如何使用 C# 将 HTML 转换为 PDF 和法律行业的 OCR 文档

// Extract all contents of the ZIP file to a specified directory
IronZipArchive.ExtractArchiveToDirectory("assets/website.zip", "extracted");

' Extract all contents of the ZIP file to a specified directory
IronZipArchive.ExtractArchiveToDirectory("assets/website.zip", "extracted")

// Create a ChromePdfRenderer object for rendering HTML to PDF (consider using IronHtmlRenderer for better HTML to PDF conversion)
ChromePdfRenderer renderer = new ChromePdfRenderer();

// Initialize an empty list to store the individual PDF documents
List<PdfDocument> pdfs = new List<PdfDocument>();

// Get all HTML files with the .html extension from the "extracted" folder
var htmlFiles = Directory.EnumerateFiles("extracted", "*.html");

// Loop through each HTML file
foreach (var htmlFile in htmlFiles)
{
    // Render the current HTML file as a PDF document using the ChromePdfRenderer
    var pdf = renderer.RenderHtmlFileAsPdf(htmlFile);

    // Add the generated PDF document to the list
    pdfs.Add(pdf);
}

// Merge all the individual PDF documents in the list into a single PDF document
var document = PdfDocument.Merge(pdfs);

// Save the merged PDF document as "HtmlToPDF.pdf"
document.SaveAs("HtmlToPDF.pdf");

' Create a ChromePdfRenderer object for rendering HTML to PDF (consider using IronHtmlRenderer for better HTML to PDF conversion)
Dim renderer As New ChromePdfRenderer()

' Initialize an empty list to store the individual PDF documents
Dim pdfs As New List(Of PdfDocument)()

' Get all HTML files with the .html extension from the "extracted" folder
Dim htmlFiles = Directory.EnumerateFiles("extracted", "*.html")

' Loop through each HTML file
For Each htmlFile In htmlFiles
	' Render the current HTML file as a PDF document using the ChromePdfRenderer
	Dim pdf = renderer.RenderHtmlFileAsPdf(htmlFile)

	' Add the generated PDF document to the list
	pdfs.Add(pdf)
Next htmlFile

' Merge all the individual PDF documents in the list into a single PDF document
Dim document = PdfDocument.Merge(pdfs)

' Save the merged PDF document as "HtmlToPDF.pdf"
document.SaveAs("HtmlToPDF.pdf")

// Create an IronTesseract object for Optical Character Recognition (OCR)
var ocrTesseract = new IronTesseract();

// Create an OcrInput object to specify the input for OCR processing
using var ocrInput = new OcrInput();

// Load the PDF document for text extraction
ocrInput.LoadPdf("HtmlToPDF.pdf");

// Perform OCR on the loaded PDF using the IronTesseract engine
var ocrResult = ocrTesseract.Read(ocrInput);

// Print the extracted text to the console
Console.WriteLine(ocrResult.Text);

' Create an IronTesseract object for Optical Character Recognition (OCR)
Dim ocrTesseract = New IronTesseract()

' Create an OcrInput object to specify the input for OCR processing
Dim ocrInput As New OcrInput()

' Load the PDF document for text extraction
ocrInput.LoadPdf("HtmlToPDF.pdf")

' Perform OCR on the loaded PDF using the IronTesseract engine
Dim ocrResult = ocrTesseract.Read(ocrInput)

' Print the extracted text to the console
Console.WriteLine(ocrResult.Text)