1

我一直在尝试调试一些旨在通过字符串变量将网页转换为 PDF 文档的代码。它使用 iTextSharp c# 工具 (xmlworker)，是对 sourceforge 源代码 html2pdf.csproj 附带的示例代码的修改。此示例代码将现有的 html 文件转换为 PDF 文件，并将其保存在与转换文件相同的目录中。我有一个包含 html 格式文本的字符串变量，我试图使它能够作为字节数组返回，该数组将传递给 Web 环境中的客户端以进行打印。问题是我收到一条“IOException 未被用户代码处理”消息，指出“文档没有页面”。我有点不确定这是什么意思，也不知道如何诊断问题。使用基于文件的系统的示例代码有效，我已成功将 html 字符串的静态版本转换为 PDF。下面是修改后的代码：

       private byte[] createPDF(string html, string filename) {
            MemoryStream msOutput = new MemoryStream();
            string printPDFCSS = Server.MapPath("/content/printPDF.css");
            Document doc = new Document(PageSize.LETTER);
            doc.SetMargins(doc.LeftMargin, doc.RightMargin, 35, 0);
            PdfWriter pdfWriter = PdfWriter.GetInstance(doc, msOutput);

            doc.Open();
            Dictionary<String, String> substFonts = new Dictionary<String, String>();
            substFonts["Arial Unicode MS"] = "Helvetica";
            CssFilesImpl cssFiles = new CssFilesImpl();
            cssFiles.Add(XMLWorkerHelper.GetCSS(new FileStream(printPDFCSS, FileMode.Open)));
            StyleAttrCSSResolver cssResolver = new StyleAttrCSSResolver(cssFiles);
            HtmlPipelineContext hpc = new HtmlPipelineContext(new CssAppliersImpl(new UnembedFontProvider(XMLWorkerFontProvider.DONTLOOKFORFONTS, substFonts)));
            hpc.SetImageProvider(new ImageProvider(filename));
            hpc.SetAcceptUnknown(true).AutoBookmark(true).SetTagFactory(Tags.GetHtmlTagProcessorFactory());
            HtmlPipeline htmlPipeline = new HtmlPipeline(hpc, new PdfWriterPipeline(doc, pdfWriter));
            IPipeline pipeline = new CssResolverPipeline(cssResolver, htmlPipeline);
            XMLWorker worker = new XMLWorker(pipeline, true);
            XMLParser xmlParse = new XMLParser(true, worker);
            xmlParse.Parse(msOutput);
            doc.Close();
            return msOutput.ToArray();
        }
4

1 回答 1

2

贝娄是我最终发现有效的代码，上面的代码存在许多问题，但这似乎有效：

private byte[] createPDF(string html, string filename){
        MemoryStream msInput = new MemoryStream(ASCIIEncoding.Default.GetBytes(html));
        MemoryStream msOutput = new MemoryStream();
        string printPDFCSS = Server.MapPath("/content/printPDF.css");
        Document doc = new Document(PageSize.LETTER);
        doc.SetMargins(doc.LeftMargin, doc.RightMargin, 35, 0);
        PdfWriter pdfWriter = PdfWriter.GetInstance(doc, msOutput);
        doc.Open();
        Dictionary<String, String> substFonts = new Dictionary<String, String>();
        substFonts["Arial Unicode MS"] = "Helvetica";
        CssFilesImpl cssFiles = new CssFilesImpl();
        cssFiles.Add(XMLWorkerHelper.GetCSS(new FileStream(printPDFCSS, FileMode.Open)));
        StyleAttrCSSResolver cssResolver = new StyleAttrCSSResolver(cssFiles);
        HtmlPipelineContext hpc = new HtmlPipelineContext(new CssAppliersImpl(new UnembedFontProvider(XMLWorkerFontProvider.DONTLOOKFORFONTS, substFonts)));
        hpc.SetImageProvider(new ImageProvider(filename));
        hpc.SetAcceptUnknown(true).AutoBookmark(true).SetTagFactory(Tags.GetHtmlTagProcessorFactory());
        HtmlPipeline htmlPipeline = new HtmlPipeline(hpc, new PdfWriterPipeline(doc, pdfWriter));
        IPipeline pipeline = new CssResolverPipeline(cssResolver, htmlPipeline);
        XMLWorker worker = new XMLWorker(pipeline, true);
        XMLParser xmlParse = new XMLParser(true, worker);
        xmlParse.Parse(msInput);
        doc.Close();
        return msOutput.ToArray();
    }
于 2012-11-06T19:42:52.300 回答