pdf提取页面为jpg图片

convert_pdf2jpg.py

import glob
import argparse
from wand.image import Image
import pdb

def convert2jpg(diag, pg=None):
    with(Image(filename=diag,resolution=200)) as source:
        images=source.sequence
        pages=len(images)
        if pg is not None:
            pages=pg
        for i in range(pages):
            Image(images[i]).save(filename="{}_{}.jpg".format(diag,i))


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('file', help='Input file paths')
    parser.add_argument('--pages', type=int, help='获取前多少页')
    args = parser.parse_args()
    pg = args.pages
    file_list = list(glob.iglob(args.file))
    print("to convert: {}".format((",").join(file_list)))
    # pdb.set_trace()
    for file_name in file_list:
        convert2jpg(file_name, pg)