利用 HtmlAgilityPack 抓取网页

之前都是用正则抓取页面，本人正则不咋地，有些东西用抓取来很费劲，呵呵

在网上看到别人推荐一个 HtmlAgilityPack 的东西，网上找了资料，自己写了个抓取网页的例子，框架用的ASP.NET MVC 4，先看看效果

演示地址：http://www.5imvc.com/Html/cnblogs

首先下载插件，NuGet里就有

创建 model

　　 /// <summary>
    /// 页面抓取结果
    /// </summary>
    public class Result
    {
        /// <summary>
        /// 链接
        /// </summary>
        public string url { get; set; }
        /// <summary>
        /// 标题
        /// </summary>
        public string title { get; set; }
        /// <summary>
        /// 头像地址
        /// </summary>
        public string img { get; set; }
        /// <summary>
        /// 正文内容
        /// </summary>
        public string content { get; set; }
    }

Controllers：

导入命名空间：

using HtmlAgilityPack;

        public ActionResult Index()
        {
            return View(getList());
        }

　　　　 /// <summary>
        /// 抓取方法
        /// </summary>
        /// <returns></returns>
        public List<Result> getList()
        {
            List<Result> list = new List<Result>();

            #region 老式的正则抓取

            //System.Net.WebRequest req = System.Net.WebRequest.Create("http://www.cnblogs.com/");
            //System.Net.WebResponse res = req.GetResponse();    // GetResponse blocks until the response arrives
            //System.IO.Stream ReceiveStream = res.GetResponseStream();    // Read the stream into a string
            //System.IO.StreamReader sr = new System.IO.StreamReader(ReceiveStream);
            //string resultstring = sr.ReadToEnd();

            //string regstr = "<h3><a class=\"titlelnk\" href=\"(.*?)\" target=\"_blank\">(.*?)</a></h3>";

            //MatchCollection matches = Regex.Matches(resultstring, regstr, RegexOptions.Multiline);
            //foreach (Match item in matches)
            //{
            //    list.Add(new Result { url = item.Groups[1].Value, title = item.Groups[2].Value });
            //}


            #endregion

            HtmlWeb htmlWeb = new HtmlWeb();
            HtmlDocument htmlDoc = htmlWeb.Load(@"http://www.cnblogs.com/");

            //选择博客园首页文章列表
            htmlDoc.DocumentNode.SelectNodes("//div[@id='post_list']/div[@class='post_item']").
                AsParallel().ToList().ForEach(ac =>
                {
                    //抓取图片，因为有空的，所以拿变量存起来
                    HtmlNode node = ac.SelectSingleNode(".//p[@class='post_item_summary']/a/img");

                    list.Add(new Result
                    {
                        url = ac.SelectSingleNode(".//a[@class='titlelnk']").Attributes["href"].Value,
                        title = ac.SelectSingleNode(".//a[@class='titlelnk']").InnerText,
                        //图片如果为空，显示默认图片
                        img = node == null ? VirtualPathUtility.ToAbsolute("~/Content/img/avatar.png") : node.Attributes["src"].Value,
                        content = ac.SelectSingleNode(".//p[@class='post_item_summary']").InnerText
                    });
                });

            return list;

        }

View：

@model IEnumerable<Result>

@{
    foreach (var item in Model)
    {
    <div class="newsitem">
        <div>
            <img src="@item.img" class="hoverimg" alt="News" />
            <h3><a href="@item.url" target="_blank">@item.title</a>
            </h3>
            <p>
                @item.content
            </p>
        </div>
        <div>
            <p>
                <a href="@item.url" title="">查看全文</a>
            </p>
        </div>
    </div>
    }
}