HTML in PDF konvertieren hinter Login-Authentifizierung in C

public async Task<string> DownloadAuthenticatedHtmlWithAssets(string url, string authToken)
{
    using (var client = new HttpClient())
    {
        // Set authentication header
        client.DefaultRequestHeaders.Authorization = 
            new System.Net.Http.Headers.AuthenticationHeaderValue("Bearer", authToken);

        // Download the main HTML
        string html = await client.GetStringAsync(url);

        // Parse HTML to find assets
        var doc = new HtmlDocument();
        doc.LoadHtml(html);

        // Create a base URI for resolving relative paths
        var baseUri = new Uri(url);

        // Download CSS files
        var cssLinks = doc.DocumentNode.SelectNodes("//link[@rel='stylesheet']");
        if (cssLinks != null)
        {
            foreach (var link in cssLinks)
            {
                string href = link.GetAttributeValue("href", "");
                if (!string.IsNullOrEmpty(href))
                {
                    var cssUri = new Uri(baseUri, href);
                    string cssContent = await client.GetStringAsync(cssUri);

                    // Embed CSS directly in the HTML
                    var styleNode = doc.CreateElement("style");
                    styleNode.InnerHtml = cssContent;
                    doc.DocumentNode.SelectSingleNode("//head").AppendChild(styleNode);

                    // Remove the external link
                    link.Remove();
                }
            }
        }

        // Return the modified HTML with embedded assets
        return doc.DocumentNode.OuterHtml;
    }
}

Imports System
Imports System.Net.Http
Imports System.Threading.Tasks
Imports HtmlAgilityPack

Public Class HtmlDownloader
    Public Async Function DownloadAuthenticatedHtmlWithAssets(url As String, authToken As String) As Task(Of String)
        Using client As New HttpClient()
            ' Set authentication header
            client.DefaultRequestHeaders.Authorization = New System.Net.Http.Headers.AuthenticationHeaderValue("Bearer", authToken)

            ' Download the main HTML
            Dim html As String = Await client.GetStringAsync(url)

            ' Parse HTML to find assets
            Dim doc As New HtmlDocument()
            doc.LoadHtml(html)

            ' Create a base URI for resolving relative paths
            Dim baseUri As New Uri(url)

            ' Download CSS files
            Dim cssLinks = doc.DocumentNode.SelectNodes("//link[@rel='stylesheet']")
            If cssLinks IsNot Nothing Then
                For Each link In cssLinks
                    Dim href As String = link.GetAttributeValue("href", "")
                    If Not String.IsNullOrEmpty(href) Then
                        Dim cssUri As New Uri(baseUri, href)
                        Dim cssContent As String = Await client.GetStringAsync(cssUri)

                        ' Embed CSS directly in the HTML
                        Dim styleNode = doc.CreateElement("style")
                        styleNode.InnerHtml = cssContent
                        doc.DocumentNode.SelectSingleNode("//head").AppendChild(styleNode)

                        ' Remove the external link
                        link.Remove()
                    End If
                Next
            End If

            ' Return the modified HTML with embedded assets
            Return doc.DocumentNode.OuterHtml
        End Using
    End Function
End Class

// Basic Authentication (most common)
var basicAuth = new ChromeHttpLoginCredentials
{
    NetworkUsername = "user@domain.com",
    NetworkPassword = "password123",
    AuthenticationType = ChromeHttpLoginCredentials.AuthType.Basic
};

// NTLM/Windows Authentication
var ntlmAuth = new ChromeHttpLoginCredentials
{
    NetworkUsername = "DOMAIN\\username", // Include domain
    NetworkPassword = "password123",
    AuthenticationType = ChromeHttpLoginCredentials.AuthType.Ntlm
};

// Custom authentication headers
var renderer = new ChromePdfRenderer();
renderer.RenderingOptions.CustomHttpHeaders.Add("X-API-Key", "your-api-key");
renderer.RenderingOptions.CustomHttpHeaders.Add("Authorization", "Bearer " + jwtToken);

Imports System.Collections.Generic

' Basic Authentication (most common)
Dim basicAuth As New ChromeHttpLoginCredentials With {
    .NetworkUsername = "user@domain.com",
    .NetworkPassword = "password123",
    .AuthenticationType = ChromeHttpLoginCredentials.AuthType.Basic
}

' NTLM/Windows Authentication
Dim ntlmAuth As New ChromeHttpLoginCredentials With {
    .NetworkUsername = "DOMAIN\username", ' Include domain
    .NetworkPassword = "password123",
    .AuthenticationType = ChromeHttpLoginCredentials.AuthType.Ntlm
}

' Custom authentication headers
Dim renderer As New ChromePdfRenderer()
renderer.RenderingOptions.CustomHttpHeaders.Add("X-API-Key", "your-api-key")
renderer.RenderingOptions.CustomHttpHeaders.Add("Authorization", "Bearer " & jwtToken)

// Enable detailed logging
IronPdf.Logging.Logger.EnableDebugging = true;
IronPdf.Logging.Logger.LogFilePath = "IronPdf.log";
IronPdf.Logging.Logger.LoggingMode = IronPdf.Logging.Logger.LoggingModes.All;

// Test authentication
try 
{
    var pdf = renderer.RenderUrlAsPdf("https://secure.example.com");
    pdf.SaveAs("authenticated.pdf");
}
catch (Exception ex)
{
    Console.WriteLine($"Authentication failed: {ex.Message}");
    // Check IronPdf.log for detailed error information
}

Imports IronPdf
Imports System

' Enable detailed logging
Logging.Logger.EnableDebugging = True
Logging.Logger.LogFilePath = "IronPdf.log"
Logging.Logger.LoggingMode = Logging.Logger.LoggingModes.All

' Test authentication
Try
    Dim pdf = renderer.RenderUrlAsPdf("https://secure.example.com")
    pdf.SaveAs("authenticated.pdf")
Catch ex As Exception
    Console.WriteLine($"Authentication failed: {ex.Message}")
    ' Check IronPdf.log for detailed error information
End Try

// Use this helper method to extract form fields
public Dictionary<string, string> ExtractFormFields(string loginPageHtml)
{
    var formData = new Dictionary<string, string>();
    var doc = new HtmlDocument();
    doc.LoadHtml(loginPageHtml);

    // Find all input fields
    var inputs = doc.DocumentNode.SelectNodes("//input");
    if (inputs != null)
    {
        foreach (var input in inputs)
        {
            string name = input.GetAttributeValue("name", "");
            string value = input.GetAttributeValue("value", "");
            string type = input.GetAttributeValue("type", "text");

            if (!string.IsNullOrEmpty(name))
            {
                // Handle different input types
                switch (type.ToLower())
                {
                    case "checkbox":
                        if (input.Attributes["checked"] != null)
                            formData[name] = "on";
                        break;
                    case "radio":
                        if (input.Attributes["checked"] != null)
                            formData[name] = value;
                        break;
                    default:
                        formData[name] = value;
                        break;
                }
            }
        }
    }

    // Don't forget select elements
    var selects = doc.DocumentNode.SelectNodes("//select");
    if (selects != null)
    {
        foreach (var select in selects)
        {
            string name = select.GetAttributeValue("name", "");
            var selected = select.SelectSingleNode(".//option[@selected]");
            if (selected != null && !string.IsNullOrEmpty(name))
            {
                formData[name] = selected.GetAttributeValue("value", "");
            }
        }
    }

    return formData;
}

Imports HtmlAgilityPack

Public Function ExtractFormFields(loginPageHtml As String) As Dictionary(Of String, String)
    Dim formData As New Dictionary(Of String, String)()
    Dim doc As New HtmlDocument()
    doc.LoadHtml(loginPageHtml)

    ' Find all input fields
    Dim inputs = doc.DocumentNode.SelectNodes("//input")
    If inputs IsNot Nothing Then
        For Each input In inputs
            Dim name As String = input.GetAttributeValue("name", "")
            Dim value As String = input.GetAttributeValue("value", "")
            Dim type As String = input.GetAttributeValue("type", "text")

            If Not String.IsNullOrEmpty(name) Then
                ' Handle different input types
                Select Case type.ToLower()
                    Case "checkbox"
                        If input.Attributes("checked") IsNot Nothing Then
                            formData(name) = "on"
                        End If
                    Case "radio"
                        If input.Attributes("checked") IsNot Nothing Then
                            formData(name) = value
                        End If
                    Case Else
                        formData(name) = value
                End Select
            End If
        Next
    End If

    ' Don't forget select elements
    Dim selects = doc.DocumentNode.SelectNodes("//select")
    If selects IsNot Nothing Then
        For Each selectNode In selects
            Dim name As String = selectNode.GetAttributeValue("name", "")
            Dim selected = selectNode.SelectSingleNode(".//option[@selected]")
            If selected IsNot Nothing AndAlso Not String.IsNullOrEmpty(name) Then
                formData(name) = selected.GetAttributeValue("value", "")
            End If
        Next
    End If

    Return formData
End Function

public string ExtractFormAction(string loginPageUrl, string loginPageHtml)
{
    var doc = new HtmlDocument();
    doc.LoadHtml(loginPageHtml);

    // Find the login form
    var form = doc.DocumentNode.SelectSingleNode("//form[contains(@action, 'login') or contains(@id, 'login') or contains(@class, 'login')]");

    if (form == null)
    {
        // Try finding any form with password field
        form = doc.DocumentNode.SelectSingleNode("//form[.//input[@type='password']]");
    }

    if (form != null)
    {
        string action = form.GetAttributeValue("action", "");

        // Resolve relative URLs
        if (!string.IsNullOrEmpty(action))
        {
            var baseUri = new Uri(loginPageUrl);
            var actionUri = new Uri(baseUri, action);
            return actionUri.ToString();
        }
    }

    // Default to the login page URL if no action found
    return loginPageUrl;
}

Imports System

Public Function ExtractFormAction(loginPageUrl As String, loginPageHtml As String) As String
    Dim doc As New HtmlDocument()
    doc.LoadHtml(loginPageHtml)

    ' Find the login form
    Dim form = doc.DocumentNode.SelectSingleNode("//form[contains(@action, 'login') or contains(@id, 'login') or contains(@class, 'login')]")

    If form Is Nothing Then
        ' Try finding any form with password field
        form = doc.DocumentNode.SelectSingleNode("//form[.//input[@type='password']]")
    End If

    If form IsNot Nothing Then
        Dim action As String = form.GetAttributeValue("action", "")

        ' Resolve relative URLs
        If Not String.IsNullOrEmpty(action) Then
            Dim baseUri As New Uri(loginPageUrl)
            Dim actionUri As New Uri(baseUri, action)
            Return actionUri.ToString()
        End If
    End If

    ' Default to the login page URL if no action found
    Return loginPageUrl
End Function

// Strategies for handling anti-bot measures
var renderer = new ChromePdfRenderer
{
    RenderingOptions = new ChromePdfRenderOptions
    {
        // Mimic real browser behavior
        ViewPortWidth = 1920,
        ViewPortHeight = 1080,
        EnableJavaScript = true,
        RenderDelay = 5000, // Wait for JavaScript

        // Set a real user agent
        CustomHttpHeaders = new Dictionary<string, string>
        {
            {"User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}
        }
    }
};

 // For sites with rate limiting, add delays between requests
 System.Threading.Thread.Sleep(2000);

' Strategies for handling anti-bot measures
Dim renderer = New ChromePdfRenderer With {
    .RenderingOptions = New ChromePdfRenderOptions With {
        ' Mimic real browser behavior
        .ViewPortWidth = 1920,
        .ViewPortHeight = 1080,
        .EnableJavaScript = True,
        .RenderDelay = 5000, ' Wait for JavaScript

        ' Set a real user agent
        .CustomHttpHeaders = New Dictionary(Of String, String) From {
            {"User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}
        }
    }
}

' For sites with rate limiting, add delays between requests
System.Threading.Thread.Sleep(2000)

public class InvoiceController : Controller
{
    private readonly IInvoiceService _invoiceService;

    public async Task<ActionResult> DownloadInvoicePdf(int invoiceId)
    {
        // Load data within authenticated context
        var invoice = await _invoiceService.GetInvoiceAsync(invoiceId);

        if (invoice == null || invoice.UserId != User.Identity.GetUserId())
        {
            return HttpNotFound();
        }

        // Create view model
        var viewModel = new InvoiceDetailsViewModel
        {
            Invoice = invoice,
            Company = await _invoiceService.GetCompanyDetailsAsync(),
            LineItems = await _invoiceService.GetLineItemsAsync(invoiceId),
            TaxDetails = await _invoiceService.GetTaxDetailsAsync(invoiceId)
        };

        // Render to HTML string
        string html = this.RenderPartialViewToString("~/Views/Invoice/DetailsPdf.cshtml", viewModel);

        // Add custom styling for PDF
        html = $@"
            <html>
            <head>
                <style>
                    body {{ font-family: Arial, sans-serif; }}
                    .invoice-header {{ background-color: #f0f0f0; padding: 20px; }}
                    .line-items {{ width: 100%; border-collapse: collapse; }}
                    .line-items th, .line-items td {{ border: 1px solid #ddd; padding: 8px; }}
                </style>
            </head>
            <body>
                {html}
            </body>
            </html>";

        // Convert to PDF with options
        var renderer = new ChromePdfRenderer
        {
            RenderingOptions = new ChromePdfRenderOptions
            {
                MarginTop = 20,
                MarginBottom = 20,
                MarginLeft = 10,
                MarginRight = 10,
                PrintHtmlBackgrounds = true
            }
        };

        var pdf = renderer.RenderHtmlAsPdf(html);

        // Add metadata
        pdf.MetaData.Author = "Invoice System";
        pdf.MetaData.Title = $"Invoice #{invoice.Number}";
        pdf.MetaData.CreationDate = DateTime.Now;

        return File(pdf.BinaryData, "application/pdf", $"Invoice-{invoice.Number}.pdf");
    }
}

Imports System.Threading.Tasks
Imports System.Web.Mvc

Public Class InvoiceController
    Inherits Controller

    Private ReadOnly _invoiceService As IInvoiceService

    Public Async Function DownloadInvoicePdf(invoiceId As Integer) As Task(Of ActionResult)
        ' Load data within authenticated context
        Dim invoice = Await _invoiceService.GetInvoiceAsync(invoiceId)

        If invoice Is Nothing OrElse invoice.UserId <> User.Identity.GetUserId() Then
            Return HttpNotFound()
        End If

        ' Create view model
        Dim viewModel As New InvoiceDetailsViewModel With {
            .Invoice = invoice,
            .Company = Await _invoiceService.GetCompanyDetailsAsync(),
            .LineItems = Await _invoiceService.GetLineItemsAsync(invoiceId),
            .TaxDetails = Await _invoiceService.GetTaxDetailsAsync(invoiceId)
        }

        ' Render to HTML string
        Dim html As String = Me.RenderPartialViewToString("~/Views/Invoice/DetailsPdf.cshtml", viewModel)

        ' Add custom styling for PDF
        html = $"
            <html>
            <head>
                <style>
                    body {{ font-family: Arial, sans-serif; }}
                    .invoice-header {{ background-color: #f0f0f0; padding: 20px; }}
                    .line-items {{ width: 100%; border-collapse: collapse; }}
                    .line-items th, .line-items td {{ border: 1px solid #ddd; padding: 8px; }}
                </style>
            </head>
            <body>
                {html}
            </body>
            </html>"

        ' Convert to PDF with options
        Dim renderer As New ChromePdfRenderer With {
            .RenderingOptions = New ChromePdfRenderOptions With {
                .MarginTop = 20,
                .MarginBottom = 20,
                .MarginLeft = 10,
                .MarginRight = 10,
                .PrintHtmlBackgrounds = True
            }
        }

        Dim pdf = renderer.RenderHtmlAsPdf(html)

        ' Add metadata
        pdf.MetaData.Author = "Invoice System"
        pdf.MetaData.Title = $"Invoice #{invoice.Number}"
        pdf.MetaData.CreationDate = DateTime.Now

        Return File(pdf.BinaryData, "application/pdf", $"Invoice-{invoice.Number}.pdf")
    End Function
End Class