pdf_detect_scanned.go hosted by Oembed Proxy for GitHub
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
/*
 * Detect scanned PDF files by looking through the object types and determining whether it is likely to be a scanned file.
 *
 * Run as: go run pdf_detect_scanned.go input.pdf
 */

package main

import (
	"fmt"
	"os"

	"github.com/unidoc/unipdf/v3/common/license"
	"github.com/unidoc/unipdf/v3/model"
)

func init() {
	// Make sure to load your metered License API key prior to using the library.
	// If you need a key, you can sign up and create a free one at https://cloud.unidoc.io
	err := license.SetMeteredKey(os.Getenv(`UNIDOC_LICENSE_API_KEY`))
	if err != nil {
		panic(err)
	}
}

func main() {
	if len(os.Args) < 2 {
		fmt.Printf("Syntax: go run pdf_detect_scanned.go input1.pdf input2.pdf ...\n")
		os.Exit(1)
	}

	for _, inputPath := range os.Args[1:] {
		err := detectScanned(inputPath)
		if err != nil {
			fmt.Printf("Error: %v\n", err)
		}
	}
}

func detectScanned(inputPath string) error {
	pdfReader, f, err := model.NewPdfReaderFromFile(inputPath, nil)
	if err != nil {
		return err
	}
	defer f.Close()

	numPages, err := pdfReader.GetNumPages()
	if err != nil {
		return err
	}
	fmt.Printf("%s (%d pages) - ", inputPath, numPages)
	objTypes, err := pdfReader.Inspect()
	if err != nil {
		return err
	}

	fontObjs, ok := objTypes["Font"]
	if !ok || fontObjs < 2 {
		fmt.Printf("SCANNED!\n")
	} else {
		fmt.Printf("not scanned (has text objects)\n")
	}

	return nil
}