csharp 例如-CSHARP-GroupDocs.Text.Examples.CSharp-DocumentTextExtractor-ExtractTextFromPdfPortfolios.c

Posted 2021-05-12

//get file actual path
String filePath = Common.getFilePath(fileName);
// Create an extractor factory 
var factory = new ExtractorFactory();
// Create an instance of PdfTextExtractor class 
var extractor = new PdfTextExtractor(filePath);
//Set extraction mode to Fast text extraction
extractor.ExtractMode = ExtractMode.Simple; 
// Iterate over all files in the portfolio 
for (var i = 0; i < extractor.Entities.Count; i++)
{
  // Print the name of a file   
  Console.WriteLine(extractor.Entities[i].Name);
  // Open the stream of a file   
  using (var stream = extractor.Entities[i].OpenStream())
  {
      // Create the text extractor for a file     
      var entityExtractor = factory.CreateTextExtractor(stream);
      // If a media type is supported
      if (entityExtractor != null) 
      try
      {
        // Print the content of a file       
        Console.WriteLine(entityExtractor.ExtractAll());
      }
      finally
      {
        entityExtractor.Dispose();
      }
  }
}