Extract lines between two keywords in Word Document

Hi, It seems like you're using the Microsoft Office Interop library to search for keywords in a Word document. However, there are a few issues with your code

using Word = Microsoft.Office.Interop.Word;
using System.Linq;

string fileName = "D:\\Files\\Scan.doc"; // The file path goes here
string keyword1 = "Keyword1"; // The first keyword
string keyword2 = "Keyword2"; // The second keyword

Word.Application wordApp = new Word.Application();
Word.Document doc = null;

try
{
    doc = wordApp.Documents.Open(fileName);
    doc.Activate();

    List linesBetweenKeywords = new List();
    bool isBetweenKeywords = false;

    foreach (Word.Range wordRange in doc.Words)
    {
        string wordText = wordRange.Text.Trim();

        if (wordText.Equals(keyword1, StringComparison.CurrentCultureIgnoreCase))
        {
            isBetweenKeywords = true;
        }
        else if (wordText.Equals(keyword2, StringComparison.CurrentCultureIgnoreCase))
        {
            isBetweenKeywords = false;
            break; // Stop searching once the second keyword is found
        }

        if (isBetweenKeywords)
        {
            linesBetweenKeywords.Add(wordText);
        }
    }

    // Print the lines between the keywords
    foreach (string line in linesBetweenKeywords)
    {
        Console.WriteLine(line);
    }
}
catch (Exception ex)
{
    Console.WriteLine("Error: " + ex.Message);
}
finally
{
    // Close and release the Word objects
    if (doc != null)
    {
        doc.Close();
        Marshal.ReleaseComObject(doc);
    }

    if (wordApp != null)
    {
        wordApp.Quit();
        Marshal.ReleaseComObject(wordApp);
    }
}

Make sure to add the necessary using directives at the beginning of your code file:

using Word = Microsoft.Office.Interop.Word;
using System.Linq;
using System.Runtime.InteropServices;

This code will search for the lines between Keyword1 and Keyword2 in the Word document specified by the fileName variable. The lines will be stored in the linesBetweenKeywords list and then printed out. Remember to modify the fileName, keyword1, and keyword2 variables according to your specific requirements.

A solution you can look into is leveraging the DocumentAnazlyer class which allows you to specify a ruleset contained within a Json file. The ruleset would allow you to map exactly what kind of words you want to look out for. With this you'll be able to parse the results and know exactly where the words are located within the file. Here is a snippet which demonstrates this:

   // Initialize the OCR Engine 
   using (IOcrEngine ocrEngine = OcrEngineManager.CreateEngine(OcrEngineType.LEAD)) 
   { 
      // Load the document to be analyzed 
      using (LEADDocument document = DocumentFactory.LoadFromFile(@"C:\Desktop\test.docx", new LoadDocumentOptions())) 
      { 
         document.Text.OcrEngine = ocrEngine; 
 
         // Initialize the Document Analyzer 
         var analyzer = new DocumentAnalyzer() 
         { 
            Reader = new UnstructuredDataReader(), 
            QueryContext = new FileRepositoryContext(@"C:\Desktop\test.json") 
         }; 
 
         // Initialize the Document Options 
         var options = new DocumentAnalyzerRunOptions() 
         { 
            ElementQuery = new RepositoryQuery() 
         }; 
 
         // Create the list of results 
         List results = analyzer.Run(document, options); 
 
         string resultsMessage = string.Empty; 
 
         // Parse the results and output text to console 
         foreach (ElementSetResult result in results) 
            foreach (ElementResult item in result.Items) 
               Console.Write($"{(item.Value)} "); 
      } 

https://www.leadtools.com/help/sdk/dh/doxa/documentanalyzer-run.html
https://www.leadtools.com/help/sdk/tutorials/dotnet-console-parse-data-with-the-document-analyzer.html