C#如何使用正则表达式抓取网站信息的代码案例

这篇文章主要介绍了C#使用正则表达式抓取网站信息,结合实例形式分析了C#针对网页信息的正则抓取操作相关技巧,具有一定参考借鉴价值,需要的朋友可以参考下

本文实例讲述了C#使用正则表达式抓取网站信息的方法。分享给大家供大家参考，具体如下：

这里以抓取京东商城商品详情为例。

1、创建JdRobber.cs程序类

public class JdRobber
{
  /// <summary>
  /// 判断是否京东链接
  /// </summary>
  /// <param name="param"></param>
  /// <returns></returns>
  public bool ValidationUrl(string url)
  {
    bool result = false;
    if (!String.IsNullOrEmpty(url))
    {
      Regex regex = new Regex(@"^http://item.jd.com/\d+.html$");
      Match match = regex.Match(url);
      if (match.Success)
      {
        result = true;
      }
    }
    return result;
  }
  /// <summary>
  /// 抓取京东信息
  /// </summary>
  /// <param name="param"></param>
  /// <returns></returns>
  public void GetInfo(string url)
  {
    if (ValidationUrl(url))
    {
      string htmlStr = WebHandler.GetHtmlStr(url, "Default");
      if (!String.IsNullOrEmpty(htmlStr))
      {
        string pattern = "";     //正则表达式
        string sourceWebID = "";   //商品关键ID
        string title = "";      //标题
        decimal price = 0;      //价格
        string picName = "";     //图片
        //提取商品关键ID
        pattern = @"http://item.jd.com/(?<Object>\d+).html";
        sourceWebID = WebHandler.GetRegexText(url, pattern);
        //提取标题
        pattern = @"<p.*id=\""name\"".*>[\s\S]*<h1>(?<Object>.*?)</h1>";
        title = WebHandler.GetRegexText(htmlStr, pattern);
        //提取图片
        int begin = htmlStr.IndexOf("<p id=\"spec-n1\"");
        int end = htmlStr.IndexOf("</p>", begin + 1);
        if (begin > 0 && end > 0)
        {
          string subPicHtml = htmlStr.Substring(begin, end - begin);
          pattern = @"<img.*src=\""(?<Object>.*?)\"".*/>";
          picName = WebHandler.GetRegexText(subPicHtml, pattern);
        }
        //提取价格
        if (sourceWebID != "")
        {
          string priceUrl = @"http://p.3.cn/prices/get?skuid=J_" + sourceWebID + "&type=1";
          string priceJson = WebHandler.GetHtmlStr(priceUrl, "Default");
          pattern = @"\""p\"":\""(?<Object>\d+(\.\d{1,2})?)\""";
          price = WebHandler.GetValidPrice(WebHandler.GetRegexText(priceJson, pattern));
        }
        Console.WriteLine("商品名称：{0}", title);
        Console.WriteLine("图片：{0}", picName);
        Console.WriteLine("价格：{0}", price);
      }
    }
  }
}

2、创建WebHandler.cs公共方法类

/// <summary>
/// 公共方法类
/// </summary>
public class WebHandler
{
  /// <summary>
  /// 获取网页的HTML码
  /// </summary>
  /// <param name="url">链接地址</param>
  /// <param name="encoding">编码类型</param>
  /// <returns></returns>
  public static string GetHtmlStr(string url, string encoding)
  {
    string htmlStr = "";
    try
    {
      if (!String.IsNullOrEmpty(url))
      {
        WebRequest request = WebRequest.Create(url); //实例化WebRequest对象
        WebResponse response = request.GetResponse(); //创建WebResponse对象
        Stream datastream = response.GetResponseStream(); //创建流对象
        Encoding ec = Encoding.Default;
        if (encoding == "UTF8")
        {
          ec = Encoding.UTF8;
        }
        else if (encoding == "Default")
        {
          ec = Encoding.Default;
        }
        StreamReader reader = new StreamReader(datastream, ec);
        htmlStr = reader.ReadToEnd(); //读取数据
        reader.Close();
        datastream.Close();
        response.Close();
      }
    }
    catch { }
    return htmlStr;
  }
  /// <summary>
  /// 获取正则表达式中的关键字
  /// </summary>
  /// <param name="input">文本</param>
  /// <param name="pattern">表达式</param>
  /// <returns></returns>
  public static string GetRegexText(string input, string pattern)
  {
    string result = "";
    if (!String.IsNullOrEmpty(input) && !String.IsNullOrEmpty(pattern))
    {
      Regex regex = new Regex(pattern, RegexOptions.IgnoreCase);
      Match match = regex.Match(input);
      if (match.Success)
      {
        result = match.Groups["Object"].Value;
      }
    }
    return result;
  }
  /// <summary>
  /// 返回有效价格
  /// </summary>
  /// <param name="strPrice"></param>
  /// <returns></returns>
  public static decimal GetValidPrice(string strPrice)
  {
    decimal price = 0;
    try
    {
      if (!String.IsNullOrEmpty(strPrice))
      {
        Regex regex = new Regex(@"^\d+(\.\d{1,2})?$", RegexOptions.IgnoreCase);
        Match match = regex.Match(strPrice);
        if (match.Success)
        {
          price = decimal.Parse(strPrice);
        }
      }
    }
    catch { }
    return price;
  }
}

以上是C#如何使用正则表达式抓取网站信息的代码案例的详细内容。更多信息请关注PHP中文网其他相关文章！