PyPI - crawlo - Versions diffs - 1.2.7__py3-none-any.whl → 1.2.9__py3-none-any.whl - Mend

crawlo 1.2.7py3-none-any.whl → 1.2.9py3-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 (221) hide show

crawlo/__init__.py +63 -61
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 +323 -323
crawlo/commands/startproject.py +436 -436
crawlo/commands/stats.py +187 -187
crawlo/commands/utils.py +186 -186
crawlo/config.py +312 -312
crawlo/config_validator.py +277 -251
crawlo/core/__init__.py +2 -2
crawlo/core/engine.py +366 -365
crawlo/core/processor.py +40 -40
crawlo/core/scheduler.py +256 -251
crawlo/crawler.py +1103 -1100
crawlo/data/__init__.py +5 -5
crawlo/data/user_agents.py +194 -107
crawlo/downloader/__init__.py +273 -266
crawlo/downloader/aiohttp_downloader.py +226 -228
crawlo/downloader/cffi_downloader.py +245 -256
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 +43 -43
crawlo/extension/memory_monitor.py +104 -104
crawlo/extension/performance_profiler.py +133 -133
crawlo/extension/request_recorder.py +107 -107
crawlo/filters/__init__.py +154 -154
crawlo/filters/aioredis_filter.py +234 -234
crawlo/filters/memory_filter.py +269 -269
crawlo/items/__init__.py +23 -23
crawlo/items/base.py +21 -21
crawlo/items/fields.py +52 -52
crawlo/items/items.py +104 -104
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 +136 -136
crawlo/middleware/offsite.py +114 -114
crawlo/middleware/proxy.py +386 -368
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 -0
crawlo/mode_manager.py +211 -211
crawlo/network/__init__.py +21 -21
crawlo/network/request.py +379 -338
crawlo/network/response.py +359 -359
crawlo/pipelines/__init__.py +21 -21
crawlo/pipelines/bloom_dedup_pipeline.py +157 -157
crawlo/pipelines/console_pipeline.py +39 -39
crawlo/pipelines/csv_pipeline.py +316 -316
crawlo/pipelines/database_dedup_pipeline.py +223 -223
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 +317 -317
crawlo/pipelines/pipeline_manager.py +62 -62
crawlo/pipelines/redis_dedup_pipeline.py +167 -167
crawlo/project.py +290 -315
crawlo/queue/pqueue.py +37 -37
crawlo/queue/queue_manager.py +379 -378
crawlo/queue/redis_priority_queue.py +306 -306
crawlo/settings/__init__.py +7 -7
crawlo/settings/default_settings.py +216 -220
crawlo/settings/setting_manager.py +163 -122
crawlo/spider/__init__.py +639 -639
crawlo/stats_collector.py +59 -59
crawlo/subscriber.py +129 -129
crawlo/task_manager.py +30 -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 +261 -288
crawlo/templates/project/settings_distributed.py.tmpl +174 -157
crawlo/templates/project/settings_gentle.py.tmpl +95 -100
crawlo/templates/project/settings_high_performance.py.tmpl +125 -134
crawlo/templates/project/settings_minimal.py.tmpl +30 -0
crawlo/templates/project/settings_simple.py.tmpl +96 -98
crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
crawlo/templates/run.py.tmpl +47 -45
crawlo/templates/spider/spider.py.tmpl +143 -143
crawlo/tools/__init__.py +200 -182
crawlo/tools/anti_crawler.py +268 -268
crawlo/tools/authenticated_proxy.py +240 -240
crawlo/{cleaners → tools}/data_formatter.py +225 -225
crawlo/tools/data_validator.py +180 -180
crawlo/tools/date_tools.py +290 -36
crawlo/tools/distributed_coordinator.py +388 -387
crawlo/{cleaners → tools}/encoding_converter.py +127 -126
crawlo/tools/request_tools.py +83 -0
crawlo/tools/retry_mechanism.py +224 -221
crawlo/tools/scenario_adapter.py +262 -262
crawlo/{cleaners → tools}/text_cleaner.py +232 -232
crawlo/utils/__init__.py +35 -35
crawlo/utils/batch_processor.py +259 -259
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 +123 -123
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 +187 -128
crawlo/utils/performance_monitor.py +285 -285
crawlo/utils/queue_helper.py +175 -175
crawlo/utils/redis_connection_pool.py +351 -351
crawlo/utils/redis_key_validator.py +198 -198
crawlo/utils/request.py +267 -267
crawlo/utils/request_serializer.py +218 -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-1.2.7.dist-info → crawlo-1.2.9.dist-info}/METADATA +1011 -764
crawlo-1.2.9.dist-info/RECORD +219 -0
examples/__init__.py +7 -7
tests/DOUBLE_CRAWLO_PREFIX_FIX_REPORT.md +81 -81
tests/__init__.py +7 -7
tests/advanced_tools_example.py +275 -275
tests/authenticated_proxy_example.py +107 -237
tests/cleaners_example.py +160 -160
tests/config_validation_demo.py +143 -103
tests/controlled_spider_example.py +205 -205
tests/date_tools_example.py +180 -180
tests/debug_pipelines.py +67 -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/redis_key_validation_demo.py +130 -130
tests/request_params_example.py +151 -0
tests/response_improvements_example.py +144 -144
tests/test_advanced_tools.py +148 -148
tests/test_all_redis_key_configs.py +145 -145
tests/test_authenticated_proxy.py +141 -141
tests/test_cleaners.py +54 -54
tests/test_comprehensive.py +146 -146
tests/test_config_consistency.py +80 -80
tests/test_config_merge.py +153 -0
tests/test_config_validator.py +182 -193
tests/test_crawlo_proxy_integration.py +109 -173
tests/test_date_tools.py +123 -123
tests/test_default_header_middleware.py +158 -158
tests/test_distributed.py +65 -0
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_env_config.py +121 -121
tests/test_error_handler_compatibility.py +112 -112
tests/test_final_validation.py +153 -153
tests/test_framework_env_usage.py +103 -103
tests/test_integration.py +169 -357
tests/test_item_dedup_redis_key.py +122 -122
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_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 +185 -0
tests/test_proxy_providers.py +56 -56
tests/test_proxy_stats.py +19 -19
tests/test_proxy_strategies.py +59 -59
tests/test_queue_manager_double_crawlo.py +173 -173
tests/test_queue_manager_redis_key.py +176 -176
tests/test_random_user_agent.py +73 -0
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 +112 -0
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 -153
tests/test_user_agents.py +97 -0
tests/tools_example.py +260 -257
tests/verify_distributed.py +117 -0
crawlo/cleaners/__init__.py +0 -61
crawlo/utils/date_tools.py +0 -290
crawlo-1.2.7.dist-info/RECORD +0 -209
{crawlo-1.2.7.dist-info → crawlo-1.2.9.dist-info}/WHEEL +0 -0
{crawlo-1.2.7.dist-info → crawlo-1.2.9.dist-info}/entry_points.txt +0 -0
{crawlo-1.2.7.dist-info → crawlo-1.2.9.dist-info}/top_level.txt +0 -0

tests/test_response_improvements.py CHANGED Viewed

@@ -1,153 +1,153 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-"""
-Response 改进功能测试
-"""
-import unittest
-from crawlo.network.response import Response
-class TestResponseImprovements(unittest.TestCase):
-    """Response 改进功能测试类"""
-    def setUp(self):
-        """测试前准备"""
-        # 创建一个模拟的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>
-                <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>
-        """
-        self.response = Response(
-            url="https://example.com/test",
-            body=html_content.encode('utf-8'),
-            headers={"content-type": "text/html; charset=utf-8"}
-        )
-    def test_extract_text_with_css(self):
-        """测试使用CSS选择器提取文本"""
-        # 测试提取单个元素文本
-        title = self.response.extract_text('title')
-        self.assertEqual(title, "测试页面")
-        # 测试提取class元素文本
-        h1_text = self.response.extract_text('.content h1')
-        self.assertEqual(h1_text, "主标题")
-        # 测试提取带有默认值的情况
-        non_exist = self.response.extract_text('.non-exist', default='默认值')
-        self.assertEqual(non_exist, '默认值')
-    def test_extract_text_with_xpath(self):
-        """测试使用XPath选择器提取文本"""
-        # 测试提取单个元素文本
-        title = self.response.extract_text('//title')
-        self.assertEqual(title, "测试页面")
-        # 测试提取class元素文本
-        h1_text = self.response.extract_text('//div[@class="content"]/h1')
-        self.assertEqual(h1_text, "主标题")
-    def test_extract_texts_with_css(self):
-        """测试使用CSS选择器提取多个文本"""
-        # 测试提取多个li元素的文本
-        list_items = self.response.extract_texts('.list li')
-        expected = ["项目1", "项目2", "项目3"]
-        self.assertEqual(list_items, expected)
-        # 测试提取不存在元素的默认值
-        non_exist = self.response.extract_texts('.non-exist', default=['默认值'])
-        self.assertEqual(non_exist, ['默认值'])
-    def test_extract_texts_with_xpath(self):
-        """测试使用XPath选择器提取多个文本"""
-        # 测试提取多个li元素的文本
-        list_items = self.response.extract_texts('//ul[@class="list"]/li')
-        expected = ["项目1", "项目2", "项目3"]
-        self.assertEqual(list_items, expected)
-    def test_extract_attr(self):
-        """测试提取元素属性"""
-        # 测试提取链接的href属性
-        link_href = self.response.extract_attr('.link', 'href')
-        self.assertEqual(link_href, "https://example.com")
-        # 测试提取图片的alt属性
-        img_alt = self.response.extract_attr('.image', 'alt')
-        self.assertEqual(img_alt, "图片描述")
-        # 测试提取不存在属性的默认值
-        non_exist = self.response.extract_attr('.link', 'non-exist', default='默认值')
-        self.assertEqual(non_exist, '默认值')
-    def test_extract_attrs(self):
-        """测试提取多个元素的属性"""
-        # 测试提取所有li元素的属性（这里我们测试class属性）
-        list_classes = self.response.extract_attrs('.list li', 'class')
-        # 注意：在当前HTML中li元素没有class属性，所以应该返回空列表
-        self.assertEqual(list_classes, [])
-        # 测试提取所有图片元素的alt属性
-        img_alts = self.response.extract_attrs('.image', 'alt')
-        self.assertEqual(img_alts, ['图片描述'])
-        # 测试提取不存在元素时的默认值
-        non_exist = self.response.extract_attrs('.non-exist-elements', 'alt', default=['默认值'])
-        self.assertEqual(non_exist, ['默认值'])
-    def test_extract_text_from_elements(self):
-        """测试从复杂元素中提取文本"""
-        # 创建包含嵌套标签的HTML
-        complex_html = """
-        <div class="complex">
-            <p>段落文本 <strong>粗体文本</strong> 普通文本</p>
-            <p>第二段落 <em>斜体文本</em></p>
-        </div>
-        """
-        complex_response = Response(
-            url="https://example.com/complex",
-            body=complex_html.encode('utf-8')
-        )
-        # 测试提取复杂元素的文本
-        complex_text = complex_response.extract_text('.complex p', join_str=' ')
-        self.assertIn("段落文本", complex_text)
-        self.assertIn("粗体文本", complex_text)
-        self.assertIn("普通文本", complex_text)
-    def test_edge_cases(self):
-        """测试边界情况"""
-        # 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')
-        self.assertEqual(empty_text, '默认标题')
-        # 测试只包含空白字符的元素
-        whitespace_html = "<div class='whitespace'>   </div>"
-        whitespace_response = Response(
-            url="https://example.com/whitespace",
-            body=whitespace_html.encode('utf-8')
-        )
-        whitespace_text = whitespace_response.extract_text('.whitespace')
-        self.assertEqual(whitespace_text, '')
-if __name__ == '__main__':
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+Response 改进功能测试
+"""
+import unittest
+from crawlo.network.response import Response
+class TestResponseImprovements(unittest.TestCase):
+    """Response 改进功能测试类"""
+    def setUp(self):
+        """测试前准备"""
+        # 创建一个模拟的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>
+                <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>
+        """
+        self.response = Response(
+            url="https://example.com/test",
+            body=html_content.encode('utf-8'),
+            headers={"content-type": "text/html; charset=utf-8"}
+        )
+    def test_extract_text_with_css(self):
+        """测试使用CSS选择器提取文本"""
+        # 测试提取单个元素文本
+        title = self.response.extract_text('title')
+        self.assertEqual(title, "测试页面")
+        # 测试提取class元素文本
+        h1_text = self.response.extract_text('.content h1')
+        self.assertEqual(h1_text, "主标题")
+        # 测试提取带有默认值的情况
+        non_exist = self.response.extract_text('.non-exist', default='默认值')
+        self.assertEqual(non_exist, '默认值')
+    def test_extract_text_with_xpath(self):
+        """测试使用XPath选择器提取文本"""
+        # 测试提取单个元素文本
+        title = self.response.extract_text('//title')
+        self.assertEqual(title, "测试页面")
+        # 测试提取class元素文本
+        h1_text = self.response.extract_text('//div[@class="content"]/h1')
+        self.assertEqual(h1_text, "主标题")
+    def test_extract_texts_with_css(self):
+        """测试使用CSS选择器提取多个文本"""
+        # 测试提取多个li元素的文本
+        list_items = self.response.extract_texts('.list li')
+        expected = ["项目1", "项目2", "项目3"]
+        self.assertEqual(list_items, expected)
+        # 测试提取不存在元素的默认值
+        non_exist = self.response.extract_texts('.non-exist', default=['默认值'])
+        self.assertEqual(non_exist, ['默认值'])
+    def test_extract_texts_with_xpath(self):
+        """测试使用XPath选择器提取多个文本"""
+        # 测试提取多个li元素的文本
+        list_items = self.response.extract_texts('//ul[@class="list"]/li')
+        expected = ["项目1", "项目2", "项目3"]
+        self.assertEqual(list_items, expected)
+    def test_extract_attr(self):
+        """测试提取元素属性"""
+        # 测试提取链接的href属性
+        link_href = self.response.extract_attr('.link', 'href')
+        self.assertEqual(link_href, "https://example.com")
+        # 测试提取图片的alt属性
+        img_alt = self.response.extract_attr('.image', 'alt')
+        self.assertEqual(img_alt, "图片描述")
+        # 测试提取不存在属性的默认值
+        non_exist = self.response.extract_attr('.link', 'non-exist', default='默认值')
+        self.assertEqual(non_exist, '默认值')
+    def test_extract_attrs(self):
+        """测试提取多个元素的属性"""
+        # 测试提取所有li元素的属性（这里我们测试class属性）
+        list_classes = self.response.extract_attrs('.list li', 'class')
+        # 注意：在当前HTML中li元素没有class属性，所以应该返回空列表
+        self.assertEqual(list_classes, [])
+        # 测试提取所有图片元素的alt属性
+        img_alts = self.response.extract_attrs('.image', 'alt')
+        self.assertEqual(img_alts, ['图片描述'])
+        # 测试提取不存在元素时的默认值
+        non_exist = self.response.extract_attrs('.non-exist-elements', 'alt', default=['默认值'])
+        self.assertEqual(non_exist, ['默认值'])
+    def test_extract_text_from_elements(self):
+        """测试从复杂元素中提取文本"""
+        # 创建包含嵌套标签的HTML
+        complex_html = """
+        <div class="complex">
+            <p>段落文本 <strong>粗体文本</strong> 普通文本</p>
+            <p>第二段落 <em>斜体文本</em></p>
+        </div>
+        """
+        complex_response = Response(
+            url="https://example.com/complex",
+            body=complex_html.encode('utf-8')
+        )
+        # 测试提取复杂元素的文本
+        complex_text = complex_response.extract_text('.complex p', join_str=' ')
+        self.assertIn("段落文本", complex_text)
+        self.assertIn("粗体文本", complex_text)
+        self.assertIn("普通文本", complex_text)
+    def test_edge_cases(self):
+        """测试边界情况"""
+        # 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')
+        self.assertEqual(empty_text, '默认标题')
+        # 测试只包含空白字符的元素
+        whitespace_html = "<div class='whitespace'>   </div>"
+        whitespace_response = Response(
+            url="https://example.com/whitespace",
+            body=whitespace_html.encode('utf-8')
+        )
+        whitespace_text = whitespace_response.extract_text('.whitespace')
+        self.assertEqual(whitespace_text, '')
+if __name__ == '__main__':
     unittest.main()

crawlo 1.2.7__py3-none-any.whl → 1.2.9__py3-none-any.whl

Potentially problematic release.

crawlo 1.2.7py3-none-any.whl → 1.2.9py3-none-any.whl