Performing OCR on Japanese PDFs Using Tesseract and Pytesseract

1
import re
2
from datetime import datetime
3

4
import pdf2image
5
import pytesseract
6

7

8
def to_images(pdf_path: str, first_page: int = None, last_page: int = None) -> list:
9
    """ Convert a PDF to a PNG image.
10

11
    Args:
12
        pdf_path (str): PDF path
13
        first_page (int): First page starting 1 to be converted
14
        last_page (int): Last page to be converted
15

16
    Returns:
17
        list: List of image data
18
    """
19

20
    print(f'Convert a PDF ({pdf_path}) to a png...')
21
    images = pdf2image.convert_from_path(
22
        pdf_path=pdf_path,
23
        fmt='png',
24
        first_page=first_page,
25
        last_page=last_page,
26
    )
27
    print(f'A total of converted png images is {len(images)}.')
28
    return images
29

30

31
def to_string(image) -> str:
32
    """ OCR an image data.
33

34
    Args:
35
        image: Image data
36

37
    Returns:
38
        str: OCR processed characters
39
    """
40

41
    print(f'Extract characters from an image...')
42
    return pytesseract.image_to_string(image, lang='jpn')
43

44

45
def normalize(target: str) -> str:
46
    """ Normalize result text.
47

48
    Applying the following:
49
    - Remove new line.
50
    - Remove spaces between Japanese characters.
51

52
    Args:
53
        target (str): Target text to be normalized
54

55
    Returns:
56
        str: Normalized text
57
    """
58

59
    result = re.sub('\n', '', target)
60
    result = re.sub('([あ-んア-ン一-鿐])\s+((?=[あ-んア-ン一-鿐]))', r'\1\2', result)
61
    return result
62

63

64
def save(result: str) -> str:
65
    """ Save the result text in a text file.
66

67
    Args:
68
        result (str): Result text
69

70
    Returns:
71
        str: Text file path
72
    """
73

74
    path = 'result.txt'
75
    with open(path, 'w') as f:
76
        f.write(result)
77
    return path
78

79

80
def main() -> None:
81
    start = datetime.now()
82
    result = ''
83

84
    images = to_images('run-melos.pdf', 1, 2)
85
    for image in images:
86
        result += to_string(image)
87
    result = normalize(result)
88
    path = save(result)
89

90
    end = datetime.now()
91
    duration = end.timestamp() - start.timestamp()
92

93
    print('----------------------------------------')
94
    print(f'Start: {start}')
95
    print(f'End: {end}')
96
    print(f'Duration: {int(duration)} seconds')
97
    print(f'Result file path: {path}')
98
    print('----------------------------------------')
99

100

101
if __name__ == '__main__':
102
    main()

1
FROM python:3.10
2

3
WORKDIR /usr/src/app
4
COPY app.py ./
5
COPY requirements.txt ./
6
COPY run-melos.pdf ./
7
RUN apt update && apt install -y poppler-utils tesseract-ocr tesseract-ocr-jpn \
8
    && pip install -r requirements.txt
9

10
CMD ["python", "app.py"]
11
# CMD ["/bin/sh", "-c", "while :; do sleep 10; done"]