最近做的一个东东，想要去除掉保存的字符串内容的所有html格式，也就是只取纯文本，
从网上查了些相关资料，以及正则表达式的用法，
有一个方法向大家推荐，基本去除了我想要去除的html格式，可能根据需要不同，还需要你自己编写相关正则匹配，这里我自己加了一个去除所有空格的匹配，
下面把这个提取纯文本的方法跟贴出来跟大家学习，请多多指点。
参阅网络资料：http://www.suzhou35.com/blog/article.asp?id=169
1、［用正则表达式来提取html中的文本］
需要引用的命名空间是System.Text.RegularExpressions
using System.Text.RegularExpressions;
思路：
a、先将html文本中的所有空格、换行符去掉（因为html中的空格和换行是被忽略的）
b、将<head>标记中的所有内容去掉
c、将<script>标记中的所有内容去掉
d、将<style>标记中的所有内容去掉
e、将td换成空格，tr,li,br,p 等标记换成换行符
f、去掉所有以“<>”符号为头尾的标记去掉。
g、转换&，&nbps;等转义字符换成相应的符号
h、去掉多余的空格和空行
?方法如下：???????
??????? /// <summary>
??????? /// 将HTML内容转换成纯文本形式，即去除HTML格式
??????? /// </summary>
??????? /// <param name="source"></param>
??????? /// <returns></returns>
??????? public static string ConvertToText(string source)
??????? {
??????????? string result;??????????? //remove line breaks,tabs
??????????? result = source.Replace("\r", " ");
??????????? result = result.Replace("\n", " ");
??????????? result = result.Replace("\t", " ");
??????????? //remove the header
??????????? result = Regex.Replace(result, "(<head>).*(</head>)", string.Empty, RegexOptions.IgnoreCase);
??????????? result = Regex.Replace(result, @"<( )*script([^>])*>", "<script>", RegexOptions.IgnoreCase);
??????????? result = Regex.Replace(result, @"(<script>).*(</script>)", string.Empty, RegexOptions.IgnoreCase);
??????????? //remove all styles
??????????? result = Regex.Replace(result, @"<( )*style([^>])*>", "<style>", RegexOptions.IgnoreCase); //clearing attributes
??????????? result = Regex.Replace(result, "(<style>).*(</style>)", string.Empty, RegexOptions.IgnoreCase);
??????????? //insert tabs in spaces of <td> tags
??????????? result = Regex.Replace(result, @"<( )*td([^>])*>", " ", RegexOptions.IgnoreCase);
??????????? //insert line breaks in places of <br> and <li> tags
??????????? result = Regex.Replace(result, @"<( )*br( )*>", "\r", RegexOptions.IgnoreCase);
??????????? result = Regex.Replace(result, @"<( )*li( )*>", "\r", RegexOptions.IgnoreCase);
??????????? //insert line paragraphs in places of <tr> and <p> tags
??????????? result = Regex.Replace(result, @"<( )*tr([^>])*>", "\r\r", RegexOptions.IgnoreCase);
??????????? result = Regex.Replace(result, @"<( )*p([^>])*>", "\r\r", RegexOptions.IgnoreCase);
??????????? //remove anything thats enclosed inside < >
??????????? result = Regex.Replace(result, @"<[^>]*>", string.Empty, RegexOptions.IgnoreCase);
??????????? //replace special characters:
??????????? result = Regex.Replace(result, @"&", "&", RegexOptions.IgnoreCase);
??????????? result = Regex.Replace(result, @" ", " ", RegexOptions.IgnoreCase);
??????????? result = Regex.Replace(result, @"<", "<", RegexOptions.IgnoreCase);
??????????? result = Regex.Replace(result, @">", ">", RegexOptions.IgnoreCase);
??????????? result = Regex.Replace(result, @"&(.{2,6});", string.Empty, RegexOptions.IgnoreCase);
??????????? //remove extra line breaks and tabs
??????????? result = Regex.Replace(result, @" ( )+", " ");
??????????? result = Regex.Replace(result, "(\r)( )+(\r)", "\r\r");
??????????? result = Regex.Replace(result, @"(\r\r)+", "\r\n");
??????????? //remove blank
??????????? result = Regex.Replace(result, @"\s", "");
??????????? return result;
??????? }
?
2、［取出文本中的图片地址］
程序代码
???????? {
????????????string str = string .Empty ;
????????????string sPattern = @ "^<img\s+[^>]*>" ;
????????????Regex r = new Regex (@ "<img\s+[^>]*\s*src\s*=\s*([']?)(?<url>\S+)'?[^>]*>" ,
????????????????RegexOptions 美国高防vps .Compiled ) ;
????????????Match m = r .Match (HTMLStr .ToLower ( ) ) ;
???????????? if (m .Success )
????????????????str = m .Result ( "${url}" ) ;
???????????? return str ;
???????? }
转载于:https://www.cnblogs.com/aminta/articles/1353846.html
73937600