###pdf转化为图片###

import sys, fitz
import os
import datetime


def pyMuPDF_fitz(pdfPath, imagePath):
    startTime_pdf2img = datetime.datetime.now()  # 开始时间

    print("imagePath=" + imagePath)
    pdfDoc = fitz.open(pdfPath)
    for pg in range(pdfDoc.pageCount):
        page = pdfDoc[pg]
        rotate = int(0)
        # 每个尺寸的缩放系数为1.3，这将为我们生成分辨率提高2.6的图像。
        # 此处若是不做设置，默认图片大小为：792X612, dpi=72
        zoom_x = 1.33333333  # (1.33333333-->1056x816)   (2-->1584x1224)
        zoom_y = 1.33333333
        mat = fitz.Matrix(zoom_x, zoom_y).preRotate(rotate)
        pix = page.getPixmap(matrix=mat, alpha=False)

        if not os.path.exists(imagePath):  # 判断存放图片的文件夹是否存在
            os.makedirs(imagePath)  # 若图片文件夹不存在就创建

        pix.writePNG(imagePath + '/' + 'images_%s.png' % pg)  # 将图片写入指定的文件夹内

    endTime_pdf2img = datetime.datetime.now()  # 结束时间
    print('pdf2img时间=', (endTime_pdf2img - startTime_pdf2img).seconds)


if __name__ == "__main__":
    pdfPath = '2.pdf'   # pdf文件名
    imagePath = 'book'  # 提取出的pdf，转化的图片存放的文件夹名
    pyMuPDF_fitz(pdfPath, imagePath)


    def to_page(file_img):
        image = Image.open(file_img)
        image_arr = np.array(image)
        for i in range(len(image_arr)):
            t = 0
            for j in range(len(image_arr[0])):
                if not str(image_arr[i][j]) == '[255 255 255]':
                    t += 1
                if t >= 300:
                    return True
            if t != 0:
                return False


    def page(path):
        path = list(path)
        path[-5] = str(int(path[-5]) + 1)
        path = ''.join(path)
        if to_page(path):
            results = OCR(path)
            for re in results:
                re[0][0][1] += 1100
                re[0][1][1] += 1100
                re[0][2][1] += 1100
                re[0][3][1] += 1100
            return results

        return None
def to_page(file_img):
    image = Image.open(file_img)
    image_arr = np.array(image)
    for i in range(len(image_arr)):
        t = 0
        for j in range(len(image_arr[0])):
            if not str(image_arr[i][j]) == '[255 255 255]':
                t += 1
            if t >= 300:
                return True
        if t != 0:
            return False

def page(path):
    path = list(path)
    path[-5] = str(int(path[-5])+1)
    path = ''.join(path)
    if to_page(path):
        results = OCR(path)
        for re in results:
            re[0][0][1] += 1100
            re[0][1][1] += 1100
            re[0][2][1] += 1100
            re[0][3][1] += 1100
        return results

    return None