学步园

    /// <summary>
    /// 利用正则表达式获取文本中图片的URL
    /// </summary>
    /// <param name="sHtmlText">文本</param>
    /// <returns>返回图片路径集合</returns>
    public static 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);
        int i = 0;
        string[] sUrlList = new string[matches.Count];
        // 取得匹配项列表
        foreach (Match match in matches)
            sUrlList[i++] = match.Groups["imgUrl"].Value;
        return sUrlList;
    }