C # generates PDFs based on HTML

Http://www.cnblogs.com/kongxiaoshuang/p/6347565.html

http://blog.csdn.net/zhang116868/article/details/44879401

Using the Itextsharp control

Using System;
Using System.Collections.Generic;

Using System.Web;
Using System.Web.UI;
Using System.Web.UI.WebControls;
Using Itextsharp.text;
Using ITextSharp.text.pdf;
Using System.IO;
Using ITextSharp.tool.xml;
Using System.Text;
Using System.Net;

Namespace Pdftools
{
public partial class CreatePdf:System.Web.UI.Page
{
String inpath = System.Web.HttpContext.Current.Server.MapPath ("~/bin/temp.html");

protected void Page_Load (object sender, EventArgs e)
{
String path = System.Web.HttpContext.Current.Server.MapPath ("~/uploadpdf");
if (! Directory.Exists (PATH))
Directory.CreateDirectory (path);

WebClient WC = new WebClient ();
Download the HTML string from the URL
Wc. Encoding = System.Text.Encoding.UTF8;
String htmltext = Getwebcontent ();
Byte[] Pdffile = this. Converthtmltexttopdf (HTMLText);

String fileId = "/file_" + DateTime.Now.ToString ("YYYYMMDDHHMMSS") + ". pdf";
System.IO.File.WriteAllBytes (path + fileId, pdffile);
}

<summary>
Determine if there are garbled characters
</summary>
<param name= "TXT" ></param>
<returns></returns>
public bool Ismessycode (string txt)
{
var bytes = Encoding.UTF8.GetBytes (TXT); 239 191 189
for (var i = 0; i < bytes. Length; i++)
{
if (I < bytes. Length-3)
if (bytes[i] = = 239 && bytes[i + 1] = = 191 && bytes[i + 2] = = 189)
{
return true;
}
}
return false;
}
<summary>
Get the content of the website, including HTML+CSS+JS
</summary>
<returns>string back to Web information </returns>
public string getwebcontent ()
{
Try
{
WebClient mywebclient = new WebClient ();
Mywebclient.credentials = CredentialCache.DefaultCredentials;
Gets or sets the network credentials that are used to authenticate requests to Internet resources
byte[] Pagedata = Mywebclient.downloaddata (Inpath);
Download data from a specified Web site
String pagehtml = Encoding.UTF8.GetString (pagedata);
If you are using GB2312 to get a website page, use this sentence
BOOL Isbool = Ismessycode (pagehtml);//determine which encoding to use to read Web page information
if (!isbool)
{
String pageHtml1 = Encoding.UTF8.GetString (pagedata);
pagehtml = PAGEHTML1;
}
Else
{
String pageHtml2 = Encoding.Default.GetString (pagedata);
pagehtml = PAGEHTML2;
}
return pagehtml;
}

catch (WebException webEx)
{
Console.WriteLine (WebEx.Message.ToString ());
return webex.message;
}
}


<summary>
Output HTML text to a PDF file
</summary>
<param name= "HTMLText" ></param>
<returns></returns>
Public byte[] Converthtmltexttopdf (string htmltext)
{
if (string. IsNullOrEmpty (HTMLText))
{
return null;
}
Avoid htmltext when the text is not in any HTML tag tag, when you go to PDF, it hangs, so add <p> tag
HTMLText = "<p>" + htmltext + "</p>";

MemoryStream outputstream = new MemoryStream ();//to which stream to write the PDF
byte[] data = Encoding.UTF8.GetBytes (htmltext);//string turns into byte[]
MemoryStream msinput = new MemoryStream (data);
Document doc = new document ();//To write a PDF file, the constructor is not filled with the pre-set straight A4
PDFWriter writer = pdfwriter.getinstance (doc, OutputStream);
Specifies that the file preset is scaled to 100% when it is opened

Pdfdestination pdfdest = new Pdfdestination (pdfdestination.xyz, 0, Doc. Pagesize.height, 1f);
Open Document File
Doc. Open ();

Use Xmlworkerhelper to parse HTML into PDF file
Xmlworkerhelper.getinstance (). Parsexhtml (writer, doc, msinput, NULL, Encoding.UTF8, New Unicodefontfactory ());
Xmlworkerhelper.getinstance (). Parsexhtml (writer, doc, msinput, NULL, ENCODING.UTF8);

Write the pdfdest data to a PDF file
Pdfaction action = pdfaction.gotolocalpage (1, pdfdest, writer);
Writer. Setopenaction (action);
Doc. Close ();
Msinput.close ();
Outputstream.close ();
return PDF file
return Outputstream.toarray ();

}

Set the Font class
public class Unicodefontfactory:fontfactoryimp
{
private static readonly String Arialfontpath = Path.Combine (Environment.getfolderpath ( Environment.SpecialFolder.Fonts),
"Arialuni.ttf");//arial Unicode MS is the complete Unicode font.
private static readonly string marked in italics Path = Path.Combine (Environment.getfolderpath (Environment.SpecialFolder.Fonts),
"Kaiu. TTF ");//mark in italics


public override Font GetFont (string fontname, string encoding, bool embedded, float size, int style, basecolor color, bool Cached
{
Basefont bfchiness = Basefont.createfont (@ "C:\Windows\Fonts\SIMSUN. ttc,1 ", Basefont.identity_h, basefont.not_embedded);
Use Arial or italic, choose one of your own
Basefont Basefont = Basefont.createfont (marked in italics path, basefont.identity_h, basefont.embedded);
return new Font (bfchiness, size, style, color);
}
}
}
}

C # generates PDFs based on HTML