C# 用itextsharp把Html转PDF

逃离我推掉我的手 2022-05-19 11:27 329阅读 0赞

首先得下载itextsharp

有两个dll, itextsharp.dll和itextsharp.xmlworker.dll

一、新建一个HtmlToPdfHelper类

namespace ClassLibrary1
    {
        /// <summary>
        /// HTML转PDF帮助类
        /// </summary>
        public class HtmlToPdfHelper
        {
            /// <summary>
            /// 准备好的html字符串
            /// </summary>
            private string m_HtmlString;
    
            /// <summary>
            /// PDF保存目录（绝对路径）
            /// </summary>
            private string m_PDFSaveFloder;
    
            /// <summary>
            /// 图片XY字典，例如 [{img1, 100,200},{img2,20,30}}
            /// </summary>
            private Dictionary<string, Tuple<float, float>> m_ImageXYDic = null;
    
            public HtmlToPdfHelper(string htmlString, string pdfSaveFloder, Dictionary<string, Tuple<float, float>> imageXYDic)
            {
                m_HtmlString = htmlString;
                m_PDFSaveFloder = pdfSaveFloder;
                m_ImageXYDic = imageXYDic;
            }
    
            //生成PDF
            public bool BuilderPDF()
            {
                try
                {
                    string pdfSavePath = Path.Combine(m_PDFSaveFloder, Guid.NewGuid().ToString()+".pdf");
                    if (!Directory.Exists(m_PDFSaveFloder))
                    {
                        Directory.CreateDirectory(m_PDFSaveFloder);
                    }
                    using (FileStream fs = new FileStream(pdfSavePath, FileMode.OpenOrCreate))
                    {
                        byte[] htmlByte = ConvertHtmlTextToPDF(m_HtmlString);
                        fs.Write(htmlByte, 0, htmlByte.Length);
                        return true;
                    }
                }
                catch (Exception ex)
                {
                    throw new ApplicationException("保存PDF到磁盘时异常", ex);
                }
            }
    
            //将html字符串转为字节数组（代码来自百度）
            private byte[] ConvertHtmlTextToPDF(string htmlText)
            {
                if (string.IsNullOrEmpty(htmlText))
                {
                    return null;
                }
                //避免當htmlText無任何html tag標籤的純文字時，轉PDF時會掛掉，所以一律加上<p>標籤
                //htmlText = "<p>" + htmlText + "</p>";
    
                try
                {
                    MemoryStream outputStream = new MemoryStream(); //要把PDF寫到哪個串流
                    byte[] data = Encoding.UTF8.GetBytes(htmlText); //字串轉成byte[]
                    MemoryStream msInput = new MemoryStream(data);
                    Document doc = new Document(); //要寫PDF的文件，建構子沒填的話預設直式A4
                    PdfWriter writer = PdfWriter.GetInstance(doc, outputStream);  
    
                    //指定文件預設開檔時的縮放為100%
                    PdfDestination pdfDest = new PdfDestination(PdfDestination.XYZ, 0, doc.PageSize.Height, 1f);
                    //開啟Document文件 
                    doc.Open();
    
                    #region 图片的处理
                    CssFilesImpl cssFiles = new CssFilesImpl();
                    cssFiles.Add(XMLWorkerHelper.GetInstance().GetDefaultCSS());
                    var cssResolver = new StyleAttrCSSResolver(cssFiles);
    
                    var tagProcessors = (DefaultTagProcessorFactory)Tags.GetHtmlTagProcessorFactory();
                    tagProcessors.RemoveProcessor(HTML.Tag.IMG); // remove the default processor
                    tagProcessors.AddProcessor(HTML.Tag.IMG, new CustomImageTagProcessor(m_ImageXYDic)); // use new processor
    
                    var hpc = new HtmlPipelineContext(new CssAppliersImpl(new XMLWorkerFontProvider()));
                    hpc.SetAcceptUnknown(true).AutoBookmark(true).SetTagFactory(tagProcessors); // inject the tagProcessors
    
                    var charset = Encoding.UTF8;
                    var htmlPipeline = new HtmlPipeline(hpc, new PdfWriterPipeline(doc, writer));
                    var pipeline = new CssResolverPipeline(cssResolver, htmlPipeline);
                    var worker = new XMLWorker(pipeline, true);
                    var xmlParser = new XMLParser(true, worker, charset);
                    xmlParser.Parse(new StringReader(htmlText));
                    #endregion
    
                    //使用XMLWorkerHelper把Html parse到PDF檔裡
                    XMLWorkerHelper.GetInstance().ParseXHtml(writer, doc, msInput, null, Encoding.UTF8, new UnicodeFontFactory());
    
                    //將pdfDest設定的資料寫到PDF檔
                    PdfAction action = PdfAction.GotoLocalPage(1, pdfDest, writer);
                    writer.SetOpenAction(action);
    
                    doc.Close();
                    msInput.Close();
                    outputStream.Close();
    
                    return outputStream.ToArray();
                }
                catch (Exception ex)
                {
                    throw new ApplicationException("转PDF时异常", ex);
                }
            }
    
            //字体工厂（代码来自百度）
            public class UnicodeFontFactory : FontFactoryImp
            {
                private static readonly string arialFontPath = Path.Combine(AppDomain.CurrentDomain.BaseDirectory
                    , "Content/arialuni.ttf");//arial unicode MS是完整的unicode字型。
    
                public override Font GetFont(string fontname, string encoding, bool embedded, float size, int style, BaseColor color,
                    bool cached)
                {
                    BaseFont baseFont = BaseFont.CreateFont(arialFontPath, BaseFont.IDENTITY_H, BaseFont.EMBEDDED);
                    return new Font(baseFont, size, style, color);
                }
            }
    
            //自定义的图片处理类（代码来自百度）
            public class CustomImageTagProcessor : iTextSharp.tool.xml.html.Image
            {
                //个人加入的图片位置处理代码
                private float _offsetX=0;
                private float _offsetY=0;
    
                private Dictionary<string, Tuple<float, float>> _imageXYDict;//个人加入的图片位置处理代码
                public CustomImageTagProcessor(Dictionary<string, Tuple<float, float>> imageXYDict)//个人加入的图片位置处理代码
                {
                    _imageXYDict = imageXYDict;
                }
    
                protected void SetImageXY(string imageId)//个人加入的图片位置处理代码
                {
                    if (_imageXYDict == null)
                    {
                        return;
                    }
                    Tuple<float, float> xyTuple = null;
                    _imageXYDict.TryGetValue(imageId, out xyTuple);
    
                    if (xyTuple != null)
                    {
                        _offsetX = xyTuple.Item1;
                        _offsetY = xyTuple.Item2;
                    }
                }
    
                public override IList<IElement> End(IWorkerContext ctx, Tag tag, IList<IElement> currentContent)
                {
                    IDictionary<string, string> attributes = tag.Attributes;
                    string src;
                    if (!attributes.TryGetValue(HTML.Attribute.SRC, out src))
                        return new List<IElement>(1);
    
                    if (string.IsNullOrEmpty(src))
                        return new List<IElement>(1);
    
                    string imageId;//个人加入的图片位置处理代码
                    if (!attributes.TryGetValue(HTML.Attribute.ID, out imageId))//个人加入的图片位置处理代码
                        return new List<IElement>(1);
    
                    if (string.IsNullOrEmpty(imageId))
                        return new List<IElement>(1);
    
                    SetImageXY(imageId);//个人加入的图片位置处理代码
    
                    if (src.StartsWith("data:image/", StringComparison.InvariantCultureIgnoreCase))
                    {
                        // data:[][;charset=][;base64],
                        var base64Data = src.Substring(src.IndexOf(",") + 1);
                        var imagedata = Convert.FromBase64String(base64Data);
                        var image = iTextSharp.text.Image.GetInstance(imagedata);
    
                        var list = new List<IElement>();
                        var htmlPipelineContext = GetHtmlPipelineContext(ctx);
                        list.Add(GetCssAppliers().Apply(new Chunk((iTextSharp.text.Image)GetCssAppliers().Apply(image, tag, htmlPipelineContext), _offsetX, _offsetY, true), tag, htmlPipelineContext));
                        return list;
                    }
                    else
                    {
                        return base.End(ctx, tag, currentContent);
                    }
                }
            }
        }
    }

二、新建一个测式类

namespace ClassLibrary1
    {
        /// <summary>
        /// 测试类
        /// </summary>
        public class PersonEntity
        {
            /// <summary>
            /// html模版绝对路径
            /// </summary>
            public string m_HtmlTemplatePath = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, "Scripts/person.html");
    
            /// <summary>
            /// PDF生成的目录（绝对路径）
            /// </summary>
            public string m_PdfSaveFolder = Path.Combine(AppDomain.CurrentDomain.BaseDirectory,"PDFFolder");
    
            public PersonEntity()
            {
            }
    
            /// <summary>
            /// 生成PDF
            /// </summary>
            public void BuildPDF()
            {
      
                using (StreamReader reader = new StreamReader(m_HtmlTemplatePath))
                {
                    string htmlStr = reader.ReadToEnd();//读取html模版
    
                    string iamgeBase64Str1 = ImageToBase64String(Path.Combine(AppDomain.CurrentDomain.BaseDirectory, "Scripts/img1.jpg"));
                    string iamgeBase64Str2 = ImageToBase64String(Path.Combine(AppDomain.CurrentDomain.BaseDirectory, "Scripts/img2.jpg"));
    
                    htmlStr = htmlStr.Replace("@PersonName", "张三");
                    htmlStr = htmlStr.Replace("@PersonImage1", iamgeBase64Str1);
                    htmlStr = htmlStr.Replace("@PersonImage2", iamgeBase64Str2);
    
                    Dictionary<string, Tuple<float, float>> imageXYDic = new Dictionary<string, Tuple<float, float>>();
                    imageXYDic.Add("img1", new Tuple<float,float>(10,20));
                    imageXYDic.Add("img2", new Tuple<float, float>(200, 300));
    
                    HtmlToPdfHelper pdfHelper = new HtmlToPdfHelper(htmlStr, m_PdfSaveFolder, imageXYDic);
    
                    pdfHelper.BuilderPDF();//生成PDF
                }
            }
    
            //图片转为base64字符串
            public string ImageToBase64String(string imagePath)
            {
                try
                {
                    Bitmap bitmap = new Bitmap(imagePath);
    
                    MemoryStream ms = new MemoryStream();
    
                    bitmap.Save(ms, ImageFormat.Jpeg);
                    byte[] bytes = new byte[ms.Length];
    
                    ms.Position = 0;
                    ms.Read(bytes, 0, (int) ms.Length);
                    ms.Close();
    
                    return Convert.ToBase64String(bytes);
                }
                catch (Exception ex)
                {
                    throw new ApplicationException("图片转base64字符串时异常", ex);
                }
            }
        }
    }

三、在网站的Scripts目录下添加person.htm 模版

<!DOCTYPE html>
    <html>
    <head>
        <meta charset="utf-8" />
        <title></title>
    </head>
    <body>
    <p>@PersonName</p>
    <table border="1px">
        <tr>
            <td>
                <img id="img1" src="data:image/jpeg;base64,@PersonImage1" style="width: 50px; height: 50px;"/>
            </td>
        </tr>
    </table>
    
    <img id="img2" src="data:image/jpeg;base64,@PersonImage2" style="width: 50px; height: 50px;" />
    </body>
    </html>

四、在网站的Scripts目录下添加img1.jpg和imag2.jpg两张图片，在Content目录下添加从百度找的字体arialuni.ttf

五、在Default.aspx界面写入调用代码

public partial class _Default : Page
    {
        protected void Page_Load(object sender, EventArgs e)
        {
            PersonEntity personEntity = new PersonEntity();
            personEntity.BuildPDF();
        }
    }

六、运行Default.aspx页面后，将在网站目录PDFFolder中生成了一个PDF，效果如下图

![70][]

七、源码在我上传的CSDN资源中 [https://download.csdn.net/download/junshangshui/10561974][https_download.csdn.net_download_junshangshui_10561974]

[70]: /images/20220519/97874b25c01b4f0ebf95899035bcaf08.png
[https_download.csdn.net_download_junshangshui_10561974]: https://download.csdn.net/download/junshangshui/10561974