How to extract pool information from a Word document?

Question

I want to extract information about the bullets present in a text document. I want something like this: Suppose the text below is in a text document:

Steps to start the car:

• Opened door
• Sit inside
• Close the door
• Insert key
• and etc.

Then I need a text file as shown below:

Steps to start the car:

<Bulet> Open Door </BULET>

<Bulet> Sit inside </BULET>

<Bulet> Close the door </BULET>

<Bulet> Insert Key </BULET>

<Bulet> etc. </Bulet>

I use C # language for this.

, , .., , .

- , ?

Answer 1

.....

. , doc , , - . , , . - , .

Answer 2

, . doc.Sentences - Range. , Range Paragraph.

        foreach (Paragraph para in oDoc.Paragraphs)
        {
            string paraNumber = para.Range.ListFormat.ListLevelNumber.ToString();
            string bulletStr = para.Range.ListFormat.ListString;
            MessageBox.Show(paraNumber + "\t" + bulletStr + "\t" + para.Range.Text);
        }

paraNumber buttetStr .

Answer 3

OpenXMLPower Eric White. NUGet. Visual Studio.

He provided a ready-made piece of code. This tool saved me many hours. Below is a way to configure a code snippet for my requirement. Infact you can use these methods in your project.

 private static WordprocessingDocument _wordDocument;
 private StringBuilder textItemSB = new StringBuilder();
 private List<string> textItemList = new List<string>();


/// Open word document using office SDK and reads all contents from body of document
/// </summary>
/// <param name="filepath">path of file to be processed</param>
/// <returns>List of paragraphs with their text contents</returns>
private void GetDocumentBodyContents()
{
    string modifiedString = string.Empty;
    List<string> allList = new List<string>();
    List<string> allListText = new List<string>();

    try
    {
_wordDocument = WordprocessingDocument.Open(wordFileStream, false);
        //RevisionAccepter.AcceptRevisions(_wordDocument);
        XElement root = _wordDocument.MainDocumentPart.GetXDocument().Root;
        XElement body = root.LogicalChildrenContent().First();
        OutputBlockLevelContent(_wordDocument, body);
    }
    catch (Exception ex)
    {
        logger.Error("ERROR in GetDocumentBodyContents:" + ex.Message.ToString());
    }
}


// This is recursive method. At each iteration it tries to fetch listitem and Text item. Once you have these items in hand 
// You can manipulate and create your own collection.
private void OutputBlockLevelContent(WordprocessingDocument wordDoc, XElement blockLevelContentContainer)
{
    try
    {
        string listItem = string.Empty, itemText = string.Empty, numberText = string.Empty;
        foreach (XElement blockLevelContentElement in
            blockLevelContentContainer.LogicalChildrenContent())
        {
            if (blockLevelContentElement.Name == W.p)
            {
                listItem = ListItemRetriever.RetrieveListItem(wordDoc, blockLevelContentElement);
                itemText = blockLevelContentElement
                    .LogicalChildrenContent(W.r)
                    .LogicalChildrenContent(W.t)
                    .Select(t => (string)t)
                    .StringConcatenate();
                if (itemText.Trim().Length > 0)
                {
                    if (null == listItem)
                    {
                        // Add html break tag 
                        textItemSB.Append( itemText + "<br/>");
                    }
                    else
                    {
                        //if listItem == "" bullet character, replace it with equivalent html encoded character                                   
                        textItemSB.Append("&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;" + (listItem == "" ? "&bull;" : listItem) + "&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;" + itemText + "<br/>");
                    }
                }
                else if (null != listItem)
                {
                    //If bullet character is found, replace it with equivalent html encoded character  
                    textItemSB.Append(listItem == "" ? "&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&bull;" : listItem);
                }
                else
                    textItemSB.Append("<blank>");
                continue;
            }
            // If element is not a paragraph, it must be a table.

            foreach (var row in blockLevelContentElement.LogicalChildrenContent())
            {                        
                foreach (var cell in row.LogicalChildrenContent())
                {                            
                    // Cells are a block-level content container, so can call this method recursively.
                    OutputBlockLevelContent(wordDoc, cell);
                }
            }
        }
        if (textItemSB.Length > 0)
        {
            textItemList.Add(textItemSB.ToString());
            textItemSB.Clear();
        }
    }
    catch (Exception ex)
    {
        .....
    }
}