pdf_extract_text.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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
/*
 * PDF to text: Extract all text for each page of a pdf file.
 *
 * Run as: go run pdf_extract_text.go input.pdf
 */

package main

import (
	"fmt"
	"os"

	"github.com/unidoc/unipdf/v3/common/license"
	"github.com/unidoc/unipdf/v3/extractor"
	"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("Usage: go run pdf_extract_text.go input.pdf\n")
		os.Exit(1)
	}

	inputPath := os.Args[1]

	err := outputPdfText(inputPath)
	if err != nil {
		fmt.Printf("Error: %v\n", err)
		os.Exit(1)
	}
}

// outputPdfText prints out contents of PDF file to stdout.
func outputPdfText(inputPath string) error {
	f, err := os.Open(inputPath)
	if err != nil {
		return err
	}

	defer f.Close()

	pdfReader, err := model.NewPdfReader(f)
	if err != nil {
		return err
	}

	numPages, err := pdfReader.GetNumPages()
	if err != nil {
		return err
	}

	fmt.Printf("--------------------\n")
	fmt.Printf("PDF to text extraction:\n")
	fmt.Printf("--------------------\n")
	for i := 0; i < numPages; i++ {
		pageNum := i + 1

		page, err := pdfReader.GetPage(pageNum)
		if err != nil {
			return err
		}

		ex, err := extractor.New(page)
		if err != nil {
			return err
		}

		text, err := ex.ExtractText()
		if err != nil {
			return err
		}

		fmt.Println("------------------------------")
		fmt.Printf("Page %d:\n", pageNum)
		fmt.Printf("\"%s\"\n", text)
		fmt.Println("------------------------------")
	}

	return nil
}