C#自寫的一個HTML解析類（相似XElement語法）

C#自寫的一個HTML解析類（相似XElement語法）。本站提示廣大學習愛好者：（C#自寫的一個HTML解析類（相似XElement語法））文章只能為提供參考，不一定能成為您想要的結果。以下是C#自寫的一個HTML解析類（相似XElement語法）正文

功效：

1、輕松獲得指元素HTML元素。
2、可以依據屬性標簽停止挑選
3、前往的都是Llist強類型無需轉換

 
用過XElement的都曉得 用來解析XML異常的便利，然則關於HTML的格局多樣化其實是沒方法兼容。

所以我就寫了這麼一個相似XElement的 XHTMLElement

用法：

string filePath = Server.MapPath("~/file/test.htm");
      //獲得HTML代碼
      string mailBody = FileHelper.FileToString(filePath);

      XHtmlElement xh = new XHtmlElement(mailBody);

      //獲得body的子集a標簽而且class="icon"
      var link = xh.Descendants("body").ChildDescendants("a").Where(c => c.Attributes.Any(a => a.Key == "class" && a.Value == "icon")).ToList();

      //獲得帶href的a元素
      var links = xh.Descendants("a").Where(c => c.Attributes.Any(a => a.Key == "href")).ToList();
      foreach (var r in links)
      {
        Response.Write(r.Attributes.Single(c => c.Key == "href").Value); //出輸href
      }

      //獲得第一個img
      var img = xh.Descendants("img");

      //獲得比來的第一個p元素和與他統一級的其它p元素
      var ps = xh.Descendants("p");

代碼：

using System;
using System.Collections.Generic;
using System.Linq;
using System.Web;
using System.Text;
using System.Text.RegularExpressions;

namespace SyntacticSugar
{
  /// <summary>
  /// ** 描寫：html解析類
  /// ** 開創時光：2015-4-23
  /// ** 修正時光：-
  /// ** 作者：sunkaixuan
  /// ** qq：610262374 迎接交換,配合進步 ,定名語法等寫的欠好的處所迎接年夜家的給出名貴建議
  /// </summary>
  public class XHtmlElement
  {
    private string _html;
    public XHtmlElement(string html)
    {
      _html = html;
    }

    /// <summary>
    /// 獲得比來的雷同層級的HTML元素
    /// </summary>
    /// <param name="elementName">等於null為一切元素</param>
    /// <returns></returns>
    public List<HtmlInfo> Descendants(string elementName = null)
    {
      if (_html == null)
      {
        throw new ArgumentNullException("html不克不及這空！");
      }
      var allList = RootDescendants(_html);
      var reval = allList.Where(c => elementName == null || c.TagName.ToLower() == elementName.ToLower()).ToList();
      if (reval == null || reval.Count == 0)
      {
        reval = GetDescendantsSource(allList, elementName);
      }
      return reval;
    }


    /// <summary>
    /// 獲得第一級元素
    /// </summary>
    /// <param name="elementName"></param>
    /// <returns></returns>
    public List<HtmlInfo> RootDescendants(string html = null)
    {
      /*
       * 營業邏輯:
             * 1、獲得第一個html標簽一向找開頭標簽，假如在這個進程中碰到雷同的標簽掃尾標簽就要加1
             * 2、第一個標簽取到後持續第一步操作，找第2個元素 。。第N個元素
       */
      if (html == null) html = _html;
      var firstTag = Regex.Match(html, "<.+?>");

      List<string> eleList = new List<string>();
      List<HtmlInfo> reval = new List<HtmlInfo>();
      GetElementsStringList(html, ref eleList);
      foreach (var r in eleList)
      {
        HtmlInfo data = new HtmlInfo();
        data.OldFullHtml = r;
        data.SameLeveHtml = html;
        data.TagName = Regex.Match(r, @"(?<=\s{1}|\<)[a-z,A-Z]+(?=\>|\s)", RegexOptions.IgnoreCase).Value;
        data.InnerHtml = Regex.Match(r, @"(?<=\>).+(?=<)", RegexOptions.Singleline).Value;
        var eleBegin = Regex.Match(r, "<.+?>").Value;
        var attrList = Regex.Matches(eleBegin, @"[a-z,A-Z]+\="".+?""").Cast<Match>().Select(c => new { key = c.Value.Split('=').First(), value = c.Value.Split('=').Last().TrimEnd('"').TrimStart('"') }).ToList();
        data.Attributes = new Dictionary<string, string>();
        if (attrList != null && attrList.Count > 0)
        {
          foreach (var a in attrList)
          {
            data.Attributes.Add(a.key, a.value);
          }
        }
        reval.Add(data);
      }
      return reval;

    }





    #region private
    private List<HtmlInfo> GetDescendantsSource(List<HtmlInfo> allList, string elementName)
    {
      foreach (var r in allList)
      {
        if (r.InnerHtml == null || !r.InnerHtml.Contains("<")) continue;
        var childList = RootDescendants(r.InnerHtml).Where(c => elementName == null || c.TagName.ToLower() == elementName.ToLower()).ToList();
        if (childList == null || childList.Count == 0)
        {
          childList = GetDescendantsSource(RootDescendants(r.InnerHtml), elementName);
          if (childList != null && childList.Count > 0)
            return childList;
        }
        else
        {
          return childList;
        }
      }
      return null;
    }

    private void GetElementsStringList(string html, ref List<string> eleList)
    {
      HtmlInfo info = new HtmlInfo();
      info.TagName = Regex.Match(html, @"(?<=\<\s{0,5}|\<)([a-z,A-Z]+|h\d{1})(?=\>|\s)", RegexOptions.IgnoreCase).Value;
      string currentTagBeginReg = @"<\s{0,10}" + info.TagName + @".*?>";//獲得以後標簽元素開端標簽正則
      string currentTagEndReg = @"\<\/" + info.TagName + @"\>";//獲得以後標簽元素掃尾標簽正則
      if (string.IsNullOrEmpty(info.TagName)) return;

      string eleHtml = "";
      //情形1 <a/>
      //情形2 <a></a>
      //情形3 <a> 毛病格局
      //情形4endif
      if (Regex.IsMatch(html, @"<\s{0,10}" + info.TagName + "[^<].*?/>"))//單標簽
      {
        eleHtml = Regex.Match(html, @"<\s{0,10}" + info.TagName + "[^<].*?/>").Value;
      }
      else if (!Regex.IsMatch(html, currentTagEndReg))//沒有掃尾
      {
        if (Regex.IsMatch(html, @"\s{0,10}\<\!\-\-\[if"))
        {
          eleHtml = GetElementString(html, @"\s{0,10}\<\!\-\-\[if", @"\[endif\]\-\-\>", 1);
        }
        else
        {
          eleHtml = Regex.Match(html, currentTagBeginReg,RegexOptions.Singleline).Value;
        }
      }
      else
      {
        eleHtml = GetElementString(html, currentTagBeginReg, currentTagEndReg, 1);
      }


      try
      {
        eleList.Add(eleHtml);
        html = html.WordStr(eleHtml, "");
        html = Regex.WordStr(html, @"<\!DOCTYPE.*?>", "");
        if (!Regex.IsMatch(html, @"^\s*$"))
        {
          GetElementsStringList(html, ref eleList);
        }

      }
      catch (Exception ex)
      {
        throw new Exception("SORRY,您的HTML格局不克不及解析！！！");

      }

    }

    private string GetElementString(string html, string currentTagBeginReg, string currentTagEndReg, int i)
    {

      string newHtml = GetRegNextByNum(html, currentTagBeginReg, currentTagEndReg, i);
      var currentTagBeginMatches = Regex.Matches(newHtml, currentTagBeginReg, RegexOptions.Singleline).Cast<Match>().Select(c => c.Value).ToList();
      var currentTagEndMatches = Regex.Matches(newHtml, currentTagEndReg).Cast<Match>().Select(c => c.Value).ToList();
      if (currentTagBeginMatches.Count == currentTagEndMatches.Count)
      { //兩個簽標元素相等
        return newHtml;
      }
      return GetElementString(html, currentTagBeginReg, currentTagEndReg, ++i);
    }

    private string GetRegNextByNum(string val, string currentTagBeginReg, string currentTagEndReg, int i)
    {
      return Regex.Match(val, currentTagBeginReg + @"((.*?)" + currentTagEndReg + "){" + i + "}?", RegexOptions.IgnoreCase | RegexOptions.Singleline).Value;
    }
    #endregion



  }
  public static class XHtmlElementExtendsion
  {
    /// <summary>
    /// 獲得比來的雷同層級的HTML元素
    /// </summary>
    /// <param name="elementName">等於null為一切元素</param>
    /// <returns></returns>
    public static List<HtmlInfo> Descendants(this IEnumerable<HtmlInfo> htmlInfoList, string elementName = null)
    {
      var html = htmlInfoList.First().InnerHtml;
      XHtmlElement xhe = new XHtmlElement(html);
      return xhe.Descendants(elementName);
    }
    /// <summary>
    /// 獲得上級元素
    /// </summary>
    /// <param name="elementName"></param>
    /// <returns></returns>
    public static List<HtmlInfo> ChildDescendants(this IEnumerable<HtmlInfo> htmlInfoList, string elementName = null)
    {
      var html = htmlInfoList.First().InnerHtml;
      XHtmlElement xhe = new XHtmlElement(html);
      return xhe.RootDescendants(html).Where(c => elementName == null || c.TagName == elementName).ToList();
    }

    /// <summary>
    /// 獲得父級
    /// </summary>
    /// <param name="htmlInfoList"></param>
    /// <returns></returns>
    public static List<HtmlInfo> ParentDescendant(this IEnumerable<HtmlInfo> htmlInfoList,string fullHtml)
    {
      var saveLeveHtml = htmlInfoList.First().SameLeveHtml;
      string replaceGuid=Guid.NewGuid().ToString();
      fullHtml = fullHtml.WordStr(saveLeveHtml,replaceGuid);
      var parentHtml = Regex.Match(fullHtml, @"<[^<]+?>[^<]*?" + replaceGuid + @".*?<\/.+?>").Value;
      parentHtml = parentHtml.WordStr(replaceGuid, saveLeveHtml);
      XHtmlElement xhe = new XHtmlElement(parentHtml);
      return xhe.RootDescendants();
    }
  }
  /// <summary>
  /// html信息類
  /// </summary>
  public class HtmlInfo
  {
    /// <summary>
    /// 元素名
    /// </summary>
    public string TagName { get; set; }
    /// <summary>
    /// 元素屬性
    /// </summary>
    public Dictionary<string, string> Attributes { get; set; }
    /// <summary>
    /// 元素外部html
    /// </summary>
    public string InnerHtml { get; set; }

    public string OldFullHtml { get; set; }

    public string SameLeveHtml { get; set; }

    /// <summary>
    /// 獲得元素的html
    /// </summary>
    /// <returns></returns>
    public string FullHtml
    {
      get
      {
        StringBuilder reval = new StringBuilder();
        string attributesString = string.Empty;
        if (Attributes != null && Attributes.Count > 0)
        {
          attributesString = string.Join(" ", Attributes.Select(c => string.Format("{0}=\"{1}\"", c.Key, c.Value)));
        }
        reval.AppendFormat("<{0} {2}>{1}</{0}>", TagName, InnerHtml, attributesString);
        return reval.ToString();
      }
    }
  }
}

前台HTML:

<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
  <title></title>
</head>
<body>
  <a id="1">我是1</a> 
  <a id="2" class="icon">icon</a>
  <img />
</body>
</html>