我想通过将HTML内容传递给函数来生成PDF。我已经为此使用了iTextSharp,但它在遇到表和布局时表现不佳。

有没有更好的办法?


当前回答

下面是一个使用iTextSharp将html + css转换为PDF的示例(iTextSharp + iTextSharp .xmlworker)

using iTextSharp.text;
using iTextSharp.text.pdf;
using iTextSharp.tool.xml;


byte[] pdf; // result will be here

var cssText = File.ReadAllText(MapPath("~/css/test.css"));
var html = File.ReadAllText(MapPath("~/css/test.html"));

using (var memoryStream = new MemoryStream())
{
        var document = new Document(PageSize.A4, 50, 50, 60, 60);
        var writer = PdfWriter.GetInstance(document, memoryStream);
        document.Open();

        using (var cssMemoryStream = new MemoryStream(System.Text.Encoding.UTF8.GetBytes(cssText)))
        {
            using (var htmlMemoryStream = new MemoryStream(System.Text.Encoding.UTF8.GetBytes(html)))
            {
                XMLWorkerHelper.GetInstance().ParseXHtml(writer, document, htmlMemoryStream, cssMemoryStream);
            }
        }

        document.Close();

        pdf = memoryStream.ToArray();
}

其他回答

HTML到PDF的转换大多依赖于IE来完成HTML的解析和渲染。这可以打破用户更新他们的IE。这里有一个不依赖IE的。

代码是这样的:

EO.Pdf.HtmlToPdf.ConvertHtml(htmlText, pdfFileName);

像许多其他转换器一样,您可以传递文本、文件名或Url。结果可以保存到文件或流中。

你可以使用WebBrowser控件的另一个技巧,下面是我的完整工作代码

在我的例子中,为文本框控件分配Url

  protected void Page_Load(object sender, EventArgs e)
{

   txtweburl.Text = "https://www.google.com/";

 }

下面是使用线程生成屏幕的代码

  protected void btnscreenshot_click(object sender, EventArgs e)
  {
    //  btnscreenshot.Visible = false;
    allpanels.Visible = true;
    Thread thread = new Thread(GenerateThumbnail);
    thread.SetApartmentState(ApartmentState.STA);
    thread.Start();
    thread.Join();

}

private void GenerateThumbnail()
{
    //  btnscreenshot.Visible = false;
    WebBrowser webrowse = new WebBrowser();
    webrowse.ScrollBarsEnabled = false;
    webrowse.AllowNavigation = true;
    string url = txtweburl.Text.Trim();
    webrowse.Navigate(url);
    webrowse.Width = 1400;
    webrowse.Height = 50000;

    webrowse.DocumentCompleted += webbrowse_DocumentCompleted;
    while (webrowse.ReadyState != WebBrowserReadyState.Complete)
    {
        System.Windows.Forms.Application.DoEvents();
    }
}

在下面的代码中,我下载后保存pdf文件

        private void webbrowse_DocumentCompleted(object sender, WebBrowserDocumentCompletedEventArgs e)
{
    // btnscreenshot.Visible = false;
    string folderPath = Server.MapPath("~/ImageFiles/");

    WebBrowser webrowse = sender as WebBrowser;
    //Bitmap bitmap = new Bitmap(webrowse.Width, webrowse.Height);

    Bitmap bitmap = new Bitmap(webrowse.Width, webrowse.Height, PixelFormat.Format16bppRgb565);

    webrowse.DrawToBitmap(bitmap, webrowse.Bounds);


    string Systemimagedownloadpath = System.Configuration.ConfigurationManager.AppSettings["Systemimagedownloadpath"].ToString();
    string fullOutputPath = Systemimagedownloadpath + Request.QueryString["VisitedId"].ToString() + ".png";
    MemoryStream stream = new MemoryStream();
    bitmap.Save(fullOutputPath, System.Drawing.Imaging.ImageFormat.Jpeg);



    //generating pdf code 
     Document pdfDoc = new Document(new iTextSharp.text.Rectangle(1100f, 20000.25f));
     PdfWriter writer = PdfWriter.GetInstance(pdfDoc, Response.OutputStream);
     pdfDoc.Open();
     iTextSharp.text.Image img = iTextSharp.text.Image.GetInstance(fullOutputPath);   
     img.ScaleAbsoluteHeight(20000);
     img.ScaleAbsoluteWidth(1024);     
     pdfDoc.Add(img);
     pdfDoc.Close();
     //Download the PDF file.
     Response.ContentType = "application/pdf";
     Response.AddHeader("content-disposition", "attachment;filename=ImageExport.pdf");
     Response.Cache.SetCacheability(HttpCacheability.NoCache);
     Response.Write(pdfDoc);
     Response.End();


}

你也可以参考我最老的帖子了解更多信息:在asp.net web表单中导航到网页被取消了

下面是一个使用iTextSharp将html + css转换为PDF的示例(iTextSharp + iTextSharp .xmlworker)

using iTextSharp.text;
using iTextSharp.text.pdf;
using iTextSharp.tool.xml;


byte[] pdf; // result will be here

var cssText = File.ReadAllText(MapPath("~/css/test.css"));
var html = File.ReadAllText(MapPath("~/css/test.html"));

using (var memoryStream = new MemoryStream())
{
        var document = new Document(PageSize.A4, 50, 50, 60, 60);
        var writer = PdfWriter.GetInstance(document, memoryStream);
        document.Open();

        using (var cssMemoryStream = new MemoryStream(System.Text.Encoding.UTF8.GetBytes(cssText)))
        {
            using (var htmlMemoryStream = new MemoryStream(System.Text.Encoding.UTF8.GetBytes(html)))
            {
                XMLWorkerHelper.GetInstance().ParseXHtml(writer, document, htmlMemoryStream, cssMemoryStream);
            }
        }

        document.Close();

        pdf = memoryStream.ToArray();
}

你可以使用谷歌Chrome打印到pdf功能从它的无头模式。我发现这是最简单但最健壮的方法。

var url = "https://stackoverflow.com/questions/564650/convert-html-to-pdf-in-net";
var chromePath = @"C:\Program Files (x86)\Google\Chrome\Application\chrome.exe";
var output = Path.Combine(Environment.CurrentDirectory, "printout.pdf");
using (var p = new Process())
    {
        p.StartInfo.FileName = chromePath;
        p.StartInfo.Arguments = $"--headless --disable-gpu --print-to-pdf={output} {url}";
        p.Start();
        p.WaitForExit();
    }

如果你需要完美的html pdf渲染,你需要使用商业库。

ExpertPdf Html To Pdf Converter非常容易使用,它支持最新的html5/css3。您可以将整个url转换为pdf:

using ExpertPdf.HtmlToPdf; 
byte[] pdfBytes = new PdfConverter().GetPdfBytesFromUrl(url);

或者HTML字符串:

using ExpertPdf.HtmlToPdf; 
byte[] pdfBytes = new PdfConverter().GetPdfBytesFromHtmlString(html, baseUrl);

您还可以选择直接将生成的pdf文档保存到磁盘上的文件流。