如何在 .NET Core 中建立 PDF 生成器

Install-Package Selenium.WebDriver
Install-Package Selenium.WebDriver.ChromeDriver

using IronPdf;
using OpenQA.Selenium;
using OpenQA.Selenium.Chrome;
using System.IO;

Imports IronPdf
Imports OpenQA.Selenium
Imports OpenQA.Selenium.Chrome
Imports System.IO

// Initialize Chrome driver
var driver = new ChromeDriver();

// Navigate to a webpage containing a PDF link
driver.Navigate().GoToUrl("https://ironpdf.com/");

// Find and capture the PDF URL
IWebElement pdfLink = driver.FindElement(By.CssSelector("a[href$='.pdf']"));
string pdfUrl = pdfLink.GetAttribute("href");

// Load the PDF directly from the URL -- no download needed
var pdf = PdfDocument.FromUrl(new Uri(pdfUrl));
string extractedText = pdf.ExtractAllText();

// Assert expected content
if (extractedText.Contains("IronPDF"))
{
    Console.WriteLine("PDF validation passed!");
}

driver.Quit();

Imports OpenQA.Selenium
Imports OpenQA.Selenium.Chrome
Imports IronPdf

' Initialize Chrome driver
Dim driver As IWebDriver = New ChromeDriver()

' Navigate to a webpage containing a PDF link
driver.Navigate().GoToUrl("https://ironpdf.com/")

' Find and capture the PDF URL
Dim pdfLink As IWebElement = driver.FindElement(By.CssSelector("a[href$='.pdf']"))
Dim pdfUrl As String = pdfLink.GetAttribute("href")

' Load the PDF directly from the URL -- no download needed
Dim pdf As PdfDocument = PdfDocument.FromUrl(New Uri(pdfUrl))
Dim extractedText As String = pdf.ExtractAllText()

' Assert expected content
If extractedText.Contains("IronPDF") Then
    Console.WriteLine("PDF validation passed!")
End If

driver.Quit()

// Configure Chrome to auto-download PDFs
var chromeOptions = new ChromeOptions();
chromeOptions.AddUserProfilePreference("download.default_directory", @"C:\PDFTests");
chromeOptions.AddUserProfilePreference("plugins.always_open_pdf_externally", true);

var driver = new ChromeDriver(chromeOptions);
string appUrl = "https://example.com/reports";

// Trigger the download
driver.Navigate().GoToUrl(appUrl);
driver.FindElement(By.Id("downloadReport")).Click();

// Wait for the download -- replace Thread.Sleep with a file-system watcher in production tests
System.Threading.Thread.Sleep(3000);

// Read the downloaded PDF
string pdfPath = @"C:\PDFTests\report.pdf";
var pdf = PdfDocument.FromFile(pdfPath);
string content = pdf.ExtractAllText();

// Validate specific data
bool hasExpectedData = content.Contains("Quarterly Revenue: $1.2M");
Console.WriteLine($"Revenue data found: {hasExpectedData}");

// Extract text from a specific page (zero-indexed)
string page2Content = pdf.ExtractTextFromPage(1);

// Clean up
File.Delete(pdfPath);
driver.Quit();

Imports OpenQA.Selenium
Imports OpenQA.Selenium.Chrome
Imports System.IO
Imports System.Threading

' Configure Chrome to auto-download PDFs
Dim chromeOptions As New ChromeOptions()
chromeOptions.AddUserProfilePreference("download.default_directory", "C:\PDFTests")
chromeOptions.AddUserProfilePreference("plugins.always_open_pdf_externally", True)

Dim driver As New ChromeDriver(chromeOptions)
Dim appUrl As String = "https://example.com/reports"

' Trigger the download
driver.Navigate().GoToUrl(appUrl)
driver.FindElement(By.Id("downloadReport")).Click()

' Wait for the download -- replace Thread.Sleep with a file-system watcher in production tests
Thread.Sleep(3000)

' Read the downloaded PDF
Dim pdfPath As String = "C:\PDFTests\report.pdf"
Dim pdf = PdfDocument.FromFile(pdfPath)
Dim content As String = pdf.ExtractAllText()

' Validate specific data
Dim hasExpectedData As Boolean = content.Contains("Quarterly Revenue: $1.2M")
Console.WriteLine($"Revenue data found: {hasExpectedData}")

' Extract text from a specific page (zero-indexed)
Dim page2Content As String = pdf.ExtractTextFromPage(1)

' Clean up
File.Delete(pdfPath)
driver.Quit()

bool ValidatePdfContent(string pdfPath, string[] expectedTerms)
{
    var pdf = PdfDocument.FromFile(pdfPath);
    string fullText = pdf.ExtractAllText();

    // Verify each required term
    foreach (string term in expectedTerms)
    {
        if (!fullText.Contains(term, StringComparison.OrdinalIgnoreCase))
        {
            Console.WriteLine($"Missing expected term: {term}");
            return false;
        }
    }

    // Validate first-page structure
    if (pdf.PageCount > 0)
    {
        string firstPageText = pdf.ExtractTextFromPage(0);
        if (!firstPageText.Contains("Invoice #") && !firstPageText.Contains("Date:"))
        {
            Console.WriteLine("Header validation failed");
            return false;
        }
    }

    return true;
}

Imports System

Function ValidatePdfContent(pdfPath As String, expectedTerms As String()) As Boolean
    Dim pdf = PdfDocument.FromFile(pdfPath)
    Dim fullText As String = pdf.ExtractAllText()

    ' Verify each required term
    For Each term As String In expectedTerms
        If Not fullText.Contains(term, StringComparison.OrdinalIgnoreCase) Then
            Console.WriteLine($"Missing expected term: {term}")
            Return False
        End If
    Next

    ' Validate first-page structure
    If pdf.PageCount > 0 Then
        Dim firstPageText As String = pdf.ExtractTextFromPage(0)
        If Not firstPageText.Contains("Invoice #") AndAlso Not firstPageText.Contains("Date:") Then
            Console.WriteLine("Header validation failed")
            Return False
        End If
    End If

    Return True
End Function