如何在 Mac 和 Windows 上将网页另存为 PDF 文件

using System;
using System.Text;
using PdfSharp.Pdf;
using PdfSharp.Pdf.IO;
using PdfSharp.Pdf.Content;
using PdfSharp.Pdf.Content.Objects;

class Program
{
    static void Main()
    {
        // Specify the path to the PDF file
        string pdfFilePath = "output.pdf";

        // Open the PDF document in import mode
        // Note: PDFsharp requires specific open modes for different operations
        PdfDocument document = PdfReader.Open(pdfFilePath, PdfDocumentOpenMode.Import);

        // Create StringBuilder for extracted text
        // This approach is less efficient than IronPDF's built-in methods
        StringBuilder extractedText = new StringBuilder();

        // Iterate through each page of the document
        for (int pageIndex = 0; pageIndex < document.PageCount; pageIndex++)
        {
            // Get the current page
            PdfPage page = document.Pages[pageIndex];

            // Extract text using content reader (simplified approach)
            // Real implementation requires extensive operator parsing
            CObject content = ContentReader.ReadContent(page);

            // Parse content objects to extract text
            // This is where PDFsharp becomes significantly complex
            ExtractText(content, extractedText);

            // Note: Actual text extraction requires parsing operators
            // This is a simplified representation
            Console.WriteLine($"Page {pageIndex + 1} processed");
        }

        Console.WriteLine("Extracted Text: " + extractedText.ToString());
        Console.ReadLine(); // Wait for user input before closing the console
    }

    static void ExtractText(CObject content, StringBuilder text)
    {
        // PDFsharp requires manual parsing of content streams
        // This is significantly more complex than shown here
        // Real implementation would need to handle:
        // - Text operators (Tj, TJ, ', ", etc.)
        // - Font encoding and character mapping
        // - Text positioning and transformation matrices
        // - Unicode mapping and glyph substitution
        // - Whitespace detection and word boundaries

        if (content is CArray array)
        {
            foreach (var item in array)
            {
                ExtractText(item, text);
            }
        }
        else if (content is CString str)
        {
            // Simplified text extraction - real implementation needs encoding handling
            text.Append(str.Value);
        }
        // Additional operators would need handling for complete extraction
    }
}

Imports System
Imports System.Text
Imports PdfSharp.Pdf
Imports PdfSharp.Pdf.IO
Imports PdfSharp.Pdf.Content
Imports PdfSharp.Pdf.Content.Objects

Class Program
    Shared Sub Main()
        ' Specify the path to the PDF file
        Dim pdfFilePath As String = "output.pdf"

        ' Open the PDF document in import mode
        ' Note: PDFsharp requires specific open modes for different operations
        Dim document As PdfDocument = PdfReader.Open(pdfFilePath, PdfDocumentOpenMode.Import)

        ' Create StringBuilder for extracted text
        ' This approach is less efficient than IronPDF's built-in methods
        Dim extractedText As New StringBuilder()

        ' Iterate through each page of the document
        For pageIndex As Integer = 0 To document.PageCount - 1
            ' Get the current page
            Dim page As PdfPage = document.Pages(pageIndex)

            ' Extract text using content reader (simplified approach)
            ' Real implementation requires extensive operator parsing
            Dim content As CObject = ContentReader.ReadContent(page)

            ' Parse content objects to extract text
            ' This is where PDFsharp becomes significantly complex
            ExtractText(content, extractedText)

            ' Note: Actual text extraction requires parsing operators
            ' This is a simplified representation
            Console.WriteLine($"Page {pageIndex + 1} processed")
        Next

        Console.WriteLine("Extracted Text: " & extractedText.ToString())
        Console.ReadLine() ' Wait for user input before closing the console
    End Sub

    Shared Sub ExtractText(content As CObject, text As StringBuilder)
        ' PDFsharp requires manual parsing of content streams
        ' This is significantly more complex than shown here
        ' Real implementation would need to handle:
        ' - Text operators (Tj, TJ, ', ", etc.)
        ' - Font encoding and character mapping
        ' - Text positioning and transformation matrices
        ' - Unicode mapping and glyph substitution
        ' - Whitespace detection and word boundaries

        If TypeOf content Is CArray Then
            Dim array As CArray = CType(content, CArray)
            For Each item In array
                ExtractText(item, text)
            Next
        ElseIf TypeOf content Is CString Then
            Dim str As CString = CType(content, CString)
            ' Simplified text extraction - real implementation needs encoding handling
            text.Append(str.Value)
        End If
        ' Additional operators would need handling for complete extraction
    End Sub
End Class

using IronPdf;
using System;
using System.Collections.Generic;

class Program
{
    static void Main()
    {
        // Load the PDF document with error handling
        var pdf = PdfDocument.FromFile("output.pdf");

        // Extract all the text content from the PDF
        string text = pdf.ExtractAllText();

        // Print the extracted text to the console
        Console.WriteLine("Full document text:");
        Console.WriteLine(text);

        // Additional extraction options demonstrating IronPDF's versatility

        // Extract text from specific pages with formatting preserved
        string pageText = pdf.ExtractTextFromPage(0);
        Console.WriteLine($"\nPage 1 text: {pageText}");

        // Extract all images and save them
        var images = pdf.ExtractAllImages();
        for (int i = 0; i < images.Count; i++)
        {
            images[i].SaveAs($"extracted_image_{i}.png");
        }

        // Access complete metadata
        string author = pdf.MetaData.Author;
        string title = pdf.MetaData.Title;
        string subject = pdf.MetaData.Subject;
        DateTime creationDate = pdf.MetaData.CreationDate;

        Console.WriteLine($"\nDocument Info:");
        Console.WriteLine($"Title: {title}");
        Console.WriteLine($"Author: {author}");
        Console.WriteLine($"Created: {creationDate}");

        // Search for specific text
        var searchResults = pdf.Search("invoice");
        foreach (var result in searchResults)
        {
            Console.WriteLine($"Found '{result.Text}' on page {result.PageIndex}");
        }

        // Extract form field data
        var form = pdf.Form;
        foreach (var field in form.Fields)
        {
            Console.WriteLine($"Field: {field.Name} = {field.Value}");
        }
    }
}

Imports IronPdf
Imports System
Imports System.Collections.Generic

Module Program
    Sub Main()
        ' Load the PDF document with error handling
        Dim pdf = PdfDocument.FromFile("output.pdf")

        ' Extract all the text content from the PDF
        Dim text As String = pdf.ExtractAllText()

        ' Print the extracted text to the console
        Console.WriteLine("Full document text:")
        Console.WriteLine(text)

        ' Additional extraction options demonstrating IronPDF's versatility

        ' Extract text from specific pages with formatting preserved
        Dim pageText As String = pdf.ExtractTextFromPage(0)
        Console.WriteLine(vbCrLf & "Page 1 text: " & pageText)

        ' Extract all images and save them
        Dim images = pdf.ExtractAllImages()
        For i As Integer = 0 To images.Count - 1
            images(i).SaveAs($"extracted_image_{i}.png")
        Next

        ' Access complete metadata
        Dim author As String = pdf.MetaData.Author
        Dim title As String = pdf.MetaData.Title
        Dim subject As String = pdf.MetaData.Subject
        Dim creationDate As DateTime = pdf.MetaData.CreationDate

        Console.WriteLine(vbCrLf & "Document Info:")
        Console.WriteLine("Title: " & title)
        Console.WriteLine("Author: " & author)
        Console.WriteLine("Created: " & creationDate)

        ' Search for specific text
        Dim searchResults = pdf.Search("invoice")
        For Each result In searchResults
            Console.WriteLine($"Found '{result.Text}' on page {result.PageIndex}")
        Next

        ' Extract form field data
        Dim form = pdf.Form
        For Each field In form.Fields
            Console.WriteLine($"Field: {field.Name} = {field.Value}")
        Next
    End Sub
End Module

// IronPDF: Clean, maintainable code following SOLID principles
public class InvoiceService
{
    private readonly ITemplateEngine _templateEngine;
    private readonly IConfiguration _config;

    public async Task<byte[]> GenerateInvoicePdf(Invoice invoice)
    {
        // Render HTML from template with full CSS support
        var html = await _templateEngine.RenderAsync("invoice.html", invoice);

        // Configure rendering with fluent API
        var renderer = new ChromePdfRenderer
        {
            RenderingOptions = new ChromePdfRenderOptions
            {
                MarginTop = 50,
                MarginBottom = 50,
                PaperSize = PdfPaperSize.A4,
                Title = $"Invoice #{invoice.Number}",
                // Enable JavaScript for dynamic content
                EnableJavaScript = true,
                // Wait for AJAX calls to complete
                WaitFor = WaitFor.NetworkIdle0,
                // Custom headers and footers
                HtmlHeader = "<div style='text-align: center;'>{page} of {total-pages}</div>",
                HtmlFooter = "<div style='text-align: center;'>© 2024 Your Company</div>"
            }
        };

        // Render with full Chrome engine support
        var pdf = await renderer.RenderHtmlAsPdfAsync(html);

        // Add security features
        pdf.SecuritySettings.SetPassword("user-password", "owner-password");
        pdf.SecuritySettings.AllowPrinting = true;
        pdf.SecuritySettings.AllowCopy = false;

        // Add digital signature for authenticity
        pdf.SignWithCertificate(certificate, "Authorized Signature");

        // Improve for web delivery
        pdf.CompressImages(90);

        return pdf.BinaryData;
    }
}

Imports System.Threading.Tasks

' IronPDF: Clean, maintainable code following SOLID principles
Public Class InvoiceService
    Private ReadOnly _templateEngine As ITemplateEngine
    Private ReadOnly _config As IConfiguration

    Public Async Function GenerateInvoicePdf(invoice As Invoice) As Task(Of Byte())
        ' Render HTML from template with full CSS support
        Dim html = Await _templateEngine.RenderAsync("invoice.html", invoice)

        ' Configure rendering with fluent API
        Dim renderer = New ChromePdfRenderer With {
            .RenderingOptions = New ChromePdfRenderOptions With {
                .MarginTop = 50,
                .MarginBottom = 50,
                .PaperSize = PdfPaperSize.A4,
                .Title = $"Invoice #{invoice.Number}",
                ' Enable JavaScript for dynamic content
                .EnableJavaScript = True,
                ' Wait for AJAX calls to complete
                .WaitFor = WaitFor.NetworkIdle0,
                ' Custom headers and footers
                .HtmlHeader = "<div style='text-align: center;'>{page} of {total-pages}</div>",
                .HtmlFooter = "<div style='text-align: center;'>© 2024 Your Company</div>"
            }
        }

        ' Render with full Chrome engine support
        Dim pdf = Await renderer.RenderHtmlAsPdfAsync(html)

        ' Add security features
        pdf.SecuritySettings.SetPassword("user-password", "owner-password")
        pdf.SecuritySettings.AllowPrinting = True
        pdf.SecuritySettings.AllowCopy = False

        ' Add digital signature for authenticity
        pdf.SignWithCertificate(certificate, "Authorized Signature")

        ' Improve for web delivery
        pdf.CompressImages(90)

        Return pdf.BinaryData
    End Function
End Class