tidy实现html文件转化为xml（tidy.dll实现方式）(原创)
using System;
using System.Data;
using System.Configuration;
using System.Web;
using System.Web.Security;
using System.Web.UI;
using System.Web.UI.WebControls;
using System.Web.UI.WebControls.WebParts;
using System.Web.UI.HtmlControls;
using System.Xml;
using System.Text;
using System.Data.SqlClient;
using System.IO;
using System.Text.RegularExpressions;
public partial class CreateNewsXML : System.Web.UI.Page
{
protected void Page_Load(object sender, EventArgs e)
{
if (!Page.IsPostBack)
{
string path = "C:\\NewsXML";
//美食
writeNewsXML("269", path + "cy.xml");
Response.Write("生成成功");
// <a>
//<xsl:attribute name="href">
// <xsl:value-of select="link"/>
//</xsl:attribute>
// <xsl:value-of select="link"/>
//</a>
}
}
public void writeNewsXML(string typeID,string file)
{
string strSql = @"select top 100 news.* where news_type" + typeID + " ";
StringBuilder sb = new StringBuilder();
sb.Append("<?xml version=\"1.0\" encoding=\"gb2312\"?>");
sb.Append("<document>");
sb.Append("<website>www.jmw.com.cn</website>");
sb.Append("<webMaster>pc_lijiaming@jmw.com.cn</webMaster>");
sb.Append("<updatePeri>15</updatePeri>");
using (SqlConnection con = new SqlConnection(PriorJoin.News.DBConnect.JMWDB))
{
con.Open();
SqlCommand command = new SqlCommand(strSql, con);
command.CommandType = CommandType.Text;
DataSet ds = new DataSet("DATASET");
SqlDataAdapter sda = new SqlDataAdapter();
sda.SelectCommand = command;
sda.Fill(ds, "DATATABLE");
DataTable dt = ds.Tables[0];
for (int i = 0; i < dt.Rows.Count; i++)
{
sb.Append("<item>");
if (dt.Rows[i]["title"]!=null)
sb.Append("<title>" + Convert(dt.Rows[i]["title"].ToString()) + "</title>");
if (dt.Rows[i]["filename"]!=null)
sb.Append("<linkURL>" + GetLinkStr(dt.Rows[i]["filename"].ToString()) + "</linkURL>");
if (dt.Rows[i]["description"].ToString() != null)
sb.Append("<description>" + GetSubStr(100, dt.Rows[i]["description"].ToString()) + "</description>");
if (dt.Rows[i]["content"]!=null)
sb.Append("<text>" + Convert(dt.Rows[i]["content"].ToString()) + "</text>");
if (dt.Rows[i]["topimg"]!=null)
sb.Append("<image>" + dt.Rows[i]["topimg"] + "</image>");
if (dt.Rows[i]["sname"]!=null)
sb.Append("<category>" + dt.Rows[i]["sname"] + "</category>");
if (dt.Rows[i]["uptime"]!=null)
sb.Append("<pubDate>" + DateTime.Parse(dt.Rows[i]["uptime"].ToString()).ToString("yyyy-MM-dd HH:mm") + "</pubDate>");
if (dt.Rows[i]["author"]!=null)
sb.Append("<author>" + dt.Rows[i]["author"] + "</author>");
sb.Append("</item>");
}
}
sb.Append("</document>");
//tidy实现补全或剔除html特殊字符
HtmlAgilityPack.HtmlDocument htmlDoc = new HtmlAgilityPack.HtmlDocument();
htmlDoc.OptionOutputAsXml = true;
htmlDoc.LoadHtml(sb.ToString());
StringBuilder sbXml = new StringBuilder();
StringWriter sw = new StringWriter(sbXml);
htmlDoc.Save(sw);
//写入文件
WriteFile(file, sbXml.ToString());
}
protected bool WriteFile(string path, string _value)
{
StreamWriter sr = new StreamWriter(path, false, Encoding.Default);
try
{
sr.Write(_value.ToString());
return true;
}
catch
{
return false;
}
finally
{
sr.Close();
}
}
protected string GetLinkStr(string link)
{
return link.Replace(".htm", ".shtml");
}
protected string GetSubStr(int len,string str)
{
if (str.Length > len)
return str.Substring(0, len);
return str;
}
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");
result = Regex.Replace(result, @"([imga]).*([/imga])", "");
result = Regex.Replace(result, @"([img).*([/img])", "");
result = Regex.Replace(result, @"[COLOR=red]","");
result = Regex.Replace(result, @"[/COLOR]", "");
return result;
}
}
浙公网安备 33010602011771号