C# 元素不允许错误itextSharp_C#_Pdf_Itext

C# 元素不允许错误itextSharp

c# pdf itext

C# 元素不允许错误itextSharp,c#,pdf,itext,C#,Pdf,Itext,我正在尝试使用itextsharp将html转换为pdf。但始终使用HtmlAgilityPack获取错误“element not allowed”Html格式。 ........................................................................................................................................................................

我正在尝试使用itextsharp将html转换为pdf。但始终使用HtmlAgilityPack获取错误“element not allowed”Html格式。 ..................................................................................................................................................................................................... 这是我的密码

 hDocument.LoadHtml(html);
            var closedTags = hDocument.DocumentNode.WriteTo();
            var _cssSource = Server.MapPath("~/css/style.css");
            var css = System.IO.File.ReadAllText(_cssSource);
            var memoryStram = new MemoryStream();
            var memmoryStram = new MemoryStream();
            var document = new Document(PageSize.A4, 10, 10, 10, 10);
            var writer = PdfWriter.GetInstance(document, memmoryStram);
            document.Open();
            using (var cssMemoryStream = new MemoryStream(System.Text.Encoding.UTF8.GetBytes(css)))
            {
                using (var htmlMemoryStream = new MemoryStream(System.Text.Encoding.UTF8.GetBytes(closedTags)))
                {
                    // XMLWorker _worker = new XMLWorker(
                    StringReader htmls = new StringReader(html);
                    var p = XMLWorkerHelper.GetInstance();
                    p.ParseXHtml(writer, document, htmlMemoryStream, cssMemoryStream);
                }
            }
            document.Close();

错误：

         at iTextSharp.text.pdf.ColumnText.AddElement(IElement element)
      at iTextSharp.text.pdf.PdfPCell.AddElement(IElement element)
     at iTextSharp.tool.xml.html.table.TableData.End(IWorkerContext ctx, Tag tag, IList`1 currentContent)
   at iTextSharp.tool.xml.html.AbstractTagProcessor.EndElement(IWorkerContext ctx, Tag tag, IList`1 currentContent)
   at iTextSharp.tool.xml.pipeline.html.HtmlPipeline.Close(IWorkerContext context, Tag t, ProcessObject po)
 at iTextSharp.tool.xml.XMLWorker.EndElement(String tag, String ns)
 at iTextSharp.tool.xml.parser.XMLParser.EndElement()
 at iTextSharp.tool.xml.parser.state.ClosingTagState.Process(Char character)
 at iTextSharp.tool.xml.parser.XMLParser.ParseWithReader(TextReader reader)
  at iTextSharp.tool.xml.parser.XMLParser.Parse(TextReader reader)
 at iTextSharp.tool.xml.parser.XMLParser.Parse(Stream inp)
  at iTextSharp.tool.xml.XMLWorkerHelper.ParseXHtml(PdfWriter writer, Document doc, Stream inp, Stream inCssFile, Encoding charset, IFontProvider fontProvider, String resourcesRootPath)
  at iTextSharp.tool.xml.XMLWorkerHelper.ParseXHtml(PdfWriter writer, Document doc, Stream inp, Stream inCssFile, Encoding charset, IFontProvider fontProvider)
  at iTextSharp.tool.xml.XMLWorkerHelper.ParseXHtml(PdfWriter writer, Document doc, Stream inp, Stream inCssFile)
  at IBATechnologies.IBA.SyncApp.Interface.Controllers.UtilitiesController.pdfBytes(String html) in E:\IBASyncApp\IBA.SyncApp.Interface\IBATechnologies.IBA.SyncApp.Interface\Controllers\UtilitiesController.cs:line 54

封闭式标签

     <!-- ngInclude: _rpt.tmpUrl --><div class="col-all-12 PDF-report-holder   ng-  scope" ng-include="_rpt.tmpUrl"><table id="myTable" class="table-responsive ng-scope">
     <tbody><tr class="header">
   <th colspan="5">
   <h2 class="col-all-12"> Branch</h2>
   <p class="col-all-12 ng-binding">WMS Stock Status - Item Summary</p>
  </th>

 <th class="-Pdf-logo">
       <a href="http://technologies.com/" class="col-all-12"><img       src="/image/default/logo.png" /></a>
     </th>
     </tr>
     <tr class="-Pdf-head">
  <td>SKU</td>
   <td>Base Unit</td>
   <td>Base Qty</td>
  <td>Pltpos(s)</td>
   <td>CBM</td>
   <td>Weight TON</td>

    </tr>
     </tbody><!-- ngRepeat: cust in _rpt.data --><tbody ng-repeat="cust in _rpt.data"    class="ng-scope">
<tr>
<td colspan="6"><strong><p class="ng-binding">Test Customer</p></strong></td>

 </tr>
  <!-- ngRepeat: row in cust.itemGroup --><tr ng-repeat="row in    cust.itemGroup"     ng-repeat-finished="rpt_ng_repeat" class="ng-scope">
     <td><p class="ng-binding">100 Test Item</p></td>
      <td><p class="ng-binding">PLT</p></td>
      <td><p class="ng-binding">68</p></td>
        <td><p class="ng-binding">68</p></td>
       <td><p class="ng-binding">68</p></td>
       <td><p class="ng-binding">0.068</p></td>
       </tr><!-- end ngRepeat: row in cust.itemGroup -->
       <tr class="-Pdf-head">
       <td colspan="3"><p>Total</p></td>
     <td><p class="ng-binding">68</p></td>
   <td><p class="ng-binding">68</p></td>
   <td><p class="ng-binding">0.068</p></td>
   </tr>
       </tbody><!-- end ngRepeat: cust in _rpt.data -->
      </table>
    </div>

回应

public class PdfContent : ActionResult
{
    public MemoryStream MemoryStream { get; set; }
    public string FileName { get; set; }
    public override void ExecuteResult(ControllerContext context)
    {
        if (context == null)
        {
            throw new ArgumentNullException("context");
        }
        var response = context.HttpContext.Response;
        response.ContentType = "pdf/application";
        response.AddHeader("content-disposition", "attachment;filename=" + FileName + ".pdf");
        response.OutputStream.Write(MemoryStream.GetBuffer(), 0, MemoryStream.GetBuffer().Length);
    }
}

CSS

原因显然，iText

XMLWorker

不接受表头元素（

h1

，

h2

，

h3

，

h4

，

h5

，或

h6

）中的标题元素（

th

）：如果您在此处删除

h2

元素

<th colspan="5">
  <h2 class="col-all-12"> Branch</h2>
  <p class="col-all-12 ng-binding">WMS Stock Status - Item Summary</p>
</th>

及

被拒绝，与HTML的异常情况相同

说明书根据HTML5规范，表标题中的标题元素实际上是不允许的：

4.9.10

th

元素 [……]

内容模型：

流动内容，但没有页眉、页脚、分段内容或标题内容子体

（）

其中标题内容定义为
3.2.4.1.4标题内容 标题内容定义节的标题（无论是使用节内容元素显式标记，还是由标题内容本身暗示）
=>h1 h2 h3 h4 h5 h6
（）
底线因此，您的HTML输入不是有效的HTML，因此，iText（或任何HTML处理器）可能无法处理它

测试代码作为参考，源于您的代码，这是我用于测试的代码：

public void CreatePdfAjithOriginal() { String html = "" + "<div class=\"col-all-12 PDF-report-holder ng-scope\" ng-include=\"_rpt.tmpUrl\">" + "<table id=\"myTable\" class=\"table-responsive ng-scope\">" + "<tbody>" + "<tr class=\"header\">" + "<th colspan=\"5\">" // + "<h2 class=\"col-all-12\"> Branch</h2>" + "<p class=\"col-all-12 ng-binding\">WMS Stock Status - Item Summary</p>" + "</th>" + "<th class=\"-Pdf-logo\">" + "<a href=\"http://technologies.com/\" class=\"col-all-12\"><img src=\"/image/default/logo.png\" /></a>" + "</th>" + "</tr>" + "<tr class=\"-Pdf-head\">" + "<td>SKU</td>" + "<td>Base Unit</td>" + "<td>Pltpos(s)</td>" + "<td>CBM</td>" + "<td>Weight TON</td>" + "</tr>" + "</tbody>" + "" + "<tbody ng-repeat=\"cust in _rpt.data\" class=\"ng-scope\">" + "<tr>" + "<td colspan=\"6\"><strong><p class=\"ng-binding\">Test Customer</p></strong></td>" + "</tr>" + "" + "<tr ng-repeat=\"row in cust.itemGroup\" ng-repeat-finished=\"rpt_ng_repeat\" class=\"ng-scope\">" + "<td><p class=\"ng-binding\">100 Test Item</p></td>" + "<td><p class=\"ng-binding\">PLT</p></td>" + "<td><p class=\"ng-binding\">68</p></td>" + "<td><p class=\"ng-binding\">68</p></td>" + "<td><p class=\"ng-binding\">68</p></td>" + "<td><p class=\"ng-binding\">0.068</p></td>" + "</tr>" + "" + "<tr class=\"-Pdf-head\">" + "<td colspan=\"3\"><p>Total</p></td>" + "<td><p class=\"ng-binding\">68</p></td>" + "<td><p class=\"ng-binding\">68</p></td>" + "<td><p class=\"ng-binding\">0.068</p></td>" + "</tr>" + "</tbody>" + "" + "</table>" + "</div>"; // A minimal example provoking the exception: // String html = "<table><tr><th><h1>Test</h1></th></tr></table>"; String css = ".PDF-report{position:fixed; top:0; right:-100%; background:#fff; width:75%; height:100%; z-index:100; padding:10px; border-left:1px solid #ccc}" + " .PDF-report-active{ right: 0}" + " .PDF-report table{background:#fff; min-width:100%}" + " .PDF-report table td{ min-width:100px;}" + " .IBA-Pdf-logo img{ float:right}" + " .IBA-Pdf-head{ border-top:5px solid #000; font-weight:bold }" + " .PDF-report-holder{ height: 100 %; overflow: scroll}" + " .col-all-12{width:100%;}" + " .col-all-12, .all-col{height:auto; padding:0; margin:0; float:left}"; Directory.CreateDirectory(@"C:\Temp\test-results\xmlworker\"); var document = new Document(PageSize.A4, 10, 10, 10, 10); var writer = PdfWriter.GetInstance(document, new FileStream(@"C:\Temp\test-results\xmlworker\AjithOriginal.pdf", FileMode.Create)); document.Open(); using (var cssMemoryStream = new MemoryStream(System.Text.Encoding.UTF8.GetBytes(css))) { using (var htmlMemoryStream = new MemoryStream(System.Text.Encoding.UTF8.GetBytes(html))) { var p = XMLWorkerHelper.GetInstance(); p.ParseXHtml(writer, document, htmlMemoryStream, cssMemoryStream); } } document.Close(); }

public void CreatePdfAjithOriginal（） { 字符串html=“” + "" + "" + "" + "" + "" //+“分支” +“WMS库存状态-物料汇总” + "" + "" + "" + "" + "" + "" +“SKU” +“基本单位” +"公共交通工具" +“CBM” +“重量吨” + "" + "" + "" + "" + "" +测试客户 + "" + "" + "" +“100个测试项目” +“PLT” +“68” +“68” +“68” +“0.068” + "" + "" + "" +“总计” +“68” +“68” +“0.068” + "" + "" + "" + "" + ""; //引发异常的一个最小示例： //字符串html=“Test”；字符串css=“.PDF报告{位置：固定；顶部：0；右侧：-100%；背景：fff；宽度：75%；高度：100%；z索引：100；填充：10px；边框左侧：1px实心#ccc}” +“.PDF报告处于活动状态{右侧：0}” +“.PDF报告表{背景：#fff；最小宽度：100%}” +“.PDF报告表td{最小宽度：100px；}” +“.IBA Pdf徽标img{float:right}” +“.IBA Pdf头{边框顶部：5px实心#000；字体重量：粗体}” +“.PDF报表持有者{高度：100%；溢出：滚动}” +“.col-all-12{宽度：100%；}” +“.col-all-12，.all col{height:自动；padding:0；margin:0；float:left}”； CreateDirectory（@“C:\Temp\test results\xmlworker\”）； var文件=新文件（PageSize.A4、10、10、10、10）； var writer=PdfWriter.GetInstance（文档，新文件流（@“C:\Temp\test results\xmlworker\ajithoriging.pdf”，FileMode.Create））； document.Open（）；使用（var cssMemoryStream=newmemorystream（System.Text.Encoding.UTF8.GetBytes（css））） { 使用（var htmlemorystream=newmemorystream（System.Text.Encoding.UTF8.GetBytes（html））） { var p=XMLWorkerHelper.GetInstance（）； p、 ParseXHtml（编写器、文档、htmlMemoryStream、cssMemoryStream）； } } document.Close（）； }
html和css中的额外空格都已从源代码中删除，因为我假设它们是复制到堆栈溢出时引入的工件。如果这个假设是错误的，那么在继续之前，应该对原始HTML和CSS进行清理
此外，还删除了未使用的代码，例如
var memoryStram
和
StringReader htmls
。原始代码也应该被清理
无论如何，上述结果是

另一方面，你说

生成的pdf文件为空
考虑到您最近添加的代码，我假设您的意思是，它在某些浏览器中显示为空白。因此，它要么在发送到
HttpContext.Response
的过程中丢失了，要么您的浏览器不喜欢它的发送方式
要验证PDF是否正确地访问了
HttpContext.Response
，您应该始终检查相关的
MemoryStream
实例是否携带PDF，例如通过将相应的
MemoryStream
的
ToArray（）值存储到文件系统中一个可能的问题：您没有显示您的方法pdfBytes 如何实际返回MemoryStream ；也许您使用空的memoryStram 而不是生成PDF的memoryStram 一旦您确定PDF确实到达HttpContext.Response且已损坏，请使用浏览器再次测试。如果是这样的话 <th colspan="5"> <h2 class="col-all-12"> Branch</h2> <p class="col-all-12 ng-binding">WMS Stock Status - Item Summary</p> </th> <table><tr><td><h1>Test</h1></td></tr></table> <table><tr><th><p>Test</p></th></tr></table> <table><tr><th><h1>Test</h1></th></tr></table> public void CreatePdfAjithOriginal() { String html = "" + "<div class=\"col-all-12 PDF-report-holder ng-scope\" ng-include=\"_rpt.tmpUrl\">" + "<table id=\"myTable\" class=\"table-responsive ng-scope\">" + "<tbody>" + "<tr class=\"header\">" + "<th colspan=\"5\">" // + "<h2 class=\"col-all-12\"> Branch</h2>" + "<p class=\"col-all-12 ng-binding\">WMS Stock Status - Item Summary</p>" + "</th>" + "<th class=\"-Pdf-logo\">" + "<a href=\"http://technologies.com/\" class=\"col-all-12\"><img src=\"/image/default/logo.png\" /></a>" + "</th>" + "</tr>" + "<tr class=\"-Pdf-head\">" + "<td>SKU</td>" + "<td>Base Unit</td>" + "<td>Pltpos(s)</td>" + "<td>CBM</td>" + "<td>Weight TON</td>" + "</tr>" + "</tbody>" + "" + "<tbody ng-repeat=\"cust in _rpt.data\" class=\"ng-scope\">" + "<tr>" + "<td colspan=\"6\"><strong><p class=\"ng-binding\">Test Customer</p></strong></td>" + "</tr>" + "" + "<tr ng-repeat=\"row in cust.itemGroup\" ng-repeat-finished=\"rpt_ng_repeat\" class=\"ng-scope\">" + "<td><p class=\"ng-binding\">100 Test Item</p></td>" + "<td><p class=\"ng-binding\">PLT</p></td>" + "<td><p class=\"ng-binding\">68</p></td>" + "<td><p class=\"ng-binding\">68</p></td>" + "<td><p class=\"ng-binding\">68</p></td>" + "<td><p class=\"ng-binding\">0.068</p></td>" + "</tr>" + "" + "<tr class=\"-Pdf-head\">" + "<td colspan=\"3\"><p>Total</p></td>" + "<td><p class=\"ng-binding\">68</p></td>" + "<td><p class=\"ng-binding\">68</p></td>" + "<td><p class=\"ng-binding\">0.068</p></td>" + "</tr>" + "</tbody>" + "" + "</table>" + "</div>"; // A minimal example provoking the exception: // String html = "<table><tr><th><h1>Test</h1></th></tr></table>"; String css = ".PDF-report{position:fixed; top:0; right:-100%; background:#fff; width:75%; height:100%; z-index:100; padding:10px; border-left:1px solid #ccc}" + " .PDF-report-active{ right: 0}" + " .PDF-report table{background:#fff; min-width:100%}" + " .PDF-report table td{ min-width:100px;}" + " .IBA-Pdf-logo img{ float:right}" + " .IBA-Pdf-head{ border-top:5px solid #000; font-weight:bold }" + " .PDF-report-holder{ height: 100 %; overflow: scroll}" + " .col-all-12{width:100%;}" + " .col-all-12, .all-col{height:auto; padding:0; margin:0; float:left}"; Directory.CreateDirectory(@"C:\Temp\test-results\xmlworker\"); var document = new Document(PageSize.A4, 10, 10, 10, 10); var writer = PdfWriter.GetInstance(document, new FileStream(@"C:\Temp\test-results\xmlworker\AjithOriginal.pdf", FileMode.Create)); document.Open(); using (var cssMemoryStream = new MemoryStream(System.Text.Encoding.UTF8.GetBytes(css))) { using (var htmlMemoryStream = new MemoryStream(System.Text.Encoding.UTF8.GetBytes(html))) { var p = XMLWorkerHelper.GetInstance(); p.ParseXHtml(writer, document, htmlMemoryStream, cssMemoryStream); } } document.Close(); }