +370 -367
- crawlo/settings/__init__.py +7 -7
- crawlo/settings/default_settings.py +284 -284
- crawlo/settings/setting_manager.py +219 -219
- crawlo/spider/__init__.py +657 -657
- crawlo/stats_collector.py +73 -73
- crawlo/subscriber.py +129 -129
- crawlo/task_manager.py +138 -138
- 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 +118 -118
- crawlo/templates/project/pipelines.py.tmpl +96 -96
- crawlo/templates/project/settings.py.tmpl +170 -170
- crawlo/templates/project/settings_distributed.py.tmpl +169 -169
- crawlo/templates/project/settings_gentle.py.tmpl +166 -166
- crawlo/templates/project/settings_high_performance.py.tmpl +167 -167
- crawlo/templates/project/settings_minimal.py.tmpl +65 -65
- crawlo/templates/project/settings_simple.py.tmpl +164 -164
- crawlo/templates/project/spiders/__init__.py.tmpl +9 -9
- crawlo/templates/run.py.tmpl +34 -34
- crawlo/templates/spider/spider.py.tmpl +143 -143
- crawlo/templates/spiders_init.py.tmpl +9 -9
- crawlo/tools/__init__.py +200 -200
- crawlo/tools/anti_crawler.py +268 -268
- crawlo/tools/authenticated_proxy.py +240 -240
- crawlo/tools/data_formatter.py +225 -225
- crawlo/tools/data_validator.py +180 -180
- crawlo/tools/date_tools.py +289 -289
- crawlo/tools/distributed_coordinator.py +384 -384
- crawlo/tools/encoding_converter.py +127 -127
- crawlo/tools/network_diagnostic.py +364 -364
- crawlo/tools/request_tools.py +82 -82
- crawlo/tools/retry_mechanism.py +224 -224
- crawlo/tools/scenario_adapter.py +262 -262
- crawlo/tools/text_cleaner.py +232 -232
- crawlo/utils/__init__.py +34 -34
- crawlo/utils/batch_processor.py +259 -259
- crawlo/utils/class_loader.py +25 -25
- crawlo/utils/controlled_spider_mixin.py +439 -439
- crawlo/utils/db_helper.py +343 -343
- crawlo/utils/enhanced_error_handler.py +356 -356
- crawlo/utils/env_config.py +142 -142
- crawlo/utils/error_handler.py +165 -165
- crawlo/utils/fingerprint.py +122 -122
- crawlo/utils/func_tools.py +82 -82
- crawlo/utils/large_scale_config.py +286 -286
- crawlo/utils/large_scale_helper.py +344 -344
- crawlo/utils/log.py +79 -79
- crawlo/utils/performance_monitor.py +285 -285
- crawlo/utils/queue_helper.py +175 -175
- crawlo/utils/redis_connection_pool.py +388 -388
- crawlo/utils/redis_key_validator.py +198 -198
- crawlo/utils/request.py +267 -267
- crawlo/utils/request_serializer.py +225 -225
- crawlo/utils/spider_loader.py +61 -61
- crawlo/utils/system.py +11 -11
- crawlo/utils/tools.py +4 -4
- crawlo/utils/url.py +39 -39
- crawlo-1.4.3.dist-info/METADATA +190 -0
- crawlo-1.4.3.dist-info/RECORD +326 -0
- examples/__init__.py +7 -7
- examples/test_project/__init__.py +7 -7
- examples/test_project/run.py +34 -34
- examples/test_project/test_project/__init__.py +3 -3
- examples/test_project/test_project/items.py +17 -17
- examples/test_project/test_project/middlewares.py +118 -118
- examples/test_project/test_project/pipelines.py +96 -96
- examples/test_project/test_project/settings.py +169 -169
- examples/test_project/test_project/spiders/__init__.py +9 -9
- examples/test_project/test_project/spiders/of_week_dis.py +143 -143
- tests/__init__.py +7 -7
- tests/advanced_tools_example.py +275 -275
- tests/authenticated_proxy_example.py +106 -106
- tests/baidu_performance_test.py +108 -108
- tests/baidu_test.py +59 -59
- 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/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/env_config_example.py +133 -133
- tests/error_handling_example.py +171 -171
- 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/optimized_performance_test.py +211 -211
- tests/performance_comparison.py +245 -245
- 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_command_test.py +119 -119
- tests/simple_crawlo_test.py +127 -127
- tests/simple_log_test.py +57 -57
- tests/simple_log_test2.py +137 -137
- tests/simple_optimization_test.py +128 -128
- tests/simple_queue_type_test.py +41 -41
- tests/simple_spider_test.py +49 -49
- tests/simple_test.py +47 -47
- 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_authenticated_proxy.py +141 -141
- tests/test_batch_processor.py +178 -178
- tests/test_cleaners.py +54 -54
- tests/test_component_factory.py +174 -174
- tests/test_comprehensive.py +146 -146
- 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_crawlo_proxy_integration.py +108 -108
- tests/test_date_tools.py +123 -123
- tests/test_dedup_fix.py +220 -220
- tests/test_dedup_pipeline_consistency.py +125 -0
- 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 +268 -268
- 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_enhanced_error_handler_comprehensive.py +245 -245
- tests/test_env_config.py +121 -121
- tests/test_error_handler_compatibility.py +112 -112
- tests/test_factories.py +252 -252
- tests/test_final_validation.py +153 -153
- tests/test_fingerprint_consistency.py +135 -135
- tests/test_fingerprint_simple.py +51 -51
- tests/test_framework_env_usage.py +103 -103
- tests/test_framework_logger.py +66 -66
- tests/test_framework_startup.py +64 -64
- 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_config.py +112 -112
- tests/test_large_scale_helper.py +235 -235
- tests/test_logging_enhancements.py +375 -0
- tests/test_logging_final.py +185 -0
- tests/test_logging_integration.py +313 -0
- tests/test_logging_system.py +282 -282
- tests/test_middleware_debug.py +142 -0
- tests/test_mode_change.py +72 -72
- tests/test_mode_consistency.py +51 -51
- tests/test_offsite_middleware.py +244 -244
- tests/test_offsite_middleware_simple.py +203 -203
- 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 +212 -0
- tests/test_priority_consistency.py +152 -0
- tests/test_priority_consistency_fixed.py +250 -0
- tests/test_proxy_api.py +264 -264
- tests/test_proxy_health_check.py +32 -32
- tests/test_proxy_middleware.py +121 -121
- tests/test_proxy_middleware_enhanced.py +216 -216
- tests/test_proxy_middleware_integration.py +136 -136
- tests/test_proxy_middleware_refactored.py +184 -184
- tests/test_proxy_providers.py +56 -56
- tests/test_proxy_stats.py +19 -19
- tests/test_proxy_strategies.py +59 -59
- 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 +131 -0
- tests/test_random_headers_default.py +323 -0
- tests/test_random_headers_necessity.py +309 -0
- tests/test_random_user_agent.py +72 -72
- tests/test_real_scenario_proxy.py +195 -195
- 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 +130 -0
- 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_improvements.py +152 -152
- tests/test_retry_middleware.py +334 -242
- tests/test_retry_middleware_realistic.py +274 -0
- tests/test_scheduler.py +252 -252
- tests/test_scheduler_config_update.py +133 -133
- 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 +159 -159
- tests/test_user_agent_randomness.py +177 -0
- tests/test_user_agents.py +96 -96
- tests/tools_example.py +260 -260
- 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
- crawlo-1.4.1.dist-info/METADATA +0 -1199
- crawlo-1.4.1.dist-info/RECORD +0 -309
- {crawlo-1.4.1.dist-info → crawlo-1.4.3.dist-info}/WHEEL +0 -0
- {crawlo-1.4.1.dist-info → crawlo-1.4.3.dist-info}/entry_points.txt +0 -0
- {crawlo-1.4.1.dist-info → crawlo-1.4.3.dist-info}/top_level.txt +0 -0
crawlo/utils/url.py
CHANGED
|
@@ -1,40 +1,40 @@
|
|
|
1
|
-
from urllib.parse import urldefrag
|
|
2
|
-
from w3lib.url import add_or_replace_parameter
|
|
3
|
-
|
|
4
|
-
|
|
5
|
-
def escape_ajax(url: str) -> str:
|
|
6
|
-
"""
|
|
7
|
-
根据Google AJAX爬取规范转换URL(处理哈希片段#!):
|
|
8
|
-
https://developers.google.com/webmasters/ajax-crawling/docs/getting-started
|
|
9
|
-
|
|
10
|
-
规则说明:
|
|
11
|
-
1. 仅当URL包含 `#!` 时才转换(表示这是AJAX可爬取页面)
|
|
12
|
-
2. 将 `#!key=value` 转换为 `?_escaped_fragment_=key%3Dvalue`
|
|
13
|
-
3. 保留原始查询参数(如果有)
|
|
14
|
-
|
|
15
|
-
示例:
|
|
16
|
-
>>> escape_ajax("www.example.com/ajax.html#!key=value")
|
|
17
|
-
'www.example.com/ajax.html?_escaped_fragment_=key%3Dvalue'
|
|
18
|
-
>>> escape_ajax("www.example.com/ajax.html?k1=v1#!key=value")
|
|
19
|
-
'www.example.com/ajax.html?k1=v1&_escaped_fragment_=key%3Dvalue'
|
|
20
|
-
>>> escape_ajax("www.example.com/ajax.html#!")
|
|
21
|
-
'www.example.com/ajax.html?_escaped_fragment_='
|
|
22
|
-
|
|
23
|
-
非AJAX可爬取的URL(无#!)原样返回:
|
|
24
|
-
>>> escape_ajax("www.example.com/ajax.html#normal")
|
|
25
|
-
'www.example.com/ajax.html#normal'
|
|
26
|
-
"""
|
|
27
|
-
# 分离URL的基础部分和哈希片段
|
|
28
|
-
de_frag, frag = urldefrag(url)
|
|
29
|
-
|
|
30
|
-
# 仅处理以"!"开头的哈希片段(Google规范)
|
|
31
|
-
if not frag.startswith("!"):
|
|
32
|
-
return url # 不符合规则则原样返回
|
|
33
|
-
|
|
34
|
-
# 调用辅助函数添加 `_escaped_fragment_` 参数
|
|
35
|
-
return add_or_replace_parameter(de_frag, "_escaped_fragment_", frag[1:])
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
if __name__ == '__main__':
|
|
39
|
-
f = escape_ajax('http://example.com/page#!')
|
|
1
|
+
from urllib.parse import urldefrag
|
|
2
|
+
from w3lib.url import add_or_replace_parameter
|
|
3
|
+
|
|
4
|
+
|
|
5
|
+
def escape_ajax(url: str) -> str:
|
|
6
|
+
"""
|
|
7
|
+
根据Google AJAX爬取规范转换URL(处理哈希片段#!):
|
|
8
|
+
https://developers.google.com/webmasters/ajax-crawling/docs/getting-started
|
|
9
|
+
|
|
10
|
+
规则说明:
|
|
11
|
+
1. 仅当URL包含 `#!` 时才转换(表示这是AJAX可爬取页面)
|
|
12
|
+
2. 将 `#!key=value` 转换为 `?_escaped_fragment_=key%3Dvalue`
|
|
13
|
+
3. 保留原始查询参数(如果有)
|
|
14
|
+
|
|
15
|
+
示例:
|
|
16
|
+
>>> escape_ajax("www.example.com/ajax.html#!key=value")
|
|
17
|
+
'www.example.com/ajax.html?_escaped_fragment_=key%3Dvalue'
|
|
18
|
+
>>> escape_ajax("www.example.com/ajax.html?k1=v1#!key=value")
|
|
19
|
+
'www.example.com/ajax.html?k1=v1&_escaped_fragment_=key%3Dvalue'
|
|
20
|
+
>>> escape_ajax("www.example.com/ajax.html#!")
|
|
21
|
+
'www.example.com/ajax.html?_escaped_fragment_='
|
|
22
|
+
|
|
23
|
+
非AJAX可爬取的URL(无#!)原样返回:
|
|
24
|
+
>>> escape_ajax("www.example.com/ajax.html#normal")
|
|
25
|
+
'www.example.com/ajax.html#normal'
|
|
26
|
+
"""
|
|
27
|
+
# 分离URL的基础部分和哈希片段
|
|
28
|
+
de_frag, frag = urldefrag(url)
|
|
29
|
+
|
|
30
|
+
# 仅处理以"!"开头的哈希片段(Google规范)
|
|
31
|
+
if not frag.startswith("!"):
|
|
32
|
+
return url # 不符合规则则原样返回
|
|
33
|
+
|
|
34
|
+
# 调用辅助函数添加 `_escaped_fragment_` 参数
|
|
35
|
+
return add_or_replace_parameter(de_frag, "_escaped_fragment_", frag[1:])
|
|
36
|
+
|
|
37
|
+
|
|
38
|
+
if __name__ == '__main__':
|
|
39
|
+
f = escape_ajax('http://example.com/page#!')
|
|
40
40
|
print(f)
|
|
@@ -0,0 +1,190 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: crawlo
|
|
3
|
+
Version: 1.4.3
|
|
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 https://github.com/your-username/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
|
+
## 日志系统
|
|
98
|
+
|
|
99
|
+
Crawlo 拥有一个功能强大的日志系统,支持多种配置选项:
|
|
100
|
+
|
|
101
|
+
### 基本配置
|
|
102
|
+
|
|
103
|
+
```python
|
|
104
|
+
from crawlo.logging import configure_logging, get_logger
|
|
105
|
+
|
|
106
|
+
# 配置日志系统
|
|
107
|
+
configure_logging(
|
|
108
|
+
LOG_LEVEL='INFO',
|
|
109
|
+
LOG_FILE='logs/app.log',
|
|
110
|
+
LOG_MAX_BYTES=10*1024*1024, # 10MB
|
|
111
|
+
LOG_BACKUP_COUNT=5
|
|
112
|
+
)
|
|
113
|
+
|
|
114
|
+
# 获取logger
|
|
115
|
+
logger = get_logger('my_module')
|
|
116
|
+
logger.info('这是一条日志消息')
|
|
117
|
+
```
|
|
118
|
+
|
|
119
|
+
### 高级配置
|
|
120
|
+
|
|
121
|
+
```python
|
|
122
|
+
# 分别配置控制台和文件日志级别
|
|
123
|
+
configure_logging(
|
|
124
|
+
LOG_LEVEL='INFO',
|
|
125
|
+
LOG_CONSOLE_LEVEL='WARNING', # 控制台只显示WARNING及以上级别
|
|
126
|
+
LOG_FILE_LEVEL='DEBUG', # 文件记录DEBUG及以上级别
|
|
127
|
+
LOG_FILE='logs/app.log',
|
|
128
|
+
LOG_INCLUDE_THREAD_ID=True, # 包含线程ID
|
|
129
|
+
LOG_INCLUDE_PROCESS_ID=True # 包含进程ID
|
|
130
|
+
)
|
|
131
|
+
|
|
132
|
+
# 模块特定日志级别
|
|
133
|
+
configure_logging(
|
|
134
|
+
LOG_LEVEL='WARNING',
|
|
135
|
+
LOG_LEVELS={
|
|
136
|
+
'my_module.debug': 'DEBUG',
|
|
137
|
+
'my_module.info': 'INFO'
|
|
138
|
+
}
|
|
139
|
+
)
|
|
140
|
+
```
|
|
141
|
+
|
|
142
|
+
### 性能监控
|
|
143
|
+
|
|
144
|
+
```python
|
|
145
|
+
from crawlo.logging import get_monitor
|
|
146
|
+
|
|
147
|
+
# 启用日志性能监控
|
|
148
|
+
monitor = get_monitor()
|
|
149
|
+
monitor.enable_monitoring()
|
|
150
|
+
|
|
151
|
+
# 获取性能报告
|
|
152
|
+
report = monitor.get_performance_report()
|
|
153
|
+
print(report)
|
|
154
|
+
```
|
|
155
|
+
|
|
156
|
+
### 日志采样
|
|
157
|
+
|
|
158
|
+
```python
|
|
159
|
+
from crawlo.logging import get_sampler
|
|
160
|
+
|
|
161
|
+
# 设置采样率(只记录30%的日志)
|
|
162
|
+
sampler = get_sampler()
|
|
163
|
+
sampler.set_sample_rate('my_module', 0.3)
|
|
164
|
+
|
|
165
|
+
# 设置速率限制(每秒最多100条日志)
|
|
166
|
+
sampler.set_rate_limit('my_module', 100)
|
|
167
|
+
```
|
|
168
|
+
|
|
169
|
+
## Windows 兼容性说明
|
|
170
|
+
|
|
171
|
+
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:
|
|
172
|
+
|
|
173
|
+
```bash
|
|
174
|
+
pip install concurrent-log-handler
|
|
175
|
+
```
|
|
176
|
+
|
|
177
|
+
Crawlo 框架会自动检测并使用这个库来提供更好的 Windows 兼容性。
|
|
178
|
+
|
|
179
|
+
如果未安装 `concurrent-log-handler`,在 Windows 上运行时可能会出现以下错误:
|
|
180
|
+
```
|
|
181
|
+
PermissionError: [WinError 32] 另一个程序正在使用此文件,进程无法访问。
|
|
182
|
+
```
|
|
183
|
+
|
|
184
|
+
## 文档
|
|
185
|
+
|
|
186
|
+
请查看 [文档](https://your-docs-url.com) 获取更多信息。
|
|
187
|
+
|
|
188
|
+
## 许可证
|
|
189
|
+
|
|
190
|
+
MIT
|
|
@@ -0,0 +1,326 @@
|
|
|
1
|
+
crawlo/__init__.py,sha256=2Io5P9qJghOAjjD3YWdaiIq5laPLyLWVkEqgiVfUa3o,2381
|
|
2
|
+
crawlo/__version__.py,sha256=adPldP4cMp2T8pbTFGYTXV50hu_smS3hxWkk5kLXpZE,23
|
|
3
|
+
crawlo/cli.py,sha256=AQnAB5NMI-Ic1VPw_Jjng8L4AI4-wMozOwzE6CfXkZU,2402
|
|
4
|
+
crawlo/config.py,sha256=EQIT7WpkXAlr2ocd5SYJYOKTSWUlQx2AkTHX7ErEWxw,9798
|
|
5
|
+
crawlo/config_validator.py,sha256=oY4-2bwXUlwHAnGgkI-EznviDfML_dcxbWSGXNSxC2k,11516
|
|
6
|
+
crawlo/crawler.py,sha256=i4rc9beEOilKGK633nRh5UxCNgciil9Lyfj38xgIauU,26998
|
|
7
|
+
crawlo/event.py,sha256=ZhoPW5CglCEuZNFEwviSCBIw0pT5O6jT98bqYrDFd3E,324
|
|
8
|
+
crawlo/exceptions.py,sha256=YVIDnC1bKSMv3fXH_6tinWMuD9HmKHIaUfO4_fkX5sY,1247
|
|
9
|
+
crawlo/framework.py,sha256=9gP6VN4MHqutGXaxnwpNMSULfVYbNp906UdZiJGywlQ,9458
|
|
10
|
+
crawlo/mode_manager.py,sha256=S4dUoeVZ4fMnd4pXWutcHwk5Zv68ZBTgo9taR9OkQiM,7768
|
|
11
|
+
crawlo/project.py,sha256=nVRc0CIdd9g863NGfuItvajl8zlO5mEta4FQCx9_vZ8,14060
|
|
12
|
+
crawlo/stats_collector.py,sha256=hIjlnX750jU4Oncyand1jBccfaX4Tu7egd2DBYu2N7A,2379
|
|
13
|
+
crawlo/subscriber.py,sha256=h8fx69NJZeWem0ZkCmfHAi2kgfDGFObHpwN0aGNUM6Y,5115
|
|
14
|
+
crawlo/task_manager.py,sha256=I9h3Rl0VRAfwqp24CHT3TuEAapNdTbVghkmuJhtM7jg,5966
|
|
15
|
+
crawlo/commands/__init__.py,sha256=orvY6wLOBwGUEJKeF3h_T1fxj8AaQLjngBDd-3xKOE4,392
|
|
16
|
+
crawlo/commands/check.py,sha256=TKDhI_sj7kErgiJpt2vCZ9QL-g6yWjrrPWKbgh8pgEU,23199
|
|
17
|
+
crawlo/commands/genspider.py,sha256=7YGZdv12G341SWmkGbyDeMde2RgqGYxYXRExFy7KKNc,5088
|
|
18
|
+
crawlo/commands/help.py,sha256=8xPC0iNCg1rRBoK2bb6noAEANc1JwrdM35eF-j6yeZM,5111
|
|
19
|
+
crawlo/commands/list.py,sha256=trzcd3kG6DhkOqYZADcl3yR7M8iJBgRw5fE-g9e0gVM,5877
|
|
20
|
+
crawlo/commands/run.py,sha256=EjpIilgCTkXGVSV4rEISbJubdhqrok9nNe5-xDfDK5E,13169
|
|
21
|
+
crawlo/commands/startproject.py,sha256=-Bo8vvDfIhqzGmWyhxMatBlPLhYpRwJC7l4fpbN8vVk,16506
|
|
22
|
+
crawlo/commands/stats.py,sha256=vlGJLyiXZtY0ASdzCK59JNereSsAel4W9JCGaOzCr-8,6201
|
|
23
|
+
crawlo/commands/utils.py,sha256=YVNEEzlm_qNY3SVvU8h6o2lQMkVgypvoB4ZFrP4gln0,5578
|
|
24
|
+
crawlo/core/__init__.py,sha256=BWkj3AqZwp2Bk73UzUlC_qsqv_MH_HNrzy4DY1hosj4,1330
|
|
25
|
+
crawlo/core/engine.py,sha256=y9mj0nKHb3Ki4scXkxsMO6XoTIqxmbsD0WuryR_6iHg,19385
|
|
26
|
+
crawlo/core/processor.py,sha256=hR5MrbeZvDUx0ShKntr4qwkeVZzjlPJ8EAKgIFkNVts,1555
|
|
27
|
+
crawlo/core/scheduler.py,sha256=-6DBz7gUg8WwUl39DAbi6Ng2AJSswNBCDr_mV3sUZFs,14088
|
|
28
|
+
crawlo/data/__init__.py,sha256=UPqgioMdu3imSUmpLWzVlpvoBnEfaPSAT-crCcWd7iw,121
|
|
29
|
+
crawlo/data/user_agents.py,sha256=zjjFkldQkqtrn45j0WZplaZLannPxZDeAU0JofxQcBc,9891
|
|
30
|
+
crawlo/downloader/__init__.py,sha256=VZG5HiSHOmimiH9okQN3MBwgXsCzxr2awflVz5UiboY,8897
|
|
31
|
+
crawlo/downloader/aiohttp_downloader.py,sha256=-dIFucMOQhiiEmtgEpG2Lqh1vF-PvDddbIrZ8Hge0Ig,9556
|
|
32
|
+
crawlo/downloader/cffi_downloader.py,sha256=QxoeocCE2DsQCnhZla6-BjhplaTZDWMbEJmNrghWSDA,10488
|
|
33
|
+
crawlo/downloader/httpx_downloader.py,sha256=MpgDeIdGqNsiSKLOEDBnr5Z0eUbhHnqVEmAuoIfJmFU,12296
|
|
34
|
+
crawlo/downloader/hybrid_downloader.py,sha256=dNnFeegRnyLaOxTWI6XrWKqqVPx80AZBZNgmrcKRVBM,8240
|
|
35
|
+
crawlo/downloader/playwright_downloader.py,sha256=L-TVzG7cYfuBlqW0XSZuz5C_r9fpJrmYNcoQ-cDEna4,16663
|
|
36
|
+
crawlo/downloader/selenium_downloader.py,sha256=P8GuhEw6OYVeN3oeksuBLpUJCELXiu0mAR23X6IIOAA,21508
|
|
37
|
+
crawlo/extension/__init__.py,sha256=-R4P9fklpgSB8cGEduMsjkbJZ7ReYSrZaYjApgYUm9U,2986
|
|
38
|
+
crawlo/extension/health_check.py,sha256=stDpyP4gOzAdbBlPbSf0rge0QounAhF8CtrGq5fa_7c,5657
|
|
39
|
+
crawlo/extension/log_interval.py,sha256=N25aNjFkjh9br6g3ViFqRrz06C2geAdfGas-OT2oZh8,4497
|
|
40
|
+
crawlo/extension/log_stats.py,sha256=CWjMb_V1o8j8uwGFvh9SZ7EYLl_OYzmuIsOT5V-_BE4,2452
|
|
41
|
+
crawlo/extension/logging_extension.py,sha256=WnHVoC4aLHYLapAN0ylt3k5aanP_T1GOyJrAVy-6ePE,2415
|
|
42
|
+
crawlo/extension/memory_monitor.py,sha256=fClPchpCkVjcIiU0AJHCKDd7HEiz5B4KqNqKTRZ2hcU,4394
|
|
43
|
+
crawlo/extension/performance_profiler.py,sha256=BjWD3LOb4VwjQJQvQtWNg7GluEwFquI1CztNfgMzy3c,5032
|
|
44
|
+
crawlo/extension/request_recorder.py,sha256=KA_RmcfscDxP5wPdolO76yKfRj-1jmHhG3jkVGO1pbc,4181
|
|
45
|
+
crawlo/factories/__init__.py,sha256=24dH70p05pZerO9-9gaKpTawRGeGvQYw7j5brvq8GUg,714
|
|
46
|
+
crawlo/factories/base.py,sha256=loB_vyc0CsQK0BgwRoSOFS8gPcmv-b9irtjC9UaBGA4,1832
|
|
47
|
+
crawlo/factories/crawler.py,sha256=e9zl4qytByzsYbz66klY3cZTvQei0-9GjdFK4XCyXcg,3198
|
|
48
|
+
crawlo/factories/registry.py,sha256=YU87CdsntOz609M0aQbGcCG9glPinUJxOn-_CaM4f-M,2595
|
|
49
|
+
crawlo/filters/__init__.py,sha256=noSe07tp2Ip_zXwAbS021BojrqNRaObDO-2YV6DOQfc,4381
|
|
50
|
+
crawlo/filters/aioredis_filter.py,sha256=unms0WaRsxbCL6VaAQMT-SsBHKyxR6-o118pf-3ErK0,9512
|
|
51
|
+
crawlo/filters/memory_filter.py,sha256=ZojFhZ6gE76aQBC-rfImxSkSMwQtiotenx0pIcQOaFg,9561
|
|
52
|
+
crawlo/initialization/__init__.py,sha256=uNRMm9GccMYZi51scpvo-CPx_3ayp3Y81psBHlUoDfw,1132
|
|
53
|
+
crawlo/initialization/built_in.py,sha256=1uEEtYCTQlfx5uRW-s9oumlmIEJrjZa0QpOLAbZbZqI,15758
|
|
54
|
+
crawlo/initialization/context.py,sha256=wG9t-M-Qttj7TN6gDumPX5Q5GHaPDUpLTZZDne2r3TE,4863
|
|
55
|
+
crawlo/initialization/core.py,sha256=sMiSBueoaWoDohQJ50IFC_DSvj0EeYSB7G1MORlDtMc,6872
|
|
56
|
+
crawlo/initialization/phases.py,sha256=iWhGITh9eudfSmzf2G3DLPAIJkCDrv9TVBtnAoS1_3c,4176
|
|
57
|
+
crawlo/initialization/registry.py,sha256=kKVegqWxtPCaZ1mTyVHN4yFecAGDOPFJfebkP-SoobE,4919
|
|
58
|
+
crawlo/items/__init__.py,sha256=rFpx1qFBo0Ik7bSdnXC8EVTJUOQdoJYGVdhYjaH00nk,409
|
|
59
|
+
crawlo/items/base.py,sha256=q0YTJlqUtizsqXwfWlk0ndcINV9dDyUckwMx8_JrkeY,602
|
|
60
|
+
crawlo/items/fields.py,sha256=l-DIwK6CCpdzNvf6ELz7Ckc7YCghZD9UCXA8vhNn2UE,1852
|
|
61
|
+
crawlo/items/items.py,sha256=OmVEvMmgofMU95GkaiWkfNQ2fjsH2fY9sw3SKcmUhLs,3478
|
|
62
|
+
crawlo/logging/__init__.py,sha256=NlvL0sc9NZqy-Poplwpd2wsUleGyg33MyRb1wxyG-zs,1184
|
|
63
|
+
crawlo/logging/async_handler.py,sha256=cMBVi9Ue1y5yZ7r0Uzwr7j_4nyxwmcGXwSE1J7_yIOw,5259
|
|
64
|
+
crawlo/logging/config.py,sha256=0N7w542vlKyE5tSLAbDJYm9U4_1lQro_TQKVIJE_pA4,7167
|
|
65
|
+
crawlo/logging/factory.py,sha256=b4Z0fBmP00GpvpJ7k4QxqYP32n_EqG5KD3ouUWU7L4U,6656
|
|
66
|
+
crawlo/logging/manager.py,sha256=aem7yla0q83rf2CpwQEyg5YMbey4TzkquBVWiKtcqdQ,3182
|
|
67
|
+
crawlo/logging/monitor.py,sha256=mzZWm3rQ2mGUoAmkEJPUkBmR0VWK66l14aqqhQ0zwE8,4935
|
|
68
|
+
crawlo/logging/sampler.py,sha256=1BoRMpusP3wbXRnet5xl9_Yb_3_-AUq9WJhK9gYg7v4,5292
|
|
69
|
+
crawlo/middleware/__init__.py,sha256=PSwpRLdBUopaQzBp1S0zK_TZbrRagQ4yzvgyLy4tBk8,570
|
|
70
|
+
crawlo/middleware/default_header.py,sha256=Pw-ev8ffi16GeCh84R5L3hAZgp3G1QXS-H5kV3JEp4Q,5164
|
|
71
|
+
crawlo/middleware/download_delay.py,sha256=2iWnJFtWDlqDy5MsAob8TPiJQoiz9v21yatkBI0eptg,3542
|
|
72
|
+
crawlo/middleware/middleware_manager.py,sha256=_Kgd6Ir4cRUiPCEHJELZPOkKNtmu-WAE59dRWKPpAU8,6415
|
|
73
|
+
crawlo/middleware/offsite.py,sha256=4tUkPqXMMXsi1WwYnJ_e7wMd6sRgK19QHRCYq8-w8jk,4682
|
|
74
|
+
crawlo/middleware/proxy.py,sha256=uKk5OSLIs7jv9bBgkZwsi1rIpthooxhMrGBC2BPRDCc,16022
|
|
75
|
+
crawlo/middleware/request_ignore.py,sha256=7qdX4zAimjSGwdod_aWUbOTfzLBWZ5KzLVFchGMCxCI,2663
|
|
76
|
+
crawlo/middleware/response_code.py,sha256=d5t0hmP8QliuvvtFOqW-ogCBtZxg2eyjsOtlQAEUxM8,4533
|
|
77
|
+
crawlo/middleware/response_filter.py,sha256=tVGr06bfJBR3xAHI2G5c3WimFsGHu8qoJtDcsVuCATU,4384
|
|
78
|
+
crawlo/middleware/retry.py,sha256=Acfo95B9wF8fQTCQIqluZOS2hHdnknQu_FOHvpGKJp0,4248
|
|
79
|
+
crawlo/middleware/simple_proxy.py,sha256=rQ4RkqewGvDRCw021nGrg8ngkBzg3wqrEVqvSmBgQ6M,2256
|
|
80
|
+
crawlo/network/__init__.py,sha256=bvEnpEUBZJ79URfNZbsHhsBKna54hM2-x_BV8eotTA4,418
|
|
81
|
+
crawlo/network/request.py,sha256=e6-YLgK7SU8D19n21mQwqt_b_aeRVJFOgWPIBPal2ys,14178
|
|
82
|
+
crawlo/network/response.py,sha256=QwJhL3xJfPVy_gwtGrg61oAgaqCoCmjyj1Ug7Zju7Pg,13060
|
|
83
|
+
crawlo/pipelines/__init__.py,sha256=FDe2Pr5tiHtV8hFlheElRO_O1aVKvSWlkTcAl9BXAKA,637
|
|
84
|
+
crawlo/pipelines/bloom_dedup_pipeline.py,sha256=vIF_6noJAdpotrJpnCmrVXCi59gRmHHn28mYW6VukbM,5465
|
|
85
|
+
crawlo/pipelines/console_pipeline.py,sha256=bwe5hZgaVSWmh3R8XpOaaeAjJme-Ttrpo6G6f1cnLIg,1287
|
|
86
|
+
crawlo/pipelines/csv_pipeline.py,sha256=qbXZoqq4FIR9QkUGpC0ryWzmqGJSrM2bxmWLM4I1nXM,12490
|
|
87
|
+
crawlo/pipelines/database_dedup_pipeline.py,sha256=IxahtD_mhni-Y21_idOMX58_Htf46A7n52enG9VR2PI,7296
|
|
88
|
+
crawlo/pipelines/json_pipeline.py,sha256=wrCsh8YInmcPLAkhPrHObMx89VZfhf-c7qRrYsTixPE,8585
|
|
89
|
+
crawlo/pipelines/memory_dedup_pipeline.py,sha256=lKkYPu6vkpPjfQ1-xOLvPFT4VdTI8QVx0yjqtVR0ZB0,3598
|
|
90
|
+
crawlo/pipelines/mongo_pipeline.py,sha256=PohTKTGw3QRvuP-T6SrquwW3FAHSno8jQ2D2cH_d75U,5837
|
|
91
|
+
crawlo/pipelines/mysql_pipeline.py,sha256=Kjgu6cks1KD4FPXwlTnFaos2LG-N8LLaBDyKZ_MEcsI,14196
|
|
92
|
+
crawlo/pipelines/pipeline_manager.py,sha256=R6MRb5d-caOit7PZoglJLHa3qQ68U5YAQlwt8KcjRxo,4393
|
|
93
|
+
crawlo/pipelines/redis_dedup_pipeline.py,sha256=RB1kXLr8ZuWNrgZKYwt--tlmnWsQTbuwTsSt3pafol8,6077
|
|
94
|
+
crawlo/queue/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
95
|
+
crawlo/queue/pqueue.py,sha256=Q4H2ePag7-pBjzJ0a4S1P4z_IT_G08T6l1uZBkuxO5A,1262
|
|
96
|
+
crawlo/queue/queue_manager.py,sha256=Y2K4P-il5ACdP72X5jgTT-65Fu94_kQZ7H4c7AdRt-c,21547
|
|
97
|
+
crawlo/queue/redis_priority_queue.py,sha256=vLvg2toKaRrXD1QyEdu1ZjTmANv7clFaBF7mCtstBmI,15995
|
|
98
|
+
crawlo/settings/__init__.py,sha256=NgYFLfk_Bw7h6KSoepJn_lMBSqVbCHebjKxaE3_eMgw,130
|
|
99
|
+
crawlo/settings/default_settings.py,sha256=DdoMvB7M_OyGKlBOr0lY-T5TN4V1bo6PlPvu4ZcQXnY,12836
|
|
100
|
+
crawlo/settings/setting_manager.py,sha256=yI1tGaludevxKGGZO3Pn4aYofrg2cwYwvMZCFC5PPZw,8595
|
|
101
|
+
crawlo/spider/__init__.py,sha256=QGhe_yNsnfnCF3G9nSoWEw23b8SkP5oSFU5W79C5DzI,21881
|
|
102
|
+
crawlo/templates/crawlo.cfg.tmpl,sha256=lwiUVe5sFixJgHFEjn1OtbAeyWsECOrz37uheuVtulk,240
|
|
103
|
+
crawlo/templates/run.py.tmpl,sha256=Mt4gcw7RJu9ri4eBRnsAzf0EDt2giFWzpX36OTqEUpQ,961
|
|
104
|
+
crawlo/templates/spiders_init.py.tmpl,sha256=p6UK8KWr8FDydNxiAh6Iz29MY5WmgXIkf2z-buOGhOM,354
|
|
105
|
+
crawlo/templates/project/__init__.py.tmpl,sha256=aQnHaOjMSkTviOC8COUX0fKymuyf8lx2tGduxkMkXEE,61
|
|
106
|
+
crawlo/templates/project/items.py.tmpl,sha256=8_3DBA8HrS2XbfHzsMZNJiZbFY6fDJUUMFoFti_obJk,314
|
|
107
|
+
crawlo/templates/project/middlewares.py.tmpl,sha256=fxHqi-Sjec5GiHJciprOU-6SAUTzM728NlZckIqf9hM,4278
|
|
108
|
+
crawlo/templates/project/pipelines.py.tmpl,sha256=j9oqEhCezmmHlBhMWgYtlgup4jhWnMlv6AEiAOHODkg,2704
|
|
109
|
+
crawlo/templates/project/settings.py.tmpl,sha256=gGYwPf-RCuw1pWyBZRUvL1BHzgoLYcIQ1sXUmWDGp1k,7050
|
|
110
|
+
crawlo/templates/project/settings_distributed.py.tmpl,sha256=YSN7YcA05MT2yO5mg5MpryVyeEDhcaJEp9TU2NAUPS8,7147
|
|
111
|
+
crawlo/templates/project/settings_gentle.py.tmpl,sha256=HS1qumqDciXFBTZYm-RS__ldphDVbuo6Poz8pTCHNEg,6797
|
|
112
|
+
crawlo/templates/project/settings_high_performance.py.tmpl,sha256=u6n7S0KzSgJU23pkRifXnsS7AdQplJXefRyeG51v_QI,6887
|
|
113
|
+
crawlo/templates/project/settings_minimal.py.tmpl,sha256=GJG44CJlop0_kDwtqhbKJlG_42VThHfICGVUNijkkRs,2550
|
|
114
|
+
crawlo/templates/project/settings_simple.py.tmpl,sha256=fmy5PgrS_uVlXnIwXQFQ1Q28Ls121lbVg21Dbxrn6B4,6649
|
|
115
|
+
crawlo/templates/project/spiders/__init__.py.tmpl,sha256=llhcIItXpm0TlEeumeLwp4fcYv2NHl8Iru7tLhDhxiE,216
|
|
116
|
+
crawlo/templates/spider/spider.py.tmpl,sha256=KvU-9YpN6MifDE7XzejjyyQS7RUjLDLZ8zqJcLwSsu0,5198
|
|
117
|
+
crawlo/tools/__init__.py,sha256=tOYfYPvZlrO8cmvnMWBjTma6UTLTFZN3qdC8pJwHrzI,4142
|
|
118
|
+
crawlo/tools/anti_crawler.py,sha256=LwLC6BkxDSkxc5H1hQ6kY9j7O0PZGAMPZECr7gbqw2M,9431
|
|
119
|
+
crawlo/tools/authenticated_proxy.py,sha256=ULCK0Cc9F2rGhRqu6kzKBdxzK9v2n1CsatSQ_PMxpAg,7272
|
|
120
|
+
crawlo/tools/data_formatter.py,sha256=iBDHpZBZvn9O7pLkTQilE1TzYJQEc3z3f6HXoVus0f0,7808
|
|
121
|
+
crawlo/tools/data_validator.py,sha256=bLWnkpFdclJuqjtSAgMI5nznN4vAuPwE1YaiFWKWenM,5490
|
|
122
|
+
crawlo/tools/date_tools.py,sha256=QOT3W5MqcEQhVM3cTZYxu1MRfgX-TI4aF1RI9s0QbdE,9195
|
|
123
|
+
crawlo/tools/distributed_coordinator.py,sha256=kkRbRoxz7iXKI3AQElyTptDpYl352ErbSkM3wjSHVwU,12574
|
|
124
|
+
crawlo/tools/encoding_converter.py,sha256=CqHAsR2rwxuzsyR-TeQNb79HX5mH4KAUixEY-sX7204,4170
|
|
125
|
+
crawlo/tools/network_diagnostic.py,sha256=X1hSbUthIVbMHCU7ti43Zpu8XTaDJd5Oxr2zAkEuSB0,13013
|
|
126
|
+
crawlo/tools/request_tools.py,sha256=oXrk4yWMACVa65fDQCQgzsg6a94FH4_lS7qNR53FHYU,2420
|
|
127
|
+
crawlo/tools/retry_mechanism.py,sha256=4AQ_HLuYt4hYMI9XHoKFk2GQKEiDJB5pAnsMCfjc6Bk,7777
|
|
128
|
+
crawlo/tools/scenario_adapter.py,sha256=pzysL1B2uQ1ZSEncVHd9Hv2viHNgaxP44YAUcDcppfw,9660
|
|
129
|
+
crawlo/tools/text_cleaner.py,sha256=UrMGcgRnJaufjmDKIDsRYKMA8znCAArHDgouttWPygk,6690
|
|
130
|
+
crawlo/utils/__init__.py,sha256=8kMbOZf9bzOUjtvh2QvqXZmiZh3pYzxXH9YQhYcwcoY,597
|
|
131
|
+
crawlo/utils/batch_processor.py,sha256=8LNy-K2SrQVUxmGEWxQyYw_j9M-erN4Ie7O4d3zpBvM,9142
|
|
132
|
+
crawlo/utils/class_loader.py,sha256=kZRGfyA3OPAH2QsQ-beOKjw3JKKBs6OyJyJyXkvWDrc,675
|
|
133
|
+
crawlo/utils/controlled_spider_mixin.py,sha256=8CuM3Cr2wQLHbaO_ohbCsPcImJnyfZHpERbSeMgQ-AQ,16936
|
|
134
|
+
crawlo/utils/db_helper.py,sha256=ZqOt1d3mErVv4TOvoWlov0niUxORB9aHByTmMoNFIDw,10902
|
|
135
|
+
crawlo/utils/enhanced_error_handler.py,sha256=fJC__rnYNKTNUHNbgjZtT846HoE31qyGbPft9bwyYLU,14214
|
|
136
|
+
crawlo/utils/env_config.py,sha256=W-VD_WF63DHxsyJysvp1eJwRh3L_pBRl_PitQAY3nQY,4079
|
|
137
|
+
crawlo/utils/error_handler.py,sha256=vJ_4EVkuVn_TrM16VgN4doyhe_Pg7xWwVUWIENgJQAg,5455
|
|
138
|
+
crawlo/utils/fingerprint.py,sha256=70Me5avs40HYbz6LQ9La56EVP2qRapYjX-zF7WQDGkM,3687
|
|
139
|
+
crawlo/utils/func_tools.py,sha256=y-TYP9H3X67MS_foWy9Z2LIS6GP7Y4Cy3T168ulq3Jc,2451
|
|
140
|
+
crawlo/utils/large_scale_config.py,sha256=NZMsDj4qbVx06Fu0aHqNKX1yzo6WFT7CgrhVnvw1ZFs,8372
|
|
141
|
+
crawlo/utils/large_scale_helper.py,sha256=4ORkZcIrwJ0SlKOUh7l7WIuERORuRhNBgHCM71Rz0n0,12452
|
|
142
|
+
crawlo/utils/log.py,sha256=KmUWVYq8t6fSGOC88nnYCDxwBUdoPWvaBmpOSHn2oWI,2914
|
|
143
|
+
crawlo/utils/performance_monitor.py,sha256=32KspSo7RWvCX_fl0ZFn4ScWWOqbVVwEhPRd921Ez6I,9832
|
|
144
|
+
crawlo/utils/queue_helper.py,sha256=gFmkh1jKlIcN1rmo2Jl6vYcLP5ByUWlfHO9eNlZPBLs,4918
|
|
145
|
+
crawlo/utils/redis_connection_pool.py,sha256=EsPZkmQctWkoYU2wcrqkgwnIWnE6nG4XCXECKn216JA,12575
|
|
146
|
+
crawlo/utils/redis_key_validator.py,sha256=-UTTx0Ul184pzwSply8hVdH0lp-gkXXOc_gEHR_7VlU,5809
|
|
147
|
+
crawlo/utils/request.py,sha256=ejdKpTwc-HE04HQybafhOVywzz57IV3pY0YMkSLyGUo,9065
|
|
148
|
+
crawlo/utils/request_serializer.py,sha256=b5abcgjJk4IU6Wfg46AmOAU2wmzu_WqcpEbuAncRMGQ,8931
|
|
149
|
+
crawlo/utils/spider_loader.py,sha256=xNzQb7qhQ7TqZsfFtCLpuVcsGi-USriZosU0YSBr9II,2233
|
|
150
|
+
crawlo/utils/system.py,sha256=24zGmtHNhDFMGVo7ftMV-Pqg6_5d63zsyNey9udvJJk,248
|
|
151
|
+
crawlo/utils/tools.py,sha256=uy7qw5Z1BIhyEgiHENvtM7WoGCJxlS8EX3PmOA7ouCo,275
|
|
152
|
+
crawlo/utils/url.py,sha256=RKe_iqdjafsNcp-P2GVLYpsL1qbxiuZLiFc-SqOQkcs,1521
|
|
153
|
+
examples/__init__.py,sha256=NkRbV8_S1tb8S2AW6BE2U6P2-eGOPwMR1k0YQAwQpSE,130
|
|
154
|
+
examples/test_project/__init__.py,sha256=BQ6FVVDjB00-Vyib8h2I3P-LV5tjsFzTSLC2rFDe7Gw,136
|
|
155
|
+
examples/test_project/run.py,sha256=HHMFVY8D9ouWytp-xNvFDKB8NphrZGuFbVrah6-afG8,953
|
|
156
|
+
examples/test_project/test_project/__init__.py,sha256=RU5IUwU1oeDABAj3ZsLdMo53r3XG4saYIYgO1SXo13g,57
|
|
157
|
+
examples/test_project/test_project/items.py,sha256=L_bnTuJLW7xtuja4AaqYuSsQvVdaqMunZWdh1OTz4HY,310
|
|
158
|
+
examples/test_project/test_project/middlewares.py,sha256=fE7AUI2Yb9_ZwA4vC4ngn-s231FtEYeYWjXOwd5mkzE,4270
|
|
159
|
+
examples/test_project/test_project/pipelines.py,sha256=7EDGrvuNH6JY0XINRwzgPmB-X4Ax6J790jtxbkL2O_U,2696
|
|
160
|
+
examples/test_project/test_project/settings.py,sha256=imfrkrwSJ1V3jINe2ZhynlT4_w5bUBkeI9DFK7DS2g0,7115
|
|
161
|
+
examples/test_project/test_project/spiders/__init__.py,sha256=Lx_To88ShpAR6Pyd9PUMjct690MZH0gETxz6knRqPRY,212
|
|
162
|
+
examples/test_project/test_project/spiders/of_week_dis.py,sha256=-gDLaKGoF5birxCoLL_CX82bYopXjo4QmOV6a7I-Ci0,5178
|
|
163
|
+
tests/__init__.py,sha256=409aRX8hsPffiZCVjOogtxwhACzBp8G2UTJyUQSxhK0,136
|
|
164
|
+
tests/advanced_tools_example.py,sha256=1_iitECKCuWUYMNNGo61l3lmwMRrWdA8F_Xw56UaGZY,9340
|
|
165
|
+
tests/authenticated_proxy_example.py,sha256=fKmHXXxIxCJXjEplttCWRh7PZhbxkBSxJF91Bx-qOME,3019
|
|
166
|
+
tests/baidu_performance_test.py,sha256=wxdaI7UwKboMYH_qcaqZLxAStvndH60bvKGzD8F-jaI,3974
|
|
167
|
+
tests/baidu_test.py,sha256=NKYnwDbPJX3tmKtRn7uQ_QWzUXiLTQC-Gdr1cQkJzEo,1874
|
|
168
|
+
tests/cleaners_example.py,sha256=blVqSJ7SeWUNd17JjHZJgVTzWH65XKevLyaMB_Wg8qA,5324
|
|
169
|
+
tests/comprehensive_framework_test.py,sha256=_1N-OGbKvBTNachNvIjkL_izr4uv6OUybUkhxxz5MAk,5977
|
|
170
|
+
tests/comprehensive_test.py,sha256=wypCaB56IV8w8nd5VA5LSXUQ3IgLf0AKKUiCci6yEJQ,2969
|
|
171
|
+
tests/comprehensive_testing_summary.md,sha256=S01gclEas5oDhSLjxT_mOoeMl8FE4NMA-gveQOrIS4g,6513
|
|
172
|
+
tests/config_validation_demo.py,sha256=jbZ7h-HGsJmuqBb1euB_AhmKjllkvPmItRF1K0MQrVM,4171
|
|
173
|
+
tests/controlled_spider_example.py,sha256=2SAQKoREGHe-OzVaSkGpopCcrou6QXmeW7rLdmsyopw,7981
|
|
174
|
+
tests/date_tools_example.py,sha256=XI3iFEzeo7Nb5YepK8WHytIaBegtxWVSISpqQgpV6M8,5042
|
|
175
|
+
tests/debug_configure.py,sha256=9VZRJtA0u_SbCC_ZMdsiT9raseRE-C2spZpZuXZNysI,2213
|
|
176
|
+
tests/debug_framework_logger.py,sha256=p-dfOjEipjXQd6yk75S-SMoepzwujiwuv3rNwNSyjow,3413
|
|
177
|
+
tests/debug_log_config.py,sha256=cPS6qOLnynYTFOxpjcy9OUgIqrkasWb9f2c_PASc2_E,3714
|
|
178
|
+
tests/debug_log_levels.py,sha256=CZWG3KGDq-hYJ5TPhoZTyjKFKkkM-AoK3oP1w-JC1sc,2168
|
|
179
|
+
tests/debug_pipelines.py,sha256=FMb36bH9lQxBLb-nM579hBRK1S16Vxu1t_BC3Dj8O2w,2164
|
|
180
|
+
tests/detailed_log_test.py,sha256=oTCFF_Un7Jq2gV4rpRDFOxlHJSthnQhvEf0CSItfB7I,7501
|
|
181
|
+
tests/distributed_test.py,sha256=u6cEiymZzCItaTClKTxwVjNmOj9_PZii4_eGNAVMDW8,1825
|
|
182
|
+
tests/distributed_test_debug.py,sha256=pUv6ZKEJ5pK9xOA7lgVk6WW3cBAtnb1bsuZzJ8oGLvY,2181
|
|
183
|
+
tests/dynamic_loading_example.py,sha256=7LdeQZFevrb-U1_dgr4oX3aYo2Da4HvE_0KIf1fw4Ew,18786
|
|
184
|
+
tests/dynamic_loading_test.py,sha256=dzDW7b66HeDsIYsYgvNRihE3V6b6gEbUGQpp-eJbcIM,3413
|
|
185
|
+
tests/env_config_example.py,sha256=_ZRDh_LR23ZKpy9E--y_KM0QIOiZF5vRT98QTn52TY8,4951
|
|
186
|
+
tests/error_handling_example.py,sha256=grTeo1X17rFz4lhgASb0g5yu4NWbmNz5neyuonnNR40,5294
|
|
187
|
+
tests/final_command_test_report.md,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
188
|
+
tests/final_comprehensive_test.py,sha256=szTNbtwKfYNmE0kzDPCsE_kvnTG7FNKl2JERakGhKIk,4314
|
|
189
|
+
tests/final_log_test.py,sha256=CpZ4ZvvuvFiBvz1a50qN599XIU086ett_I0bSX42BLU,9367
|
|
190
|
+
tests/final_validation_test.py,sha256=4cuTr58i46JI6M4Tz54e7vrVFrOr3R7HSWgyQPKmM9M,5244
|
|
191
|
+
tests/fix_log_test.py,sha256=hcRy0j3j0CT0oLN7KNA0VL-_o4M-uE1amR6GziBflfU,4440
|
|
192
|
+
tests/framework_performance_test.py,sha256=Qp47VrsCK0ylEhDkFOm7lnD8rVkaJ7u1MopsEhAomrE,6985
|
|
193
|
+
tests/log_buffering_test.py,sha256=0B5UY1yQuxnBU1pEyz3IBYweN__4fOkPXly-kYfOpNU,3226
|
|
194
|
+
tests/log_generation_timing_test.py,sha256=zHb_m2FqlpRCYw-wqFWFn8cbVH8UR3VvXKSM6nNnbgo,4681
|
|
195
|
+
tests/optimized_performance_test.py,sha256=bA0dN4j7ViyTSSiCJEjlkJ9Y7jspTFKs2xX7UXHE8Gs,7379
|
|
196
|
+
tests/performance_comparison.py,sha256=CKGFbcwqsF3CAWIaOWF3Ca6o_OdEdZCgIfYb_m6CzIw,9302
|
|
197
|
+
tests/queue_blocking_test.py,sha256=hp-6hmTOO64oOAWVtlN8cFJ95GjbK3t9fj-4q_TKowk,3955
|
|
198
|
+
tests/queue_test.py,sha256=HeBiBXqAgIAbUkLVQ3McS6NdRselA30m3lnuxNBvZbk,2689
|
|
199
|
+
tests/redis_key_validation_demo.py,sha256=WD2jvuBwHhLYIb3lVFtvYSSnmXWn1EW4EPCEwFhfi6M,4467
|
|
200
|
+
tests/request_params_example.py,sha256=J50NdsnK1sDrqG-5m3oA-mu1_wHwVwHIfsWxGeQpz7o,4250
|
|
201
|
+
tests/response_improvements_example.py,sha256=t1cbG3nesp82bqog4_ku1GvQzNbhRyWa5EaKTmOPrSk,5402
|
|
202
|
+
tests/simple_command_test.py,sha256=8TowzW45ukKTPeaNC5uij3RR7rqPULiBr2PguSSMdP8,3688
|
|
203
|
+
tests/simple_crawlo_test.py,sha256=gfL910xt56HhrERAB9QhO_oxKWKw2j2IsifQkgYtwvE,4848
|
|
204
|
+
tests/simple_log_test.py,sha256=xOEGH5UzRLsCpwqgi1VEoZ7NY3DoWckwy6Wy9lKQ6ZE,1757
|
|
205
|
+
tests/simple_log_test2.py,sha256=Rn3XerVlkT0M-vbQmrQL7bVIZG3REnJNmMvUvKr6C20,3944
|
|
206
|
+
tests/simple_optimization_test.py,sha256=hflvaC81ra1ZrPOp-Z7rQrH95OnSADvAjy95BLulD6o,3678
|
|
207
|
+
tests/simple_queue_type_test.py,sha256=wAf4XLKl9oS5BlfrRJ1SLY-kYmNq4YY0LdIC7HmW-yg,1193
|
|
208
|
+
tests/simple_spider_test.py,sha256=RzziJg-fbIVJ6_CgbismfkwrLwpJp4WWp2RLgG7Tpws,1168
|
|
209
|
+
tests/simple_test.py,sha256=Pyxgg0YnBG_3_NRFla0HgJ21CYlfO4K-js3x6_-6ZEk,1258
|
|
210
|
+
tests/spider_log_timing_test.py,sha256=pvYpKZemClr4mCR76xywhsiWbT5sPdzD_taZKFjlgvM,5573
|
|
211
|
+
tests/test_advanced_tools.py,sha256=HT_TcwfFzli-CavIJSqQqnCxnBn5FDMX09zL7AJ5tNY,5398
|
|
212
|
+
tests/test_all_commands.py,sha256=VgVa9SzU5Irvn5igHpC2W4E_6ZDWDt7jc-T4UPK_PFE,7718
|
|
213
|
+
tests/test_all_pipeline_fingerprints.py,sha256=NDrBYr0f9CAhjmSezTS4NUrAdcotrSX3ElJTWqjXXbU,5308
|
|
214
|
+
tests/test_all_redis_key_configs.py,sha256=dWc4Dsr07_vuSpb4hwkMpyy6XO8SI7vglVjGuGvXoa4,5710
|
|
215
|
+
tests/test_authenticated_proxy.py,sha256=lnvmQwuf0zaZP_E05EzcNFR2VJbwTkLjOmZGNoJKaC4,4339
|
|
216
|
+
tests/test_batch_processor.py,sha256=4_nYlu9R1JkDCFHq0bYc9LUNqsg41r7sQ879hkrhEts,7212
|
|
217
|
+
tests/test_cleaners.py,sha256=HDK8_YU7GUj_3hGU415cxEeUR74mnDSk0yroLlgDI0I,1816
|
|
218
|
+
tests/test_component_factory.py,sha256=V3hO5pJHSDtViLAykXSUqkeH4g-GB4GczwutrTatS2U,5809
|
|
219
|
+
tests/test_comprehensive.py,sha256=dvRJeeVYc1cgXK9Y171hH9Y847zZpWSAFFH-EI3UepQ,5182
|
|
220
|
+
tests/test_config_consistency.py,sha256=RgSxyaypMpysltsGSh1vFMeOShiZZG0rmUKzEhNLpYw,2001
|
|
221
|
+
tests/test_config_merge.py,sha256=ts1j-TIKkFS0EO5q1I4O7f4YUKR5MLTmRSqOpOlv094,5606
|
|
222
|
+
tests/test_config_validator.py,sha256=Z4gBHkI0_fEx-xgiiG4T33F4BAuePuF81obpNTXfseY,6202
|
|
223
|
+
tests/test_controlled_spider_mixin.py,sha256=AQ493ic6AxZAKd7QCgnUES92BBWCMNteTd5DjoQlhwo,2864
|
|
224
|
+
tests/test_crawlo_proxy_integration.py,sha256=81DVwosMoiSMxj4V_jLzcL7aqvSv_8ucggkQyXsvzT0,2733
|
|
225
|
+
tests/test_date_tools.py,sha256=pcLDyhLrZ_jh-PhPm4CvLZEgNeH9kLMPKN5zacHwuWM,4053
|
|
226
|
+
tests/test_dedup_fix.py,sha256=UFdm8lIi0ZIdp40W8ruxRD69bxzijuFUfNyJmB4Fwl0,8788
|
|
227
|
+
tests/test_dedup_pipeline_consistency.py,sha256=dn5EAZSU5gQOV5EQwreHp76i5aQZ9tEdltSGO7dif5M,5176
|
|
228
|
+
tests/test_default_header_middleware.py,sha256=UDjEPIUCre1M6ndjV_uXLVCfY7WJwyN-1Xn15hzbKMo,13126
|
|
229
|
+
tests/test_distributed.py,sha256=78Pn4HPLIaO8t1IiaSkckBmuEVTcnC8IDw7znf9_Zcw,1790
|
|
230
|
+
tests/test_double_crawlo_fix.py,sha256=lZwrT5ij6Jbh0EzZswhw05FXwgKaEZsSHekLTrJJajg,7856
|
|
231
|
+
tests/test_double_crawlo_fix_simple.py,sha256=NDmCEeyvpf_D1tGQMA66iLPPKlAnSZcEg71e7GHYcjg,4768
|
|
232
|
+
tests/test_download_delay_middleware.py,sha256=Idc6KzhL3hY3aDKgn1j_v5-mLIHz7dTnV5c4tJVZh5Q,9107
|
|
233
|
+
tests/test_downloader_proxy_compatibility.py,sha256=0hgIzWXIqd92YXEB5sNneyp4Sk7PaG76up2cd6N9QQY,8903
|
|
234
|
+
tests/test_dynamic_downloaders_proxy.py,sha256=t_aWpxOHi4h3_fg2ImtIq7IIJ0r3PTHtnXiopPe2ZlM,4450
|
|
235
|
+
tests/test_dynamic_proxy.py,sha256=zi7Ocbhc9GL1zCs0XhmG2NvBBeIZ2d2hPJVh18lH4Y0,3172
|
|
236
|
+
tests/test_dynamic_proxy_config.py,sha256=C_9CEjCJtrr0SxIXCyLDhSIi88ujF7UAT1F-FAphd0w,5853
|
|
237
|
+
tests/test_dynamic_proxy_real.py,sha256=krWnbFIH26mWNPhOfPMmx3ZxJfOreZxMZFGwVb_8-K8,3511
|
|
238
|
+
tests/test_edge_cases.py,sha256=1RnFaCebYTDNNz_LK8M0MepiSwPvJUk_FBK4nQTCUbg,10729
|
|
239
|
+
tests/test_enhanced_error_handler.py,sha256=Ku_86jv7iDe25v8ZxalcXxJJjIiIvQXWH8ZldbwdVm8,8581
|
|
240
|
+
tests/test_enhanced_error_handler_comprehensive.py,sha256=j_cxyIPGks9A3untKhAdj5HU0hrLbbzOLu0uAtGUlJo,9369
|
|
241
|
+
tests/test_env_config.py,sha256=Qu1sDeADs69dSr1x0QmEe8nJrMHneE_4JClt-N901e8,4867
|
|
242
|
+
tests/test_error_handler_compatibility.py,sha256=xJ43cmCwfBGh-qBwCGiMDPPlfNDLw4ZrmlrHN9IojkU,4241
|
|
243
|
+
tests/test_factories.py,sha256=wKFfr8YBXPs-AQ8YOFgDhINn5uivKqPBZQPUe5GL9Ig,8865
|
|
244
|
+
tests/test_final_validation.py,sha256=OuZI01O0E68Pao--bD-BFDTRZFPc_Mt4W-OXUzlt6ZA,4966
|
|
245
|
+
tests/test_fingerprint_consistency.py,sha256=68V5u_2hNABI5pNWzXUrA1PJ08Xh9x3-JsMSNNjORMo,4956
|
|
246
|
+
tests/test_fingerprint_simple.py,sha256=qiSba8gF3Zl91QO_ijJO7KstLdjATs30V_GZCNHShig,1626
|
|
247
|
+
tests/test_framework_env_usage.py,sha256=bFb_ptdLeX2obdJWEqEHPWweiWR-wR2BpvEaJMQK7h4,4201
|
|
248
|
+
tests/test_framework_logger.py,sha256=nAtL_N49L7OurthY329vZK_jBjJIcPcETEIiV0HGqt0,2560
|
|
249
|
+
tests/test_framework_startup.py,sha256=I_ij7J6NO3DTBuHlh1Z4CJUcGxLEjRaIB6EdykiISEc,2267
|
|
250
|
+
tests/test_get_component_logger.py,sha256=UKj5uT1F3L3atoJFmpk7QSDO2fZHgw-7Y84vMFbHRkM,2285
|
|
251
|
+
tests/test_hash_performance.py,sha256=4eVPwbu66Oun0LVyTTNd9d2cj2V1xq0YZkRg8Z0TO-Q,3211
|
|
252
|
+
tests/test_integration.py,sha256=lVEzKNAjFzFZHRNZAyJmXxa_5Ogf_qqL4APqs620o58,4839
|
|
253
|
+
tests/test_item_dedup_redis_key.py,sha256=dp_H59exJLaZHh5oMtmMEOWh-DNZwbnwIFYDjOpHgd0,3842
|
|
254
|
+
tests/test_large_scale_config.py,sha256=Ik32ilAOQXsyw2sHR53gDPNNjY0AXybQ9ya2JY-EeqM,4296
|
|
255
|
+
tests/test_large_scale_helper.py,sha256=0L6EKHcKgh7XHvoW4wRSkxmw8GolUwSOCgZ_-ZmCyDo,8371
|
|
256
|
+
tests/test_logging_enhancements.py,sha256=YHcYWC8PG_AP5wZnmOr6H7QuU7m-3xzxEhppM0Jubvg,12731
|
|
257
|
+
tests/test_logging_final.py,sha256=K9vxyODslXza05hElVEcvzbXgzthYKK5CRj4UJTftIw,6376
|
|
258
|
+
tests/test_logging_integration.py,sha256=5WpExyt6BmYBZwrjqtQIGOw1Id64opJBAIahDk70Mlc,11131
|
|
259
|
+
tests/test_logging_system.py,sha256=LGfK14ZEWzRtl3_VkBGz-AaVa_dDtuC5zu40m8FvmMo,9206
|
|
260
|
+
tests/test_middleware_debug.py,sha256=gtiaWCxBSTcaNkdqXirM7CsThr_HfiCueBdQCpp7rqg,4572
|
|
261
|
+
tests/test_mode_change.py,sha256=GT53CBdxcG3-evcKz_OOfH4PBiq_oqQyuDjRXrvv1UU,2665
|
|
262
|
+
tests/test_mode_consistency.py,sha256=t72WX0etC_AayaL2AT6e2lIgbfP-zxTgYAiTARSN2Jk,1276
|
|
263
|
+
tests/test_offsite_middleware.py,sha256=njpXTdngOqBs60Wj6xgo5EEXlJnMHd7vtYGi9dVauW0,10602
|
|
264
|
+
tests/test_offsite_middleware_simple.py,sha256=4MfDKSXGHcoFLYnnxCH2rmnzztWyN0xByYLoHtepyiA,7918
|
|
265
|
+
tests/test_parsel.py,sha256=wuZqRFIm9xx1tt6o3Xi_OjvwhT_MPmHiUEj2ax06zlo,701
|
|
266
|
+
tests/test_performance.py,sha256=Lqs2iu3dmWipZkBPARcwIjDLXsqe42ntz1M4RzqqXKo,11457
|
|
267
|
+
tests/test_performance_monitor.py,sha256=paW3HGg6ReHb9lwnOivGCrI8STwbwp_mbuhgfds1h3I,4187
|
|
268
|
+
tests/test_pipeline_fingerprint_consistency.py,sha256=LL55oGSDGy0K8LxoyKa6ogNHXhJlZHe509vCFbibLkk,2847
|
|
269
|
+
tests/test_priority_behavior.py,sha256=p04M0HIgBaXyuVHmp-ImITA9jGaKI_RPwZ3DPY_Trt4,9134
|
|
270
|
+
tests/test_priority_consistency.py,sha256=rVX7nku5N_QpB_ffDu3xqREkCWPX5aNNiXy112o9wpA,5756
|
|
271
|
+
tests/test_priority_consistency_fixed.py,sha256=MlYi5PIr5wxunC3Ku4ilnxOatKyRu2qIvhV7pjadkjg,10765
|
|
272
|
+
tests/test_proxy_api.py,sha256=XnmklS-xU4ke_560gV6AIlBsRmG8YLQTGFAZrTUZuhc,11013
|
|
273
|
+
tests/test_proxy_health_check.py,sha256=_tDlxa_6TdL3M5RLkHF82roXJ8WIuG5hELBp2GADyKQ,1123
|
|
274
|
+
tests/test_proxy_middleware.py,sha256=EdQAfwwAJIBxw9JmUFTDEu_pdxapaTlcJr7KcrY6-AY,4021
|
|
275
|
+
tests/test_proxy_middleware_enhanced.py,sha256=QR-p26F63N7MxNjZ2QJUeerh_xdnCDejkrGPIh7Fh4U,7035
|
|
276
|
+
tests/test_proxy_middleware_integration.py,sha256=mTPK_XvbmLCV_QoVZzA3ybWOOX61493Ew78WfTp-bYQ,4441
|
|
277
|
+
tests/test_proxy_middleware_refactored.py,sha256=VbkTWkmmomcyswobA_gf3p_bERl_eexY2e6ohJQS_A8,6960
|
|
278
|
+
tests/test_proxy_providers.py,sha256=u_R2fhab90vqvQEaOAztpAOe9tJXvUMIdoDxmStmXJ4,1749
|
|
279
|
+
tests/test_proxy_stats.py,sha256=ES00CEoDITYPFBGPk8pecFzD3ItYIv6NSpcqNd8-kvo,526
|
|
280
|
+
tests/test_proxy_strategies.py,sha256=9Z1pXmTNyw-eIhGXlf2abZbJx6igLohYq-_3hldQ5uE,1868
|
|
281
|
+
tests/test_queue_empty_check.py,sha256=ZJC6jOgZq0Wb0-ubrB1ZNcCaUiWeCxoNZmjkd6PY6t0,1182
|
|
282
|
+
tests/test_queue_manager_double_crawlo.py,sha256=MijZ3JuyHMuqGbRC-8kclFr-4O7m_T8CqezP4qiWk-E,6957
|
|
283
|
+
tests/test_queue_manager_redis_key.py,sha256=txHLq5XUZZN7h9HUlqlUCEVCTe2IXdf9r7F_P2zNVdY,7117
|
|
284
|
+
tests/test_queue_naming.py,sha256=GzPqxvATF9A5iQMgn2wQM68qTHTbsQ9dPhktAkyzDG4,4786
|
|
285
|
+
tests/test_queue_type.py,sha256=N8y3s0Cwco-XphRcIiR4bQuNAEOgmxvlRoR1jzghTtY,3304
|
|
286
|
+
tests/test_queue_type_redis_config_consistency.py,sha256=1ew7Zp9CxH1DQ0RUmsZMV-n7s8B5dCly6u3FkJbR1qE,5259
|
|
287
|
+
tests/test_random_headers_default.py,sha256=ulDb3_kRpnTCN1-TO3m6wVM-eMkZS_ezsSbd1ur8Xpg,12772
|
|
288
|
+
tests/test_random_headers_necessity.py,sha256=SSbNQIE347oCQvuG6yaAambFU-3MyQzTV5jN1kArRGY,11741
|
|
289
|
+
tests/test_random_user_agent.py,sha256=6HjU4iUcMk-J6bR2N5FhIkWDfnaFKAPNVyRzxmQQ14k,2302
|
|
290
|
+
tests/test_real_scenario_proxy.py,sha256=clmLvBfap5OpsaCE08MAWap-78jhVrxYfVfDNyoa4Hg,8454
|
|
291
|
+
tests/test_redis_config.py,sha256=51_Fy1PqIhS0MMO2nR4q6oQjBFxfqcUPK_4NNf5s83g,903
|
|
292
|
+
tests/test_redis_connection_pool.py,sha256=pKfXdE3Cm_L_fNqI9zqFmqiidCwR0t7hiM_Fu_V1cNI,9328
|
|
293
|
+
tests/test_redis_key_naming.py,sha256=MTFk656JhiGVTsMctBDhBNOMFcBDZrsQA3UfPZ-Dgj4,6911
|
|
294
|
+
tests/test_redis_key_validator.py,sha256=GszSzGADgk3uN6Bye1d8pS-AtMVgB8jwqW-22gPNM6M,4418
|
|
295
|
+
tests/test_redis_queue.py,sha256=WQV3MtGg8rJzHgC2kRfXM6lSMXpwXJVQZfqn2dVrhg0,6758
|
|
296
|
+
tests/test_redis_queue_name_fix.py,sha256=9V-qDmUz97wOdPv8pKcVnQRxeZ126WSdB5JBnow4ho8,5770
|
|
297
|
+
tests/test_redis_queue_type_fallback.py,sha256=Bg6b5bqt-TKotE_wWdkaZNQr2WXT8gaDfolv8785NyE,4692
|
|
298
|
+
tests/test_request_ignore_middleware.py,sha256=QN81wgG_W_XfXCF9LvJNxCNwbOH6_tZnLIwLDTK2K5Q,6229
|
|
299
|
+
tests/test_request_params.py,sha256=l2etiDebqylPBym1e9DSDn4wxwTHv8DQHKq9AzlzlG0,4287
|
|
300
|
+
tests/test_request_serialization.py,sha256=Ikgec8tt_sPCK6jcZyK8vRw84zRNE6nxQy9rba1WKmE,2332
|
|
301
|
+
tests/test_response_code_middleware.py,sha256=wSe525bm-bk_iWMjPDzUu1LfOQrwJY8_MLKAspq2dzk,12193
|
|
302
|
+
tests/test_response_filter_middleware.py,sha256=YWrGzJ7wmftTjJXcNTtJl3b3EdJsO4oR22ZLWwgErhg,16327
|
|
303
|
+
tests/test_response_improvements.py,sha256=vNqHKyoEoYeEGAUiRzdsff2V6yvJ9QnDwGg7gmN38Ow,6028
|
|
304
|
+
tests/test_retry_middleware.py,sha256=mi7s4HDAqmmd9nvyxs3ZgxdEKOYkCgDu3rDvU_9o8vQ,11133
|
|
305
|
+
tests/test_retry_middleware_realistic.py,sha256=Sam5y4jCN8oeElU4xxeS5zjAyzS-P8siPV7OaifgsyU,9679
|
|
306
|
+
tests/test_scheduler.py,sha256=1fCu35QgK5gzgrhD0aUZj5lxL0QbokzPav-yEJxz9Ig,8182
|
|
307
|
+
tests/test_scheduler_config_update.py,sha256=LuxjEbt20QrPyVkjSFxvTnFtUxwMaHB6TcqjFyo8bow,4261
|
|
308
|
+
tests/test_simple_response.py,sha256=_ui2PuVZvJcAuLY7HZ8xcsy_tDBimgBqX0ukj3kE5J0,1549
|
|
309
|
+
tests/test_telecom_spider_redis_key.py,sha256=c-gfixPul2VlYMQJGf0H5ZgYJ461fQgSKbCPrbAU45M,7625
|
|
310
|
+
tests/test_template_content.py,sha256=2RgCdOA3pMUSOqC_JbTGeW7KonbTqJ0ySYJNWegU-v0,2903
|
|
311
|
+
tests/test_template_redis_key.py,sha256=99-s0_-8MFJbIvGG_X__sH0qkXWTtJv8fdTdlftsq4I,4876
|
|
312
|
+
tests/test_tools.py,sha256=z50Bvq_q8FwpyxNkmh00_A3sXkSv2l1Q_EbK02FDYgk,5504
|
|
313
|
+
tests/test_user_agent_randomness.py,sha256=tE8_zh-BjMAQ9CTgScxZze6JarNher6COkdoLU68YfA,5681
|
|
314
|
+
tests/test_user_agents.py,sha256=e4haX-o8Janl-PawGJ9MemZyMqTX33_tBF_WnYSVoUw,3327
|
|
315
|
+
tests/tools_example.py,sha256=Rxu5vVKnj3CZ3mCx-EEotBWPtZs2S7ktyqq-SYeclxU,7999
|
|
316
|
+
tests/untested_features_report.md,sha256=31aUlsw_1OKe0_ijAjeH85kJ7HJ8qzKLJdOHDjWtYdY,4169
|
|
317
|
+
tests/verify_debug.py,sha256=iQ4Efwg9bQTHscr73VYAAZ8rBIe1u6mQfeaEK5YgneY,1564
|
|
318
|
+
tests/verify_distributed.py,sha256=0IolM4ymuPOz_uTfHSWFO3Vxzp7Lo6i0zhSbzJhHFtI,4045
|
|
319
|
+
tests/verify_log_fix.py,sha256=7reyVl3MXTDASyChgU5BAYuzuxvFjSLG9HywAHso0qg,4336
|
|
320
|
+
tests/scrapy_comparison/ofweek_scrapy.py,sha256=rhVds_WjYum1bLuWWe90HtXE51fZXEqhhPSc822ZasQ,5790
|
|
321
|
+
tests/scrapy_comparison/scrapy_test.py,sha256=-IsGUHPBgEL0TmXjeLZl-TUA01B7Dsc2nRo4JZbFwZA,5599
|
|
322
|
+
crawlo-1.4.3.dist-info/METADATA,sha256=PTbW7GP9xgBjFEX1adwjxeJHqM_x9VRU_ZLZsezaydU,4848
|
|
323
|
+
crawlo-1.4.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
|
324
|
+
crawlo-1.4.3.dist-info/entry_points.txt,sha256=5HoVoTSPxI8SCa5B7pQYxLSrkOdiunyO9tqNsLMv52g,43
|
|
325
|
+
crawlo-1.4.3.dist-info/top_level.txt,sha256=keG_67pbZ_wZL2dmDRA9RMaNHTaV_x_oxZ9DKNgwvR0,22
|
|
326
|
+
crawlo-1.4.3.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
|
+
"""
|
|
@@ -1,7 +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
|
-
"""
|
|
1
|
+
#!/usr/bin/python
|
|
2
|
+
# -*- coding:UTF-8 -*-
|
|
3
|
+
"""
|
|
4
|
+
# @Time : 2025-09-27 23:36
|
|
5
|
+
# @Author : crawl-coder
|
|
6
|
+
# @Desc : None
|
|
7
|
+
"""
|