C# 将 HTML 转换为图片或 PDF

首先是把 HTML 转换为图片。

public partial class Form1 : Form
    {
public Form1()
        {
            InitializeComponent();
        }

        WebBrowser webBrowser = null;

public void ConvertToImg()
        {
            webBrowser = new WebBrowser();

//是否显式滚动条
            webBrowser.ScrollBarsEnabled = false;

//加载HTML页面的地址
            webBrowser.Navigate("http://www.baidu.com");

//页面加载完成执行事件
            webBrowser.DocumentCompleted += new WebBrowserDocumentCompletedEventHandler(webBrowser_DocumentCompleted);
        }

private void webBrowser_DocumentCompleted(object sender, EventArgs e)//这个就是当网页载入完毕后要进行的操作
        {
//获取解析后HTML的大小
            System.Drawing.Rectangle rectangle = webBrowser.Document.Body.ScrollRectangle;
int width = rectangle.Width;
int height = rectangle.Height;

//设置解析后HTML的可视区域
            webBrowser.Width = width;
            webBrowser.Height = height;

            Bitmap bitmap = new System.Drawing.Bitmap(width, height);
            webBrowser.DrawToBitmap(bitmap, new System.Drawing.Rectangle(0, 0, width, height));

//设置图片文件保存路径和图片格式，格式可以自定义
string filePath = AppDomain.CurrentDomain.BaseDirectory + "../../SaveFIle/" + DateTime.Now.ToString("yyyyMMddHHmmssfff") + ".png";
            bitmap.Save(filePath, System.Drawing.Imaging.ImageFormat.Png);
        }

private void button1_Click(object sender, EventArgs e)
        {
            ConvertToImg();
        }
    }

上面这种方法是解析指定URL地址的HTML，然后转换为图片。当然，也可以直接写一些HTML标签。如下：

public partial class Form1 : Form
    {
public Form1()
        {
            InitializeComponent();
        }

        WebBrowser webBrowser = null;
public void ConvertToImg()
        {
string html = "<div><table border = \"1\" cellspacing = \"0\" cellpadding = \"3\" style = \"text-align:center;\"><tr><th style = \"width:60px;\">字段1</th><th style = \"width:60px;\">字段2</th><th style = \"width:60px;\">字段3</th></tr><tr style = \"color:green;\"><td>小明</td><td>22</td><td>185</td></tr><tr style = \"color:red;\"><td>小青</td><td>21</td><td>170</td></tr></table></div>";

            webBrowser = new WebBrowser();

//是否显式滚动条
            webBrowser.ScrollBarsEnabled = false;

//加载 html
            webBrowser.DocumentText = html;

//页面加载完成执行事件
            webBrowser.DocumentCompleted += new WebBrowserDocumentCompletedEventHandler(webBrowser_DocumentCompleted);
        }

private void webBrowser_DocumentCompleted(object sender, EventArgs e)//这个就是当网页载入完毕后要进行的操作
        {
//获取解析后HTML的大小
            System.Drawing.Rectangle rectangle = webBrowser.Document.Body.ScrollRectangle;
int width = rectangle.Width;
int height = rectangle.Height;

//设置解析后HTML的可视区域
            webBrowser.Width = width;
            webBrowser.Height = height;

            Bitmap bitmap = new System.Drawing.Bitmap(width, height);
            webBrowser.DrawToBitmap(bitmap, new System.Drawing.Rectangle(0, 0, width, height));

//设置图片文件保存路径和图片格式，格式可以自定义
string filePath = AppDomain.CurrentDomain.BaseDirectory + "../../SaveFIle/" + DateTime.Now.ToString("yyyyMMddHHmmssfff") + ".png";
            bitmap.Save(filePath, System.Drawing.Imaging.ImageFormat.Png);
        }

private void button1_Click(object sender, EventArgs e)
        {
            ConvertToImg();
        }
    }

 

然后把图片转换为PDF，这里需要用到 iTextSharp.dll 这个组件。

public partial class Form1 : Form
    {
public Form1()
        {
            InitializeComponent();
        }

        WebBrowser webBrowser = null;
public void ConvertToImg()
        {
string html = "<div><table border = \"1\" cellspacing = \"0\" cellpadding = \"3\" style = \"text-align:center;\"><tr><th style = \"width:60px;\">字段1</th><th style = \"width:60px;\">字段2</th><th style = \"width:60px;\">字段3</th></tr><tr style = \"color:green;\"><td>小明</td><td>22</td><td>185</td></tr><tr style = \"color:red;\"><td>小青</td><td>21</td><td>170</td></tr></table></div>";

            webBrowser = new WebBrowser();

//是否显式滚动条
            webBrowser.ScrollBarsEnabled = false;

//加载 html
            webBrowser.DocumentText = html;

//页面加载完成执行事件
            webBrowser.DocumentCompleted += new WebBrowserDocumentCompletedEventHandler(webBrowser_DocumentCompleted);
        }

private void webBrowser_DocumentCompleted(object sender, EventArgs e)//这个就是当网页载入完毕后要进行的操作
        {
//获取解析后HTML的大小
            System.Drawing.Rectangle rectangle = webBrowser.Document.Body.ScrollRectangle;
int width = rectangle.Width;
int height = rectangle.Height;

//设置解析后HTML的可视区域
            webBrowser.Width = width;
            webBrowser.Height = height;

            Bitmap bitmap = new System.Drawing.Bitmap(width, height);
            webBrowser.DrawToBitmap(bitmap, new System.Drawing.Rectangle(0, 0, width, height));

//设置图片文件保存路径和图片格式，格式可以自定义
string filePath = AppDomain.CurrentDomain.BaseDirectory + "../../SaveFIle/" + DateTime.Now.ToString("yyyyMMddHHmmssfff") + ".png";
            bitmap.Save(filePath, System.Drawing.Imaging.ImageFormat.Png);

//创建PDF
            FileStream fileStream = new FileStream(AppDomain.CurrentDomain.BaseDirectory + "../../SaveFIle/" + DateTime.Now.ToString("yyyyMMddHHmmssfff") + ".pdf", FileMode.Create);

byte[] result = CreatePDF(bitmap, width, height);

            fileStream.Write(result, 0, result.Length);

            fileStream.Close();
            fileStream.Dispose();
        }

private void button1_Click(object sender, EventArgs e)
        {
            ConvertToImg();
        }

public byte[] CreatePDF(Bitmap bitmap, int width, int height)
        {
using (MemoryStream ms = new MemoryStream())
            {
                Document doc = new Document(new iTextSharp.text.Rectangle(0, 0, width, height), 3, 3, 3, 3);    // 左右上下

                PdfWriter writer = PdfWriter.GetInstance(doc, ms);

                writer.CloseStream = false;

                doc.Open();

                iTextSharp.text.Image img = iTextSharp.text.Image.GetInstance(bitmap, System.Drawing.Imaging.ImageFormat.Png);

                img.ScalePercent(100);      // 放缩比例

                doc.Add(img);       // 添加图片对像
                doc.Close();

return ms.ToArray();
            }
        }
    }

不过这种生成图片之后再转成PDF，会造成像素的丢失，所以看起来要比图片模糊一点。

 

还有一种办法就是直接生成PDF，这里需要安装 ABCpdf。不过，这个是收费的。。。

public partial class Form1 : Form
    {
public Form1()
        {
            InitializeComponent();
        }

public void ConvertToPDF()
        {
string html = "<div><table border = \"1\" cellspacing = \"0\" cellpadding = \"3\" style = \"text-align:center;\"><tr><th style = \"width:60px;\">字段1</th><th style = \"width:60px;\">字段2</th><th style = \"width:60px;\">字段3</th></tr><tr style = \"color:green;\"><td>小明</td><td>22</td><td>185</td></tr><tr style = \"color:red;\"><td>小青</td><td>21</td><td>170</td></tr></table></div>";

//创建一个Doc对象
            Doc doc = new Doc();

//Rect默认是文档整个页面大小,这里的Inset表示将Rect左右留出15的空白,上下留出20的空白
            doc.Rect.Inset(15, 20);

//直接设置html
int docID = doc.AddHtml(html);

//设置URL
//int docID = doc.AddImageUrl("http://www.baidu.com");

//设置字体
            doc.AddFont("Arial");

while (true)
            {
//判断是否还有内容
if (!doc.Chainable(docID))
                {
break;
                }

//如果还有内容就添加一页
                doc.Page = doc.AddPage();

//根据ID添加内容并返回页面上该内容对应的新ID
                docID = doc.AddImageToChain(docID);
            }

string filePath = AppDomain.CurrentDomain.BaseDirectory + "../../SaveFIle/" + DateTime.Now.ToString("yyyyMMddHHmmssfff") + ".pdf";

            doc.Save(filePath);

            doc.Clear();
            doc.Dispose();
        }


private void button1_Click(object sender, EventArgs e)
        {
            ConvertToPDF();
        }

    }