PyPI - crawlo - Versions diffs - 1.4.7__py3-none-any.whl → 1.4.8__py3-none-any.whl - Mend

crawlo 1.4.7py3-none-any.whl → 1.4.8py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of crawlo might be problematic. Click here for more details.

Files changed (348) hide show

crawlo/__init__.py +90 -90
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 -140
crawlo/commands/list.py +155 -155
crawlo/commands/run.py +379 -379
crawlo/commands/startproject.py +460 -460
crawlo/commands/stats.py +187 -187
crawlo/commands/utils.py +196 -196
crawlo/config.py +320 -320
crawlo/config_validator.py +277 -277
crawlo/core/__init__.py +52 -52
crawlo/core/engine.py +451 -451
crawlo/core/processor.py +47 -47
crawlo/core/scheduler.py +290 -290
crawlo/crawler.py +698 -698
crawlo/data/__init__.py +5 -5
crawlo/data/user_agents.py +194 -194
crawlo/downloader/__init__.py +280 -280
crawlo/downloader/aiohttp_downloader.py +233 -233
crawlo/downloader/cffi_downloader.py +250 -250
crawlo/downloader/httpx_downloader.py +265 -265
crawlo/downloader/hybrid_downloader.py +212 -212
crawlo/downloader/playwright_downloader.py +425 -425
crawlo/downloader/selenium_downloader.py +486 -486
crawlo/event.py +45 -45
crawlo/exceptions.py +214 -214
crawlo/extension/__init__.py +64 -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 -53
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 -104
crawlo/factories/registry.py +84 -84
crawlo/factories/utils.py +134 -134
crawlo/filters/__init__.py +170 -170
crawlo/filters/aioredis_filter.py +347 -347
crawlo/filters/memory_filter.py +261 -261
crawlo/framework.py +306 -306
crawlo/initialization/__init__.py +44 -44
crawlo/initialization/built_in.py +391 -391
crawlo/initialization/context.py +141 -141
crawlo/initialization/core.py +240 -240
crawlo/initialization/phases.py +229 -229
crawlo/initialization/registry.py +143 -143
crawlo/initialization/utils.py +48 -48
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 -42
crawlo/logging/config.py +280 -276
crawlo/logging/factory.py +175 -175
crawlo/logging/manager.py +104 -104
crawlo/middleware/__init__.py +87 -87
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 -287
crawlo/network/__init__.py +21 -21
crawlo/network/request.py +408 -376
crawlo/network/response.py +598 -569
crawlo/pipelines/__init__.py +52 -52
crawlo/pipelines/base_pipeline.py +452 -452
crawlo/pipelines/bloom_dedup_pipeline.py +145 -146
crawlo/pipelines/console_pipeline.py +39 -39
crawlo/pipelines/csv_pipeline.py +316 -316
crawlo/pipelines/database_dedup_pipeline.py +196 -197
crawlo/pipelines/json_pipeline.py +218 -218
crawlo/pipelines/memory_dedup_pipeline.py +104 -105
crawlo/pipelines/mongo_pipeline.py +140 -139
crawlo/pipelines/mysql_pipeline.py +468 -469
crawlo/pipelines/pipeline_manager.py +100 -100
crawlo/pipelines/redis_dedup_pipeline.py +155 -155
crawlo/project.py +347 -347
crawlo/queue/__init__.py +9 -9
crawlo/queue/pqueue.py +38 -38
crawlo/queue/queue_manager.py +591 -591
crawlo/queue/redis_priority_queue.py +518 -518
crawlo/settings/__init__.py +7 -7
crawlo/settings/default_settings.py +287 -284
crawlo/settings/setting_manager.py +219 -219
crawlo/spider/__init__.py +658 -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 +1 -1
crawlo/templates/project/items.py.tmpl +13 -13
crawlo/templates/project/middlewares.py.tmpl +38 -38
crawlo/templates/project/pipelines.py.tmpl +35 -35
crawlo/templates/project/settings.py.tmpl +113 -109
crawlo/templates/project/settings_distributed.py.tmpl +160 -156
crawlo/templates/project/settings_gentle.py.tmpl +174 -170
crawlo/templates/project/settings_high_performance.py.tmpl +175 -171
crawlo/templates/project/settings_minimal.py.tmpl +102 -98
crawlo/templates/project/settings_simple.py.tmpl +172 -168
crawlo/templates/project/spiders/__init__.py.tmpl +9 -9
crawlo/templates/run.py.tmpl +23 -23
crawlo/templates/spider/spider.py.tmpl +32 -32
crawlo/templates/spiders_init.py.tmpl +4 -4
crawlo/tools/__init__.py +86 -86
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 +74 -50
crawlo/utils/batch_processor.py +276 -276
crawlo/utils/config_manager.py +442 -442
crawlo/utils/controlled_spider_mixin.py +439 -439
crawlo/utils/db_helper.py +250 -250
crawlo/utils/encoding_helper.py +190 -0
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 -335
crawlo/utils/misc.py +81 -81
crawlo/utils/mongo_connection_pool.py +157 -157
crawlo/utils/mysql_connection_pool.py +197 -197
crawlo/utils/performance_monitor.py +285 -285
crawlo/utils/queue_helper.py +175 -175
crawlo/utils/redis_checker.py +90 -90
crawlo/utils/redis_connection_pool.py +578 -578
crawlo/utils/redis_key_validator.py +198 -198
crawlo/utils/request.py +278 -278
crawlo/utils/request_serializer.py +225 -225
crawlo/utils/resource_manager.py +337 -337
crawlo/utils/response_helper.py +113 -0
crawlo/utils/selector_helper.py +138 -137
crawlo/utils/singleton.py +69 -69
crawlo/utils/spider_loader.py +201 -201
crawlo/utils/text_helper.py +94 -94
{crawlo-1.4.7.dist-info → crawlo-1.4.8.dist-info}/METADATA +831 -689
crawlo-1.4.8.dist-info/RECORD +347 -0
examples/__init__.py +7 -7
tests/__init__.py +7 -7
tests/advanced_tools_example.py +217 -217
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 -467
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 -72
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/ofweek_scrapy/spiders/__init__.py +4 -4
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 +54 -54
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 +118 -118
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/utils/log.py +0 -80
crawlo/utils/url_utils.py +0 -40
crawlo-1.4.7.dist-info/RECORD +0 -347
{crawlo-1.4.7.dist-info → crawlo-1.4.8.dist-info}/WHEEL +0 -0
{crawlo-1.4.7.dist-info → crawlo-1.4.8.dist-info}/entry_points.txt +0 -0
{crawlo-1.4.7.dist-info → crawlo-1.4.8.dist-info}/top_level.txt +0 -0

tests/test_selector_helper.py CHANGED Viewed

@@ -1,101 +1,101 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-"""
-选择器辅助工具测试
-"""
-import sys
-import os
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
-from crawlo.utils import (
-    extract_text,
-    extract_texts,
-    extract_attr,
-    extract_attrs,
-    is_xpath
-)
-from parsel import Selector, SelectorList
-def test_selector_helper():
-    """测试选择器辅助工具"""
-    print("测试选择器辅助工具...")
-    print("=" * 50)
-    # 创建测试HTML
-    html_content = """
-    <html>
-    <head>
-        <title>测试页面</title>
-    </head>
-    <body>
-        <div class="content">
-            <h1>主标题</h1>
-            <p class="intro">介绍段落</p>
-            <ul class="list">
-                <li>项目1</li>
-                <li>项目2</li>
-                <li>项目3</li>
-            </ul>
-            <a href="https://example.com" class="link">链接文本</a>
-            <img src="image.jpg" alt="图片描述" class="image">
-        </div>
-    </body>
-    </html>
-    """
-    selector = Selector(text=html_content)
-    # 测试 is_xpath
-    print("1. 测试 is_xpath:")
-    print(f"   '/' 开头: {is_xpath('/')}")
-    print(f"   '//' 开头: {is_xpath('//title')}")
-    print(f"   './' 开头: {is_xpath('./div')}")
-    print(f"   'title' 开头: {is_xpath('title')}")
-    print()
-    # 测试 extract_text
-    print("2. 测试 extract_text:")
-    title_elements = selector.css('title')
-    title_text = extract_text(title_elements)
-    print(f"   标题文本: {title_text}")
-    h1_elements = selector.css('.content h1')
-    h1_text = extract_text(h1_elements)
-    print(f"   H1文本: {h1_text}")
-    print()
-    # 测试 extract_texts_from_elements
-    print("3. 测试 extract_texts_from_elements:")
-    li_elements = selector.css('.list li')
-    li_texts = extract_texts(li_elements)
-    print(f"   列表项文本: {li_texts}")
-    print()
-    # 测试 extract_attr
-    print("4. 测试 extract_attr:")
-    link_elements = selector.css('.link')
-    link_href = extract_attr(link_elements, 'href')
-    print(f"   链接href: {link_href}")
-    img_elements = selector.css('.image')
-    img_alt = extract_attr(img_elements, 'alt')
-    print(f"   图片alt: {img_alt}")
-    print()
-    # 测试 extract_attrs
-    print("5. 测试 extract_attrs:")
-    all_links = selector.css('a')
-    all_hrefs = extract_attrs(all_links, 'href')
-    print(f"   所有链接href: {all_hrefs}")
-    all_images = selector.css('img')
-    all_srcs = extract_attrs(all_images, 'src')
-    print(f"   所有图片src: {all_srcs}")
-    print()
-    print("所有测试完成！")
-if __name__ == '__main__':
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+选择器辅助工具测试
+"""
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+from crawlo.utils import (
+    extract_text,
+    extract_texts,
+    extract_attr,
+    extract_attrs,
+    is_xpath
+)
+from parsel import Selector, SelectorList
+def test_selector_helper():
+    """测试选择器辅助工具"""
+    print("测试选择器辅助工具...")
+    print("=" * 50)
+    # 创建测试HTML
+    html_content = """
+    <html>
+    <head>
+        <title>测试页面</title>
+    </head>
+    <body>
+        <div class="content">
+            <h1>主标题</h1>
+            <p class="intro">介绍段落</p>
+            <ul class="list">
+                <li>项目1</li>
+                <li>项目2</li>
+                <li>项目3</li>
+            </ul>
+            <a href="https://example.com" class="link">链接文本</a>
+            <img src="image.jpg" alt="图片描述" class="image">
+        </div>
+    </body>
+    </html>
+    """
+    selector = Selector(text=html_content)
+    # 测试 is_xpath
+    print("1. 测试 is_xpath:")
+    print(f"   '/' 开头: {is_xpath('/')}")
+    print(f"   '//' 开头: {is_xpath('//title')}")
+    print(f"   './' 开头: {is_xpath('./div')}")
+    print(f"   'title' 开头: {is_xpath('title')}")
+    print()
+    # 测试 extract_text
+    print("2. 测试 extract_text:")
+    title_elements = selector.css('title')
+    title_text = extract_text(title_elements)
+    print(f"   标题文本: {title_text}")
+    h1_elements = selector.css('.content h1')
+    h1_text = extract_text(h1_elements)
+    print(f"   H1文本: {h1_text}")
+    print()
+    # 测试 extract_texts_from_elements
+    print("3. 测试 extract_texts_from_elements:")
+    li_elements = selector.css('.list li')
+    li_texts = extract_texts(li_elements)
+    print(f"   列表项文本: {li_texts}")
+    print()
+    # 测试 extract_attr
+    print("4. 测试 extract_attr:")
+    link_elements = selector.css('.link')
+    link_href = extract_attr(link_elements, 'href')
+    print(f"   链接href: {link_href}")
+    img_elements = selector.css('.image')
+    img_alt = extract_attr(img_elements, 'alt')
+    print(f"   图片alt: {img_alt}")
+    print()
+    # 测试 extract_attrs
+    print("5. 测试 extract_attrs:")
+    all_links = selector.css('a')
+    all_hrefs = extract_attrs(all_links, 'href')
+    print(f"   所有链接href: {all_hrefs}")
+    all_images = selector.css('img')
+    all_srcs = extract_attrs(all_images, 'src')
+    print(f"   所有图片src: {all_srcs}")
+    print()
+    print("所有测试完成！")
+if __name__ == '__main__':
     test_selector_helper()

tests/test_selector_optimizations.py CHANGED Viewed

@@ -1,147 +1,147 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-"""
-选择器方法优化测试
-"""
-import sys
-import os
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
-from crawlo.network.response import Response
-def test_selector_optimizations():
-    """测试选择器方法优化"""
-    print("测试选择器方法优化...")
-    print("=" * 50)
-    # 创建一个复杂的HTML响应
-    html_content = """
-    <html>
-    <head>
-        <title>测试页面标题</title>
-    </head>
-    <body>
-        <div class="content">
-            <h1>主标题</h1>
-            <p class="intro">这是介绍段落</p>
-            <div class="article">
-                <p>第一段内容 <strong>粗体文本</strong> 普通文本</p>
-                <p>第二段内容 <em>斜体文本</em></p>
-            </div>
-            <ul class="list">
-                <li>项目1</li>
-                <li>项目2</li>
-                <li>项目3</li>
-            </ul>
-            <a href="https://example.com" class="link">链接文本</a>
-            <img src="image.jpg" alt="图片描述" class="image">
-            <div class="products">
-                <div class="product" data-id="1">
-                    <h2>产品A</h2>
-                    <p class="price">¥99.99</p>
-                </div>
-                <div class="product" data-id="2">
-                    <h2>产品B</h2>
-                    <p class="price">¥149.99</p>
-                </div>
-            </div>
-        </div>
-    </body>
-    </html>
-    """
-    response = Response(
-        url="https://example.com/test",
-        body=html_content.encode('utf-8'),
-        headers={"content-type": "text/html; charset=utf-8"}
-    )
-    # 测试 extract_text 方法
-    print("1. 测试 extract_text 方法:")
-    title = response.extract_text('title')
-    print(f"   标题: {title}")
-    h1_text = response.extract_text('.content h1')
-    print(f"   H1文本: {h1_text}")
-    # 测试XPath
-    title_xpath = response.extract_text('//title')
-    print(f"   XPath标题: {title_xpath}")
-    # 测试复杂文本提取
-    complex_text = response.extract_text('.article p', join_str=' ')
-    print(f"   复杂文本: {complex_text}")
-    print()
-    # 测试 extract_texts 方法
-    print("2. 测试 extract_texts 方法:")
-    list_items = response.extract_texts('.list li')
-    print(f"   列表项: {list_items}")
-    # 测试XPath
-    list_items_xpath = response.extract_texts('//ul[@class="list"]/li')
-    print(f"   XPath列表项: {list_items_xpath}")
-    # 测试多个元素
-    product_names = response.extract_texts('.product h2')
-    print(f"   产品名称: {product_names}")
-    product_prices = response.extract_texts('.price')
-    print(f"   产品价格: {product_prices}")
-    print()
-    # 测试 extract_attr 方法
-    print("3. 测试 extract_attr 方法:")
-    link_href = response.extract_attr('.link', 'href')
-    print(f"   链接href: {link_href}")
-    img_alt = response.extract_attr('.image', 'alt')
-    print(f"   图片alt: {img_alt}")
-    # 测试XPath
-    link_href_xpath = response.extract_attr('//a[@class="link"]', 'href')
-    print(f"   XPath链接href: {link_href_xpath}")
-    print()
-    # 测试 extract_attrs 方法
-    print("4. 测试 extract_attrs 方法:")
-    product_ids = response.extract_attrs('.product', 'data-id')
-    print(f"   产品ID: {product_ids}")
-    # 测试XPath
-    product_ids_xpath = response.extract_attrs('//div[@class="product"]', 'data-id')
-    print(f"   XPath产品ID: {product_ids_xpath}")
-    # 测试所有链接
-    all_links = response.extract_attrs('a', 'href')
-    print(f"   所有链接: {all_links}")
-    print()
-    # 测试边界情况
-    print("5. 测试边界情况:")
-    # 测试默认值
-    non_exist = response.extract_text('.non-exist', default='默认文本')
-    print(f"   不存在元素的默认值: {non_exist}")
-    non_exist_attr = response.extract_attr('.non-exist', 'href', default='默认链接')
-    print(f"   不存在属性的默认值: {non_exist_attr}")
-    print()
-    # 测试空响应
-    print("6. 测试空响应:")
-    empty_response = Response(url="https://example.com/empty", body=b"")
-    empty_text = empty_response.extract_text('title', default='默认标题')
-    print(f"   空响应默认值: {empty_text}")
-    print()
-    print("所有测试完成！")
-if __name__ == '__main__':
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+选择器方法优化测试
+"""
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+from crawlo.network.response import Response
+def test_selector_optimizations():
+    """测试选择器方法优化"""
+    print("测试选择器方法优化...")
+    print("=" * 50)
+    # 创建一个复杂的HTML响应
+    html_content = """
+    <html>
+    <head>
+        <title>测试页面标题</title>
+    </head>
+    <body>
+        <div class="content">
+            <h1>主标题</h1>
+            <p class="intro">这是介绍段落</p>
+            <div class="article">
+                <p>第一段内容 <strong>粗体文本</strong> 普通文本</p>
+                <p>第二段内容 <em>斜体文本</em></p>
+            </div>
+            <ul class="list">
+                <li>项目1</li>
+                <li>项目2</li>
+                <li>项目3</li>
+            </ul>
+            <a href="https://example.com" class="link">链接文本</a>
+            <img src="image.jpg" alt="图片描述" class="image">
+            <div class="products">
+                <div class="product" data-id="1">
+                    <h2>产品A</h2>
+                    <p class="price">¥99.99</p>
+                </div>
+                <div class="product" data-id="2">
+                    <h2>产品B</h2>
+                    <p class="price">¥149.99</p>
+                </div>
+            </div>
+        </div>
+    </body>
+    </html>
+    """
+    response = Response(
+        url="https://example.com/test",
+        body=html_content.encode('utf-8'),
+        headers={"content-type": "text/html; charset=utf-8"}
+    )
+    # 测试 extract_text 方法
+    print("1. 测试 extract_text 方法:")
+    title = response.extract_text('title')
+    print(f"   标题: {title}")
+    h1_text = response.extract_text('.content h1')
+    print(f"   H1文本: {h1_text}")
+    # 测试XPath
+    title_xpath = response.extract_text('//title')
+    print(f"   XPath标题: {title_xpath}")
+    # 测试复杂文本提取
+    complex_text = response.extract_text('.article p', join_str=' ')
+    print(f"   复杂文本: {complex_text}")
+    print()
+    # 测试 extract_texts 方法
+    print("2. 测试 extract_texts 方法:")
+    list_items = response.extract_texts('.list li')
+    print(f"   列表项: {list_items}")
+    # 测试XPath
+    list_items_xpath = response.extract_texts('//ul[@class="list"]/li')
+    print(f"   XPath列表项: {list_items_xpath}")
+    # 测试多个元素
+    product_names = response.extract_texts('.product h2')
+    print(f"   产品名称: {product_names}")
+    product_prices = response.extract_texts('.price')
+    print(f"   产品价格: {product_prices}")
+    print()
+    # 测试 extract_attr 方法
+    print("3. 测试 extract_attr 方法:")
+    link_href = response.extract_attr('.link', 'href')
+    print(f"   链接href: {link_href}")
+    img_alt = response.extract_attr('.image', 'alt')
+    print(f"   图片alt: {img_alt}")
+    # 测试XPath
+    link_href_xpath = response.extract_attr('//a[@class="link"]', 'href')
+    print(f"   XPath链接href: {link_href_xpath}")
+    print()
+    # 测试 extract_attrs 方法
+    print("4. 测试 extract_attrs 方法:")
+    product_ids = response.extract_attrs('.product', 'data-id')
+    print(f"   产品ID: {product_ids}")
+    # 测试XPath
+    product_ids_xpath = response.extract_attrs('//div[@class="product"]', 'data-id')
+    print(f"   XPath产品ID: {product_ids_xpath}")
+    # 测试所有链接
+    all_links = response.extract_attrs('a', 'href')
+    print(f"   所有链接: {all_links}")
+    print()
+    # 测试边界情况
+    print("5. 测试边界情况:")
+    # 测试默认值
+    non_exist = response.extract_text('.non-exist', default='默认文本')
+    print(f"   不存在元素的默认值: {non_exist}")
+    non_exist_attr = response.extract_attr('.non-exist', 'href', default='默认链接')
+    print(f"   不存在属性的默认值: {non_exist_attr}")
+    print()
+    # 测试空响应
+    print("6. 测试空响应:")
+    empty_response = Response(url="https://example.com/empty", body=b"")
+    empty_text = empty_response.extract_text('title', default='默认标题')
+    print(f"   空响应默认值: {empty_text}")
+    print()
+    print("所有测试完成！")
+if __name__ == '__main__':
     test_selector_optimizations()

tests/test_simple_response.py CHANGED Viewed

@@ -1,62 +1,62 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-"""
-Response 简单功能测试
-"""
-import sys
-import os
-# 添加项目根目录到路径
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
-from crawlo.network.response import Response
-def test_basic_functionality():
-    """测试基本功能"""
-    print("测试基本功能...")
-    # 创建一个简单的HTML响应
-    html_content = """
-    <html>
-    <head>
-        <title>测试页面</title>
-    </head>
-    <body>
-        <div class="content">
-            <h1>主标题</h1>
-            <p class="intro">这是介绍段落</p>
-        </div>
-    </body>
-    </html>
-    """
-    response = Response(
-        url="https://example.com/test",
-        body=html_content.encode('utf-8'),
-        headers={"content-type": "text/html; charset=utf-8"}
-    )
-    # 测试基本属性
-    print(f"URL: {response.url}")
-    print(f"状态码: {response.status_code}")
-    # 测试文本提取（使用新方法）
-    title = response.extract_text('title')
-    print(f"标题: {title}")
-    h1_text = response.extract_text('.content h1')
-    print(f"H1文本: {h1_text}")
-    intro_text = response.extract_text('.intro')
-    print(f"介绍文本: {intro_text}")
-    # 测试XPath（使用新方法）
-    title_xpath = response.extract_text('//title')
-    print(f"XPath标题: {title_xpath}")
-    print("基本功能测试完成")
-if __name__ == '__main__':
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+Response 简单功能测试
+"""
+import sys
+import os
+# 添加项目根目录到路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+from crawlo.network.response import Response
+def test_basic_functionality():
+    """测试基本功能"""
+    print("测试基本功能...")
+    # 创建一个简单的HTML响应
+    html_content = """
+    <html>
+    <head>
+        <title>测试页面</title>
+    </head>
+    <body>
+        <div class="content">
+            <h1>主标题</h1>
+            <p class="intro">这是介绍段落</p>
+        </div>
+    </body>
+    </html>
+    """
+    response = Response(
+        url="https://example.com/test",
+        body=html_content.encode('utf-8'),
+        headers={"content-type": "text/html; charset=utf-8"}
+    )
+    # 测试基本属性
+    print(f"URL: {response.url}")
+    print(f"状态码: {response.status_code}")
+    # 测试文本提取（使用新方法）
+    title = response.extract_text('title')
+    print(f"标题: {title}")
+    h1_text = response.extract_text('.content h1')
+    print(f"H1文本: {h1_text}")
+    intro_text = response.extract_text('.intro')
+    print(f"介绍文本: {intro_text}")
+    # 测试XPath（使用新方法）
+    title_xpath = response.extract_text('//title')
+    print(f"XPath标题: {title_xpath}")
+    print("基本功能测试完成")
+if __name__ == '__main__':
     test_basic_functionality()

crawlo 1.4.7__py3-none-any.whl → 1.4.8__py3-none-any.whl

Potentially problematic release.

crawlo 1.4.7py3-none-any.whl → 1.4.8py3-none-any.whl