一、 需求：将HTML转PDF打印。Web项目中总是有这样的需求，很是让人苦恼。
二、 分析：如何完成这个工作？
1、 需要解析HTML，然后利用itextsharp绘制pdf文档。解析HTML是一个很难完成的任务，各个浏览器对HTML的解析五花八门就知道这不好解决。这条路不好走，但也是可以完成的，通过webbrowser类可以解析HTML获取各对象的位置，然后绘制到pdf中。方法是可行，其中的复杂度不小。
2、 将HTML保存为图片，然后插入到pdf文档中，这里将介绍这种方法。随之而来的问题：如何将HTML保存为图片呢？
三、 解决办法：
1、 将HTML保存为图片：需要用到webbrower类，将指定的HTML载入webbrower，然后调用其DrawToBitmap方法获取图片。代码如下：
private System.Drawing.Bitmap bitmap;
private string url;
private int w = 760, h = 900;//A4纸张对应的分辨率大概就是760*900
public void setBitmap()
{
using (WebBrowser wb = new WebBrowser())
{
wb.Width = w;
wb.Height = h;
wb.ScrollBarsEnabled = false;
wb.Navigate(url);
//确保页面被解析完全
while (wb.ReadyState != WebBrowserReadyState.Complete)
{
System.Windows.Forms.Application.DoEvents();
}
bitmap = new System.Drawing.Bitmap(w, h);
wb.DrawToBitmap(bitmap, new System.Drawing.Rectangle(0, 0, w, h));
wb.Dispose();
}
}
using System;
using System.Data;
using System.Web;
using iTextSharp.text.pdf;
using iTextSharp.text;
using System.IO;
using System.Windows.Forms;
using System.Threading;
public partial class HTML2PDF : System.Web.UI.Page
{
protected void Page_Load(object sender, EventArgs e)
{
}
protected void Button1_Click(object sender, EventArgs e)
{
CreatPdf();
}
private System.Drawing.Bitmap bitmap;
private string url;
private int w = 760, h = 900;
public void setBitmap()
{
using (WebBrowser wb = new WebBrowser())
{
wb.Width = w;
wb.Height = h;
wb.ScrollBarsEnabled = false;
wb.Navigate(url);
//确保页面被解析完全
while (wb.ReadyState != WebBrowserReadyState.Complete)
{
System.Windows.Forms.Application.DoEvents();
}
bitmap = new System.Drawing.Bitmap(w, h);
wb.DrawToBitmap(bitmap, new System.Drawing.Rectangle(0, 0, w, h));
wb.Dispose();
}
}
private void CreatPdf()
{
Document doc = new Document(PageSize.A4, 9, 18, 36, 36);//左右上下
MemoryStream ms = new MemoryStream();
try
{
PdfWriter writer = PdfWriter.GetInstance(doc, ms);
writer.CloseStream = false;
doc.Open();
url = Server.MapPath("s.html");
Thread thread = new Thread(new ThreadStart(setBitmap));
thread.SetApartmentState(ApartmentState.STA);
thread.Start();
while (thread.IsAlive)
Thread.Sleep(100);
bitmap.Save(Server.MapPath("t.bmp"));
?
iTextSharp.text.Image img = iTextSharp.text.Image.GetInstance(bitmap, System.Drawing.Imaging.ImageFormat.Bmp);
img.ScalePercent(75);//560 630
doc.Add(img);
}
catch (Exception err)
{
throw new Exception(err.Message);
}
finally
{
doc.Close();
using (FileStream fs = new FileStream(Server.MapPath("out.pdf"), FileMode.Create))
{
ms.Position = 0;
byte[] bit = new byte[ms.Length];
ms.Read(bit, 0, (int)ms.Length);
fs.Write(bit, 0, bit.Length);
}
ViewPdf(ms);
}
}
private void ViewPdf(Stream fs)
{
Response.Clear();
//中文名的话
//Response.AppendHeader("Content-Disposition", "attachment;filename=" +
// HttpUtility.UrlEncode(fileName, System.Text.Encoding.UTF8) + ";charset=GB2312");
Response.AddHeader("Content-Disposition", "attachment;FileName=out.pdf");
Response.AddHeader("Content-Length", fs.Length.ToString());
Response.ContentType = "application/pdf";
long fileLength = fs.Length;
int size = 10240;//10K一--分块下载，10K为1块
byte[] readData = new byte[size];
if (size > fileLength)
size = Convert.ToInt32(fileLength);
long fPos = 0;
bool isEnd = false;
while (!isEnd)
{
if ((fPos + size) >= fileLength)
{
size = Convert.ToInt32(fileLength - fPos);
isEnd = true;
}
readData = new byte[size];
fs.Position = fPos;
fs.Read(readData, 0, size);
Response.BinaryWrite(readData);
Response.OutputStream.Flush();
fPos += size;
}
fs.Close();
Response.OutputStream.Close();
Response.End();//非常重要，没有这句的话，页面的HTML代码将会保存到文件中
Response.Close();
}
}
- 本文标题： 如何将html转成PDF文件
- 文章分类：【.NET/Web】
- 非特殊说明，本文版权归【胡同里的砖头】个人博客 所有，转载请注明出处.