pdf转html,pdf转word等

方法一：使用Aspose.Words转

这种方法效果不是太好，毕竟Aspose.Words，主要是做word相关转换的。比如word转pdf，word转html这个库还是非常强大的

public void PdfTOHtml()
{
    string dir = _webHostEnvironment.ContentRootPath;
    PdfDocumentReaderPlugin pdfDocumentReaderPlugin = new PdfDocumentReaderPlugin();
    FileStream fileStream = new FileStream(dir + "/words/allin.pdf", FileMode.Open);
    Aspose.Words.Loading.LoadOptions loadOptions = new Aspose.Words.Loading.LoadOptions();
    Aspose.Words.Document document = new Aspose.Words.Document();
    pdfDocumentReaderPlugin.Read(fileStream, loadOptions, document);
    //这样目录位置是项目根目录
    //document.Save("xx.docx");
    HtmlSaveOptions htmlSaveOptions = new HtmlSaveOptions();
    //htmlSaveOptions.ImageResolution = 100;
    //为false图片以原生大小输出，看注释里边有就是注释太长了难得找
    htmlSaveOptions.ScaleImageToShapeSize = false;
    //wrdf.Save(dir + "/words/xss.html", Aspose.Words.SaveFormat.Html);
    document.Save(dir + "/words/html/xss.html", htmlSaveOptions);
}

方法二：使用Aspose.Pdf转

这种方法效果就好了，毕竟是本专业

public void PdfToHTmlByAsposePdf()
{
    string dir = _webHostEnvironment.ContentRootPath;
    string dataDir = dir + "/words/allin.pdf";
    // 源PDF文件
    Aspose.Pdf.Document doc = new Aspose.Pdf.Document(dataDir);
    //使用测试的功能创建HtmlSaveOption
    Aspose.Pdf.HtmlSaveOptions saveOptions = new Aspose.Pdf.HtmlSaveOptions();
    saveOptions.FixedLayout = true;
    saveOptions.SplitIntoPages = false;
    saveOptions.RasterImagesSavingMode = Aspose.Pdf.HtmlSaveOptions.RasterImagesSavingModes.AsExternalPngFilesReferencedViaSvg;
    //将输出保存为HTML格式
    doc.Save(dataDir + "SaveImages_out.html", saveOptions);
    //doc.Save(dir + "/words/html/xss.html",Aspose.Pdf.SaveFormat.Html);
}