[Python] PDF to PNG, PNG to JPG

1. PDF to PNG

!pip install PyMuPDF

import fitz

def pdf_to_png(pdf_file, output_folder, pdf_page_number = 0):
    doc = fitz.open(pdf_file)
    file_name = pdf_file.split('\\')[-1][:-4] # 파일 이름 추출
    
    try:
        if pdf_page_number == 0: # pdf_page_number 특정 값 미지정 시, 전체 변환
            for i, page in enumerate(doc):
                img = page.get_pixmap()   # 이미지 변환
                img.save(output_folder + '\\' + file_name + f'_{i}_output.png') # 변환된 이미지 저장
            print('전체 변환')
        elif pdf_page_number != 0:
            page = doc.load_page(pdf_page_number - 1) # 특정 페이지 가져오기
            i = pdf_page_number
            img = page.get_pixmap()   # 이미지 변환
            img.save(output_folder + '\\' + file_name + f'_{i}_only_output.png') # 변환된 이미지 저장
            print(pdf_page_number, '페이지 변환')
    except ValueError:
        print('Error: page not in document')
    
pdf_file = r'C:\Users\tmax\Desktop\OCR_QA\000_test\image\png\test_2.pdf'
output_folder = r'C:\Users\tmax\Desktop\OCR_QA\000_test\image\png'

pdf_to_png(pdf_file, output_folder,100)

• https://github.com/pymupdf/PyMuPDF

2. PNG to JPG

! pip install Pillow

from PIL import Image

def png_to_jpg(input_path, output_path):
    try:
        png_image = Image.open(input_path) # PNG 이미지 열기
        png_image.convert("RGB").save(output_path, "JPEG") # JPEG로 변환하여 저장
        print("성공")
    except Exception as e:
        print(f"오류 발생: {e}")

data_list = ['receipt1','receipt2','receipt3','receipt4','receipt5','receipt6','receipt7']

for a in data_list:
    
    input_path = r'C:\Users\OCR_QA\000_test\image\png\receipt' + '\\'
    output_path = r'C:\Users\OCR_QA\000_test\image\jpg\receipt' + '\\'

    input_file = input_path + a + '.png'
    output_file = output_path + a + '.jpg'
    
    png_to_jpg(input_file, output_file)