基于python的批量PDF文件转图像_pdfdoc = fitz.open(pdfpath) totalpage=pdfdoc.pages

一、基于python代码将批量的pdf转换为opencv的图像

该代码可以实现多页PDF的图像转换

import datetime
import os
import fitz  # fitz就是pip install PyMuPDF
import cv2
import numpy as np
 
 
def pix_to_image(pix):
    bytes = np.frombuffer(pix.samples, dtype=np.uint8)
    img = bytes.reshape(pix.height, pix.width, 3)
    cv_image = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
    return cv_image
 
def pyMuPDF_fitz(pdfPath):
    pdfDoc = fitz.open(pdfPath)
    pix_totall=[]
    for pg in range(pdfDoc.page_count):
        page = pdfDoc[pg]
        rotate = int(0)
        # zoom_x = 2.33333333  # (1.33333333-->1056x816)   (2-->1584x1224)
        # zoom_y = 2.33333333
        zoom_x = 4  # (1.33333333-->1056x816)   (2-->1584x1224)
        zoom_y = 4
        mat = fitz.Matrix(zoom_x, zoom_y).prerotate(rotate)
        pix = page.get_pixmap(matrix=mat, alpha=False)
        pix_totall.append(pix)
    return pix_totall
 
def get_files(path):
    """ 获取指定路径下所有文件名称 """
    files = []
    for filename in os.listdir(path):
        if os.path.isfile(os.path.join(path, filename)):
            files.append(filename)
    return files
 
if __name__ == "__main__":
    # 1、PDF地址
    pdfPath_totall = 'C:/code/box_word/PDF_BOX/pdf/'
    file_list = os.listdir(pdfPath_totall)
    imagePath = 'C:/code/box_word/PDF_BOX/pdf_images/'
    print(file_list)
    # # 2、需要储存图片的目录
    for i, name in enumerate(file_list):
        pdfPath=pdfPath_totall+name
        # image_save_Path=imagePath+'pdf3'+'.bmp'
        print(pdfPath)
        #将pdf转换成Buffer，多张图像依旧可以转换
        pix_totall=pyMuPDF_fitz(pdfPath)
        print("图像的总数为：", len(pix_totall))
 
        #将buffer转换成opencv的图像格式
        for i in range(len(pix_totall)):
            image_pfd=pix_to_image(pix_totall[i])
            gray_image = cv2.cvtColor(image_pfd, cv2.COLOR_BGR2GRAY)
            cv2.imwrite(imagePath  + name+'_'+str(i)+'pdf_.png', gray_image)
            cv2.imwrite(imagePath  + name+'_'+str(i)+'pdfcolor_.png', image_pfd)