Code example of how C# uses regular expressions to crawl website information

This article mainly introduces the use of CregularExpression Capture website information, combined with examples to analyze C#'s techniques related to regular crawling operations for web page information. It has certain reference value. Friends in need can refer to the following

Examples in this article The method of using regular expressions to capture website information in C# is shared with you for your reference. The details are as follows:

Here is an example of capturing Jingdong Mall product details. ##1. Create JdRobber.cs program class

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 id="Object">(?<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 alt="Code example of how C# uses regular expressions to crawl website information" >.*?)\"".*/>";
          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. Create WebHandler.cs public method class

/// <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;
  }
}

The above is the detailed content of Code example of how C# uses regular expressions to crawl website information. For more information, please follow other related articles on the PHP Chinese website!