Python實現(xiàn)從常規(guī)文檔中提取圖片的方法詳解

更新時間：2025年03月17日 10:34:33 作者：灝瀚星空

這篇文章主要為大家詳細介紹了如何使用Python實現(xiàn)從常規(guī)文檔(Word,PDF,Excel,HTML)中提取圖片的方法,有需要的小伙伴可以參考一下

1. 環(huán)境準備

安裝必需庫

pip install python-docx PyMuPDF openpyxl beautifulsoup4 pillow
pip install pdfplumber  # PDF解析備用方案
pip install tk          # Python自帶，無需安裝

工具選擇

開發(fā)環(huán)境：VSCode + Python插件

調(diào)試工具：Python IDLE（初學者友好）

打包工具：pyinstaller（可選，用于生成exe）

2. 項目架構設計

image-extractor/
├── main.py # 主程序入口
├── core/
│ ├── docx_extractor.py
│ ├── pdf_extractor.py
│ ├── excel_extractor.py
│ └── html_extractor.py
└── outputs/ # 默認輸出目錄

3. 核心功能實現(xiàn)

(1) Word文檔提取 (docx_extractor.py)

import zipfile
import os
from PIL import Image

def extract_docx_images(file_path, output_dir):
    # 解壓docx文件
    with zipfile.ZipFile(file_path, 'r') as zip_ref:
        # 提取media文件夾內(nèi)的圖片
        image_files = [f for f in zip_ref.namelist() if f.startswith('word/media/')]
        
        for img_file in image_files:
            # 保存圖片到輸出目錄
            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)

(2) PDF文件提取 (pdf_extractor.py)

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"]
            
            # 保存為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

(3) Excel文件提取 (excel_extractor.py)

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:
            # 獲取圖片數(shù)據(jù)
            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

(4) HTML文件提取 (html_extractor.py)

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'):
            # 處理base64編碼圖片
            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

4. 交互界面開發(fā) (main.py)

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("多格式圖片提取工具")
        
        # 文件路徑變量
        self.file_path = tk.StringVar()
        self.output_dir = tk.StringVar(value="outputs")
        
        # 創(chuàng)建界面組件
        self.create_widgets()
    
    def create_widgets(self):
        # 文件選擇
        tk.Label(self.root, text="選擇文件:").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="瀏覽", command=self.select_file).grid(row=0, column=2)
        
        # 輸出目錄
        tk.Label(self.root, text="輸出目錄:").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="選擇目錄", command=self.select_output_dir).grid(row=1, column=2)
        
        # 執(zhí)行按鈕
        tk.Button(self.root, text="開始提取", command=self.start_extraction).grid(row=2, column=1, pady=10)
        
        # 日志區(qū)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 = [
            ('支持的文件類型', '*.docx *.pdf *.xlsx *.html'),
            ('Word文檔', '*.docx'),
            ('PDF文件', '*.pdf'),
            ('Excel文件', '*.xlsx'),
            ('網(wǎng)頁文件', '*.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("錯誤", "不支持的文件類型")
                return
                
            self.log_text.insert(tk.END, f"成功提取 {count} 張圖片到 {output_dir}\n")
        except Exception as e:
            messagebox.showerror("錯誤", f"提取失敗: {str(e)}")

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