# 基礎(chǔ)圖像處理
pip install pillow
# 操作Excel文件（選一個就行）
pip install openpyxl          # 處理.xlsx文件，不支持圖片插入
pip install xlwings           # 需要本地有Excel軟件
pip install spire.xls.free    # 支持圖片操作，無需Excel環(huán)境

import xlwings as xw
import os

# 打開Excel文件
wb = xw.Book('產(chǎn)品目錄.xlsx')
sheet = wb.sheets['產(chǎn)品列表']

# 圖片存放的文件夾
image_folder = 'product_images/'

# 從第2行開始（假設(shè)第1行是表頭）
for i, filename in enumerate(os.listdir(image_folder), start=2):
    if filename.endswith(('.png', '.jpg')):
        # 構(gòu)建圖片完整路徑
        img_path = os.path.join(image_folder, filename)
        
        # 把圖片插入到B列當前行
        sheet.pictures.add(img_path, 
                          left=sheet.range(f'B{i}').left,
                          top=sheet.range(f'B{i}').top,
                          width=100,   # 設(shè)置寬度
                          height=80)   # 設(shè)置高度
        
        # 可選：調(diào)整行高讓圖片不重疊
        sheet.range(f'{i}:{i}').row_height = 80

wb.save()
wb.close()
print("搞定！圖片已全部插入")

# 假設(shè)有一個字典，鍵是產(chǎn)品編號，值是對應(yīng)圖片路徑
product_map = {
    'A001': 'images/A001.jpg',
    'A002': 'images/A002.jpg',
    # ...
}

for product_id, img_path in product_map.items():
    # 找到產(chǎn)品編號在哪一行
    cell = sheet.range('A:A').find(product_id)
    if cell:
        row = cell.row
        sheet.pictures.add(img_path,
                          left=sheet.range(f'C{row}').left,
                          top=sheet.range(f'C{row}').top,
                          width=100,
                          height=80)

from openpyxl import load_workbook
from openpyxl_image_loader import SheetImageLoader
import os

# 加載Excel文件
wb = load_workbook('帶圖片的報告.xlsx')
sheet = wb.active

# 創(chuàng)建保存圖片的文件夾
output_dir = 'extracted_images'
os.makedirs(output_dir, exist_ok=True)

# 用ImageLoader提取所有圖片
image_loader = SheetImageLoader(sheet)

# 遍歷所有單元格
for row in range(1, sheet.max_row + 1):
    for col in range(1, sheet.max_column + 1):
        cell = sheet.cell(row, col)
        if image_loader.image_in(cell.coordinate):
            img = image_loader.get(cell.coordinate)
            # 保存圖片，用行列命名
            img.save(f'{output_dir}/img_{row}_{col}.png')
            print(f'已保存：第{row}行第{col}列的圖片')

print(f'提取完成，圖片保存在{output_dir}文件夾')

from spire.xls import *

workbook = Workbook()
workbook.LoadFromFile('帶圖片的報告.xlsx')
sheet = workbook.Worksheets[0]

for i, picture in enumerate(sheet.Pictures):
    picture.Picture.Save(f'extracted_images/pic_{i}.png')

workbook.Dispose()

from PIL import Image
import os

def compress_image(input_path, output_path, quality=50):
    """
    壓縮圖片
    quality: 1-100，數(shù)值越小壓縮越狠，文件越小
    """
    img = Image.open(input_path)
    # 保存時指定quality，JPEG格式支持壓縮
    img.save(output_path, 'JPEG', quality=quality)
    
    # 看看壓縮效果
    original_size = os.path.getsize(input_path) / 1024
    compressed_size = os.path.getsize(output_path) / 1024
    print(f'{os.path.basename(input_path)}: '
          f'{original_size:.1f}KB → {compressed_size:.1f}KB')

def batch_compress(folder_path, quality=50):
    for filename in os.listdir(folder_path):
        if filename.endswith(('.png', '.jpg', '.jpeg')):
            input_path = os.path.join(folder_path, filename)
            output_path = os.path.join(folder_path, f'compressed_{filename}')
            compress_image(input_path, output_path, quality)

def compress_to_target(img_path, target_kb=100, max_attempts=5):
    """反復(fù)壓縮直到文件小于target_kb"""
    quality = 80
    for attempt in range(max_attempts):
        temp_path = f'temp_{attempt}.jpg'
        compress_image(img_path, temp_path, quality)
        
        if os.path.getsize(temp_path) / 1024 <= target_kb:
            # 壓縮成功
            os.replace(temp_path, img_path)
            return True
        
        # 還不夠小，繼續(xù)降低質(zhì)量
        quality -= 15
        os.remove(temp_path)
    
    return False

from spire.xls import *

workbook = Workbook()
workbook.LoadFromFile('需要壓縮圖片的表格.xlsx')

for sheet in workbook.Worksheets:
    for picture in sheet.Pictures:
        # 直接壓縮圖片，參數(shù)是壓縮比例
        picture.Compress(50)

workbook.SaveToFile('壓縮后的表格.xlsx', ExcelVersion.Version2016)
workbook.Dispose()

import pytesseract
from PIL import Image
import pandas as pd

# 如果Tesseract沒在系統(tǒng)路徑里，需要指定一下
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'

def image_to_excel(img_path, output_excel):
    # 讀取圖片
    img = Image.open(img_path)
    
    # 識別文字，chi_sim是中文簡體模型
    text = pytesseract.image_to_string(img, lang='chi_sim+eng')
    
    # 把識別結(jié)果按行分割
    lines = text.strip().split('\n')
    
    # 轉(zhuǎn)換成DataFrame并保存
    df = pd.DataFrame([line.split('\t') for line in lines])
    df.to_excel(output_excel, index=False, header=False)
    
    print(f'識別完成，結(jié)果保存在{output_excel}')

# 使用示例
image_to_excel('表格截圖.png', '識別結(jié)果.xlsx')

def preprocess_image(img_path):
    img = Image.open(img_path)
    # 轉(zhuǎn)為灰度圖
    img = img.convert('L')
    # 提高對比度
    from PIL import ImageEnhance
    enhancer = ImageEnhance.Contrast(img)
    img = enhancer.enhance(2.0)
    return img

img_path = r'C:\Users\name\images\product.jpg'
# 或者
img_path = 'C:/Users/name/images/product.jpg'