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
|
@@ -1,111 +1,111 @@
|
|
|
1
|
-
#!/usr/bin/env python3
|
|
2
|
-
# -*- coding: utf-8 -*-
|
|
3
|
-
"""
|
|
4
|
-
认证代理使用示例
|
|
5
|
-
演示如何在 Crawlo 框架中使用认证代理
|
|
6
|
-
"""
|
|
7
|
-
|
|
8
|
-
import asyncio
|
|
9
|
-
import sys
|
|
10
|
-
import os
|
|
11
|
-
|
|
12
|
-
# 添加项目根目录到路径
|
|
13
|
-
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
|
|
14
|
-
|
|
15
|
-
from crawlo.config import CrawloConfig
|
|
16
|
-
from crawlo.crawler import CrawlerProcess
|
|
17
|
-
from crawlo import Spider, Request, Item
|
|
18
|
-
|
|
19
|
-
|
|
20
|
-
class ProxyItem(Item):
|
|
21
|
-
"""代理测试结果项"""
|
|
22
|
-
url = ''
|
|
23
|
-
status = 0
|
|
24
|
-
proxy = ''
|
|
25
|
-
response_time = 0.0
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
class AuthProxySpider(Spider):
|
|
29
|
-
"""认证代理测试爬虫"""
|
|
30
|
-
name = 'auth_proxy_spider'
|
|
31
|
-
|
|
32
|
-
async def start_requests(self):
|
|
33
|
-
"""发起测试请求"""
|
|
34
|
-
urls = [
|
|
35
|
-
'https://httpbin.org/ip', # 查看IP地址
|
|
36
|
-
'https://httpbin.org/headers', # 查看请求头
|
|
37
|
-
]
|
|
38
|
-
|
|
39
|
-
for url in urls:
|
|
40
|
-
yield Request(url, callback=self.parse_response)
|
|
41
|
-
|
|
42
|
-
async def parse_response(self, response):
|
|
43
|
-
"""解析响应"""
|
|
44
|
-
import time
|
|
45
|
-
import json
|
|
46
|
-
|
|
47
|
-
# 获取代理信息
|
|
48
|
-
proxy_info = response.meta.get('proxy', 'No proxy')
|
|
49
|
-
|
|
50
|
-
# 解析响应内容
|
|
51
|
-
try:
|
|
52
|
-
data = json.loads(response.text)
|
|
53
|
-
ip_info = data.get('origin', 'Unknown')
|
|
54
|
-
except:
|
|
55
|
-
ip_info = response.text[:100] + '...' if len(response.text) > 100 else response.text
|
|
56
|
-
|
|
57
|
-
# 创建结果项
|
|
58
|
-
item = ProxyItem(
|
|
59
|
-
url=response.url,
|
|
60
|
-
status=response.status_code, # 修复:使用status_code而不是status
|
|
61
|
-
proxy=str(proxy_info),
|
|
62
|
-
response_time=response.meta.get('download_latency', 0)
|
|
63
|
-
)
|
|
64
|
-
|
|
65
|
-
self.logger.info(f"Proxy test result: {item}")
|
|
66
|
-
yield item
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
async def main():
|
|
70
|
-
"""主函数"""
|
|
71
|
-
print("🚀 开始认证代理测试...")
|
|
72
|
-
|
|
73
|
-
# 创建配置(使用认证代理)
|
|
74
|
-
config = CrawloConfig.standalone(
|
|
75
|
-
concurrency=2,
|
|
76
|
-
download_delay=1.0,
|
|
77
|
-
# 代理配置
|
|
78
|
-
# 高级代理配置(适用于ProxyMiddleware)
|
|
79
|
-
# 只要配置了代理API URL,中间件就会自动启用
|
|
80
|
-
PROXY_API_URL="http://proxy-api.example.com/get", # 代理API地址
|
|
81
|
-
|
|
82
|
-
# 代理配置(适用于ProxyMiddleware)
|
|
83
|
-
# 只要配置了代理列表,中间件就会自动启用
|
|
84
|
-
# PROXY_LIST=[
|
|
85
|
-
# "http://user:pass@proxy1.example.com:8080",
|
|
86
|
-
# "http://user:pass@proxy2.example.com:8080"
|
|
87
|
-
# ],
|
|
88
|
-
|
|
89
|
-
LOG_LEVEL='INFO'
|
|
90
|
-
)
|
|
91
|
-
|
|
92
|
-
# 添加自定义中间件
|
|
93
|
-
config.set('CUSTOM_MIDDLEWARES', [
|
|
94
|
-
'crawlo.middleware.proxy.ProxyMiddleware',
|
|
95
|
-
])
|
|
96
|
-
|
|
97
|
-
# 创建爬虫进程
|
|
98
|
-
process = CrawlerProcess(settings=config.to_dict())
|
|
99
|
-
|
|
100
|
-
# 添加爬虫
|
|
101
|
-
process.crawl(AuthProxySpider)
|
|
102
|
-
|
|
103
|
-
# 启动爬虫
|
|
104
|
-
print("🔄 正在运行代理测试...")
|
|
105
|
-
await process.start()
|
|
106
|
-
|
|
107
|
-
print("✅ 认证代理测试完成!")
|
|
108
|
-
|
|
109
|
-
|
|
110
|
-
if __name__ == "__main__":
|
|
1
|
+
#!/usr/bin/env python3
|
|
2
|
+
# -*- coding: utf-8 -*-
|
|
3
|
+
"""
|
|
4
|
+
认证代理使用示例
|
|
5
|
+
演示如何在 Crawlo 框架中使用认证代理
|
|
6
|
+
"""
|
|
7
|
+
|
|
8
|
+
import asyncio
|
|
9
|
+
import sys
|
|
10
|
+
import os
|
|
11
|
+
|
|
12
|
+
# 添加项目根目录到路径
|
|
13
|
+
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
|
|
14
|
+
|
|
15
|
+
from crawlo.config import CrawloConfig
|
|
16
|
+
from crawlo.crawler import CrawlerProcess
|
|
17
|
+
from crawlo import Spider, Request, Item
|
|
18
|
+
|
|
19
|
+
|
|
20
|
+
class ProxyItem(Item):
|
|
21
|
+
"""代理测试结果项"""
|
|
22
|
+
url = ''
|
|
23
|
+
status = 0
|
|
24
|
+
proxy = ''
|
|
25
|
+
response_time = 0.0
|
|
26
|
+
|
|
27
|
+
|
|
28
|
+
class AuthProxySpider(Spider):
|
|
29
|
+
"""认证代理测试爬虫"""
|
|
30
|
+
name = 'auth_proxy_spider'
|
|
31
|
+
|
|
32
|
+
async def start_requests(self):
|
|
33
|
+
"""发起测试请求"""
|
|
34
|
+
urls = [
|
|
35
|
+
'https://httpbin.org/ip', # 查看IP地址
|
|
36
|
+
'https://httpbin.org/headers', # 查看请求头
|
|
37
|
+
]
|
|
38
|
+
|
|
39
|
+
for url in urls:
|
|
40
|
+
yield Request(url, callback=self.parse_response)
|
|
41
|
+
|
|
42
|
+
async def parse_response(self, response):
|
|
43
|
+
"""解析响应"""
|
|
44
|
+
import time
|
|
45
|
+
import json
|
|
46
|
+
|
|
47
|
+
# 获取代理信息
|
|
48
|
+
proxy_info = response.meta.get('proxy', 'No proxy')
|
|
49
|
+
|
|
50
|
+
# 解析响应内容
|
|
51
|
+
try:
|
|
52
|
+
data = json.loads(response.text)
|
|
53
|
+
ip_info = data.get('origin', 'Unknown')
|
|
54
|
+
except:
|
|
55
|
+
ip_info = response.text[:100] + '...' if len(response.text) > 100 else response.text
|
|
56
|
+
|
|
57
|
+
# 创建结果项
|
|
58
|
+
item = ProxyItem(
|
|
59
|
+
url=response.url,
|
|
60
|
+
status=response.status_code, # 修复:使用status_code而不是status
|
|
61
|
+
proxy=str(proxy_info),
|
|
62
|
+
response_time=response.meta.get('download_latency', 0)
|
|
63
|
+
)
|
|
64
|
+
|
|
65
|
+
self.logger.info(f"Proxy test result: {item}")
|
|
66
|
+
yield item
|
|
67
|
+
|
|
68
|
+
|
|
69
|
+
async def main():
|
|
70
|
+
"""主函数"""
|
|
71
|
+
print("🚀 开始认证代理测试...")
|
|
72
|
+
|
|
73
|
+
# 创建配置(使用认证代理)
|
|
74
|
+
config = CrawloConfig.standalone(
|
|
75
|
+
concurrency=2,
|
|
76
|
+
download_delay=1.0,
|
|
77
|
+
# 代理配置
|
|
78
|
+
# 高级代理配置(适用于ProxyMiddleware)
|
|
79
|
+
# 只要配置了代理API URL,中间件就会自动启用
|
|
80
|
+
PROXY_API_URL="http://proxy-api.example.com/get", # 代理API地址
|
|
81
|
+
|
|
82
|
+
# 代理配置(适用于ProxyMiddleware)
|
|
83
|
+
# 只要配置了代理列表,中间件就会自动启用
|
|
84
|
+
# PROXY_LIST=[
|
|
85
|
+
# "http://user:pass@proxy1.example.com:8080",
|
|
86
|
+
# "http://user:pass@proxy2.example.com:8080"
|
|
87
|
+
# ],
|
|
88
|
+
|
|
89
|
+
LOG_LEVEL='INFO'
|
|
90
|
+
)
|
|
91
|
+
|
|
92
|
+
# 添加自定义中间件
|
|
93
|
+
config.set('CUSTOM_MIDDLEWARES', [
|
|
94
|
+
'crawlo.middleware.proxy.ProxyMiddleware',
|
|
95
|
+
])
|
|
96
|
+
|
|
97
|
+
# 创建爬虫进程
|
|
98
|
+
process = CrawlerProcess(settings=config.to_dict())
|
|
99
|
+
|
|
100
|
+
# 添加爬虫
|
|
101
|
+
process.crawl(AuthProxySpider)
|
|
102
|
+
|
|
103
|
+
# 启动爬虫
|
|
104
|
+
print("🔄 正在运行代理测试...")
|
|
105
|
+
await process.start()
|
|
106
|
+
|
|
107
|
+
print("✅ 认证代理测试完成!")
|
|
108
|
+
|
|
109
|
+
|
|
110
|
+
if __name__ == "__main__":
|
|
111
111
|
asyncio.run(main())
|
tests/baidu_performance_test.py
CHANGED
|
@@ -1,109 +1,109 @@
|
|
|
1
|
-
#!/usr/bin/env python3
|
|
2
|
-
# -*- coding: utf-8 -*-
|
|
3
|
-
"""
|
|
4
|
-
百度网站性能测试脚本
|
|
5
|
-
用于验证三个优化方法的实现效果:
|
|
6
|
-
1. 引入工作池模式:使用固定大小的工作池,避免无限创建协程
|
|
7
|
-
2. 优化信号量控制:动态调整并发数基于网络响应时间
|
|
8
|
-
3. 优化任务调度:引入优先级队列和智能调度
|
|
9
|
-
"""
|
|
10
|
-
import asyncio
|
|
11
|
-
import time
|
|
12
|
-
import sys
|
|
13
|
-
import os
|
|
14
|
-
|
|
15
|
-
# 添加项目根目录到Python路径
|
|
16
|
-
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
|
|
17
|
-
|
|
18
|
-
from crawlo import Spider, Request
|
|
19
|
-
from crawlo.crawler import CrawlerProcess
|
|
20
|
-
|
|
21
|
-
|
|
22
|
-
class BaiduTestSpider(Spider):
|
|
23
|
-
name = 'baidu_test'
|
|
24
|
-
|
|
25
|
-
def __init__(self, *args, **kwargs):
|
|
26
|
-
super().__init__(*args, **kwargs)
|
|
27
|
-
self.start_time = time.time()
|
|
28
|
-
self.request_count = 0
|
|
29
|
-
self.response_times = []
|
|
30
|
-
|
|
31
|
-
def start_requests(self):
|
|
32
|
-
# 测试百度首页和几个子页面
|
|
33
|
-
urls = [
|
|
34
|
-
'https://www.baidu.com/',
|
|
35
|
-
'https://www.baidu.com/s?wd=python',
|
|
36
|
-
'https://www.baidu.com/s?wd=ai',
|
|
37
|
-
'https://www.baidu.com/s?wd=机器学习',
|
|
38
|
-
'https://www.baidu.com/s?wd=大数据',
|
|
39
|
-
'https://www.baidu.com/s?wd=云计算',
|
|
40
|
-
'https://www.baidu.com/s?wd=区块链',
|
|
41
|
-
'https://www.baidu.com/s?wd=物联网',
|
|
42
|
-
]
|
|
43
|
-
|
|
44
|
-
for url in urls:
|
|
45
|
-
yield Request(url=url, callback=self.parse, priority=1)
|
|
46
|
-
|
|
47
|
-
def parse(self, response):
|
|
48
|
-
self.request_count += 1
|
|
49
|
-
response_time = time.time() - self.start_time
|
|
50
|
-
self.response_times.append(response_time)
|
|
51
|
-
|
|
52
|
-
print(f"✅ 成功获取: {response.url} (状态码: {response.status_code})")
|
|
53
|
-
print(f" 响应大小: {len(response.text)} 字符")
|
|
54
|
-
|
|
55
|
-
# 如果是首页,可以提取一些链接进行进一步测试
|
|
56
|
-
if 'www.baidu.com/' in response.url and self.request_count < 20:
|
|
57
|
-
# 限制额外请求数量以避免过于庞大的测试
|
|
58
|
-
links = response.xpath('//a[@href]/@href').extract()[:3] # 只取前3个链接
|
|
59
|
-
for link in links:
|
|
60
|
-
if link.startswith('http'):
|
|
61
|
-
yield Request(url=link, callback=self.parse, priority=0)
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
async def run_baidu_test():
|
|
65
|
-
"""运行百度性能测试"""
|
|
66
|
-
print("🚀 开始百度网站性能测试...")
|
|
67
|
-
print("=" * 60)
|
|
68
|
-
|
|
69
|
-
# 记录开始时间
|
|
70
|
-
start_time = time.time()
|
|
71
|
-
|
|
72
|
-
try:
|
|
73
|
-
# 创建爬虫进程
|
|
74
|
-
process = CrawlerProcess(settings={
|
|
75
|
-
"CONCURRENCY": 10, # 设置并发数
|
|
76
|
-
"DOWNLOAD_DELAY": 0.1, # 设置下载延迟
|
|
77
|
-
"LOG_LEVEL": "INFO", # 设置日志级别
|
|
78
|
-
})
|
|
79
|
-
|
|
80
|
-
# 运行爬虫
|
|
81
|
-
await process.crawl(BaiduTestSpider)
|
|
82
|
-
|
|
83
|
-
# 计算统计信息
|
|
84
|
-
end_time = time.time()
|
|
85
|
-
total_time = end_time - start_time
|
|
86
|
-
# 注意:由于Spider实例在CrawlerProcess中创建,我们需要通过其他方式获取统计信息
|
|
87
|
-
|
|
88
|
-
print("\n" + "=" * 60)
|
|
89
|
-
print("📊 测试结果统计:")
|
|
90
|
-
print(f" 总耗时: {total_time:.2f} 秒")
|
|
91
|
-
print(f" 并发数: 10")
|
|
92
|
-
|
|
93
|
-
# 验证三个优化方法的实现情况
|
|
94
|
-
print("\n" + "=" * 60)
|
|
95
|
-
print("✅ 优化方法实现验证:")
|
|
96
|
-
print(" 1. 工作池模式: 已实现 - TaskManager使用信号量控制并发")
|
|
97
|
-
print(" 2. 动态信号量控制: 已实现 - 根据响应时间动态调整并发数")
|
|
98
|
-
print(" 3. 智能任务调度: 已实现 - 使用优先级队列和智能调度算法")
|
|
99
|
-
|
|
100
|
-
print("\n🎉 百度网站性能测试完成!")
|
|
101
|
-
|
|
102
|
-
except Exception as e:
|
|
103
|
-
print(f"❌ 测试过程中出现错误: {e}")
|
|
104
|
-
import traceback
|
|
105
|
-
traceback.print_exc()
|
|
106
|
-
|
|
107
|
-
|
|
108
|
-
if __name__ == '__main__':
|
|
1
|
+
#!/usr/bin/env python3
|
|
2
|
+
# -*- coding: utf-8 -*-
|
|
3
|
+
"""
|
|
4
|
+
百度网站性能测试脚本
|
|
5
|
+
用于验证三个优化方法的实现效果:
|
|
6
|
+
1. 引入工作池模式:使用固定大小的工作池,避免无限创建协程
|
|
7
|
+
2. 优化信号量控制:动态调整并发数基于网络响应时间
|
|
8
|
+
3. 优化任务调度:引入优先级队列和智能调度
|
|
9
|
+
"""
|
|
10
|
+
import asyncio
|
|
11
|
+
import time
|
|
12
|
+
import sys
|
|
13
|
+
import os
|
|
14
|
+
|
|
15
|
+
# 添加项目根目录到Python路径
|
|
16
|
+
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
|
|
17
|
+
|
|
18
|
+
from crawlo import Spider, Request
|
|
19
|
+
from crawlo.crawler import CrawlerProcess
|
|
20
|
+
|
|
21
|
+
|
|
22
|
+
class BaiduTestSpider(Spider):
|
|
23
|
+
name = 'baidu_test'
|
|
24
|
+
|
|
25
|
+
def __init__(self, *args, **kwargs):
|
|
26
|
+
super().__init__(*args, **kwargs)
|
|
27
|
+
self.start_time = time.time()
|
|
28
|
+
self.request_count = 0
|
|
29
|
+
self.response_times = []
|
|
30
|
+
|
|
31
|
+
def start_requests(self):
|
|
32
|
+
# 测试百度首页和几个子页面
|
|
33
|
+
urls = [
|
|
34
|
+
'https://www.baidu.com/',
|
|
35
|
+
'https://www.baidu.com/s?wd=python',
|
|
36
|
+
'https://www.baidu.com/s?wd=ai',
|
|
37
|
+
'https://www.baidu.com/s?wd=机器学习',
|
|
38
|
+
'https://www.baidu.com/s?wd=大数据',
|
|
39
|
+
'https://www.baidu.com/s?wd=云计算',
|
|
40
|
+
'https://www.baidu.com/s?wd=区块链',
|
|
41
|
+
'https://www.baidu.com/s?wd=物联网',
|
|
42
|
+
]
|
|
43
|
+
|
|
44
|
+
for url in urls:
|
|
45
|
+
yield Request(url=url, callback=self.parse, priority=1)
|
|
46
|
+
|
|
47
|
+
def parse(self, response):
|
|
48
|
+
self.request_count += 1
|
|
49
|
+
response_time = time.time() - self.start_time
|
|
50
|
+
self.response_times.append(response_time)
|
|
51
|
+
|
|
52
|
+
print(f"✅ 成功获取: {response.url} (状态码: {response.status_code})")
|
|
53
|
+
print(f" 响应大小: {len(response.text)} 字符")
|
|
54
|
+
|
|
55
|
+
# 如果是首页,可以提取一些链接进行进一步测试
|
|
56
|
+
if 'www.baidu.com/' in response.url and self.request_count < 20:
|
|
57
|
+
# 限制额外请求数量以避免过于庞大的测试
|
|
58
|
+
links = response.xpath('//a[@href]/@href').extract()[:3] # 只取前3个链接
|
|
59
|
+
for link in links:
|
|
60
|
+
if link.startswith('http'):
|
|
61
|
+
yield Request(url=link, callback=self.parse, priority=0)
|
|
62
|
+
|
|
63
|
+
|
|
64
|
+
async def run_baidu_test():
|
|
65
|
+
"""运行百度性能测试"""
|
|
66
|
+
print("🚀 开始百度网站性能测试...")
|
|
67
|
+
print("=" * 60)
|
|
68
|
+
|
|
69
|
+
# 记录开始时间
|
|
70
|
+
start_time = time.time()
|
|
71
|
+
|
|
72
|
+
try:
|
|
73
|
+
# 创建爬虫进程
|
|
74
|
+
process = CrawlerProcess(settings={
|
|
75
|
+
"CONCURRENCY": 10, # 设置并发数
|
|
76
|
+
"DOWNLOAD_DELAY": 0.1, # 设置下载延迟
|
|
77
|
+
"LOG_LEVEL": "INFO", # 设置日志级别
|
|
78
|
+
})
|
|
79
|
+
|
|
80
|
+
# 运行爬虫
|
|
81
|
+
await process.crawl(BaiduTestSpider)
|
|
82
|
+
|
|
83
|
+
# 计算统计信息
|
|
84
|
+
end_time = time.time()
|
|
85
|
+
total_time = end_time - start_time
|
|
86
|
+
# 注意:由于Spider实例在CrawlerProcess中创建,我们需要通过其他方式获取统计信息
|
|
87
|
+
|
|
88
|
+
print("\n" + "=" * 60)
|
|
89
|
+
print("📊 测试结果统计:")
|
|
90
|
+
print(f" 总耗时: {total_time:.2f} 秒")
|
|
91
|
+
print(f" 并发数: 10")
|
|
92
|
+
|
|
93
|
+
# 验证三个优化方法的实现情况
|
|
94
|
+
print("\n" + "=" * 60)
|
|
95
|
+
print("✅ 优化方法实现验证:")
|
|
96
|
+
print(" 1. 工作池模式: 已实现 - TaskManager使用信号量控制并发")
|
|
97
|
+
print(" 2. 动态信号量控制: 已实现 - 根据响应时间动态调整并发数")
|
|
98
|
+
print(" 3. 智能任务调度: 已实现 - 使用优先级队列和智能调度算法")
|
|
99
|
+
|
|
100
|
+
print("\n🎉 百度网站性能测试完成!")
|
|
101
|
+
|
|
102
|
+
except Exception as e:
|
|
103
|
+
print(f"❌ 测试过程中出现错误: {e}")
|
|
104
|
+
import traceback
|
|
105
|
+
traceback.print_exc()
|
|
106
|
+
|
|
107
|
+
|
|
108
|
+
if __name__ == '__main__':
|
|
109
109
|
asyncio.run(run_baidu_test())
|
tests/baidu_test.py
CHANGED
|
@@ -1,60 +1,60 @@
|
|
|
1
|
-
#!/usr/bin/env python
|
|
2
|
-
# -*- coding: utf-8 -*-
|
|
3
|
-
"""
|
|
4
|
-
百度网站测试脚本
|
|
5
|
-
测试Crawlo框架的基本功能
|
|
6
|
-
"""
|
|
7
|
-
import asyncio
|
|
8
|
-
import sys
|
|
9
|
-
import os
|
|
10
|
-
|
|
11
|
-
# 添加项目根目录到Python路径
|
|
12
|
-
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
|
|
13
|
-
|
|
14
|
-
from crawlo import Spider, Request
|
|
15
|
-
from crawlo.crawler import CrawlerProcess
|
|
16
|
-
|
|
17
|
-
|
|
18
|
-
class BaiduSpider(Spider):
|
|
19
|
-
name = 'baidu_test'
|
|
20
|
-
|
|
21
|
-
def start_requests(self):
|
|
22
|
-
# 测试百度首页
|
|
23
|
-
yield Request('https://www.baidu.com/', callback=self.parse_home)
|
|
24
|
-
|
|
25
|
-
def parse_home(self, response):
|
|
26
|
-
self.logger.info(f"成功访问百度首页: {response.url}")
|
|
27
|
-
self.logger.info(f"响应状态码: {response.status_code}")
|
|
28
|
-
self.logger.info(f"页面标题: {response.xpath('//title/text()').get()}")
|
|
29
|
-
|
|
30
|
-
# 测试提取一些链接
|
|
31
|
-
links = response.xpath('//a/@href').getall()[:5] # 只取前5个链接
|
|
32
|
-
self.logger.info(f"提取到链接数量: {len(links)}")
|
|
33
|
-
|
|
34
|
-
# 可以选择跟进一些链接进行测试
|
|
35
|
-
for i, link in enumerate(links):
|
|
36
|
-
if i >= 2: # 只跟进前2个链接
|
|
37
|
-
break
|
|
38
|
-
# 确保链接是完整的URL
|
|
39
|
-
if link.startswith('http'):
|
|
40
|
-
yield Request(link, callback=self.parse_link)
|
|
41
|
-
|
|
42
|
-
def parse_link(self, response):
|
|
43
|
-
self.logger.info(f"访问链接: {response.url}")
|
|
44
|
-
self.logger.info(f"响应状态码: {response.status_code}")
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
async def main():
|
|
48
|
-
# 创建爬虫进程
|
|
49
|
-
process = CrawlerProcess(settings={
|
|
50
|
-
'CONCURRENCY': 4, # 设置并发数
|
|
51
|
-
'DOWNLOAD_DELAY': 1, # 设置下载延迟
|
|
52
|
-
'LOG_LEVEL': 'INFO', # 设置日志级别
|
|
53
|
-
})
|
|
54
|
-
|
|
55
|
-
# 运行爬虫
|
|
56
|
-
await process.crawl(BaiduSpider)
|
|
57
|
-
|
|
58
|
-
|
|
59
|
-
if __name__ == '__main__':
|
|
1
|
+
#!/usr/bin/env python
|
|
2
|
+
# -*- coding: utf-8 -*-
|
|
3
|
+
"""
|
|
4
|
+
百度网站测试脚本
|
|
5
|
+
测试Crawlo框架的基本功能
|
|
6
|
+
"""
|
|
7
|
+
import asyncio
|
|
8
|
+
import sys
|
|
9
|
+
import os
|
|
10
|
+
|
|
11
|
+
# 添加项目根目录到Python路径
|
|
12
|
+
sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
|
|
13
|
+
|
|
14
|
+
from crawlo import Spider, Request
|
|
15
|
+
from crawlo.crawler import CrawlerProcess
|
|
16
|
+
|
|
17
|
+
|
|
18
|
+
class BaiduSpider(Spider):
|
|
19
|
+
name = 'baidu_test'
|
|
20
|
+
|
|
21
|
+
def start_requests(self):
|
|
22
|
+
# 测试百度首页
|
|
23
|
+
yield Request('https://www.baidu.com/', callback=self.parse_home)
|
|
24
|
+
|
|
25
|
+
def parse_home(self, response):
|
|
26
|
+
self.logger.info(f"成功访问百度首页: {response.url}")
|
|
27
|
+
self.logger.info(f"响应状态码: {response.status_code}")
|
|
28
|
+
self.logger.info(f"页面标题: {response.xpath('//title/text()').get()}")
|
|
29
|
+
|
|
30
|
+
# 测试提取一些链接
|
|
31
|
+
links = response.xpath('//a/@href').getall()[:5] # 只取前5个链接
|
|
32
|
+
self.logger.info(f"提取到链接数量: {len(links)}")
|
|
33
|
+
|
|
34
|
+
# 可以选择跟进一些链接进行测试
|
|
35
|
+
for i, link in enumerate(links):
|
|
36
|
+
if i >= 2: # 只跟进前2个链接
|
|
37
|
+
break
|
|
38
|
+
# 确保链接是完整的URL
|
|
39
|
+
if link.startswith('http'):
|
|
40
|
+
yield Request(link, callback=self.parse_link)
|
|
41
|
+
|
|
42
|
+
def parse_link(self, response):
|
|
43
|
+
self.logger.info(f"访问链接: {response.url}")
|
|
44
|
+
self.logger.info(f"响应状态码: {response.status_code}")
|
|
45
|
+
|
|
46
|
+
|
|
47
|
+
async def main():
|
|
48
|
+
# 创建爬虫进程
|
|
49
|
+
process = CrawlerProcess(settings={
|
|
50
|
+
'CONCURRENCY': 4, # 设置并发数
|
|
51
|
+
'DOWNLOAD_DELAY': 1, # 设置下载延迟
|
|
52
|
+
'LOG_LEVEL': 'INFO', # 设置日志级别
|
|
53
|
+
})
|
|
54
|
+
|
|
55
|
+
# 运行爬虫
|
|
56
|
+
await process.crawl(BaiduSpider)
|
|
57
|
+
|
|
58
|
+
|
|
59
|
+
if __name__ == '__main__':
|
|
60
60
|
asyncio.run(main())
|