PyPI - crawlo - Versions diffs - 1.3.3__py3-none-any.whl → 1.3.5__py3-none-any.whl - Mend

crawlo 1.3.3py3-none-any.whl → 1.3.5py3-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 (289) hide show

crawlo/__init__.py +87 -63
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 -323
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 +46 -2
crawlo/core/engine.py +439 -365
crawlo/core/processor.py +40 -40
crawlo/core/scheduler.py +257 -256
crawlo/crawler.py +639 -1167
crawlo/data/__init__.py +5 -5
crawlo/data/user_agents.py +194 -194
crawlo/downloader/__init__.py +273 -273
crawlo/downloader/aiohttp_downloader.py +228 -226
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 +39 -39
crawlo/extension/health_check.py +141 -141
crawlo/extension/log_interval.py +57 -57
crawlo/extension/log_stats.py +81 -81
crawlo/extension/logging_extension.py +61 -52
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 +28 -0
crawlo/factories/base.py +69 -0
crawlo/factories/crawler.py +104 -0
crawlo/factories/registry.py +85 -0
crawlo/filters/__init__.py +154 -154
crawlo/filters/aioredis_filter.py +257 -234
crawlo/filters/memory_filter.py +269 -269
crawlo/framework.py +292 -0
crawlo/initialization/__init__.py +40 -0
crawlo/initialization/built_in.py +426 -0
crawlo/initialization/context.py +142 -0
crawlo/initialization/core.py +194 -0
crawlo/initialization/phases.py +149 -0
crawlo/initialization/registry.py +146 -0
crawlo/items/__init__.py +23 -23
crawlo/items/base.py +23 -22
crawlo/items/fields.py +52 -52
crawlo/items/items.py +104 -104
crawlo/logging/__init__.py +38 -0
crawlo/logging/config.py +97 -0
crawlo/logging/factory.py +129 -0
crawlo/logging/manager.py +112 -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 +163 -163
crawlo/middleware/response_filter.py +136 -136
crawlo/middleware/retry.py +124 -124
crawlo/middleware/simple_proxy.py +65 -65
crawlo/mode_manager.py +212 -187
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 +156 -156
crawlo/pipelines/console_pipeline.py +39 -39
crawlo/pipelines/csv_pipeline.py +316 -316
crawlo/pipelines/database_dedup_pipeline.py +222 -222
crawlo/pipelines/json_pipeline.py +218 -218
crawlo/pipelines/memory_dedup_pipeline.py +115 -115
crawlo/pipelines/mongo_pipeline.py +131 -131
crawlo/pipelines/mysql_pipeline.py +325 -318
crawlo/pipelines/pipeline_manager.py +76 -75
crawlo/pipelines/redis_dedup_pipeline.py +166 -166
crawlo/project.py +327 -325
crawlo/queue/pqueue.py +43 -37
crawlo/queue/queue_manager.py +503 -379
crawlo/queue/redis_priority_queue.py +326 -306
crawlo/settings/__init__.py +7 -7
crawlo/settings/default_settings.py +321 -225
crawlo/settings/setting_manager.py +214 -198
crawlo/spider/__init__.py +657 -639
crawlo/stats_collector.py +73 -59
crawlo/subscriber.py +129 -129
crawlo/task_manager.py +139 -30
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 +168 -267
crawlo/templates/project/settings_distributed.py.tmpl +167 -180
crawlo/templates/project/settings_gentle.py.tmpl +167 -61
crawlo/templates/project/settings_high_performance.py.tmpl +168 -131
crawlo/templates/project/settings_minimal.py.tmpl +66 -35
crawlo/templates/project/settings_simple.py.tmpl +165 -102
crawlo/templates/project/spiders/__init__.py.tmpl +10 -6
crawlo/templates/run.py.tmpl +34 -38
crawlo/templates/spider/spider.py.tmpl +143 -143
crawlo/templates/spiders_init.py.tmpl +10 -0
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 +388 -388
crawlo/tools/encoding_converter.py +127 -127
crawlo/tools/network_diagnostic.py +365 -0
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 +26 -0
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 -124
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 +80 -200
crawlo/utils/performance_monitor.py +285 -285
crawlo/utils/queue_helper.py +175 -175
crawlo/utils/redis_connection_pool.py +388 -351
crawlo/utils/redis_key_validator.py +198 -198
crawlo/utils/request.py +267 -267
crawlo/utils/request_serializer.py +225 -218
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-1.3.3.dist-info → crawlo-1.3.5.dist-info}/METADATA +1126 -1020
crawlo-1.3.5.dist-info/RECORD +288 -0
examples/__init__.py +7 -7
tests/__init__.py +7 -7
tests/advanced_tools_example.py +275 -275
tests/authenticated_proxy_example.py +107 -107
tests/baidu_performance_test.py +109 -0
tests/baidu_test.py +60 -0
tests/cleaners_example.py +160 -160
tests/comprehensive_framework_test.py +213 -0
tests/comprehensive_test.py +82 -0
tests/comprehensive_testing_summary.md +187 -0
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 +70 -0
tests/debug_framework_logger.py +85 -0
tests/debug_log_config.py +127 -0
tests/debug_log_levels.py +64 -0
tests/debug_pipelines.py +66 -66
tests/detailed_log_test.py +234 -0
tests/distributed_test.py +67 -0
tests/distributed_test_debug.py +77 -0
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_command_test_report.md +0 -0
tests/final_comprehensive_test.py +152 -0
tests/final_log_test.py +261 -0
tests/final_validation_test.py +183 -0
tests/fix_log_test.py +143 -0
tests/framework_performance_test.py +203 -0
tests/log_buffering_test.py +112 -0
tests/log_generation_timing_test.py +154 -0
tests/optimized_performance_test.py +212 -0
tests/performance_comparison.py +246 -0
tests/queue_blocking_test.py +114 -0
tests/queue_test.py +90 -0
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 +139 -0
tests/scrapy_comparison/scrapy_test.py +134 -0
tests/simple_command_test.py +120 -0
tests/simple_crawlo_test.py +128 -0
tests/simple_log_test.py +58 -0
tests/simple_log_test2.py +138 -0
tests/simple_optimization_test.py +129 -0
tests/simple_spider_test.py +50 -0
tests/simple_test.py +48 -0
tests/spider_log_timing_test.py +178 -0
tests/test_advanced_tools.py +148 -148
tests/test_all_commands.py +231 -0
tests/test_all_redis_key_configs.py +145 -145
tests/test_authenticated_proxy.py +141 -141
tests/test_batch_processor.py +179 -0
tests/test_cleaners.py +54 -54
tests/test_component_factory.py +175 -0
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 +80 -0
tests/test_crawlo_proxy_integration.py +108 -108
tests/test_date_tools.py +123 -123
tests/test_default_header_middleware.py +158 -158
tests/test_distributed.py +65 -65
tests/test_double_crawlo_fix.py +207 -207
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 +246 -0
tests/test_env_config.py +121 -121
tests/test_error_handler_compatibility.py +112 -112
tests/test_factories.py +253 -0
tests/test_final_validation.py +153 -153
tests/test_framework_env_usage.py +103 -103
tests/test_framework_logger.py +67 -0
tests/test_framework_startup.py +65 -0
tests/test_get_component_logger.py +84 -0
tests/test_integration.py +169 -169
tests/test_item_dedup_redis_key.py +122 -122
tests/test_large_scale_config.py +113 -0
tests/test_large_scale_helper.py +236 -0
tests/test_logging_system.py +283 -0
tests/test_mode_change.py +73 -0
tests/test_mode_consistency.py +51 -51
tests/test_offsite_middleware.py +221 -221
tests/test_parsel.py +29 -29
tests/test_performance.py +327 -327
tests/test_performance_monitor.py +116 -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 +42 -0
tests/test_queue_manager_double_crawlo.py +173 -173
tests/test_queue_manager_redis_key.py +176 -176
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_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 +241 -241
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_agents.py +96 -96
tests/tools_example.py +260 -260
tests/untested_features_report.md +139 -0
tests/verify_debug.py +52 -0
tests/verify_distributed.py +117 -117
tests/verify_log_fix.py +112 -0
crawlo-1.3.3.dist-info/RECORD +0 -219
tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +0 -82
{crawlo-1.3.3.dist-info → crawlo-1.3.5.dist-info}/WHEEL +0 -0
{crawlo-1.3.3.dist-info → crawlo-1.3.5.dist-info}/entry_points.txt +0 -0
{crawlo-1.3.3.dist-info → crawlo-1.3.5.dist-info}/top_level.txt +0 -0

tests/response_improvements_example.py CHANGED Viewed

@@ -1,145 +1,145 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-"""
-Response 改进功能使用示例
-"""
-from crawlo.network.response import Response
-def demo_response_improvements():
-    """演示Response改进功能"""
-    print("=== Response 改进功能演示 ===\n")
-    # 创建一个示例HTML响应
-    html_content = """
-    <html>
-    <head>
-        <title>Crawlo框架示例页面</title>
-    </head>
-    <body>
-        <div class="container">
-            <h1>产品列表</h1>
-            <div class="product-list">
-                <div class="product-item" data-id="1">
-                    <h2>产品A</h2>
-                    <p class="price">¥99.99</p>
-                    <p class="description">这是产品A的描述信息</p>
-                    <a href="/product/1" class="details-link">查看详情</a>
-                </div>
-                <div class="product-item" data-id="2">
-                    <h2>产品B</h2>
-                    <p class="price">¥149.99</p>
-                    <p class="description">这是产品B的描述信息</p>
-                    <a href="/product/2" class="details-link">查看详情</a>
-                </div>
-                <div class="product-item" data-id="3">
-                    <h2>产品C</h2>
-                    <p class="price">¥199.99</p>
-                    <p class="description">这是产品C的描述信息</p>
-                    <a href="/product/3" class="details-link">查看详情</a>
-                </div>
-            </div>
-            <div class="pagination">
-                <a href="/page/1" class="page-link">1</a>
-                <a href="/page/2" class="page-link active">2</a>
-                <a href="/page/3" class="page-link">3</a>
-            </div>
-        </div>
-    </body>
-    </html>
-    """
-    # 创建Response对象
-    response = Response(
-        url="https://example.com/products",
-        body=html_content.encode('utf-8'),
-        headers={"content-type": "text/html; charset=utf-8"}
-    )
-    # 1. 演示 extract_text 方法（支持CSS和XPath）
-    print("1. 提取文本内容:")
-    title = response.extract_text('title')
-    print(f"   页面标题: {title}")
-    # 使用CSS选择器提取第一个产品名称
-    first_product_name = response.extract_text('.product-item:first-child h2')
-    print(f"   第一个产品名称 (CSS): {first_product_name}")
-    # 使用XPath选择器
-    first_product_name_xpath = response.extract_text('//div[@class="product-item"][1]/h2')
-    print(f"   第一个产品名称 (XPath): {first_product_name_xpath}")
-    # 使用默认值处理不存在的元素
-    non_exist = response.extract_text('.non-exist', default='未找到')
-    print(f"   不存在的元素: {non_exist}")
-    print()
-    # 2. 演示 extract_texts 方法（提取多个元素的文本）
-    print("2. 提取多个元素的文本:")
-    # 提取所有产品名称
-    product_names = response.extract_texts('.product-item h2')
-    print(f"   所有产品名称: {product_names}")
-    # 提取所有价格
-    prices = response.extract_texts('.price')
-    print(f"   所有价格: {prices}")
-    # 使用XPath提取所有产品名称
-    product_names_xpath = response.extract_texts('//div[@class="product-item"]/h2')
-    print(f"   所有产品名称 (XPath): {product_names_xpath}")
-    print()
-    # 3. 演示 extract_attr 方法（提取元素属性）
-    print("3. 提取元素属性:")
-    # 提取第一个产品项的data-id属性
-    first_product_id = response.extract_attr('.product-item', 'data-id')
-    print(f"   第一个产品ID: {first_product_id}")
-    # 提取详情链接的href属性
-    first_detail_link = response.extract_attr('.details-link', 'href')
-    print(f"   第一个详情链接: {first_detail_link}")
-    # 提取不存在属性的默认值
-    non_exist_attr = response.extract_attr('.product-item', 'non-exist', default='默认值')
-    print(f"   不存在的属性: {non_exist_attr}")
-    print()
-    # 4. 演示 extract_attrs 方法（提取多个元素的属性）
-    print("4. 提取多个元素的属性:")
-    # 提取所有产品项的data-id属性
-    product_ids = response.extract_attrs('.product-item', 'data-id')
-    print(f"   所有产品ID: {product_ids}")
-    # 提取所有详情链接的href属性
-    detail_links = response.extract_attrs('.details-link', 'href')
-    print(f"   所有详情链接: {detail_links}")
-    # 提取分页链接的href属性
-    page_links = response.extract_attrs('.page-link', 'href')
-    print(f"   分页链接: {page_links}")
-    print()
-    # 5. 演示复杂文本提取
-    print("5. 复杂文本提取:")
-    # 提取所有产品描述
-    descriptions = response.extract_texts('.description')
-    print(f"   所有产品描述: {descriptions}")
-    print()
-    # 6. 边界情况处理
-    print("6. 边界情况处理:")
-    # 空响应测试
-    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("\n=== 演示完成 ===")
-if __name__ == '__main__':
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+Response 改进功能使用示例
+"""
+from crawlo.network.response import Response
+def demo_response_improvements():
+    """演示Response改进功能"""
+    print("=== Response 改进功能演示 ===\n")
+    # 创建一个示例HTML响应
+    html_content = """
+    <html>
+    <head>
+        <title>Crawlo框架示例页面</title>
+    </head>
+    <body>
+        <div class="container">
+            <h1>产品列表</h1>
+            <div class="product-list">
+                <div class="product-item" data-id="1">
+                    <h2>产品A</h2>
+                    <p class="price">¥99.99</p>
+                    <p class="description">这是产品A的描述信息</p>
+                    <a href="/product/1" class="details-link">查看详情</a>
+                </div>
+                <div class="product-item" data-id="2">
+                    <h2>产品B</h2>
+                    <p class="price">¥149.99</p>
+                    <p class="description">这是产品B的描述信息</p>
+                    <a href="/product/2" class="details-link">查看详情</a>
+                </div>
+                <div class="product-item" data-id="3">
+                    <h2>产品C</h2>
+                    <p class="price">¥199.99</p>
+                    <p class="description">这是产品C的描述信息</p>
+                    <a href="/product/3" class="details-link">查看详情</a>
+                </div>
+            </div>
+            <div class="pagination">
+                <a href="/page/1" class="page-link">1</a>
+                <a href="/page/2" class="page-link active">2</a>
+                <a href="/page/3" class="page-link">3</a>
+            </div>
+        </div>
+    </body>
+    </html>
+    """
+    # 创建Response对象
+    response = Response(
+        url="https://example.com/products",
+        body=html_content.encode('utf-8'),
+        headers={"content-type": "text/html; charset=utf-8"}
+    )
+    # 1. 演示 extract_text 方法（支持CSS和XPath）
+    print("1. 提取文本内容:")
+    title = response.extract_text('title')
+    print(f"   页面标题: {title}")
+    # 使用CSS选择器提取第一个产品名称
+    first_product_name = response.extract_text('.product-item:first-child h2')
+    print(f"   第一个产品名称 (CSS): {first_product_name}")
+    # 使用XPath选择器
+    first_product_name_xpath = response.extract_text('//div[@class="product-item"][1]/h2')
+    print(f"   第一个产品名称 (XPath): {first_product_name_xpath}")
+    # 使用默认值处理不存在的元素
+    non_exist = response.extract_text('.non-exist', default='未找到')
+    print(f"   不存在的元素: {non_exist}")
+    print()
+    # 2. 演示 extract_texts 方法（提取多个元素的文本）
+    print("2. 提取多个元素的文本:")
+    # 提取所有产品名称
+    product_names = response.extract_texts('.product-item h2')
+    print(f"   所有产品名称: {product_names}")
+    # 提取所有价格
+    prices = response.extract_texts('.price')
+    print(f"   所有价格: {prices}")
+    # 使用XPath提取所有产品名称
+    product_names_xpath = response.extract_texts('//div[@class="product-item"]/h2')
+    print(f"   所有产品名称 (XPath): {product_names_xpath}")
+    print()
+    # 3. 演示 extract_attr 方法（提取元素属性）
+    print("3. 提取元素属性:")
+    # 提取第一个产品项的data-id属性
+    first_product_id = response.extract_attr('.product-item', 'data-id')
+    print(f"   第一个产品ID: {first_product_id}")
+    # 提取详情链接的href属性
+    first_detail_link = response.extract_attr('.details-link', 'href')
+    print(f"   第一个详情链接: {first_detail_link}")
+    # 提取不存在属性的默认值
+    non_exist_attr = response.extract_attr('.product-item', 'non-exist', default='默认值')
+    print(f"   不存在的属性: {non_exist_attr}")
+    print()
+    # 4. 演示 extract_attrs 方法（提取多个元素的属性）
+    print("4. 提取多个元素的属性:")
+    # 提取所有产品项的data-id属性
+    product_ids = response.extract_attrs('.product-item', 'data-id')
+    print(f"   所有产品ID: {product_ids}")
+    # 提取所有详情链接的href属性
+    detail_links = response.extract_attrs('.details-link', 'href')
+    print(f"   所有详情链接: {detail_links}")
+    # 提取分页链接的href属性
+    page_links = response.extract_attrs('.page-link', 'href')
+    print(f"   分页链接: {page_links}")
+    print()
+    # 5. 演示复杂文本提取
+    print("5. 复杂文本提取:")
+    # 提取所有产品描述
+    descriptions = response.extract_texts('.description')
+    print(f"   所有产品描述: {descriptions}")
+    print()
+    # 6. 边界情况处理
+    print("6. 边界情况处理:")
+    # 空响应测试
+    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("\n=== 演示完成 ===")
+if __name__ == '__main__':
     demo_response_improvements()

tests/scrapy_comparison/ofweek_scrapy.py ADDED Viewed

@@ -0,0 +1,139 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from urllib.parse import urljoin
+class NewsItem(scrapy.Item):
+    title = scrapy.Field()
+    publish_time = scrapy.Field()
+    url = scrapy.Field()
+    source = scrapy.Field()
+    content = scrapy.Field()
+class OfweekScrapySpider(scrapy.Spider):
+    name = 'ofweek_scrapy'
+    allowed_domains = ['ee.ofweek.com']
+    def start_requests(self):
+        headers = {
+            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+            "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
+            "Cache-Control": "no-cache",
+            "Connection": "keep-alive",
+            "Pragma": "no-cache",
+            "Referer": "https://ee.ofweek.com/CATList-2800-8100-ee-2.html",
+            "Sec-Fetch-Dest": "document",
+            "Sec-Fetch-Mode": "navigate",
+            "Sec-Fetch-Site": "same-origin",
+            "Sec-Fetch-User": "?1",
+            "Upgrade-Insecure-Requests": "1",
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36",
+            "sec-ch-ua": "\"Not;A=Brand\";v=\"99\", \"Google Chrome\";v=\"139\", \"Chromium\";v=\"139\"",
+            "sec-ch-ua-mobile": "?0",
+            "sec-ch-ua-platform": "\"Windows\""
+        }
+        cookies = {
+            "__utmz": "57425525.1730117117.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)",
+            "Hm_lvt_abe9900db162c6d089cdbfd107db0f03": "1739244841",
+            "Hm_lvt_af50e2fc51af73da7720fb324b88a975": "1740100727",
+            "JSESSIONID": "FEA96D3B5FC31350B2285E711BF2A541",
+            "Hm_lvt_28a416fcfc17063eb9c4f9bb1a1f5cda": "1757477622",
+            "HMACCOUNT": "08DF0D235A291EAA",
+            "__utma": "57425525.2080994505.1730117117.1747970718.1757477622.50",
+            "__utmc": "57425525",
+            "__utmt": "1",
+            "__utmb": "57425525.2.10.1757477622",
+            "Hm_lpvt_28a416fcfc17063eb9c4f9bb1a1f5cda": "1757477628",
+            "index_burying_point": "c64d6c31e69d560efe319cc9f8be279f"
+        }
+        # 使用较少的页数进行测试
+        max_page = 50
+        for page in range(1, max_page + 1):
+            url = f'https://ee.ofweek.com/CATList-2800-8100-ee-{page}.html'
+            yield scrapy.Request(
+                url=url,
+                callback=self.parse,
+                headers=headers,
+                cookies=cookies
+            )
+    def parse(self, response):
+        self.logger.info(f'正在解析页面: {response.url}')
+        rows = response.xpath(
+            '//div[@class="main_left"]/div[@class="list_model"]/div[@class="model_right model_right2"]')
+        self.logger.info(f"在页面 {response.url} 中找到 {len(rows)} 个条目")
+        for row in rows:
+            try:
+                # 提取URL和标题
+                url = row.xpath('./h3/a/@href').extract_first()
+                title = row.xpath('./h3/a/text()').extract_first()
+                # 容错处理
+                if not url:
+                    self.logger.warning(f"条目缺少URL，跳过")
+                    continue
+                if not title:
+                    self.logger.warning(f"条目缺少标题，跳过")
+                    continue
+                # 确保 URL 是绝对路径
+                absolute_url = urljoin(response.url, url)
+                # 验证URL格式
+                if not absolute_url.startswith(('http://', 'https://')):
+                    self.logger.warning(f"无效的URL格式，跳过: {absolute_url}")
+                    continue
+                self.logger.info(f"提取到详情页链接: {absolute_url}, 标题: {title}")
+                yield scrapy.Request(
+                    url=absolute_url,
+                    meta={
+                        "title": title.strip() if title else '',
+                        "parent_url": response.url
+                    },
+                    callback=self.parse_detail
+                )
+            except Exception as e:
+                self.logger.error(f"处理条目时出错: {e}")
+                continue
+    def parse_detail(self, response):
+        self.logger.info(f'正在解析详情页: {response.url}')
+        try:
+            title = response.meta.get('title', '')
+            # 提取内容，增加容错处理
+            content_elements = response.xpath('//div[@class="TRS_Editor"]|//*[@id="articleC"]')
+            if content_elements:
+                content = content_elements.xpath('.//text()').extract()
+                content = '\n'.join([text.strip() for text in content if text.strip()])
+            else:
+                content = ''
+                self.logger.warning(f"未找到内容区域: {response.url}")
+            # 提取发布时间
+            publish_time = response.xpath('//div[@class="time fl"]/text()').extract_first()
+            if publish_time:
+                publish_time = publish_time.strip()
+            source = response.xpath('//div[@class="source-name"]/text()').extract_first()
+            # 创建数据项
+            item = NewsItem()
+            item['title'] = title.strip() if title else ''
+            item['publish_time'] = publish_time if publish_time else ''
+            item['url'] = response.url
+            item['source'] = source if source else ''
+            item['content'] = content
+            self.logger.info(f"成功提取详情页数据: {item['title']}")
+            yield item
+        except Exception as e:
+            self.logger.error(f"解析详情页 {response.url} 时出错: {e}")

tests/scrapy_comparison/scrapy_test.py ADDED Viewed

@@ -0,0 +1,134 @@
+# -*- coding: utf-8 -*-
+import scrapy
+from urllib.parse import urljoin
+class NewsItem(scrapy.Item):
+    title = scrapy.Field()
+    publish_time = scrapy.Field()
+    url = scrapy.Field()
+    source = scrapy.Field()
+    content = scrapy.Field()
+class OfweekScrapyTestSpider(scrapy.Spider):
+    name = 'ofweek_scrapy_test'
+    allowed_domains = ['ee.ofweek.com']
+    def start_requests(self):
+        headers = {
+            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
+            "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
+            "Cache-Control": "no-cache",
+            "Connection": "keep-alive",
+            "Pragma": "no-cache",
+            "Referer": "https://ee.ofweek.com/CATList-2800-8100-ee-2.html",
+            "Sec-Fetch-Dest": "document",
+            "Sec-Fetch-Mode": "navigate",
+            "Sec-Fetch-Site": "same-origin",
+            "Sec-Fetch-User": "?1",
+            "Upgrade-Insecure-Requests": "1",
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/139.0.0.0 Safari/537.36",
+        }
+        cookies = {
+            "__utmz": "57425525.1730117117.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)",
+            "Hm_lvt_abe9900db162c6d089cdbfd107db0f03": "1739244841",
+            "Hm_lvt_af50e2fc51af73da7720fb324b88a975": "1740100727",
+            "JSESSIONID": "FEA96D3B5FC31350B2285E711BF2A541",
+            "Hm_lvt_28a416fcfc17063eb9c4f9bb1a1f5cda": "1757477622",
+            "HMACCOUNT": "08DF0D235A291EAA",
+            "__utma": "57425525.2080994505.1730117117.1747970718.1757477622.50",
+            "__utmc": "57425525",
+            "__utmt": "1",
+            "__utmb": "57425525.2.10.1757477622",
+            "Hm_lpvt_28a416fcfc17063eb9c4f9bb1a1f5cda": "1757477628",
+            "index_burying_point": "c64d6c31e69d560efe319cc9f8be279f"
+        }
+        # 使用较少的页数进行测试
+        max_page = 5
+        for page in range(1, max_page + 1):
+            url = f'https://ee.ofweek.com/CATList-2800-8100-ee-{page}.html'
+            yield scrapy.Request(
+                url=url,
+                callback=self.parse,
+                headers=headers,
+                cookies=cookies
+            )
+    def parse(self, response):
+        self.logger.info(f'正在解析页面: {response.url}')
+        rows = response.xpath(
+            '//div[@class="main_left"]/div[@class="list_model"]/div[@class="model_right model_right2"]')
+        self.logger.info(f"在页面 {response.url} 中找到 {len(rows)} 个条目")
+        for row in rows:
+            try:
+                # 提取URL和标题
+                url = row.xpath('./h3/a/@href').extract_first()
+                title = row.xpath('./h3/a/text()').extract_first()
+                # 容错处理
+                if not url:
+                    self.logger.warning(f"条目缺少URL，跳过")
+                    continue
+                if not title:
+                    self.logger.warning(f"条目缺少标题，跳过")
+                    continue
+                # 确保 URL 是绝对路径
+                absolute_url = urljoin(response.url, url)
+                # 验证URL格式
+                if not absolute_url.startswith(('http://', 'https://')):
+                    self.logger.warning(f"无效的URL格式，跳过: {absolute_url}")
+                    continue
+                self.logger.info(f"提取到详情页链接: {absolute_url}, 标题: {title}")
+                yield scrapy.Request(
+                    url=absolute_url,
+                    meta={
+                        "title": title.strip() if title else '',
+                        "parent_url": response.url
+                    },
+                    callback=self.parse_detail
+                )
+            except Exception as e:
+                self.logger.error(f"处理条目时出错: {e}")
+                continue
+    def parse_detail(self, response):
+        self.logger.info(f'正在解析详情页: {response.url}')
+        try:
+            title = response.meta.get('title', '')
+            # 提取内容，增加容错处理
+            content_elements = response.xpath('//div[@class="TRS_Editor"]|//*[@id="articleC"]')
+            if content_elements:
+                content = content_elements.xpath('.//text()').extract()
+                content = '\n'.join([text.strip() for text in content if text.strip()])
+            else:
+                content = ''
+                self.logger.warning(f"未找到内容区域: {response.url}")
+            # 提取发布时间
+            publish_time = response.xpath('//div[@class="time fl"]/text()').extract_first()
+            if publish_time:
+                publish_time = publish_time.strip()
+            source = response.xpath('//div[@class="source-name"]/text()').extract_first()
+            # 创建数据项
+            item = NewsItem()
+            item['title'] = title.strip() if title else ''
+            item['publish_time'] = publish_time if publish_time else ''
+            item['url'] = response.url
+            item['source'] = source if source else ''
+            item['content'] = content
+            self.logger.info(f"成功提取详情页数据: {item['title']}")
+            yield item
+        except Exception as e:
+            self.logger.error(f"解析详情页 {response.url} 时出错: {e}")

crawlo 1.3.3__py3-none-any.whl → 1.3.5__py3-none-any.whl

Potentially problematic release.

crawlo 1.3.3py3-none-any.whl → 1.3.5py3-none-any.whl