在網頁剛流行起來的時候，提取html中的文本有一個簡單的方法，就是將html文本（包含標記）中的所有以“<”符號開頭到以“>”符號之間的內容去掉即可。
但對於現在複雜的網頁而言，用這種方法提取出來的文本會有大量的空格、空行、script段落、還有一些html轉義字符，效果很差。
下面用正則表達式來提取html中的文本，
代碼的實現的思路是：
a、先將html文本中的所有空格、換行符去掉（因爲html中的空格和換行是被忽略的）
b、將<head>標記中的所有內容去掉
c、將<script>標記中的所有內容去掉
d、將<style>標記中的所有內容去掉
e、將td換成空格，tr,li,br,p 等標記換成換行符
f、去掉所有以“<>”符號爲頭尾的標記去掉。
g、轉換&，&nbps;等轉義字符換成相應的符號
h、去掉多餘的空格和空行
代碼如下：
using System;
using System.Text.RegularExpressions;
namespace Kwanhong.Utilities
{
/// <summary>
/// HtmlToText 的摘要說明。
/// </summary>
public class HtmlToText
{
public string Convert(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");
return result;
}
}//end class
}//end namespace
using System.Text.RegularExpressions;
namespace Kwanhong.Utilities
{
/// <summary>
/// HtmlToText 的摘要說明。
/// </summary>
public class HtmlToText
{
public string Convert(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");
return result;
}
}//end class
}//end namespace