使用Python批量处理图片的实战指南

pip install python-docx pillow

from docx import Document
from docx.shared import Inches, Cm
from PIL import Image
import io
import os

def extract_images_from_docx(folder_path):
    # 遍历文件夹里所有docx文件
    for filename in os.listdir(folder_path):
        if not filename.endswith('.docx'):
            continue
            
        doc_path = os.path.join(folder_path, filename)
        doc = Document(doc_path)
        
        # 准备一个文件夹存放提取出的图片
        img_folder = os.path.join(folder_path, filename.replace('.docx', '_images'))
        if not os.path.exists(img_folder):
            os.makedirs(img_folder)
        
        img_count = 0
        # 遍历文档中的所有段落
        for paragraph in doc.paragraphs:
            for run in paragraph.runs:
                # 在run的XML中查找图片标记
                blip = run._r.find('.//a:blip', 
                    namespaces={'a': 'http://schemas.openxmlformats.org/drawingml/2006/main'})
                if blip is not None:
                    embed_id = blip.get('{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed')
                    if embed_id and embed_id in run.part.related_parts:
                        image_part = run.part.related_parts[embed_id]
                        img_stream = io.BytesIO(image_part.blob)
                        img = Image.open(img_stream)
                        
                        img_count += 1
                        img_path = os.path.join(img_folder, f'image_{img_count}.jpg')
                        img.save(img_path, 'JPEG')
                        print(f'已提取: {img_path}')
        
        print(f'{filename} 处理完成，共提取 {img_count} 张图片')

def resize_images(image_folder, output_width=500):
    # 获取文件夹里所有图片
    image_files = [f for f in os.listdir(image_folder) 
                   if f.endswith(('.jpg', '.jpeg', '.png'))]
    
    for img_file in image_files:
        img_path = os.path.join(image_folder, img_file)
        img = Image.open(img_path)
        
        # 计算等比例缩放后的高度
        original_width, original_height = img.size
        new_height = int(output_width * original_height / original_width)
        
        # 使用高质量缩放算法
        resized_img = img.resize((output_width, new_height), Image.Resampling.LANCZOS)
        
        # 覆盖原图或者保存为新文件
        resized_img.save(img_path, quality=95)
        print(f'已调整尺寸: {img_file} -> {output_width}x{new_height}')

def create_photo_report(image_folder, output_path='report.docx'):
    # 创建新文档
    doc = Document()
    
    # 添加标题
    doc.add_heading('活动照片集锦', 0)
    
    # 获取所有图片文件并排序
    image_files = sorted([f for f in os.listdir(image_folder) 
                          if f.endswith(('.jpg', '.jpeg', '.png'))])
    
    for img_file in image_files:
        img_path = os.path.join(image_folder, img_file)
        
        # 添加一个段落，放图片说明
        doc.add_heading(img_file.replace('_', ' ').replace('.jpg', ''), level=2)
        
        # 插入图片，宽度设为6英寸，高度自动缩放
        doc.add_picture(img_path, width=Inches(6))
        
        # 添加一点留白
        doc.add_paragraph()
    
    doc.save(output_path)
    print(f'报告已生成: {output_path}')

# 假设我们要在文档的第一个段落之后插入图片
doc = Document('existing.docx')
target_paragraph = doc.paragraphs[0]  # 获取第一个段落
run = target_paragraph.add_run()       # 在段落中创建一个新run
run.add_picture('image.jpg', width=Inches(3))  # 插入图片

table = doc.add_table(rows=2, cols=2)
cell = table.cell(0, 0)  # 第一行第一列
paragraph = cell.paragraphs[0]
run = paragraph.add_run()
run.add_picture('image.jpg', width=Cm(5))