TEAMModelOS/TEAMModelOS.SDK/Helper/Common/StringHelper/HtmlHelper.cs

using HtmlAgilityPack;
using System;
using System.Collections.Generic;
using System.Text;
using System.Text.RegularExpressions;
using TEAMModelOS.SDK.Helper.Common.CollectionHelper;

namespace TEAMModelOS.SDK.Helper.Common.StringHelper
{
    public class HtmlHelper
    {
        public static string DoUselessTag(string str)
        {
            if (str.StartsWith("</p>"))
            {
                str = str.Substring(4);
            }
            if (str.EndsWith("<p>"))
            {
                str = str.Substring(0, str.Length - 1 - 2);
            }
            if (str.EndsWith("<p >"))
            {
                str = str.Substring(0, str.Length - 1 - 3);
            }
            if (str.EndsWith("<p  >"))
            {
                str = str.Substring(0, str.Length - 1 - 4);
            }
            if (str.StartsWith("<p >") && !str.Contains("</p>"))
            {
                str = str.Replace("<p >", "");
            }
            if (str.StartsWith("<p  >") && !str.Contains("</p>"))
            {
                str = str.Replace("<p  >", "");
            }
            if (str.StartsWith("<p>") && !str.Contains("</p>"))
            {
                str = str.Replace("<p>", "");
            }
            if (str.EndsWith("</p>") && !str.Contains("<p>")&& !str.Contains("<p >") && !str.Contains("<p  >")){
                str = str.Replace("</p>", "");
            }

            return str;
        }

        /// <summary>
        /// 从html获取文本及img的url  去掉其他标签的干扰。以获取更准确的sha1校验值
        /// </summary>
        /// <param name="html"></param>
        /// <returns></returns>
        public static string DoTextImg(string html)
        {
            HtmlDocument doc = new HtmlDocument();
            doc.LoadHtml(html);
            List<string> urls = GetHtmlImageUrlList(html);
            StringBuilder builder = new StringBuilder(doc.DocumentNode.InnerText);
            if (urls.IsNotEmpty())
            {
                foreach (string url in urls)
                {
                    builder.Append(url);
                }
            }
            return builder.ToString();
        }

        public static List<string> GetHtmlImageUrlList(string sHtmlText)
        {
            // 定义正则表达式用来匹配 img 标签   
            Regex regImg = new Regex(@"<img\b[^<>]*?\bsrc[\s\t\r\n]*=[\s\t\r\n]*[""']?[\s\t\r\n]*(?<imgUrl>[^\s\t\r\n""'<>]*)[^<>]*?/?[\s\t\r\n]*>", RegexOptions.IgnoreCase);

            // 搜索匹配的字符串   
            MatchCollection matches = regImg.Matches(sHtmlText);
            //string[] sUrlList = new string[matches.Count];
            List<string> urls = new List<string>();
            // 取得匹配项列表   
            foreach (Match match in matches)
                urls.Add(match.Groups["imgUrl"].Value);
            return urls;
        }
    }
}