Python实现从常规文档中提取图片的方法详解

pip install python-docx pymupdf openpyxl beautifulsoup4 pillow
pip install pdfplumber  # pdf解析备用方案
pip install tk          # python自带，无需安装

import zipfile
import os
from pil import image

def extract_docx_images(file_path, output_dir):
    # 解压docx文件
    with zipfile.zipfile(file_path, 'r') as zip_ref:
        # 提取media文件夹内的图片
        image_files = [f for f in zip_ref.namelist() if f.startswith('word/media/')]
        
        for img_file in image_files:
            # 保存图片到输出目录
            zip_ref.extract(img_file, output_dir)
            # 重命名文件
            src = os.path.join(output_dir, img_file)
            dst = os.path.join(output_dir, os.path.basename(img_file))
            os.rename(src, dst)
            
    return len(image_files)

import fitz  # pymupdf
import os

def extract_pdf_images(file_path, output_dir):
    doc = fitz.open(file_path)
    img_count = 0
    
    for page_num in range(len(doc)):
        page = doc.load_page(page_num)
        images = page.get_images(full=true)
        
        for img_index, img in enumerate(images):
            xref = img[0]
            base_image = doc.extract_image(xref)
            img_data = base_image["image"]
            
            # 保存为png
            img_path = os.path.join(output_dir, f"pdf_page{page_num}_img{img_index}.png")
            with open(img_path, "wb") as f:
                f.write(img_data)
            img_count += 1
                
    return img_count

from openpyxl import load_workbook
import os

def extract_excel_images(file_path, output_dir):
    wb = load_workbook(file_path)
    img_count = 0
    
    for sheet in wb.worksheets:
        for image in sheet._images:
            # 获取图片数据
            img = image._data
            img_path = os.path.join(output_dir, f"excel_{sheet.title}_img{img_count}.png")
            with open(img_path, "wb") as f:
                f.write(img)
            img_count += 1
                
    return img_count

import requests
from bs4 import beautifulsoup
import os
import base64

def extract_html_images(html_path, output_dir):
    if html_path.startswith('http'):
        response = requests.get(html_path)
        soup = beautifulsoup(response.text, 'html.parser')
    else:
        with open(html_path, 'r') as f:
            soup = beautifulsoup(f.read(), 'html.parser')
    
    img_tags = soup.find_all('img')
    img_count = 0
    
    for img in img_tags:
        src = img.get('src')
        if src.startswith('data:image'):
            # 处理base64编码图片
            header, data = src.split(',', 1)
            img_format = header.split('/')[1].split(';')[0]
            img_data = base64.b64decode(data)
            img_path = os.path.join(output_dir, f"html_img{img_count}.{img_format}")
            with open(img_path, 'wb') as f:
                f.write(img_data)
            img_count += 1
                
    return img_count

import tkinter as tk
from tkinter import filedialog, messagebox
from core import docx_extractor, pdf_extractor, excel_extractor, html_extractor
import os

class imageextractorapp:
    def __init__(self, root):
        self.root = root
        self.root.title("多格式图片提取工具")
        
        # 文件路径变量
        self.file_path = tk.stringvar()
        self.output_dir = tk.stringvar(value="outputs")
        
        # 创建界面组件
        self.create_widgets()
    
    def create_widgets(self):
        # 文件选择
        tk.label(self.root, text="选择文件:").grid(row=0, column=0, padx=5, pady=5)
        tk.entry(self.root, textvariable=self.file_path, width=40).grid(row=0, column=1)
        tk.button(self.root, text="浏览", command=self.select_file).grid(row=0, column=2)
        
        # 输出目录
        tk.label(self.root, text="输出目录:").grid(row=1, column=0)
        tk.entry(self.root, textvariable=self.output_dir, width=40).grid(row=1, column=1)
        tk.button(self.root, text="选择目录", command=self.select_output_dir).grid(row=1, column=2)
        
        # 执行按钮
        tk.button(self.root, text="开始提取", command=self.start_extraction).grid(row=2, column=1, pady=10)
        
        # 日志区域
        self.log_text = tk.text(self.root, height=10, width=50)
        self.log_text.grid(row=3, column=0, columnspan=3)
    
    def select_file(self):
        file_types = [
            ('支持的文件类型', '*.docx *.pdf *.xlsx *.html'),
            ('word文档', '*.docx'),
            ('pdf文件', '*.pdf'),
            ('excel文件', '*.xlsx'),
            ('网页文件', '*.html')
        ]
        self.file_path.set(filedialog.askopenfilename(filetypes=file_types))
    
    def select_output_dir(self):
        self.output_dir.set(filedialog.askdirectory())
    
    def start_extraction(self):
        file_path = self.file_path.get()
        output_dir = self.output_dir.get()
        
        if not os.path.exists(output_dir):
            os.makedirs(output_dir)
            
        ext = os.path.splitext(file_path)[1].lower()
        
        try:
            if ext == '.docx':
                count = docx_extractor.extract_docx_images(file_path, output_dir)
            elif ext == '.pdf':
                count = pdf_extractor.extract_pdf_images(file_path, output_dir)
            elif ext == '.xlsx':
                count = excel_extractor.extract_excel_images(file_path, output_dir)
            elif ext == '.html':
                count = html_extractor.extract_html_images(file_path, output_dir)
            else:
                messagebox.showerror("错误", "不支持的文件类型")
                return
                
            self.log_text.insert(tk.end, f"成功提取 {count} 张图片到 {output_dir}\n")
        except exception as e:
            messagebox.showerror("错误", f"提取失败: {str(e)}")

if __name__ == "__main__":
    root = tk.tk()
    app = imageextractorapp(root)
    root.mainloop()