如何从ASP.NET Core中的PDF文件读取数据

Install-Package IronPdf
dotnet add package IronPdf

using IronPdf;

Imports IronPdf

// Load a PDF document from disk
var pdf = PdfDocument.FromFile("document.pdf");

// Extract all text from every page
string allText = pdf.ExtractAllText();

// Extract text from a specific page (zero-based index)
string pageOneText = pdf.ExtractTextFromPage(0);

Console.WriteLine(allText);

Imports System

' Load a PDF document from disk
Dim pdf = PdfDocument.FromFile("document.pdf")

' Extract all text from every page
Dim allText As String = pdf.ExtractAllText()

' Extract text from a specific page (zero-based index)
Dim pageOneText As String = pdf.ExtractTextFromPage(0)

Console.WriteLine(allText)

[HttpPost("extract-form")]
public IActionResult ExtractForm([FromForm] IFormFile pdfFile)
{
    if (pdfFile == null || pdfFile.Length == 0)
        return BadRequest("No PDF file uploaded.");

    using var stream = new MemoryStream();
    pdfFile.CopyTo(stream);

    var pdf = new PdfDocument(stream.ToArray());
    var formData = new Dictionary<string, string>();

    if (pdf.Form != null)
    {
        foreach (var field in pdf.Form)
        {
            formData[field.Name] = field.Value;
        }
    }

    return Ok(new { formFields = formData });
}

Imports Microsoft.AspNetCore.Mvc
Imports System.IO

<HttpPost("extract-form")>
Public Function ExtractForm(<FromForm> pdfFile As IFormFile) As IActionResult
    If pdfFile Is Nothing OrElse pdfFile.Length = 0 Then
        Return BadRequest("No PDF file uploaded.")
    End If

    Using stream As New MemoryStream()
        pdfFile.CopyTo(stream)

        Dim pdf = New PdfDocument(stream.ToArray())
        Dim formData As New Dictionary(Of String, String)()

        If pdf.Form IsNot Nothing Then
            For Each field In pdf.Form
                formData(field.Name) = field.Value
            Next
        End If

        Return Ok(New With {.formFields = formData})
    End Using
End Function

[HttpPost("extract-table")]
public IActionResult ExtractTable([FromForm] IFormFile pdfFile)
{
    if (pdfFile == null || pdfFile.Length == 0)
        return BadRequest("No PDF file uploaded.");

    using var memoryStream = new MemoryStream();
    pdfFile.CopyTo(memoryStream);

    var pdf = new PdfDocument(memoryStream.ToArray());
    string text = pdf.ExtractAllText();

    // Split into lines, then split each line into columns
    string[] lines = text.Split(
        new[] { '\r', '\n' },
        StringSplitOptions.RemoveEmptyEntries
    );

    var tableData = new List<string[]>();
    foreach (string line in lines)
    {
        string[] columns = line
            .Split('\t')
            .Where(c => !string.IsNullOrWhiteSpace(c))
            .ToArray();

        if (columns.Length > 0)
            tableData.Add(columns);
    }

    var table = tableData.Select(r => string.Join(" | ", r)).ToList();
    return Ok(new { Table = table });
}

Imports Microsoft.AspNetCore.Mvc
Imports System.IO
Imports System.Linq

<HttpPost("extract-table")>
Public Function ExtractTable(<FromForm> pdfFile As IFormFile) As IActionResult
    If pdfFile Is Nothing OrElse pdfFile.Length = 0 Then
        Return BadRequest("No PDF file uploaded.")
    End If

    Using memoryStream As New MemoryStream()
        pdfFile.CopyTo(memoryStream)

        Dim pdf As New PdfDocument(memoryStream.ToArray())
        Dim text As String = pdf.ExtractAllText()

        ' Split into lines, then split each line into columns
        Dim lines As String() = text.Split(New Char() {ControlChars.Cr, ControlChars.Lf}, StringSplitOptions.RemoveEmptyEntries)

        Dim tableData As New List(Of String())()
        For Each line As String In lines
            Dim columns As String() = line.Split(ControlChars.Tab).Where(Function(c) Not String.IsNullOrWhiteSpace(c)).ToArray()

            If columns.Length > 0 Then
                tableData.Add(columns)
            End If
        Next

        Dim table = tableData.Select(Function(r) String.Join(" | ", r)).ToList()
        Return Ok(New With {.Table = table})
    End Using
End Function

[HttpPost("process-upload")]
public async Task<IActionResult> ProcessPdf([FromForm] IFormFile file)
{
    if (file == null || file.Length == 0)
        return BadRequest("No PDF file uploaded.");

    using var ms = new MemoryStream();
    await file.CopyToAsync(ms);

    var pdf = new PdfDocument(ms.ToArray());
    string text = pdf.ExtractAllText();
    int pageCount = pdf.PageCount;

    return Ok(new
    {
        text,
        pages = pageCount
    });
}

Imports System.IO
Imports Microsoft.AspNetCore.Mvc

<HttpPost("process-upload")>
Public Async Function ProcessPdf(<FromForm> file As IFormFile) As Task(Of IActionResult)
    If file Is Nothing OrElse file.Length = 0 Then
        Return BadRequest("No PDF file uploaded.")
    End If

    Using ms As New MemoryStream()
        Await file.CopyToAsync(ms)

        Dim pdf As New PdfDocument(ms.ToArray())
        Dim text As String = pdf.ExtractAllText()
        Dim pageCount As Integer = pdf.PageCount

        Return Ok(New With {
            .text = text,
            .pages = pageCount
        })
    End Using
End Function