Для конвертації pdf в jpeg використаємо пакет pdf2image. Суть проста: перебираємо всі файли в папці для того, щоб конвертувати pdf в jpeg та зберегти файл в новій папці.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import os | |
| import tempfile | |
| from pdf2image import convert_from_path | |
| folder = 'pdf' # older with pdfs. You need to create it manually. | |
| save_dir = 'saved' # folder dor images. You need to create it manually. | |
| log = open("log.txt", "a") | |
| for r, d, f in os.walk(folder): | |
| for filename in f: | |
| print(f'./{folder}/{filename}') | |
| log.write(filename + "\n") | |
| with tempfile.TemporaryDirectory() as path: | |
| images_from_path = convert_from_path(f'./{folder}/{filename}', dpi=200, output_folder=path) | |
| base_filename = os.path.splitext(os.path.basename(filename))[0] + '.jpg' | |
| for page in images_from_path: | |
| index = images_from_path.index(page) | |
| name = f'{base_filename}_{index}.jpg' | |
| print(name) | |
| page.save(os.path.join(save_dir, name), 'JPEG') | |
| log.close() |