PDF Extractor

https://www.npmjs.com/package/pdf-extractor
Admin
Pdf-extractor is a wrapper around pdf.js to generate images, svgs, html files, text files and json...
Tokens:1,901
Snippets:30
Trust Score:9.6
Update:3 months ago
Show doc for...
Tokens:
Raw
### Install Package

Source: https://www.npmjs.com/package/pdf-extractor?activeTab=dependencies

Command to install the library via npm.

```bash
npm i pdf-extractor
```

--------------------------------

### Implement Custom Renderer

Source: https://www.npmjs.com/package/pdf-extractor?activeTab=dependencies

Extend the library by creating custom writers and renderers, such as this example for generating JPG files using the Canvas renderer.

```javascript
const PdfExtractor = require('pdf-extractor').PdfExtractor;
const CanvasRenderer = require('pdf-extractor').CanvasRenderer;
const SvgRenderer = require('pdf-extractor').SvgRenderer;
const FileWriter = require('pdf-extractor').FileWriter;

class JPGWriter extends FileWriter
{
	getFilePathForPage(page) {
		return super.getPagePath(page.pageNumber, 'png');
	}

	writeCanvasPage(page, viewport, canvas) {
		return this.writeStreamToFile(canvas.jpgStream(), this.getFilePathForPage(page))
	}
}

class JPGCanvasRenderer extends CanvasRenderer
{
	getWriters(writerOptions) {
		let writers = super.getWriters(writerOptions);
		writers.push(new JPGWriter(this.outputDir, writerOptions));
		return writers;
	}
}

let outputDir = '/path/to/output',

pdfExtractor = new PdfExtractor(outputDir, {
	renderers: [
		new JPGCanvasRenderer(outputDir, rendererOptions),
		new SvgRenderer(outputDir, rendererOptions)
	]
});

pdfExtractor.parse('/path/to/dummy.pdf').then(function () {
	console.log('# End of Document');
}).catch(function (err) {
	console.error('Error: ' + err);
});
```

--------------------------------

### Initialize Default Extractor

Source: https://www.npmjs.com/package/pdf-extractor?activeTab=dependencies

Use the default PdfExtractor to generate PNG, HTML, and text files from a specified page range of a PDF.

```javascript
const PdfExtractor = require('pdf-extractor').PdfExtractor;

let outputDir = '/path/to/output',

pdfExtractor = new PdfExtractor(outputDir, {
    viewportScale: (width, height) => {
        //dynamic zoom based on rendering a page to a fixed page size 
        if (width > height) {
            //landscape: 1100px wide
            return 1100 / width;
        }
        //portrait: 800px wide
        return 800 / width;
    },
    pageRange: [1,5],
});

pdfExtractor.parse('/path/to/dummy.pdf').then(function () {
	console.log('# End of Document');
}).catch(function (err) {
	console.error('Error: ' + err);
});
```

--------------------------------

### Generated File List

Source: https://www.npmjs.com/package/pdf-extractor?activeTab=dependencies

The expected output files generated by the default extractor configuration.

```text
info.json
page-1.png
page-2.png
page-3.png
page-4.png
page-5.png
stylesheet.css
text-1.html
text-1.txt
text-2.html
text-2.txt
text-3.html
text-3.txt
text-4.html
text-4.txt
text-5.html
text-5.txt
```
Tokens:
Raw