[开源 .NET 跨平台 Crawler 数据采集爬虫框架: DotnetSpider] [三] 配置式爬虫

提示：扫一扫查出行
【扫一扫了解最新限行尾号】
复制提示

[DotnetSpider 系列目录]

一、初衷与架构设计
二、基本使用
三、配置式爬虫
四、JSON数据解析与配置系统
五、如何做全站采集

上一篇介绍的基本的使用方式，自由度很高，但是编写的代码相对就多了。而我所在的行业其实大部分都是定题爬虫, 只需要采集指定的页面并结构化数据。为了提高开发效率, 我实现了利用实体配置的方式来实现爬虫

创建 Console 项目

利用NUGET添加包

DotnetSpider2.Extension

定义配置式数据对象

数据对象必须继承 SpiderEntity

EntityTableAttribute中可以定义数据名称、表名及表名后缀、索引、主键或者需要更新的字段

EntitySelector 定义从页面数据中抽取数据对象的规则

TargetUrlsSelector定义符合规则(正则)的目标链接, 用于加入到队列中

定义一个原始的数据对象类

public class Product : SpiderEntity

{

}

使用Chrome打开京东商品页 http://list.jd.com/list.html?cat=9987,653,655&page=2&JL=6_0_0&ms=5#J_main

使用快捷键F12打开开发者工具
选中一个商品，并观察Html结构

可以看到每个商品都在class为gl-i-wrap j-sku-item的DIV下面，因此添加EntitySelector到数据对象Product的类名上面。（ XPath的写法不是唯一的，不熟悉的可以去W3CSCHOLL学习一下, 框架也支持使用Css甚至正则来选择出正确的Html片段）。

        [EntitySelector(Expression = "//li[@class='gl-item']/div[contains(@class,'j-sku-item')]")]

        public class Product : SpiderEntity

        {

        }

添加数据库及索引信息

        [EntityTable("test", "sku", EntityTable.Monday, Indexs = new[] { "Category" }, Uniques = new[] { "Category,Sku", "Sku" })]

        [EntitySelector(Expression = "//li[@class='gl-item']/div[contains(@class,'j-sku-item')]")]

        public class Product : SpiderEntity

        {

        }

假设你需要采集SKU信息，观察HTML结构，计算出相对的XPath, 为什么是相对XPath？因为EntitySelector已经把HTML截成片段了，内部的Html元素查询都是相对于EntitySelector查询出来的元素。最后再加上数据库中列的信息

        [EntityTable("test", "sku", EntityTable.Monday, Indexs = new[] { "Category" }, Uniques = new[] { "Category,Sku", "Sku" })]

        [EntitySelector(Expression = "//li[@class='gl-item']/div[contains(@class,'j-sku-item')]")]

        public class Product : SpiderEntity

        {

            [PropertyDefine(Expression = "./@data-sku")]

            public string Sku { get; set; }

        }

爬虫内部，链接是通过Request对象来存储信息的，构造Request对象时可以添加额外的属性值，这时候允许数据对象从Request的额外属性值中查询数据

        [EntityTable("test", "sku", EntityTable.Monday, Indexs = new[] { "Category" }, Uniques = new[] { "Category,Sku", "Sku" })]

        [EntitySelector(Expression = "//li[@class='gl-item']/div[contains(@class,'j-sku-item')]")]

        public class Product : SpiderEntity

        {

            [PropertyDefine(Expression = "./@data-sku")]

            public string Sku { get; set; }

            [PropertyDefine(Expression = "name", Type = SelectorType.Enviroment)]

            public string Category { get; set; }

        }

配置爬虫（继承EntitySpider）

    public class JdSkuSampleSpider : EntitySpider

    {

        public JdSkuSampleSpider() : base("JdSkuSample", new Site

        {

            //HttpProxyPool = new HttpProxyPool(new KuaidailiProxySupplier("快代理API"))

        })

        {

        }

        protected override void MyInit(params string[] arguments)

        {

            Identity = Identity ?? "JD SKU SAMPLE";

            ThreadNum = ;

            // dowload html by http client

            Downloader = new HttpClientDownloader();

            // storage data to mysql, default is mysql entity pipeline, so you can comment this line. Don't miss sslmode.

            AddPipeline(new MySqlEntityPipeline("Database='mysql';Data Source=localhost;User ID=root;Password=;Port=3306;SslMode=None;"));

            AddStartUrl("http://list.jd.com/list.html?cat=9987,653,655&page=2&JL=6_0_0&ms=5#J_main", new Dictionary<string, object> { { "name", "手机" }, { "cat3", "" } });

            AddEntityType<Product>();

        }

    }

其中AddStartUrl第二个参数Dictionary<string, object>就是用于Enviroment查询的数据

TargetUrlsSelector，可以配置数据链接的合法性验证，以及目标URL的获取。如下表示目标URL的获取区域是由XPATH选择，并且要符合正则表达式 &page=[0-9]+&

        [EntityTable("test", "jd_sku", EntityTable.Monday, Indexs = new[] { "Category" }, Uniques = new[] { "Category,Sku", "Sku" })]

        [EntitySelector(Expression = "//li[@class='gl-item']/div[contains(@class,'j-sku-item')]")]

        [TargetUrlsSelector(XPaths = new[] { "//span[@class=\"p-num\"]" }, Patterns = new[] { @"&page=[0-9]+&" })]

        public class Product : SpiderEntity

        {

            [PropertyDefine(Expression = "./@data-sku")]

            public string Sku { get; set; }

            [PropertyDefine(Expression = "name", Type = SelectorType.Enviroment)]

            public string Category { get; set; }

        }

添加一个MySql的数据管道，只需要配置好连接字符串即可

context.AddPipeline(new MySqlEntityPipeline("Database='test';Data Source=localhost;User ID=root;Password=1qazZAQ!;Port=3306"));

完整代码

    public class JdSkuSampleSpider : EntitySpider

    {

        public JdSkuSampleSpider() : base("JdSkuSample", new Site

        {

            //HttpProxyPool = new HttpProxyPool(new KuaidailiProxySupplier("快代理API"))

        })

        {

        }

        protected override void MyInit(params string[] arguments)

        {

            Identity = Identity ?? "JD SKU SAMPLE";

            ThreadNum = ;

            // dowload html by http client

            Downloader = new HttpClientDownloader();

            // storage data to mysql, default is mysql entity pipeline, so you can comment this line. Don't miss sslmode.

            AddPipeline(new MySqlEntityPipeline("Database='mysql';Data Source=localhost;User ID=root;Password=;Port=3306;SslMode=None;"));

            AddStartUrl("http://list.jd.com/list.html?cat=9987,653,655&page=2&JL=6_0_0&ms=5#J_main", new Dictionary<string, object> { { "name", "手机" }, { "cat3", "" } });

            AddEntityType<Product>();

        }

    }

    [EntityTable("test", "jd_sku", EntityTable.Monday, Indexs = new[] { "Category" }, Uniques = new[] { "Category,Sku", "Sku" })]

    [EntitySelector(Expression = "//li[@class='gl-item']/div[contains(@class,'j-sku-item')]")]

    [TargetUrlsSelector(XPaths = new[] { "//span[@class=\"p-num\"]" }, Patterns = new[] { @"&page=[0-9]+&" })]

    public class Product : SpiderEntity

    {

        [PropertyDefine(Expression = "./@data-sku", Length = )]

        public string Sku { get; set; }

        [PropertyDefine(Expression = "name", Type = SelectorType.Enviroment, Length = )]

        public string Category { get; set; }

        [PropertyDefine(Expression = "cat3", Type = SelectorType.Enviroment)]

        public int CategoryId { get; set; }

        [PropertyDefine(Expression = "./div[1]/a/@href")]

        public string Url { get; set; }

        [PropertyDefine(Expression = "./div[5]/strong/a")]

        public long CommentsCount { get; set; }

        [PropertyDefine(Expression = ".//div[@class='p-shop']/@data-shop_name", Length = )]

        public string ShopName { get; set; }

        [PropertyDefine(Expression = ".//div[@class='p-name']/a/em", Length = )]

        public string Name { get; set; }

        [PropertyDefine(Expression = "./@venderid", Length = )]

        public string VenderId { get; set; }

        [PropertyDefine(Expression = "./@jdzy_shop_id", Length = )]

        public string JdzyShopId { get; set; }

        [PropertyDefine(Expression = "Monday", Type = SelectorType.Enviroment)]

        public DateTime RunId { get; set; }

    }

运行爬虫

public class Program

{

    public static void Main(string[] args)

    {

        JdSkuSampleSpider spider = new JdSkuSampleSpider();

        spider.Run();

    }

}