raw = cv2.imread(src, 1)
# 灰度图片
gray = cv2.cvtColor(raw, cv2.COLOR_BGR2GRAY)

binary = cv2.adaptiveThreshold(~gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 35, -5)
# 展示图片
cv2.imshow("binary_picture", binary)

rows, cols = binary.shape
scale = 40
# 自适应获取核值
# 识别横线:
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (cols // scale, 1))
eroded = cv2.erode(binary, kernel, iterations=1)
dilated_col = cv2.dilate(eroded, kernel, iterations=1)
cv2.imshow("excel_horizontal_line", dilated_col)# 识别竖线：
scale = 20
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, rows // scale))
eroded = cv2.erode(binary, kernel, iterations=1)
dilated_row = cv2.dilate(eroded, kernel, iterations=1)
cv2.imshow("excel_vertical_line：", dilated_row)

# 将识别出来的横竖线合起来
bitwise_and = cv2.bitwise_and(dilated_col, dilated_row)
cv2.imshow("excel_bitwise_and", bitwise_and)# 标识表格轮廓
merge = cv2.add(dilated_col, dilated_row)
cv2.imshow("entire_excel_contour：", merge)# 两张图片进行减法运算，去掉表格框线
merge2 = cv2.subtract(binary, merge)
cv2.imshow("binary_sub_excel_rect", merge2)new_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (2, 2))
erode_image = cv2.morphologyEx(merge2, cv2.MORPH_OPEN, new_kernel)
cv2.imshow('erode_image2', erode_image)
merge3 = cv2.add(erode_image, bitwise_and)
cv2.imshow('merge3', merge3)# 将焦点标识取出来
ys, xs = np.where(bitwise_and > 0)

# 横纵坐标数组

# 循环y坐标，x坐标分割表格
data = [[] for i in range(len(y_point_arr))]
for i in range(len(y_point_arr) - 1):for j in range(len(x_point_arr) - 1):# 在分割时，第一个参数为y坐标，第二个参数为x坐标cell = src[y_point_arr[i]:y_point_arr[i + 1], x_point_arr[j]:x_point_arr[j + 1]]cv2.imshow("sub_pic" + str(i) + str(j), cell)# 读取文字，此为默认英文# pytesseract.pytesseract.tesseract_cmd = 'E:/Tesseract-OCR/tesseract.exe'text1 = pytesseract.image_to_string(cell, lang="chi_sim+eng")# 去除特殊字符text1 = re.findall(r'[^*"/:?|<>″′‖ 〈n]', text1, re.S)text1 = "".join(text1)print('单元格图片信息：' + text1)data[i].append(text1)j = j + 1i = i + 1

with open(path, "w", newline='') as csv_file:writer = csv.writer(file, dialect='excel')for index, item in enumerate(data):if index != 0 and index != len(data) - 1:writer.writerows([[item[0], item[1], item[2], item[3], item[4], item[5]]])