crawlo 1.2.6__py3-none-any.whl → 1.2.7__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 +61 -61
- crawlo/__version__.py +1 -1
- crawlo/cleaners/__init__.py +60 -60
- crawlo/cleaners/data_formatter.py +225 -225
- crawlo/cleaners/encoding_converter.py +125 -125
- crawlo/cleaners/text_cleaner.py +232 -232
- crawlo/cli.py +75 -88
- crawlo/commands/__init__.py +14 -14
- crawlo/commands/check.py +594 -594
- crawlo/commands/genspider.py +151 -151
- crawlo/commands/help.py +138 -144
- 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 +251 -251
- crawlo/core/__init__.py +2 -2
- crawlo/core/engine.py +365 -356
- crawlo/core/processor.py +40 -40
- crawlo/core/scheduler.py +251 -239
- crawlo/crawler.py +1099 -1110
- crawlo/data/__init__.py +5 -5
- crawlo/data/user_agents.py +107 -107
- crawlo/downloader/__init__.py +266 -266
- crawlo/downloader/aiohttp_downloader.py +228 -221
- crawlo/downloader/cffi_downloader.py +256 -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 -38
- 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 +131 -131
- crawlo/middleware/download_delay.py +104 -104
- crawlo/middleware/middleware_manager.py +136 -135
- crawlo/middleware/offsite.py +114 -114
- crawlo/middleware/proxy.py +367 -367
- 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/mode_manager.py +211 -211
- crawlo/network/__init__.py +21 -21
- crawlo/network/request.py +338 -338
- 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 +317 -317
- crawlo/pipelines/pipeline_manager.py +62 -61
- crawlo/pipelines/redis_dedup_pipeline.py +166 -165
- crawlo/project.py +314 -279
- crawlo/queue/pqueue.py +37 -37
- crawlo/queue/queue_manager.py +377 -376
- crawlo/queue/redis_priority_queue.py +306 -306
- crawlo/settings/__init__.py +7 -7
- crawlo/settings/default_settings.py +219 -215
- crawlo/settings/setting_manager.py +122 -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 +288 -288
- crawlo/templates/project/settings_distributed.py.tmpl +157 -157
- crawlo/templates/project/settings_gentle.py.tmpl +100 -100
- crawlo/templates/project/settings_high_performance.py.tmpl +134 -134
- crawlo/templates/project/settings_simple.py.tmpl +98 -98
- crawlo/templates/project/spiders/__init__.py.tmpl +5 -5
- crawlo/templates/run.py.tmpl +45 -45
- crawlo/templates/spider/spider.py.tmpl +143 -143
- crawlo/tools/__init__.py +182 -182
- crawlo/tools/anti_crawler.py +268 -268
- crawlo/tools/authenticated_proxy.py +240 -240
- crawlo/tools/data_validator.py +180 -180
- crawlo/tools/date_tools.py +35 -35
- crawlo/tools/distributed_coordinator.py +386 -386
- crawlo/tools/retry_mechanism.py +220 -220
- crawlo/tools/scenario_adapter.py +262 -262
- crawlo/utils/__init__.py +35 -35
- crawlo/utils/batch_processor.py +259 -259
- crawlo/utils/controlled_spider_mixin.py +439 -439
- crawlo/utils/date_tools.py +290 -290
- crawlo/utils/db_helper.py +343 -343
- crawlo/utils/enhanced_error_handler.py +356 -356
- crawlo/utils/env_config.py +143 -106
- 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 +128 -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-1.2.6.dist-info → crawlo-1.2.7.dist-info}/METADATA +764 -764
- crawlo-1.2.7.dist-info/RECORD +209 -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 +236 -236
- tests/cleaners_example.py +160 -160
- tests/config_validation_demo.py +102 -102
- tests/controlled_spider_example.py +205 -205
- tests/date_tools_example.py +180 -180
- 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/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 +81 -0
- tests/test_config_validator.py +193 -193
- tests/test_crawlo_proxy_integration.py +172 -172
- tests/test_date_tools.py +123 -123
- tests/test_default_header_middleware.py +158 -158
- 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 +356 -356
- tests/test_item_dedup_redis_key.py +122 -122
- tests/test_mode_consistency.py +52 -0
- 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_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_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_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 -241
- tests/test_scheduler_config_update.py +134 -0
- 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 +153 -153
- tests/tools_example.py +257 -257
- crawlo-1.2.6.dist-info/RECORD +0 -206
- {crawlo-1.2.6.dist-info → crawlo-1.2.7.dist-info}/WHEEL +0 -0
- {crawlo-1.2.6.dist-info → crawlo-1.2.7.dist-info}/entry_points.txt +0 -0
- {crawlo-1.2.6.dist-info → crawlo-1.2.7.dist-info}/top_level.txt +0 -0
|
@@ -1,764 +1,764 @@
|
|
|
1
|
-
Metadata-Version: 2.4
|
|
2
|
-
Name: crawlo
|
|
3
|
-
Version: 1.2.
|
|
4
|
-
Summary: Crawlo 是一款基于异步IO的高性能Python爬虫框架,支持分布式抓取。
|
|
5
|
-
Home-page: https://github.com/crawl-coder/Crawlo.git
|
|
6
|
-
Author: crawl-coder
|
|
7
|
-
Author-email: crawlo@qq.com
|
|
8
|
-
License: MIT
|
|
9
|
-
Classifier: Programming Language :: Python :: 3
|
|
10
|
-
Classifier: License :: OSI Approved :: MIT License
|
|
11
|
-
Classifier: Operating System :: OS Independent
|
|
12
|
-
Requires-Python: >=3.6
|
|
13
|
-
Description-Content-Type: text/markdown
|
|
14
|
-
Requires-Dist: aiohttp>=3.12.14
|
|
15
|
-
Requires-Dist: aiomysql>=0.2.0
|
|
16
|
-
Requires-Dist: aioredis>=2.0.1
|
|
17
|
-
Requires-Dist: asyncmy>=0.2.10
|
|
18
|
-
Requires-Dist: cssselect>=1.2.0
|
|
19
|
-
Requires-Dist: dateparser>=1.2.2
|
|
20
|
-
Requires-Dist: httpx[http2]>=0.27.0
|
|
21
|
-
Requires-Dist: curl-cffi>=0.13.0
|
|
22
|
-
Requires-Dist: lxml>=5.2.1
|
|
23
|
-
Requires-Dist: motor>=3.7.0
|
|
24
|
-
Requires-Dist: parsel>=1.9.1
|
|
25
|
-
Requires-Dist: pydantic>=2.11.7
|
|
26
|
-
Requires-Dist: pymongo>=4.11
|
|
27
|
-
Requires-Dist: PyMySQL>=1.1.1
|
|
28
|
-
Requires-Dist: python-dateutil>=2.9.0.post0
|
|
29
|
-
Requires-Dist: redis>=6.2.0
|
|
30
|
-
Requires-Dist: requests>=2.32.4
|
|
31
|
-
Requires-Dist: six>=1.17.0
|
|
32
|
-
Requires-Dist: ujson>=5.9.0
|
|
33
|
-
Requires-Dist: urllib3>=2.5.0
|
|
34
|
-
Requires-Dist: w3lib>=2.1.2
|
|
35
|
-
Requires-Dist: rich>=14.1.0
|
|
36
|
-
Requires-Dist: astor>=0.8.1
|
|
37
|
-
Requires-Dist: watchdog>=6.0.0
|
|
38
|
-
Provides-Extra: render
|
|
39
|
-
Requires-Dist: webdriver-manager>=4.0.0; extra == "render"
|
|
40
|
-
Requires-Dist: playwright; extra == "render"
|
|
41
|
-
Requires-Dist: selenium>=3.141.0; extra == "render"
|
|
42
|
-
Provides-Extra: all
|
|
43
|
-
Requires-Dist: bitarray>=1.5.3; extra == "all"
|
|
44
|
-
Requires-Dist: PyExecJS>=1.5.1; extra == "all"
|
|
45
|
-
Requires-Dist: pymongo>=3.10.1; extra == "all"
|
|
46
|
-
Requires-Dist: redis-py-cluster>=2.1.0; extra == "all"
|
|
47
|
-
Requires-Dist: webdriver-manager>=4.0.0; extra == "all"
|
|
48
|
-
Requires-Dist: playwright; extra == "all"
|
|
49
|
-
Requires-Dist: selenium>=3.141.0; extra == "all"
|
|
50
|
-
|
|
51
|
-
<!-- markdownlint-disable MD033 MD041 -->
|
|
52
|
-
<div align="center">
|
|
53
|
-
<h1 align="center">Crawlo</h1>
|
|
54
|
-
<p align="center">异步分布式爬虫框架</p>
|
|
55
|
-
<p align="center"><strong>基于 asyncio 的高性能异步分布式爬虫框架,支持单机和分布式部署</strong></p>
|
|
56
|
-
|
|
57
|
-
<p align="center">
|
|
58
|
-
<a href="https://www.python.org/downloads/">
|
|
59
|
-
<img src="https://img.shields.io/badge/python-3.8%2B-blue" alt="Python Version">
|
|
60
|
-
</a>
|
|
61
|
-
<a href="LICENSE">
|
|
62
|
-
<img src="https://img.shields.io/badge/license-MIT-green" alt="License">
|
|
63
|
-
</a>
|
|
64
|
-
<a href="https://crawlo.readthedocs.io/">
|
|
65
|
-
<img src="https://img.shields.io/badge/docs-latest-brightgreen" alt="Documentation">
|
|
66
|
-
</a>
|
|
67
|
-
<a href="https://github.com/crawlo/crawlo/actions">
|
|
68
|
-
<img src="https://github.com/crawlo/crawlo/workflows/CI/badge.svg" alt="CI Status">
|
|
69
|
-
</a>
|
|
70
|
-
</p>
|
|
71
|
-
|
|
72
|
-
<p align="center">
|
|
73
|
-
<a href="#-特性">特性</a> •
|
|
74
|
-
<a href="#-快速开始">快速开始</a> •
|
|
75
|
-
<a href="#-命令行工具">命令行工具</a> •
|
|
76
|
-
<a href="#-示例项目">示例项目</a>
|
|
77
|
-
</p>
|
|
78
|
-
</div>
|
|
79
|
-
|
|
80
|
-
<br />
|
|
81
|
-
|
|
82
|
-
<!-- 特性 section -->
|
|
83
|
-
<div align="center">
|
|
84
|
-
<h2>🌟 特性</h2>
|
|
85
|
-
|
|
86
|
-
<table>
|
|
87
|
-
<thead>
|
|
88
|
-
<tr>
|
|
89
|
-
<th>特性</th>
|
|
90
|
-
<th>描述</th>
|
|
91
|
-
</tr>
|
|
92
|
-
</thead>
|
|
93
|
-
<tbody>
|
|
94
|
-
<tr>
|
|
95
|
-
<td>⚡ <strong>异步高性能</strong></td>
|
|
96
|
-
<td>基于 asyncio 实现,充分利用现代 CPU 夯性能</td>
|
|
97
|
-
</tr>
|
|
98
|
-
<tr>
|
|
99
|
-
<td>🌐 <strong>分布式支持</strong></td>
|
|
100
|
-
<td>内置 Redis 队列,轻松实现分布式部署</td>
|
|
101
|
-
</tr>
|
|
102
|
-
<tr>
|
|
103
|
-
<td>🔧 <strong>模块化设计</strong></td>
|
|
104
|
-
<td>中间件、管道、扩展组件系统,易于定制和扩展</td>
|
|
105
|
-
</tr>
|
|
106
|
-
<tr>
|
|
107
|
-
<td>🔄 <strong>智能去重</strong></td>
|
|
108
|
-
<td>多种去重策略(内存、Redis、Bloom Filter)</td>
|
|
109
|
-
</tr>
|
|
110
|
-
<tr>
|
|
111
|
-
<td>⚙️ <strong>灵活配置</strong></td>
|
|
112
|
-
<td>支持多种配置方式,适应不同场景需求</td>
|
|
113
|
-
</tr>
|
|
114
|
-
<tr>
|
|
115
|
-
<td>📋 <strong>高级日志</strong></td>
|
|
116
|
-
<td>支持日志轮转、结构化日志、JSON格式等高级功能</td>
|
|
117
|
-
</tr>
|
|
118
|
-
<tr>
|
|
119
|
-
<td>📚 <strong>丰富文档</strong></td>
|
|
120
|
-
<td>完整的中英文双语文档和示例项目</td>
|
|
121
|
-
</tr>
|
|
122
|
-
</tbody>
|
|
123
|
-
</table>
|
|
124
|
-
</div>
|
|
125
|
-
|
|
126
|
-
<br />
|
|
127
|
-
|
|
128
|
-
---
|
|
129
|
-
|
|
130
|
-
<!-- 快速开始 section -->
|
|
131
|
-
<h2 align="center">🚀 快速开始</h2>
|
|
132
|
-
|
|
133
|
-
### 安装
|
|
134
|
-
|
|
135
|
-
```bash
|
|
136
|
-
pip install crawlo
|
|
137
|
-
```
|
|
138
|
-
|
|
139
|
-
### 创建项目
|
|
140
|
-
|
|
141
|
-
```bash
|
|
142
|
-
# 创建默认项目
|
|
143
|
-
crawlo startproject myproject
|
|
144
|
-
|
|
145
|
-
# 创建分布式模板项目
|
|
146
|
-
crawlo startproject myproject distributed
|
|
147
|
-
|
|
148
|
-
# 创建项目并选择特定模块
|
|
149
|
-
crawlo startproject myproject --modules mysql,redis,proxy
|
|
150
|
-
|
|
151
|
-
cd myproject
|
|
152
|
-
```
|
|
153
|
-
|
|
154
|
-
### 生成爬虫
|
|
155
|
-
|
|
156
|
-
```bash
|
|
157
|
-
# 在项目目录中生成爬虫
|
|
158
|
-
crawlo genspider news_spider news.example.com
|
|
159
|
-
```
|
|
160
|
-
|
|
161
|
-
### 编写爬虫
|
|
162
|
-
|
|
163
|
-
```python
|
|
164
|
-
from crawlo import Spider, Request, Item
|
|
165
|
-
|
|
166
|
-
class MyItem(Item):
|
|
167
|
-
title = ''
|
|
168
|
-
url = ''
|
|
169
|
-
|
|
170
|
-
class MySpider(Spider):
|
|
171
|
-
name = 'myspider'
|
|
172
|
-
|
|
173
|
-
async def start_requests(self):
|
|
174
|
-
yield Request('https://httpbin.org/get', callback=self.parse)
|
|
175
|
-
|
|
176
|
-
async def parse(self, response):
|
|
177
|
-
yield MyItem(
|
|
178
|
-
title='Example Title',
|
|
179
|
-
url=response.url
|
|
180
|
-
)
|
|
181
|
-
```
|
|
182
|
-
|
|
183
|
-
### 运行爬虫
|
|
184
|
-
|
|
185
|
-
```bash
|
|
186
|
-
# 使用命令行工具运行爬虫(推荐)
|
|
187
|
-
crawlo run myspider
|
|
188
|
-
|
|
189
|
-
# 使用项目自带的 run.py 脚本运行
|
|
190
|
-
python run.py
|
|
191
|
-
|
|
192
|
-
# 运行所有爬虫
|
|
193
|
-
crawlo run all
|
|
194
|
-
|
|
195
|
-
# 在项目子目录中也能正确运行
|
|
196
|
-
cd subdirectory
|
|
197
|
-
crawlo run myspider
|
|
198
|
-
```
|
|
199
|
-
|
|
200
|
-
---
|
|
201
|
-
|
|
202
|
-
<!-- 命令行工具 section -->
|
|
203
|
-
<h2 align="center">🔧 命令行工具</h2>
|
|
204
|
-
|
|
205
|
-
Crawlo 提供了丰富的命令行工具,简化项目创建和管理。
|
|
206
|
-
|
|
207
|
-
### crawlo startproject
|
|
208
|
-
|
|
209
|
-
创建新的爬虫项目。
|
|
210
|
-
|
|
211
|
-
```bash
|
|
212
|
-
# 创建默认项目
|
|
213
|
-
crawlo startproject myproject
|
|
214
|
-
|
|
215
|
-
# 创建指定模板的项目
|
|
216
|
-
crawlo startproject myproject simple
|
|
217
|
-
crawlo startproject myproject distributed
|
|
218
|
-
```
|
|
219
|
-
|
|
220
|
-
### crawlo genspider
|
|
221
|
-
|
|
222
|
-
在现有项目中生成新的爬虫。
|
|
223
|
-
|
|
224
|
-
```bash
|
|
225
|
-
# 在当前目录生成爬虫
|
|
226
|
-
crawlo genspider myspider http://example.com
|
|
227
|
-
|
|
228
|
-
# 指定模板生成爬虫
|
|
229
|
-
crawlo genspider myspider http://example.com --template basic
|
|
230
|
-
```
|
|
231
|
-
|
|
232
|
-
### crawlo run
|
|
233
|
-
|
|
234
|
-
运行指定的爬虫。
|
|
235
|
-
|
|
236
|
-
```bash
|
|
237
|
-
# 运行单个爬虫
|
|
238
|
-
crawlo run myspider
|
|
239
|
-
|
|
240
|
-
# 运行所有爬虫
|
|
241
|
-
crawlo run all
|
|
242
|
-
|
|
243
|
-
# 以JSON格式输出结果
|
|
244
|
-
crawlo run myspider --json
|
|
245
|
-
|
|
246
|
-
# 禁用统计信息
|
|
247
|
-
crawlo run myspider --no-stats
|
|
248
|
-
```
|
|
249
|
-
|
|
250
|
-
### crawlo list
|
|
251
|
-
|
|
252
|
-
列出项目中所有可用的爬虫。
|
|
253
|
-
|
|
254
|
-
```bash
|
|
255
|
-
crawlo list
|
|
256
|
-
```
|
|
257
|
-
|
|
258
|
-
### crawlo check
|
|
259
|
-
|
|
260
|
-
检查项目配置和爬虫实现。
|
|
261
|
-
|
|
262
|
-
```bash
|
|
263
|
-
crawlo check
|
|
264
|
-
```
|
|
265
|
-
|
|
266
|
-
### crawlo stats
|
|
267
|
-
|
|
268
|
-
查看爬虫统计数据。
|
|
269
|
-
|
|
270
|
-
```bash
|
|
271
|
-
# 查看最新统计数据
|
|
272
|
-
crawlo stats
|
|
273
|
-
|
|
274
|
-
# 查看指定爬虫的统计数据
|
|
275
|
-
crawlo stats myspider
|
|
276
|
-
```
|
|
277
|
-
|
|
278
|
-
---
|
|
279
|
-
|
|
280
|
-
### 分布式模式
|
|
281
|
-
|
|
282
|
-
Crawlo支持分布式爬取,通过Redis实现任务队列和去重过滤,支持多节点协同工作。
|
|
283
|
-
|
|
284
|
-
#### 配置分布式项目
|
|
285
|
-
|
|
286
|
-
```bash
|
|
287
|
-
# 创建分布式模板项目
|
|
288
|
-
crawlo startproject myproject distributed
|
|
289
|
-
|
|
290
|
-
cd myproject
|
|
291
|
-
```
|
|
292
|
-
|
|
293
|
-
#### 运行分布式爬虫
|
|
294
|
-
|
|
295
|
-
```
|
|
296
|
-
# 使用命令行工具运行分布式爬虫
|
|
297
|
-
crawlo run-distributed myspider
|
|
298
|
-
|
|
299
|
-
# 指定Redis配置运行
|
|
300
|
-
crawlo run-distributed myspider --redis-host 192.168.1.100 --redis-port 6379
|
|
301
|
-
|
|
302
|
-
# 使用项目自带的 run_distributed.py 脚本运行
|
|
303
|
-
python run_distributed.py --spider myspider
|
|
304
|
-
|
|
305
|
-
# 使用 crawlo run 命令运行分布式模式
|
|
306
|
-
crawlo run myspider
|
|
307
|
-
```
|
|
308
|
-
|
|
309
|
-
#### 分布式配置
|
|
310
|
-
|
|
311
|
-
分布式模式使用Redis作为任务队列和去重过滤器:
|
|
312
|
-
|
|
313
|
-
- **队列后端**: Redis(RedisPriorityQueue)
|
|
314
|
-
- **去重过滤器**: AioRedisFilter
|
|
315
|
-
- **状态共享**: Redis协调
|
|
316
|
-
- **可扩展性**: 多节点集群
|
|
317
|
-
|
|
318
|
-
<!-- 配置方式 section -->
|
|
319
|
-
<h2 align="center">⚙️ 配置方式</h2>
|
|
320
|
-
|
|
321
|
-
Crawlo 提供了多种灵活的配置方式,以适应不同的使用场景和开发需求。
|
|
322
|
-
|
|
323
|
-
### 三种配置方式详解
|
|
324
|
-
|
|
325
|
-
#### 1. 配置工厂方式(推荐)
|
|
326
|
-
|
|
327
|
-
使用 `CrawloConfig` 配置工厂是推荐的配置方式,它提供了类型安全和智能提示。
|
|
328
|
-
|
|
329
|
-
```python
|
|
330
|
-
from crawlo.config import CrawloConfig
|
|
331
|
-
from crawlo.crawler import CrawlerProcess
|
|
332
|
-
|
|
333
|
-
# 单机模式配置
|
|
334
|
-
config = CrawloConfig.standalone(
|
|
335
|
-
concurrency=8,
|
|
336
|
-
download_delay=1.0
|
|
337
|
-
)
|
|
338
|
-
|
|
339
|
-
# 分布式模式配置
|
|
340
|
-
config = CrawloConfig.distributed(
|
|
341
|
-
redis_host='127.0.0.1',
|
|
342
|
-
redis_port=6379,
|
|
343
|
-
project_name='myproject',
|
|
344
|
-
concurrency=16
|
|
345
|
-
)
|
|
346
|
-
|
|
347
|
-
# 自动检测模式配置
|
|
348
|
-
config = CrawloConfig.auto(concurrency=12)
|
|
349
|
-
|
|
350
|
-
# 从环境变量读取配置
|
|
351
|
-
config = CrawloConfig.from_env()
|
|
352
|
-
|
|
353
|
-
# 创建爬虫进程
|
|
354
|
-
process = CrawlerProcess(settings=config.to_dict())
|
|
355
|
-
```
|
|
356
|
-
|
|
357
|
-
#### 2. 直接配置方式
|
|
358
|
-
|
|
359
|
-
直接在 `settings.py` 文件中配置各项参数,适合需要精细控制的场景。
|
|
360
|
-
|
|
361
|
-
```python
|
|
362
|
-
# settings.py
|
|
363
|
-
PROJECT_NAME = 'myproject'
|
|
364
|
-
RUN_MODE = 'standalone' # 或 'distributed' 或 'auto'
|
|
365
|
-
CONCURRENCY = 8
|
|
366
|
-
DOWNLOAD_DELAY = 1.0
|
|
367
|
-
|
|
368
|
-
# 分布式模式下需要配置Redis
|
|
369
|
-
REDIS_HOST = '127.0.0.1'
|
|
370
|
-
REDIS_PORT = 6379
|
|
371
|
-
REDIS_PASSWORD = ''
|
|
372
|
-
|
|
373
|
-
# 其他配置...
|
|
374
|
-
```
|
|
375
|
-
|
|
376
|
-
#### 3. 环境变量方式
|
|
377
|
-
|
|
378
|
-
通过环境变量配置,适合部署和CI/CD场景。
|
|
379
|
-
|
|
380
|
-
```bash
|
|
381
|
-
# 设置环境变量
|
|
382
|
-
export CRAWLO_MODE=standalone
|
|
383
|
-
export CONCURRENCY=8
|
|
384
|
-
export DOWNLOAD_DELAY=1.0
|
|
385
|
-
export REDIS_HOST=127.0.0.1
|
|
386
|
-
export REDIS_PORT=6379
|
|
387
|
-
```
|
|
388
|
-
|
|
389
|
-
```python
|
|
390
|
-
# 在代码中读取环境变量
|
|
391
|
-
from crawlo.config import CrawloConfig
|
|
392
|
-
config = CrawloConfig.from_env()
|
|
393
|
-
process = CrawlerProcess(settings=config.to_dict())
|
|
394
|
-
```
|
|
395
|
-
|
|
396
|
-
### 不同运行模式下的最佳配置方式
|
|
397
|
-
|
|
398
|
-
#### 单机模式 (standalone)
|
|
399
|
-
|
|
400
|
-
适用于开发调试、小规模数据采集、个人项目。
|
|
401
|
-
|
|
402
|
-
**推荐配置方式:**
|
|
403
|
-
```python
|
|
404
|
-
from crawlo.config import CrawloConfig
|
|
405
|
-
config = CrawloConfig.standalone(concurrency=4, download_delay=1.0)
|
|
406
|
-
process = CrawlerProcess(settings=config.to_dict())
|
|
407
|
-
```
|
|
408
|
-
|
|
409
|
-
**特点:**
|
|
410
|
-
- 简单易用,资源占用少
|
|
411
|
-
- 无需额外依赖(如Redis)
|
|
412
|
-
- 适合个人开发环境
|
|
413
|
-
|
|
414
|
-
#### 分布式模式 (distributed)
|
|
415
|
-
|
|
416
|
-
适用于大规模数据采集、多节点协同工作、高并发需求。
|
|
417
|
-
|
|
418
|
-
**推荐配置方式:**
|
|
419
|
-
```python
|
|
420
|
-
from crawlo.config import CrawloConfig
|
|
421
|
-
config = CrawloConfig.distributed(
|
|
422
|
-
redis_host='your_redis_host',
|
|
423
|
-
redis_port=6379,
|
|
424
|
-
project_name='myproject',
|
|
425
|
-
concurrency=16
|
|
426
|
-
)
|
|
427
|
-
process = CrawlerProcess(settings=config.to_dict())
|
|
428
|
-
```
|
|
429
|
-
|
|
430
|
-
**特点:**
|
|
431
|
-
- 支持多节点扩展
|
|
432
|
-
- 高并发处理能力
|
|
433
|
-
- 需要Redis支持
|
|
434
|
-
|
|
435
|
-
#### 自动检测模式 (auto)
|
|
436
|
-
|
|
437
|
-
适用于希望根据环境自动选择最佳运行方式。
|
|
438
|
-
|
|
439
|
-
**推荐配置方式:**
|
|
440
|
-
```python
|
|
441
|
-
from crawlo.config import CrawloConfig
|
|
442
|
-
config = CrawloConfig.auto(concurrency=12)
|
|
443
|
-
process = CrawlerProcess(settings=config.to_dict())
|
|
444
|
-
```
|
|
445
|
-
|
|
446
|
-
**特点:**
|
|
447
|
-
- 智能检测环境配置
|
|
448
|
-
- 自动选择运行模式
|
|
449
|
-
- 适合在不同环境中使用同一套配置
|
|
450
|
-
|
|
451
|
-
<!-- 架构设计 section -->
|
|
452
|
-
<h2 align="center">🏗️ 架构设计</h2>
|
|
453
|
-
|
|
454
|
-
### 核心组件说明
|
|
455
|
-
|
|
456
|
-
Crawlo 框架由以下核心组件构成:
|
|
457
|
-
|
|
458
|
-
<table>
|
|
459
|
-
<thead>
|
|
460
|
-
<tr>
|
|
461
|
-
<th>组件</th>
|
|
462
|
-
<th>功能描述</th>
|
|
463
|
-
</tr>
|
|
464
|
-
</thead>
|
|
465
|
-
<tbody>
|
|
466
|
-
<tr>
|
|
467
|
-
<td><strong>Crawler</strong></td>
|
|
468
|
-
<td>爬虫运行实例,管理Spider与引擎的生命周期</td>
|
|
469
|
-
</tr>
|
|
470
|
-
<tr>
|
|
471
|
-
<td><strong>Engine</strong></td>
|
|
472
|
-
<td>引擎组件,协调Scheduler、Downloader、Processor</td>
|
|
473
|
-
</tr>
|
|
474
|
-
<tr>
|
|
475
|
-
<td><strong>Scheduler</strong></td>
|
|
476
|
-
<td>调度器,管理请求队列和去重过滤</td>
|
|
477
|
-
</tr>
|
|
478
|
-
<tr>
|
|
479
|
-
<td><strong>Downloader</strong></td>
|
|
480
|
-
<td>下载器,负责网络请求,支持多种实现(aiohttp, httpx, curl-cffi)</td>
|
|
481
|
-
</tr>
|
|
482
|
-
<tr>
|
|
483
|
-
<td><strong>Processor</strong></td>
|
|
484
|
-
<td>处理器,处理响应数据和管道</td>
|
|
485
|
-
</tr>
|
|
486
|
-
<tr>
|
|
487
|
-
<td><strong>QueueManager</strong></td>
|
|
488
|
-
<td>统一的队列管理器,支持内存队列和Redis队列的自动切换</td>
|
|
489
|
-
</tr>
|
|
490
|
-
<tr>
|
|
491
|
-
<td><strong>Filter</strong></td>
|
|
492
|
-
<td>请求去重过滤器,支持内存和Redis两种实现</td>
|
|
493
|
-
</tr>
|
|
494
|
-
<tr>
|
|
495
|
-
<td><strong>Middleware</strong></td>
|
|
496
|
-
<td>中间件系统,处理请求/响应的预处理和后处理</td>
|
|
497
|
-
</tr>
|
|
498
|
-
<tr>
|
|
499
|
-
<td><strong>Pipeline</strong></td>
|
|
500
|
-
<td>数据处理管道,支持多种存储方式(控制台、数据库等)和去重功能</td>
|
|
501
|
-
</tr>
|
|
502
|
-
<tr>
|
|
503
|
-
<td><strong>Spider</strong></td>
|
|
504
|
-
<td>爬虫基类,定义爬取逻辑</td>
|
|
505
|
-
</tr>
|
|
506
|
-
</tbody>
|
|
507
|
-
</table>
|
|
508
|
-
|
|
509
|
-
### 运行模式
|
|
510
|
-
|
|
511
|
-
Crawlo支持三种运行模式:
|
|
512
|
-
|
|
513
|
-
<table>
|
|
514
|
-
<thead>
|
|
515
|
-
<tr>
|
|
516
|
-
<th>模式</th>
|
|
517
|
-
<th>描述</th>
|
|
518
|
-
<th>队列类型</th>
|
|
519
|
-
<th>过滤器类型</th>
|
|
520
|
-
</tr>
|
|
521
|
-
</thead>
|
|
522
|
-
<tbody>
|
|
523
|
-
<tr>
|
|
524
|
-
<td><strong>standalone</strong></td>
|
|
525
|
-
<td>单机模式</td>
|
|
526
|
-
<td>内存队列</td>
|
|
527
|
-
<td>内存过滤器</td>
|
|
528
|
-
</tr>
|
|
529
|
-
<tr>
|
|
530
|
-
<td><strong>distributed</strong></td>
|
|
531
|
-
<td>分布式模式</td>
|
|
532
|
-
<td>Redis队列</td>
|
|
533
|
-
<td>Redis过滤器</td>
|
|
534
|
-
</tr>
|
|
535
|
-
<tr>
|
|
536
|
-
<td><strong>auto</strong></td>
|
|
537
|
-
<td>自动检测模式</td>
|
|
538
|
-
<td>根据环境自动选择最佳运行方式</td>
|
|
539
|
-
<td>根据环境自动选择</td>
|
|
540
|
-
</tr>
|
|
541
|
-
</tbody>
|
|
542
|
-
</table>
|
|
543
|
-
|
|
544
|
-
#### 运行模式选择指南
|
|
545
|
-
|
|
546
|
-
##### 1. 单机模式 (standalone)
|
|
547
|
-
- **适用场景**:
|
|
548
|
-
- 开发和测试阶段
|
|
549
|
-
- 小规模数据采集(几千到几万条数据)
|
|
550
|
-
- 学习和演示用途
|
|
551
|
-
- 对目标网站负载要求不高的场景
|
|
552
|
-
- **优势**:
|
|
553
|
-
- 配置简单,无需额外依赖
|
|
554
|
-
- 资源消耗低
|
|
555
|
-
- 启动快速
|
|
556
|
-
- 适合本地开发调试
|
|
557
|
-
- **限制**:
|
|
558
|
-
- 无法跨会话去重
|
|
559
|
-
- 无法分布式部署
|
|
560
|
-
- 内存占用随数据量增长
|
|
561
|
-
|
|
562
|
-
##### 2. 分布式模式 (distributed)
|
|
563
|
-
- **适用场景**:
|
|
564
|
-
- 大规模数据采集(百万级以上)
|
|
565
|
-
- 需要多节点协同工作
|
|
566
|
-
- 要求跨会话、跨节点去重
|
|
567
|
-
- 生产环境部署
|
|
568
|
-
- **优势**:
|
|
569
|
-
- 支持水平扩展
|
|
570
|
-
- 跨节点任务协调
|
|
571
|
-
- 持久化去重过滤
|
|
572
|
-
- 高可用性
|
|
573
|
-
- **要求**:
|
|
574
|
-
- 需要Redis服务器
|
|
575
|
-
- 网络环境稳定
|
|
576
|
-
- 更复杂的配置管理
|
|
577
|
-
|
|
578
|
-
##### 3. 自动模式 (auto)
|
|
579
|
-
- **适用场景**:
|
|
580
|
-
- 希望根据环境自动选择最佳配置
|
|
581
|
-
- 开发和生产环境使用同一套代码
|
|
582
|
-
- 动态适应运行环境
|
|
583
|
-
- **工作机制**:
|
|
584
|
-
- 检测Redis可用性
|
|
585
|
-
- Redis可用时自动切换到分布式模式
|
|
586
|
-
- Redis不可用时回退到单机模式
|
|
587
|
-
- **优势**:
|
|
588
|
-
- 环境适应性强
|
|
589
|
-
- 部署灵活
|
|
590
|
-
- 开发和生产环境配置统一
|
|
591
|
-
|
|
592
|
-
#### 队列类型选择指南
|
|
593
|
-
|
|
594
|
-
Crawlo支持三种队列类型,可通过`QUEUE_TYPE`配置项设置:
|
|
595
|
-
|
|
596
|
-
- **memory**:使用内存队列,适用于单机模式
|
|
597
|
-
- **redis**:使用Redis队列,适用于分布式模式
|
|
598
|
-
- **auto**:自动检测模式,根据Redis可用性自动选择
|
|
599
|
-
|
|
600
|
-
推荐使用`auto`模式,让框架根据环境自动选择最适合的队列类型。
|
|
601
|
-
|
|
602
|
-
<!-- 配置系统 section -->
|
|
603
|
-
<h2 align="center">🎛️ 配置系统</h2>
|
|
604
|
-
|
|
605
|
-
### 传统配置方式
|
|
606
|
-
|
|
607
|
-
```
|
|
608
|
-
# settings.py
|
|
609
|
-
PROJECT_NAME = 'myproject'
|
|
610
|
-
CONCURRENCY = 16
|
|
611
|
-
DOWNLOAD_DELAY = 1.0
|
|
612
|
-
QUEUE_TYPE = 'memory' # 单机模式
|
|
613
|
-
# QUEUE_TYPE = 'redis' # 分布式模式
|
|
614
|
-
|
|
615
|
-
# Redis 配置 (分布式模式下使用)
|
|
616
|
-
REDIS_HOST = 'localhost'
|
|
617
|
-
REDIS_PORT = 6379
|
|
618
|
-
REDIS_DB = 0
|
|
619
|
-
REDIS_PASSWORD = ''
|
|
620
|
-
|
|
621
|
-
# 数据管道配置
|
|
622
|
-
PIPELINES = [
|
|
623
|
-
'crawlo.pipelines.console_pipeline.ConsolePipeline',
|
|
624
|
-
'crawlo.pipelines.json_pipeline.JsonPipeline',
|
|
625
|
-
'crawlo.pipelines.redis_dedup_pipeline.RedisDedupPipeline', # Redis去重管道
|
|
626
|
-
'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline', # MySQL存储管道
|
|
627
|
-
]
|
|
628
|
-
|
|
629
|
-
# 高级日志配置
|
|
630
|
-
LOG_FILE = 'logs/spider.log'
|
|
631
|
-
LOG_LEVEL = 'INFO'
|
|
632
|
-
LOG_MAX_BYTES = 10 * 1024 * 1024 # 10MB
|
|
633
|
-
LOG_BACKUP_COUNT = 5
|
|
634
|
-
LOG_JSON_FORMAT = False # 设置为True启用JSON格式
|
|
635
|
-
|
|
636
|
-
# 启用高级日志扩展
|
|
637
|
-
ADVANCED_LOGGING_ENABLED = True
|
|
638
|
-
|
|
639
|
-
# 启用日志监控
|
|
640
|
-
LOG_MONITOR_ENABLED = True
|
|
641
|
-
LOG_MONITOR_INTERVAL = 30
|
|
642
|
-
LOG_MONITOR_DETAILED_STATS = True
|
|
643
|
-
|
|
644
|
-
# 添加扩展
|
|
645
|
-
EXTENSIONS = [
|
|
646
|
-
'crawlo.extension.log_interval.LogIntervalExtension',
|
|
647
|
-
'crawlo.extension.log_stats.LogStats',
|
|
648
|
-
'crawlo.extension.logging_extension.CustomLoggerExtension',
|
|
649
|
-
'crawlo.extension.memory_monitor.MemoryMonitorExtension',
|
|
650
|
-
]
|
|
651
|
-
```
|
|
652
|
-
|
|
653
|
-
### MySQL 管道配置
|
|
654
|
-
|
|
655
|
-
Crawlo 提供了现成的 MySQL 管道实现,可以轻松将爬取的数据存储到 MySQL 数据库中:
|
|
656
|
-
|
|
657
|
-
```
|
|
658
|
-
# 在 settings.py 中启用 MySQL 管道
|
|
659
|
-
PIPELINES = [
|
|
660
|
-
'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline',
|
|
661
|
-
]
|
|
662
|
-
|
|
663
|
-
# MySQL 数据库配置
|
|
664
|
-
MYSQL_HOST = 'localhost'
|
|
665
|
-
MYSQL_PORT = 3306
|
|
666
|
-
MYSQL_USER = 'your_username'
|
|
667
|
-
MYSQL_PASSWORD = 'your_password'
|
|
668
|
-
MYSQL_DB = 'your_database'
|
|
669
|
-
MYSQL_TABLE = 'your_table_name'
|
|
670
|
-
|
|
671
|
-
# 可选的批量插入配置
|
|
672
|
-
MYSQL_BATCH_SIZE = 100
|
|
673
|
-
MYSQL_USE_BATCH = True
|
|
674
|
-
```
|
|
675
|
-
|
|
676
|
-
MySQL 管道特性:
|
|
677
|
-
- **异步操作**:基于 asyncmy 驱动,提供高性能的异步数据库操作
|
|
678
|
-
- **连接池**:自动管理数据库连接,提高效率
|
|
679
|
-
- **批量插入**:支持批量插入以提高性能
|
|
680
|
-
- **事务支持**:确保数据一致性
|
|
681
|
-
- **灵活配置**:支持自定义表名、批量大小等参数
|
|
682
|
-
|
|
683
|
-
### 命令行配置
|
|
684
|
-
|
|
685
|
-
```
|
|
686
|
-
# 运行单个爬虫
|
|
687
|
-
crawlo run myspider
|
|
688
|
-
|
|
689
|
-
# 运行所有爬虫
|
|
690
|
-
crawlo run all
|
|
691
|
-
|
|
692
|
-
# 在项目子目录中也能正确运行
|
|
693
|
-
cd subdirectory
|
|
694
|
-
crawlo run myspider
|
|
695
|
-
```
|
|
696
|
-
|
|
697
|
-
---
|
|
698
|
-
|
|
699
|
-
<!-- 核心组件 section -->
|
|
700
|
-
<h2 align="center">🧩 核心组件</h2>
|
|
701
|
-
|
|
702
|
-
### 中间件系统
|
|
703
|
-
灵活的中间件系统,支持请求预处理、响应处理和异常处理。
|
|
704
|
-
|
|
705
|
-
### 管道系统
|
|
706
|
-
可扩展的数据处理管道,支持多种存储方式(控制台、数据库等)和去重功能:
|
|
707
|
-
- **ConsolePipeline**: 控制台输出管道
|
|
708
|
-
- **JsonPipeline**: JSON文件存储管道
|
|
709
|
-
- **RedisDedupPipeline**: Redis去重管道,基于Redis集合实现分布式去重
|
|
710
|
-
- **AsyncmyMySQLPipeline**: MySQL数据库存储管道,基于asyncmy驱动
|
|
711
|
-
|
|
712
|
-
### 扩展组件
|
|
713
|
-
功能增强扩展,包括日志、监控、性能分析等:
|
|
714
|
-
- **LogIntervalExtension**: 定时日志扩展
|
|
715
|
-
- **LogStats**: 统计日志扩展
|
|
716
|
-
- **CustomLoggerExtension**: 自定义日志扩展
|
|
717
|
-
- **MemoryMonitorExtension**: 内存监控扩展
|
|
718
|
-
- **PerformanceProfilerExtension**: 性能分析扩展
|
|
719
|
-
- **HealthCheckExtension**: 健康检查扩展
|
|
720
|
-
- **RequestRecorderExtension**: 请求记录扩展
|
|
721
|
-
|
|
722
|
-
### 过滤系统
|
|
723
|
-
智能去重过滤,支持多种去重策略(内存、Redis、Bloom Filter)。
|
|
724
|
-
|
|
725
|
-
---
|
|
726
|
-
|
|
727
|
-
<!-- 示例项目 section -->
|
|
728
|
-
<h2 align="center">📦 示例项目</h2>
|
|
729
|
-
|
|
730
|
-
- [OFweek分布式爬虫](examples/ofweek_distributed/) - 复杂的分布式爬虫示例,包含Redis去重功能
|
|
731
|
-
- [OFweek独立爬虫](examples/ofweek_standalone/) - 独立运行的爬虫示例
|
|
732
|
-
- [OFweek混合模式爬虫](examples/ofweek_spider/) - 支持单机和分布式模式切换的爬虫示例
|
|
733
|
-
|
|
734
|
-
---
|
|
735
|
-
|
|
736
|
-
<!-- 文档 section -->
|
|
737
|
-
<h2 align="center">📚 文档</h2>
|
|
738
|
-
|
|
739
|
-
完整的文档请访问 [Crawlo Documentation](https://crawlo.readthedocs.io/)
|
|
740
|
-
|
|
741
|
-
- [快速开始指南](docs/modules/index.md)
|
|
742
|
-
- [模块化文档](docs/modules/index.md)
|
|
743
|
-
- [核心引擎文档](docs/modules/core/engine.md)
|
|
744
|
-
- [调度器文档](docs/modules/core/scheduler.md)
|
|
745
|
-
- [下载器文档](docs/modules/downloader/index.md)
|
|
746
|
-
- [中间件文档](docs/modules/middleware/index.md)
|
|
747
|
-
- [管道文档](docs/modules/pipeline/index.md)
|
|
748
|
-
- [队列文档](docs/modules/queue/index.md)
|
|
749
|
-
- [过滤器文档](docs/modules/filter/index.md)
|
|
750
|
-
- [扩展组件文档](docs/modules/extension/index.md)
|
|
751
|
-
|
|
752
|
-
---
|
|
753
|
-
|
|
754
|
-
<!-- 贡献 section -->
|
|
755
|
-
<h2 align="center">🤝 贡献</h2>
|
|
756
|
-
|
|
757
|
-
欢迎提交 Issue 和 Pull Request 来帮助改进 Crawlo!
|
|
758
|
-
|
|
759
|
-
---
|
|
760
|
-
|
|
761
|
-
<!-- 许可证 section -->
|
|
762
|
-
<h2 align="center">📄 许可证</h2>
|
|
763
|
-
|
|
764
|
-
本项目采用 MIT 许可证,详情请见 [LICENSE](LICENSE) 文件。
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: crawlo
|
|
3
|
+
Version: 1.2.7
|
|
4
|
+
Summary: Crawlo 是一款基于异步IO的高性能Python爬虫框架,支持分布式抓取。
|
|
5
|
+
Home-page: https://github.com/crawl-coder/Crawlo.git
|
|
6
|
+
Author: crawl-coder
|
|
7
|
+
Author-email: crawlo@qq.com
|
|
8
|
+
License: MIT
|
|
9
|
+
Classifier: Programming Language :: Python :: 3
|
|
10
|
+
Classifier: License :: OSI Approved :: MIT License
|
|
11
|
+
Classifier: Operating System :: OS Independent
|
|
12
|
+
Requires-Python: >=3.6
|
|
13
|
+
Description-Content-Type: text/markdown
|
|
14
|
+
Requires-Dist: aiohttp>=3.12.14
|
|
15
|
+
Requires-Dist: aiomysql>=0.2.0
|
|
16
|
+
Requires-Dist: aioredis>=2.0.1
|
|
17
|
+
Requires-Dist: asyncmy>=0.2.10
|
|
18
|
+
Requires-Dist: cssselect>=1.2.0
|
|
19
|
+
Requires-Dist: dateparser>=1.2.2
|
|
20
|
+
Requires-Dist: httpx[http2]>=0.27.0
|
|
21
|
+
Requires-Dist: curl-cffi>=0.13.0
|
|
22
|
+
Requires-Dist: lxml>=5.2.1
|
|
23
|
+
Requires-Dist: motor>=3.7.0
|
|
24
|
+
Requires-Dist: parsel>=1.9.1
|
|
25
|
+
Requires-Dist: pydantic>=2.11.7
|
|
26
|
+
Requires-Dist: pymongo>=4.11
|
|
27
|
+
Requires-Dist: PyMySQL>=1.1.1
|
|
28
|
+
Requires-Dist: python-dateutil>=2.9.0.post0
|
|
29
|
+
Requires-Dist: redis>=6.2.0
|
|
30
|
+
Requires-Dist: requests>=2.32.4
|
|
31
|
+
Requires-Dist: six>=1.17.0
|
|
32
|
+
Requires-Dist: ujson>=5.9.0
|
|
33
|
+
Requires-Dist: urllib3>=2.5.0
|
|
34
|
+
Requires-Dist: w3lib>=2.1.2
|
|
35
|
+
Requires-Dist: rich>=14.1.0
|
|
36
|
+
Requires-Dist: astor>=0.8.1
|
|
37
|
+
Requires-Dist: watchdog>=6.0.0
|
|
38
|
+
Provides-Extra: render
|
|
39
|
+
Requires-Dist: webdriver-manager>=4.0.0; extra == "render"
|
|
40
|
+
Requires-Dist: playwright; extra == "render"
|
|
41
|
+
Requires-Dist: selenium>=3.141.0; extra == "render"
|
|
42
|
+
Provides-Extra: all
|
|
43
|
+
Requires-Dist: bitarray>=1.5.3; extra == "all"
|
|
44
|
+
Requires-Dist: PyExecJS>=1.5.1; extra == "all"
|
|
45
|
+
Requires-Dist: pymongo>=3.10.1; extra == "all"
|
|
46
|
+
Requires-Dist: redis-py-cluster>=2.1.0; extra == "all"
|
|
47
|
+
Requires-Dist: webdriver-manager>=4.0.0; extra == "all"
|
|
48
|
+
Requires-Dist: playwright; extra == "all"
|
|
49
|
+
Requires-Dist: selenium>=3.141.0; extra == "all"
|
|
50
|
+
|
|
51
|
+
<!-- markdownlint-disable MD033 MD041 -->
|
|
52
|
+
<div align="center">
|
|
53
|
+
<h1 align="center">Crawlo</h1>
|
|
54
|
+
<p align="center">异步分布式爬虫框架</p>
|
|
55
|
+
<p align="center"><strong>基于 asyncio 的高性能异步分布式爬虫框架,支持单机和分布式部署</strong></p>
|
|
56
|
+
|
|
57
|
+
<p align="center">
|
|
58
|
+
<a href="https://www.python.org/downloads/">
|
|
59
|
+
<img src="https://img.shields.io/badge/python-3.8%2B-blue" alt="Python Version">
|
|
60
|
+
</a>
|
|
61
|
+
<a href="LICENSE">
|
|
62
|
+
<img src="https://img.shields.io/badge/license-MIT-green" alt="License">
|
|
63
|
+
</a>
|
|
64
|
+
<a href="https://crawlo.readthedocs.io/">
|
|
65
|
+
<img src="https://img.shields.io/badge/docs-latest-brightgreen" alt="Documentation">
|
|
66
|
+
</a>
|
|
67
|
+
<a href="https://github.com/crawlo/crawlo/actions">
|
|
68
|
+
<img src="https://github.com/crawlo/crawlo/workflows/CI/badge.svg" alt="CI Status">
|
|
69
|
+
</a>
|
|
70
|
+
</p>
|
|
71
|
+
|
|
72
|
+
<p align="center">
|
|
73
|
+
<a href="#-特性">特性</a> •
|
|
74
|
+
<a href="#-快速开始">快速开始</a> •
|
|
75
|
+
<a href="#-命令行工具">命令行工具</a> •
|
|
76
|
+
<a href="#-示例项目">示例项目</a>
|
|
77
|
+
</p>
|
|
78
|
+
</div>
|
|
79
|
+
|
|
80
|
+
<br />
|
|
81
|
+
|
|
82
|
+
<!-- 特性 section -->
|
|
83
|
+
<div align="center">
|
|
84
|
+
<h2>🌟 特性</h2>
|
|
85
|
+
|
|
86
|
+
<table>
|
|
87
|
+
<thead>
|
|
88
|
+
<tr>
|
|
89
|
+
<th>特性</th>
|
|
90
|
+
<th>描述</th>
|
|
91
|
+
</tr>
|
|
92
|
+
</thead>
|
|
93
|
+
<tbody>
|
|
94
|
+
<tr>
|
|
95
|
+
<td>⚡ <strong>异步高性能</strong></td>
|
|
96
|
+
<td>基于 asyncio 实现,充分利用现代 CPU 夯性能</td>
|
|
97
|
+
</tr>
|
|
98
|
+
<tr>
|
|
99
|
+
<td>🌐 <strong>分布式支持</strong></td>
|
|
100
|
+
<td>内置 Redis 队列,轻松实现分布式部署</td>
|
|
101
|
+
</tr>
|
|
102
|
+
<tr>
|
|
103
|
+
<td>🔧 <strong>模块化设计</strong></td>
|
|
104
|
+
<td>中间件、管道、扩展组件系统,易于定制和扩展</td>
|
|
105
|
+
</tr>
|
|
106
|
+
<tr>
|
|
107
|
+
<td>🔄 <strong>智能去重</strong></td>
|
|
108
|
+
<td>多种去重策略(内存、Redis、Bloom Filter)</td>
|
|
109
|
+
</tr>
|
|
110
|
+
<tr>
|
|
111
|
+
<td>⚙️ <strong>灵活配置</strong></td>
|
|
112
|
+
<td>支持多种配置方式,适应不同场景需求</td>
|
|
113
|
+
</tr>
|
|
114
|
+
<tr>
|
|
115
|
+
<td>📋 <strong>高级日志</strong></td>
|
|
116
|
+
<td>支持日志轮转、结构化日志、JSON格式等高级功能</td>
|
|
117
|
+
</tr>
|
|
118
|
+
<tr>
|
|
119
|
+
<td>📚 <strong>丰富文档</strong></td>
|
|
120
|
+
<td>完整的中英文双语文档和示例项目</td>
|
|
121
|
+
</tr>
|
|
122
|
+
</tbody>
|
|
123
|
+
</table>
|
|
124
|
+
</div>
|
|
125
|
+
|
|
126
|
+
<br />
|
|
127
|
+
|
|
128
|
+
---
|
|
129
|
+
|
|
130
|
+
<!-- 快速开始 section -->
|
|
131
|
+
<h2 align="center">🚀 快速开始</h2>
|
|
132
|
+
|
|
133
|
+
### 安装
|
|
134
|
+
|
|
135
|
+
```bash
|
|
136
|
+
pip install crawlo
|
|
137
|
+
```
|
|
138
|
+
|
|
139
|
+
### 创建项目
|
|
140
|
+
|
|
141
|
+
```bash
|
|
142
|
+
# 创建默认项目
|
|
143
|
+
crawlo startproject myproject
|
|
144
|
+
|
|
145
|
+
# 创建分布式模板项目
|
|
146
|
+
crawlo startproject myproject distributed
|
|
147
|
+
|
|
148
|
+
# 创建项目并选择特定模块
|
|
149
|
+
crawlo startproject myproject --modules mysql,redis,proxy
|
|
150
|
+
|
|
151
|
+
cd myproject
|
|
152
|
+
```
|
|
153
|
+
|
|
154
|
+
### 生成爬虫
|
|
155
|
+
|
|
156
|
+
```bash
|
|
157
|
+
# 在项目目录中生成爬虫
|
|
158
|
+
crawlo genspider news_spider news.example.com
|
|
159
|
+
```
|
|
160
|
+
|
|
161
|
+
### 编写爬虫
|
|
162
|
+
|
|
163
|
+
```python
|
|
164
|
+
from crawlo import Spider, Request, Item
|
|
165
|
+
|
|
166
|
+
class MyItem(Item):
|
|
167
|
+
title = ''
|
|
168
|
+
url = ''
|
|
169
|
+
|
|
170
|
+
class MySpider(Spider):
|
|
171
|
+
name = 'myspider'
|
|
172
|
+
|
|
173
|
+
async def start_requests(self):
|
|
174
|
+
yield Request('https://httpbin.org/get', callback=self.parse)
|
|
175
|
+
|
|
176
|
+
async def parse(self, response):
|
|
177
|
+
yield MyItem(
|
|
178
|
+
title='Example Title',
|
|
179
|
+
url=response.url
|
|
180
|
+
)
|
|
181
|
+
```
|
|
182
|
+
|
|
183
|
+
### 运行爬虫
|
|
184
|
+
|
|
185
|
+
```bash
|
|
186
|
+
# 使用命令行工具运行爬虫(推荐)
|
|
187
|
+
crawlo run myspider
|
|
188
|
+
|
|
189
|
+
# 使用项目自带的 run.py 脚本运行
|
|
190
|
+
python run.py
|
|
191
|
+
|
|
192
|
+
# 运行所有爬虫
|
|
193
|
+
crawlo run all
|
|
194
|
+
|
|
195
|
+
# 在项目子目录中也能正确运行
|
|
196
|
+
cd subdirectory
|
|
197
|
+
crawlo run myspider
|
|
198
|
+
```
|
|
199
|
+
|
|
200
|
+
---
|
|
201
|
+
|
|
202
|
+
<!-- 命令行工具 section -->
|
|
203
|
+
<h2 align="center">🔧 命令行工具</h2>
|
|
204
|
+
|
|
205
|
+
Crawlo 提供了丰富的命令行工具,简化项目创建和管理。
|
|
206
|
+
|
|
207
|
+
### crawlo startproject
|
|
208
|
+
|
|
209
|
+
创建新的爬虫项目。
|
|
210
|
+
|
|
211
|
+
```bash
|
|
212
|
+
# 创建默认项目
|
|
213
|
+
crawlo startproject myproject
|
|
214
|
+
|
|
215
|
+
# 创建指定模板的项目
|
|
216
|
+
crawlo startproject myproject simple
|
|
217
|
+
crawlo startproject myproject distributed
|
|
218
|
+
```
|
|
219
|
+
|
|
220
|
+
### crawlo genspider
|
|
221
|
+
|
|
222
|
+
在现有项目中生成新的爬虫。
|
|
223
|
+
|
|
224
|
+
```bash
|
|
225
|
+
# 在当前目录生成爬虫
|
|
226
|
+
crawlo genspider myspider http://example.com
|
|
227
|
+
|
|
228
|
+
# 指定模板生成爬虫
|
|
229
|
+
crawlo genspider myspider http://example.com --template basic
|
|
230
|
+
```
|
|
231
|
+
|
|
232
|
+
### crawlo run
|
|
233
|
+
|
|
234
|
+
运行指定的爬虫。
|
|
235
|
+
|
|
236
|
+
```bash
|
|
237
|
+
# 运行单个爬虫
|
|
238
|
+
crawlo run myspider
|
|
239
|
+
|
|
240
|
+
# 运行所有爬虫
|
|
241
|
+
crawlo run all
|
|
242
|
+
|
|
243
|
+
# 以JSON格式输出结果
|
|
244
|
+
crawlo run myspider --json
|
|
245
|
+
|
|
246
|
+
# 禁用统计信息
|
|
247
|
+
crawlo run myspider --no-stats
|
|
248
|
+
```
|
|
249
|
+
|
|
250
|
+
### crawlo list
|
|
251
|
+
|
|
252
|
+
列出项目中所有可用的爬虫。
|
|
253
|
+
|
|
254
|
+
```bash
|
|
255
|
+
crawlo list
|
|
256
|
+
```
|
|
257
|
+
|
|
258
|
+
### crawlo check
|
|
259
|
+
|
|
260
|
+
检查项目配置和爬虫实现。
|
|
261
|
+
|
|
262
|
+
```bash
|
|
263
|
+
crawlo check
|
|
264
|
+
```
|
|
265
|
+
|
|
266
|
+
### crawlo stats
|
|
267
|
+
|
|
268
|
+
查看爬虫统计数据。
|
|
269
|
+
|
|
270
|
+
```bash
|
|
271
|
+
# 查看最新统计数据
|
|
272
|
+
crawlo stats
|
|
273
|
+
|
|
274
|
+
# 查看指定爬虫的统计数据
|
|
275
|
+
crawlo stats myspider
|
|
276
|
+
```
|
|
277
|
+
|
|
278
|
+
---
|
|
279
|
+
|
|
280
|
+
### 分布式模式
|
|
281
|
+
|
|
282
|
+
Crawlo支持分布式爬取,通过Redis实现任务队列和去重过滤,支持多节点协同工作。
|
|
283
|
+
|
|
284
|
+
#### 配置分布式项目
|
|
285
|
+
|
|
286
|
+
```bash
|
|
287
|
+
# 创建分布式模板项目
|
|
288
|
+
crawlo startproject myproject distributed
|
|
289
|
+
|
|
290
|
+
cd myproject
|
|
291
|
+
```
|
|
292
|
+
|
|
293
|
+
#### 运行分布式爬虫
|
|
294
|
+
|
|
295
|
+
```
|
|
296
|
+
# 使用命令行工具运行分布式爬虫
|
|
297
|
+
crawlo run-distributed myspider
|
|
298
|
+
|
|
299
|
+
# 指定Redis配置运行
|
|
300
|
+
crawlo run-distributed myspider --redis-host 192.168.1.100 --redis-port 6379
|
|
301
|
+
|
|
302
|
+
# 使用项目自带的 run_distributed.py 脚本运行
|
|
303
|
+
python run_distributed.py --spider myspider
|
|
304
|
+
|
|
305
|
+
# 使用 crawlo run 命令运行分布式模式
|
|
306
|
+
crawlo run myspider
|
|
307
|
+
```
|
|
308
|
+
|
|
309
|
+
#### 分布式配置
|
|
310
|
+
|
|
311
|
+
分布式模式使用Redis作为任务队列和去重过滤器:
|
|
312
|
+
|
|
313
|
+
- **队列后端**: Redis(RedisPriorityQueue)
|
|
314
|
+
- **去重过滤器**: AioRedisFilter
|
|
315
|
+
- **状态共享**: Redis协调
|
|
316
|
+
- **可扩展性**: 多节点集群
|
|
317
|
+
|
|
318
|
+
<!-- 配置方式 section -->
|
|
319
|
+
<h2 align="center">⚙️ 配置方式</h2>
|
|
320
|
+
|
|
321
|
+
Crawlo 提供了多种灵活的配置方式,以适应不同的使用场景和开发需求。
|
|
322
|
+
|
|
323
|
+
### 三种配置方式详解
|
|
324
|
+
|
|
325
|
+
#### 1. 配置工厂方式(推荐)
|
|
326
|
+
|
|
327
|
+
使用 `CrawloConfig` 配置工厂是推荐的配置方式,它提供了类型安全和智能提示。
|
|
328
|
+
|
|
329
|
+
```python
|
|
330
|
+
from crawlo.config import CrawloConfig
|
|
331
|
+
from crawlo.crawler import CrawlerProcess
|
|
332
|
+
|
|
333
|
+
# 单机模式配置
|
|
334
|
+
config = CrawloConfig.standalone(
|
|
335
|
+
concurrency=8,
|
|
336
|
+
download_delay=1.0
|
|
337
|
+
)
|
|
338
|
+
|
|
339
|
+
# 分布式模式配置
|
|
340
|
+
config = CrawloConfig.distributed(
|
|
341
|
+
redis_host='127.0.0.1',
|
|
342
|
+
redis_port=6379,
|
|
343
|
+
project_name='myproject',
|
|
344
|
+
concurrency=16
|
|
345
|
+
)
|
|
346
|
+
|
|
347
|
+
# 自动检测模式配置
|
|
348
|
+
config = CrawloConfig.auto(concurrency=12)
|
|
349
|
+
|
|
350
|
+
# 从环境变量读取配置
|
|
351
|
+
config = CrawloConfig.from_env()
|
|
352
|
+
|
|
353
|
+
# 创建爬虫进程
|
|
354
|
+
process = CrawlerProcess(settings=config.to_dict())
|
|
355
|
+
```
|
|
356
|
+
|
|
357
|
+
#### 2. 直接配置方式
|
|
358
|
+
|
|
359
|
+
直接在 `settings.py` 文件中配置各项参数,适合需要精细控制的场景。
|
|
360
|
+
|
|
361
|
+
```python
|
|
362
|
+
# settings.py
|
|
363
|
+
PROJECT_NAME = 'myproject'
|
|
364
|
+
RUN_MODE = 'standalone' # 或 'distributed' 或 'auto'
|
|
365
|
+
CONCURRENCY = 8
|
|
366
|
+
DOWNLOAD_DELAY = 1.0
|
|
367
|
+
|
|
368
|
+
# 分布式模式下需要配置Redis
|
|
369
|
+
REDIS_HOST = '127.0.0.1'
|
|
370
|
+
REDIS_PORT = 6379
|
|
371
|
+
REDIS_PASSWORD = ''
|
|
372
|
+
|
|
373
|
+
# 其他配置...
|
|
374
|
+
```
|
|
375
|
+
|
|
376
|
+
#### 3. 环境变量方式
|
|
377
|
+
|
|
378
|
+
通过环境变量配置,适合部署和CI/CD场景。
|
|
379
|
+
|
|
380
|
+
```bash
|
|
381
|
+
# 设置环境变量
|
|
382
|
+
export CRAWLO_MODE=standalone
|
|
383
|
+
export CONCURRENCY=8
|
|
384
|
+
export DOWNLOAD_DELAY=1.0
|
|
385
|
+
export REDIS_HOST=127.0.0.1
|
|
386
|
+
export REDIS_PORT=6379
|
|
387
|
+
```
|
|
388
|
+
|
|
389
|
+
```python
|
|
390
|
+
# 在代码中读取环境变量
|
|
391
|
+
from crawlo.config import CrawloConfig
|
|
392
|
+
config = CrawloConfig.from_env()
|
|
393
|
+
process = CrawlerProcess(settings=config.to_dict())
|
|
394
|
+
```
|
|
395
|
+
|
|
396
|
+
### 不同运行模式下的最佳配置方式
|
|
397
|
+
|
|
398
|
+
#### 单机模式 (standalone)
|
|
399
|
+
|
|
400
|
+
适用于开发调试、小规模数据采集、个人项目。
|
|
401
|
+
|
|
402
|
+
**推荐配置方式:**
|
|
403
|
+
```python
|
|
404
|
+
from crawlo.config import CrawloConfig
|
|
405
|
+
config = CrawloConfig.standalone(concurrency=4, download_delay=1.0)
|
|
406
|
+
process = CrawlerProcess(settings=config.to_dict())
|
|
407
|
+
```
|
|
408
|
+
|
|
409
|
+
**特点:**
|
|
410
|
+
- 简单易用,资源占用少
|
|
411
|
+
- 无需额外依赖(如Redis)
|
|
412
|
+
- 适合个人开发环境
|
|
413
|
+
|
|
414
|
+
#### 分布式模式 (distributed)
|
|
415
|
+
|
|
416
|
+
适用于大规模数据采集、多节点协同工作、高并发需求。
|
|
417
|
+
|
|
418
|
+
**推荐配置方式:**
|
|
419
|
+
```python
|
|
420
|
+
from crawlo.config import CrawloConfig
|
|
421
|
+
config = CrawloConfig.distributed(
|
|
422
|
+
redis_host='your_redis_host',
|
|
423
|
+
redis_port=6379,
|
|
424
|
+
project_name='myproject',
|
|
425
|
+
concurrency=16
|
|
426
|
+
)
|
|
427
|
+
process = CrawlerProcess(settings=config.to_dict())
|
|
428
|
+
```
|
|
429
|
+
|
|
430
|
+
**特点:**
|
|
431
|
+
- 支持多节点扩展
|
|
432
|
+
- 高并发处理能力
|
|
433
|
+
- 需要Redis支持
|
|
434
|
+
|
|
435
|
+
#### 自动检测模式 (auto)
|
|
436
|
+
|
|
437
|
+
适用于希望根据环境自动选择最佳运行方式。
|
|
438
|
+
|
|
439
|
+
**推荐配置方式:**
|
|
440
|
+
```python
|
|
441
|
+
from crawlo.config import CrawloConfig
|
|
442
|
+
config = CrawloConfig.auto(concurrency=12)
|
|
443
|
+
process = CrawlerProcess(settings=config.to_dict())
|
|
444
|
+
```
|
|
445
|
+
|
|
446
|
+
**特点:**
|
|
447
|
+
- 智能检测环境配置
|
|
448
|
+
- 自动选择运行模式
|
|
449
|
+
- 适合在不同环境中使用同一套配置
|
|
450
|
+
|
|
451
|
+
<!-- 架构设计 section -->
|
|
452
|
+
<h2 align="center">🏗️ 架构设计</h2>
|
|
453
|
+
|
|
454
|
+
### 核心组件说明
|
|
455
|
+
|
|
456
|
+
Crawlo 框架由以下核心组件构成:
|
|
457
|
+
|
|
458
|
+
<table>
|
|
459
|
+
<thead>
|
|
460
|
+
<tr>
|
|
461
|
+
<th>组件</th>
|
|
462
|
+
<th>功能描述</th>
|
|
463
|
+
</tr>
|
|
464
|
+
</thead>
|
|
465
|
+
<tbody>
|
|
466
|
+
<tr>
|
|
467
|
+
<td><strong>Crawler</strong></td>
|
|
468
|
+
<td>爬虫运行实例,管理Spider与引擎的生命周期</td>
|
|
469
|
+
</tr>
|
|
470
|
+
<tr>
|
|
471
|
+
<td><strong>Engine</strong></td>
|
|
472
|
+
<td>引擎组件,协调Scheduler、Downloader、Processor</td>
|
|
473
|
+
</tr>
|
|
474
|
+
<tr>
|
|
475
|
+
<td><strong>Scheduler</strong></td>
|
|
476
|
+
<td>调度器,管理请求队列和去重过滤</td>
|
|
477
|
+
</tr>
|
|
478
|
+
<tr>
|
|
479
|
+
<td><strong>Downloader</strong></td>
|
|
480
|
+
<td>下载器,负责网络请求,支持多种实现(aiohttp, httpx, curl-cffi)</td>
|
|
481
|
+
</tr>
|
|
482
|
+
<tr>
|
|
483
|
+
<td><strong>Processor</strong></td>
|
|
484
|
+
<td>处理器,处理响应数据和管道</td>
|
|
485
|
+
</tr>
|
|
486
|
+
<tr>
|
|
487
|
+
<td><strong>QueueManager</strong></td>
|
|
488
|
+
<td>统一的队列管理器,支持内存队列和Redis队列的自动切换</td>
|
|
489
|
+
</tr>
|
|
490
|
+
<tr>
|
|
491
|
+
<td><strong>Filter</strong></td>
|
|
492
|
+
<td>请求去重过滤器,支持内存和Redis两种实现</td>
|
|
493
|
+
</tr>
|
|
494
|
+
<tr>
|
|
495
|
+
<td><strong>Middleware</strong></td>
|
|
496
|
+
<td>中间件系统,处理请求/响应的预处理和后处理</td>
|
|
497
|
+
</tr>
|
|
498
|
+
<tr>
|
|
499
|
+
<td><strong>Pipeline</strong></td>
|
|
500
|
+
<td>数据处理管道,支持多种存储方式(控制台、数据库等)和去重功能</td>
|
|
501
|
+
</tr>
|
|
502
|
+
<tr>
|
|
503
|
+
<td><strong>Spider</strong></td>
|
|
504
|
+
<td>爬虫基类,定义爬取逻辑</td>
|
|
505
|
+
</tr>
|
|
506
|
+
</tbody>
|
|
507
|
+
</table>
|
|
508
|
+
|
|
509
|
+
### 运行模式
|
|
510
|
+
|
|
511
|
+
Crawlo支持三种运行模式:
|
|
512
|
+
|
|
513
|
+
<table>
|
|
514
|
+
<thead>
|
|
515
|
+
<tr>
|
|
516
|
+
<th>模式</th>
|
|
517
|
+
<th>描述</th>
|
|
518
|
+
<th>队列类型</th>
|
|
519
|
+
<th>过滤器类型</th>
|
|
520
|
+
</tr>
|
|
521
|
+
</thead>
|
|
522
|
+
<tbody>
|
|
523
|
+
<tr>
|
|
524
|
+
<td><strong>standalone</strong></td>
|
|
525
|
+
<td>单机模式</td>
|
|
526
|
+
<td>内存队列</td>
|
|
527
|
+
<td>内存过滤器</td>
|
|
528
|
+
</tr>
|
|
529
|
+
<tr>
|
|
530
|
+
<td><strong>distributed</strong></td>
|
|
531
|
+
<td>分布式模式</td>
|
|
532
|
+
<td>Redis队列</td>
|
|
533
|
+
<td>Redis过滤器</td>
|
|
534
|
+
</tr>
|
|
535
|
+
<tr>
|
|
536
|
+
<td><strong>auto</strong></td>
|
|
537
|
+
<td>自动检测模式</td>
|
|
538
|
+
<td>根据环境自动选择最佳运行方式</td>
|
|
539
|
+
<td>根据环境自动选择</td>
|
|
540
|
+
</tr>
|
|
541
|
+
</tbody>
|
|
542
|
+
</table>
|
|
543
|
+
|
|
544
|
+
#### 运行模式选择指南
|
|
545
|
+
|
|
546
|
+
##### 1. 单机模式 (standalone)
|
|
547
|
+
- **适用场景**:
|
|
548
|
+
- 开发和测试阶段
|
|
549
|
+
- 小规模数据采集(几千到几万条数据)
|
|
550
|
+
- 学习和演示用途
|
|
551
|
+
- 对目标网站负载要求不高的场景
|
|
552
|
+
- **优势**:
|
|
553
|
+
- 配置简单,无需额外依赖
|
|
554
|
+
- 资源消耗低
|
|
555
|
+
- 启动快速
|
|
556
|
+
- 适合本地开发调试
|
|
557
|
+
- **限制**:
|
|
558
|
+
- 无法跨会话去重
|
|
559
|
+
- 无法分布式部署
|
|
560
|
+
- 内存占用随数据量增长
|
|
561
|
+
|
|
562
|
+
##### 2. 分布式模式 (distributed)
|
|
563
|
+
- **适用场景**:
|
|
564
|
+
- 大规模数据采集(百万级以上)
|
|
565
|
+
- 需要多节点协同工作
|
|
566
|
+
- 要求跨会话、跨节点去重
|
|
567
|
+
- 生产环境部署
|
|
568
|
+
- **优势**:
|
|
569
|
+
- 支持水平扩展
|
|
570
|
+
- 跨节点任务协调
|
|
571
|
+
- 持久化去重过滤
|
|
572
|
+
- 高可用性
|
|
573
|
+
- **要求**:
|
|
574
|
+
- 需要Redis服务器
|
|
575
|
+
- 网络环境稳定
|
|
576
|
+
- 更复杂的配置管理
|
|
577
|
+
|
|
578
|
+
##### 3. 自动模式 (auto)
|
|
579
|
+
- **适用场景**:
|
|
580
|
+
- 希望根据环境自动选择最佳配置
|
|
581
|
+
- 开发和生产环境使用同一套代码
|
|
582
|
+
- 动态适应运行环境
|
|
583
|
+
- **工作机制**:
|
|
584
|
+
- 检测Redis可用性
|
|
585
|
+
- Redis可用时自动切换到分布式模式
|
|
586
|
+
- Redis不可用时回退到单机模式
|
|
587
|
+
- **优势**:
|
|
588
|
+
- 环境适应性强
|
|
589
|
+
- 部署灵活
|
|
590
|
+
- 开发和生产环境配置统一
|
|
591
|
+
|
|
592
|
+
#### 队列类型选择指南
|
|
593
|
+
|
|
594
|
+
Crawlo支持三种队列类型,可通过`QUEUE_TYPE`配置项设置:
|
|
595
|
+
|
|
596
|
+
- **memory**:使用内存队列,适用于单机模式
|
|
597
|
+
- **redis**:使用Redis队列,适用于分布式模式
|
|
598
|
+
- **auto**:自动检测模式,根据Redis可用性自动选择
|
|
599
|
+
|
|
600
|
+
推荐使用`auto`模式,让框架根据环境自动选择最适合的队列类型。
|
|
601
|
+
|
|
602
|
+
<!-- 配置系统 section -->
|
|
603
|
+
<h2 align="center">🎛️ 配置系统</h2>
|
|
604
|
+
|
|
605
|
+
### 传统配置方式
|
|
606
|
+
|
|
607
|
+
```
|
|
608
|
+
# settings.py
|
|
609
|
+
PROJECT_NAME = 'myproject'
|
|
610
|
+
CONCURRENCY = 16
|
|
611
|
+
DOWNLOAD_DELAY = 1.0
|
|
612
|
+
QUEUE_TYPE = 'memory' # 单机模式
|
|
613
|
+
# QUEUE_TYPE = 'redis' # 分布式模式
|
|
614
|
+
|
|
615
|
+
# Redis 配置 (分布式模式下使用)
|
|
616
|
+
REDIS_HOST = 'localhost'
|
|
617
|
+
REDIS_PORT = 6379
|
|
618
|
+
REDIS_DB = 0
|
|
619
|
+
REDIS_PASSWORD = ''
|
|
620
|
+
|
|
621
|
+
# 数据管道配置
|
|
622
|
+
PIPELINES = [
|
|
623
|
+
'crawlo.pipelines.console_pipeline.ConsolePipeline',
|
|
624
|
+
'crawlo.pipelines.json_pipeline.JsonPipeline',
|
|
625
|
+
'crawlo.pipelines.redis_dedup_pipeline.RedisDedupPipeline', # Redis去重管道
|
|
626
|
+
'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline', # MySQL存储管道
|
|
627
|
+
]
|
|
628
|
+
|
|
629
|
+
# 高级日志配置
|
|
630
|
+
LOG_FILE = 'logs/spider.log'
|
|
631
|
+
LOG_LEVEL = 'INFO'
|
|
632
|
+
LOG_MAX_BYTES = 10 * 1024 * 1024 # 10MB
|
|
633
|
+
LOG_BACKUP_COUNT = 5
|
|
634
|
+
LOG_JSON_FORMAT = False # 设置为True启用JSON格式
|
|
635
|
+
|
|
636
|
+
# 启用高级日志扩展
|
|
637
|
+
ADVANCED_LOGGING_ENABLED = True
|
|
638
|
+
|
|
639
|
+
# 启用日志监控
|
|
640
|
+
LOG_MONITOR_ENABLED = True
|
|
641
|
+
LOG_MONITOR_INTERVAL = 30
|
|
642
|
+
LOG_MONITOR_DETAILED_STATS = True
|
|
643
|
+
|
|
644
|
+
# 添加扩展
|
|
645
|
+
EXTENSIONS = [
|
|
646
|
+
'crawlo.extension.log_interval.LogIntervalExtension',
|
|
647
|
+
'crawlo.extension.log_stats.LogStats',
|
|
648
|
+
'crawlo.extension.logging_extension.CustomLoggerExtension',
|
|
649
|
+
'crawlo.extension.memory_monitor.MemoryMonitorExtension',
|
|
650
|
+
]
|
|
651
|
+
```
|
|
652
|
+
|
|
653
|
+
### MySQL 管道配置
|
|
654
|
+
|
|
655
|
+
Crawlo 提供了现成的 MySQL 管道实现,可以轻松将爬取的数据存储到 MySQL 数据库中:
|
|
656
|
+
|
|
657
|
+
```
|
|
658
|
+
# 在 settings.py 中启用 MySQL 管道
|
|
659
|
+
PIPELINES = [
|
|
660
|
+
'crawlo.pipelines.mysql_pipeline.AsyncmyMySQLPipeline',
|
|
661
|
+
]
|
|
662
|
+
|
|
663
|
+
# MySQL 数据库配置
|
|
664
|
+
MYSQL_HOST = 'localhost'
|
|
665
|
+
MYSQL_PORT = 3306
|
|
666
|
+
MYSQL_USER = 'your_username'
|
|
667
|
+
MYSQL_PASSWORD = 'your_password'
|
|
668
|
+
MYSQL_DB = 'your_database'
|
|
669
|
+
MYSQL_TABLE = 'your_table_name'
|
|
670
|
+
|
|
671
|
+
# 可选的批量插入配置
|
|
672
|
+
MYSQL_BATCH_SIZE = 100
|
|
673
|
+
MYSQL_USE_BATCH = True
|
|
674
|
+
```
|
|
675
|
+
|
|
676
|
+
MySQL 管道特性:
|
|
677
|
+
- **异步操作**:基于 asyncmy 驱动,提供高性能的异步数据库操作
|
|
678
|
+
- **连接池**:自动管理数据库连接,提高效率
|
|
679
|
+
- **批量插入**:支持批量插入以提高性能
|
|
680
|
+
- **事务支持**:确保数据一致性
|
|
681
|
+
- **灵活配置**:支持自定义表名、批量大小等参数
|
|
682
|
+
|
|
683
|
+
### 命令行配置
|
|
684
|
+
|
|
685
|
+
```
|
|
686
|
+
# 运行单个爬虫
|
|
687
|
+
crawlo run myspider
|
|
688
|
+
|
|
689
|
+
# 运行所有爬虫
|
|
690
|
+
crawlo run all
|
|
691
|
+
|
|
692
|
+
# 在项目子目录中也能正确运行
|
|
693
|
+
cd subdirectory
|
|
694
|
+
crawlo run myspider
|
|
695
|
+
```
|
|
696
|
+
|
|
697
|
+
---
|
|
698
|
+
|
|
699
|
+
<!-- 核心组件 section -->
|
|
700
|
+
<h2 align="center">🧩 核心组件</h2>
|
|
701
|
+
|
|
702
|
+
### 中间件系统
|
|
703
|
+
灵活的中间件系统,支持请求预处理、响应处理和异常处理。
|
|
704
|
+
|
|
705
|
+
### 管道系统
|
|
706
|
+
可扩展的数据处理管道,支持多种存储方式(控制台、数据库等)和去重功能:
|
|
707
|
+
- **ConsolePipeline**: 控制台输出管道
|
|
708
|
+
- **JsonPipeline**: JSON文件存储管道
|
|
709
|
+
- **RedisDedupPipeline**: Redis去重管道,基于Redis集合实现分布式去重
|
|
710
|
+
- **AsyncmyMySQLPipeline**: MySQL数据库存储管道,基于asyncmy驱动
|
|
711
|
+
|
|
712
|
+
### 扩展组件
|
|
713
|
+
功能增强扩展,包括日志、监控、性能分析等:
|
|
714
|
+
- **LogIntervalExtension**: 定时日志扩展
|
|
715
|
+
- **LogStats**: 统计日志扩展
|
|
716
|
+
- **CustomLoggerExtension**: 自定义日志扩展
|
|
717
|
+
- **MemoryMonitorExtension**: 内存监控扩展
|
|
718
|
+
- **PerformanceProfilerExtension**: 性能分析扩展
|
|
719
|
+
- **HealthCheckExtension**: 健康检查扩展
|
|
720
|
+
- **RequestRecorderExtension**: 请求记录扩展
|
|
721
|
+
|
|
722
|
+
### 过滤系统
|
|
723
|
+
智能去重过滤,支持多种去重策略(内存、Redis、Bloom Filter)。
|
|
724
|
+
|
|
725
|
+
---
|
|
726
|
+
|
|
727
|
+
<!-- 示例项目 section -->
|
|
728
|
+
<h2 align="center">📦 示例项目</h2>
|
|
729
|
+
|
|
730
|
+
- [OFweek分布式爬虫](examples/ofweek_distributed/) - 复杂的分布式爬虫示例,包含Redis去重功能
|
|
731
|
+
- [OFweek独立爬虫](examples/ofweek_standalone/) - 独立运行的爬虫示例
|
|
732
|
+
- [OFweek混合模式爬虫](examples/ofweek_spider/) - 支持单机和分布式模式切换的爬虫示例
|
|
733
|
+
|
|
734
|
+
---
|
|
735
|
+
|
|
736
|
+
<!-- 文档 section -->
|
|
737
|
+
<h2 align="center">📚 文档</h2>
|
|
738
|
+
|
|
739
|
+
完整的文档请访问 [Crawlo Documentation](https://crawlo.readthedocs.io/)
|
|
740
|
+
|
|
741
|
+
- [快速开始指南](docs/modules/index.md)
|
|
742
|
+
- [模块化文档](docs/modules/index.md)
|
|
743
|
+
- [核心引擎文档](docs/modules/core/engine.md)
|
|
744
|
+
- [调度器文档](docs/modules/core/scheduler.md)
|
|
745
|
+
- [下载器文档](docs/modules/downloader/index.md)
|
|
746
|
+
- [中间件文档](docs/modules/middleware/index.md)
|
|
747
|
+
- [管道文档](docs/modules/pipeline/index.md)
|
|
748
|
+
- [队列文档](docs/modules/queue/index.md)
|
|
749
|
+
- [过滤器文档](docs/modules/filter/index.md)
|
|
750
|
+
- [扩展组件文档](docs/modules/extension/index.md)
|
|
751
|
+
|
|
752
|
+
---
|
|
753
|
+
|
|
754
|
+
<!-- 贡献 section -->
|
|
755
|
+
<h2 align="center">🤝 贡献</h2>
|
|
756
|
+
|
|
757
|
+
欢迎提交 Issue 和 Pull Request 来帮助改进 Crawlo!
|
|
758
|
+
|
|
759
|
+
---
|
|
760
|
+
|
|
761
|
+
<!-- 许可证 section -->
|
|
762
|
+
<h2 align="center">📄 许可证</h2>
|
|
763
|
+
|
|
764
|
+
本项目采用 MIT 许可证,详情请见 [LICENSE](LICENSE) 文件。
|