摘要：
--.*"," “，RegexOptions.IgnoreCase）；Htmlstring=Regex.Replace；Htmltring=Regex.Replace；Htmlstring=Regex.Leplace；Htmlstring=Regex.Replaceags Htmlstring=Htmlstring。代替Htmlstring=Htmlstring。代替Htmlstring=Htmlstring。代替Htmlstring=Htmlstring.Replace；Htmlstring=Htmlstrig.Replace；//返回字符串returnHtmlstring；｝不带html标记//////获取Img的路径//////html字符串文本//返回数组中的图像路径publicstaticstring[]GetHtmlImageUrlList｛RegexregImg=newRegex（@“˂Img[^]*？
不记得在哪看过这个，挺实用的
/// <summary> /// 将html文本转化为 文本内容方法TextNoHTML /// </summary> /// <param name="Htmlstring">HTML文本值</param> /// <returns></returns> public string TextNoHTML(string Htmlstring) { //删除脚本 Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase); //删除HTML Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"([/r/n])[/s]+", "", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "/", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", " ", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "/xa1", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "/xa2", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "/xa3", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "/xa9", RegexOptions.IgnoreCase); Htmlstring = Regex.Replace(Htmlstring, @"&#(/d+);", "", RegexOptions.IgnoreCase); //替换掉 < 和 > 标记 Htmlstring = Htmlstring.Replace("<", ""); Htmlstring = Htmlstring.Replace(">", ""); Htmlstring = Htmlstring.Replace(" ", ""); Htmlstring = Htmlstring.Replace(" ", ""); Htmlstring = Htmlstring.Replace(" ", ""); //返回去掉html标记的字符串 return Htmlstring; }
/// <summary> /// 获取Img的路径 /// </summary> /// <param name="htmlText">Html字符串文本</param> /// <returns>以数组形式返回图片路径</returns> public static string[] GetHtmlImageUrlList(string htmlText) { Regex regImg = new Regex(@"<img[^<>]*?src[s ]*=[s ]*[""']?[s ]*(?<imgUrl>[^s ""'<>]*)[^<>]*?/?[s ]*>", RegexOptions.IgnoreCase); //新建一个matches的MatchCollection对象 保存 匹配对象个数(img标签) MatchCollection matches = regImg.Matches(htmlText); int i = 0; string[] sUrlList = new string[matches.Count]; //遍历所有的img标签对象 foreach (Match match in matches) { //获取所有Img的路径src,并保存到数组中 sUrlList[i++] = match.Groups["imgUrl"].Value; } return sUrlList; }