如何提取一个页面中所有的文字（纯文字，排除图片 、链接、html 标签）

Question

thanks!

Answer 1

/// <summary>
    /// 去掉html标记
    /// </summary>
    /// <param name="str"></param>
    /// <returns></returns>
    protected static string ConvertGettext(string str)
    {
        Regex regex = new Regex(@"\<(.*?)\>", RegexOptions.IgnoreCase);        return regex.Replace(str, "").Replace("&nbsp;", "").Replace("\n", "").Replace("\r", "");
    } 
具体情况你可以发个示例来看看

Answer 2

http://topic.csdn.net/u/20110508/21/b00b79a9-c90b-4a01-8ab6-225243547d04.html

Answer 3

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Net;
using System.IO;
using System.IO.Compression;
using System.Text.RegularExpressions;namespace WikiPageCreater.Common
{
    public class PageHelper
    {
        /// <summary>
        /// 根据 url 获取网页编码
        /// </summary>
        /// <param name="url"></param>
        /// <returns></returns>
        public static string GetEncoding(string url)
        {
            HttpWebRequest request = null;
            HttpWebResponse response = null;
            StreamReader reader = null;
            try
            {
                request = (HttpWebRequest)WebRequest.Create(url);
                request.Timeout = 20000;
                request.AllowAutoRedirect = false;                response = (HttpWebResponse)request.GetResponse();
                if (response.StatusCode == HttpStatusCode.OK && response.ContentLength < 1024 * 1024)
                {
                    if (response.ContentEncoding != null && response.ContentEncoding.Equals("gzip", StringComparison.InvariantCultureIgnoreCase))
                        reader = new StreamReader(new GZipStream(response.GetResponseStream(), CompressionMode.Decompress));
                    else
                        reader = new StreamReader(response.GetResponseStream(), Encoding.ASCII);                    string html = reader.ReadToEnd();                    Regex reg_charset = new Regex(@"charset\b\s*=\s*(?<charset>[^""]*)");
                    if (reg_charset.IsMatch(html))
                    {
                        return reg_charset.Match(html).Groups["charset"].Value;
                    }
                    else if (response.CharacterSet != string.Empty)
                    {
                        return response.CharacterSet;
                    }
                    else
                        return Encoding.Default.BodyName;
                }
            }
            catch
            {
            }
            finally
            {                if (response != null)
                {
                    response.Close();
                    response = null;
                }
                if (reader != null)
                    reader.Close();                if (request != null)
                    request = null;            }            return Encoding.Default.BodyName;
        }        /// <summary>
        /// 根据 url 和 encoding 获取当前url页面的 html 源代码        
       /// </summary>
        /// <param name="url"></param>
        /// <param name="encoding"></param>
        /// <returns></returns>
        public static string GetHtml(string url, Encoding encoding)
        {
            HttpWebRequest request = null;
            HttpWebResponse response = null;
            StreamReader reader = null;
            try
            {
                request = (HttpWebRequest)WebRequest.Create(url);
                request.Timeout = 20000;
                request.AllowAutoRedirect = false;                response = (HttpWebResponse)request.GetResponse();
                if (response.StatusCode == HttpStatusCode.OK && response.ContentLength < 1024 * 1024)
                {
                    if (response.ContentEncoding != null && response.ContentEncoding.Equals("gzip", StringComparison.InvariantCultureIgnoreCase))
                        reader = new StreamReader(new GZipStream(response.GetResponseStream(), CompressionMode.Decompress), encoding);
                    else
                        reader = new StreamReader(response.GetResponseStream(), encoding);
                    string html = reader.ReadToEnd();                    return html;
                }
            }
            catch
            {
            }
            finally
            {                if (response != null)
                {
                    response.Close();
                    response = null;
                }
                if (reader != null)
                    reader.Close();                if (request != null)
                    request = null;            }            return string.Empty;
        }
    }
}然后正则取

Answer 4

-----------------
具体情况是这样的 想调用微软的翻译实现多国语言
一次传输太多内容会翻译不了，想把需要翻译的内容，分成几段传输过去
想把网页生成的html中需要翻译的内容提取出来，然后再翻译 

Answer 5

protected static string ConvertGettext(string str)
    {
        Regex regex = new Regex(@"\<(.*?)\>", RegexOptions.IgnoreCase);        return regex.Replace(str, "").Replace("&nbsp;", "").Replace("\n", "").Replace("\r", "");
    }

Answer 6

 public static string DropHTML(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);
            Htmlstring.Replace("<", "");
            Htmlstring.Replace(">", "");
            Htmlstring.Replace("\r\n", "");
            Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
            return Htmlstring;
        }