TextWord

6 Feb 20262 minutes to read

Represents a single word of extracted text from the PDF page.

// Load an existing PDF document
let document: PdfDocument = new PdfDocument(data);
// Initialize a new instance of the `PdfDataExtractor` class
let extractor: PdfDataExtractor = new PdfDataExtractor(document);
// Extract `TextLine` from the PDF document.
let textLines: Array<TextLine> = extractor.extractTextLines({ startPageIndex: 0, endPageIndex: document.pageCount-1});
textLines.forEach((textLine: TextLine) => {
  textLine.words.forEach((textWord: TextWord) => {
     // Gets the bounds of the text word.
     let wordBounds: Rectangle = textWord.bounds;
     // Gets the single word of extracted text from the PDF page.
     let word: string = textWord.text;
     // Gets the collection of text glyphs extracted from a specified page in a PDF document.
     let glyphs: TextGlyph[] = textword.glyphs;
     // Gets the name of the font used for a particular word.
     let wordFontName: string = textword.fontName;
     // Gets the style of the font used for a particular word.
     let wordFontStyle: PdfFontStyle = textword.fontStyle;
     // Gets the size of the font used for a particular word.
     let wordFontSize: number = textword.fontSize;
  });
});
// Save the document
document.save('output.pdf');
// Destroy the document
document.destroy();

Properties

Get bounds Rectangle

Gets the bounds of the text word.

Get fontName string

Gets the name of the font used for a particular word.

Get fontSize number

Gets the size of the font used for a particular word.

Get fontStyle PdfFontStyle

Gets the style of the font used for a particular word.

Get glyphs TextGlyph[]

Gets the collection of text glyphs extracted from a specified page in a PDF document.

Get text string

Gets the single word of extracted text from the PDF page.