Text Retrieval from PDFs using C# and .NET
Полный код
GitHubusing System;
using System.IO;
using SautinSoft;
using SautinSoft.Pdf;
using SautinSoft.Pdf.Content;
using System.Linq;
namespace Sample
{
class Sample
{
/// <summary>
/// Find text in the PDF.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/pdf/help/net/developer-guide/find-text.php
/// </remarks>
static void Main(string[] args)
{
// Before starting this example, please get a free 100-day trial key:
// https://sautinsoft.com/start-for-free/
// Apply the key here:
// PdfDocument.SetLicense("...");
string pdfFile = Path.GetFullPath(@"..\..\..\simple text.pdf");
var document = PdfDocument.Load(pdfFile);
{
// Find all occurrences of a given text in a pdf file.
var text = document.Pages[0].Content.GetText().Find("the");
Console.WriteLine("Found " + text.Count() + " elements of this symbol combination.");
}
}
}
}Option Infer On
Imports System
Imports System.IO
Imports SautinSoft
Imports SautinSoft.Pdf
Imports SautinSoft.Pdf.Content
Imports System.Linq
Namespace Sample
Friend Class Sample
''' <summary>
''' Find text in the PDF.
''' </summary>
''' <remarks>
''' Details: https://sautinsoft.com/products/pdf/help/net/developer-guide/find-text.php
''' </remarks>
Shared Sub Main(ByVal args() As String)
' Before starting this example, please get a free license:
' https://sautinsoft.com/start-for-free/
' Apply the key here:
' PdfDocument.SetLicense("...");
Dim pdfFile As String = Path.GetFullPath("..\..\..\simple text.pdf")
Dim document = PdfDocument.Load(pdfFile)
If True Then
' Find all occurrences of a given text in a pdf file.
Dim text = document.Pages(0).Content.GetText().Find("the")
Console.WriteLine("Found " & text.Count() & " elements of this symbol combination.")
End If
End Sub
End Class
End Namespace
Если вам нужен пример кода или у вас есть вопрос: напишите нам по адресу [email protected] или спросите в онлайн-чате (правый нижний угол этой страницы) или используйте форму ниже: