日期:2014-05-18  浏览次数:20812 次

遇到一个正则表达式问题,很奇怪啊
C# code
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Text.RegularExpressions;

namespace justTest
{
    class RegularExp
    {
        public static void getSearchData()
        {
            [color=#FF0000]//string _regularExp = "<span class=[^>].*>(.*?)</";
            string _regularExp = "<div class=\"zitifree\">\\s([^<].*)\\s</div>|<span class=[^>].*>(.*?)</";[/color]            string _content0 = "<div class=\"zitifree\">\n历下区义忠汽车修理厂\n</div>\n\n</div>\n<div class=\"right\">\n</div>\n</div>";
            string _content1 = "\n<div class=\"xian\">\n</div>\n<div class=\"content\">\n<div class=\"sidenei\">\n<div class=\"nei\">\n联&nbsp;&nbsp;系&nbsp;&nbsp;人: <span class=\"lblLinkMan\">王立强</span>";
            string _content2 = "\n</div>\n<div class=\"nei\">\n联系电话: <span class=\"lbltel\">053186950690</span>";
            string _content3 = "\n</div>\n<div class=\"nei\">\n邮政编码: <span class=\"lblPostalCode\">250013</span>\n</div>\n<div class=\"nei\">\n电子邮箱: <span class=\"lblemail\">aaa@gmail.com</span>\n</div>\n<div class=\"nei\">\n公司地址: <span class=\"lblweb\">山东省济南市历下区历山路36号</span>\n</div>\n</div>\n</div>";

            string _contentAll = _content0 + _content1 + _content2 + _content3;
            Regex regexName = new Regex(_regularExp, RegexOptions.None);
            Match matchName = regexName.Match(_contentAll);
            int i = 0;
            bool regularState = true;
            searchData ues=new searchData();
            while (matchName.Success)
            {
                string text1 = matchName.Result("$1").Trim();
                //利用正则表达式来获取search对象的详细内容
                switch (i)
                {
                    case 0: ues.Name = text1; break;
                    case 1: ues.Person = text1; break;
                    case 2: ues.Photo = text1; break;
                    case 3: ues.Youbian = text1; break;
                    case 4: ues.Youxiang = text1; break;
                    case 5: ues.Address = text1; break;
                    //出现这种情况下说明出错了 匹配正则表达式 出现错误
                    default:
                        regularState = false; break;
                }
                matchName = matchName.NextMatch();
                i++;
            }
            Console.WriteLine(ues.Name);
            Console.WriteLine(ues.Person);
            Console.WriteLine(ues.Photo);
            Console.WriteLine(ues.Youbian);
            Console.WriteLine(ues.Youxiang);
            Console.WriteLine(ues.Address);



        }


    }
    public struct searchData
    {
       public string  Name;
       public string Person;
       public string Photo;
       public string Youbian;
       public string Youxiang;
       public string Address;
    }

}




哪位熟悉正则表达式的人帮我看看。
我就只想筛选出企业名称 和联系人 等信息。但是现在这个正则表达式 中间用| 联系,只能出来 最左边条件的正则表达式

------解决方案--------------------
[code=C#][/code]
string _regularExp = "<div class=\"zitifree\">\\s([^<].*)\\s</div>|<span class=[^>].*>(.*?)</";
C# code


=>

string _regularExp = "<div class=\"zitifree\">\\s+(?<value>[^<].*)\\s+</div>|<span class=[^>].*>(?<value>.*?)</";