image_to_pdf_converter

image_to_pdf_converter.py

import img2pdf
import os
import re
from pathlib import Path
from typing import List, Optional


class ImageToPdfConverter:
    """将图片文件转换为高质量PDF的工具类"""
    
    def __init__(self, image_folder: str, output_pdf: str, file_ext: str = '.jpg'):
        self.image_folder = Path(image_folder)
        self.output_pdf = Path(output_pdf)
        self.file_ext = file_ext
        
    def extract_number(self, filename: str) -> int:
        """从文件名中提取括号内的数字作为排序依据"""
        match = re.search(r'\((\d+)\)', filename)
        return int(match.group(1)) if match else float('inf')
        
    def get_sorted_images(self) -> List[Path]:
        """获取并按序号排序的图片文件路径列表"""
        if not self.image_folder.exists():
            raise FileNotFoundError(f"文件夹 '{self.image_folder}' 不存在")
            
        image_files = [f for f in self.image_folder.iterdir() 
                      if f.is_file() and f.suffix.lower() == self.file_ext]
        
        return sorted(image_files, key=lambda x: self.extract_number(x.name))
    
    def convert(self) -> Optional[Path]:
        """执行转换过程，返回生成的PDF文件路径"""
        try:
            image_paths = self.get_sorted_images()
            
            if not image_paths:
                print(f"在 '{self.image_folder}' 中没有找到 {self.file_ext} 文件")
                return None
                
            # 确保输出目录存在
            self.output_pdf.parent.mkdir(parents=True, exist_ok=True)
            
            # 转换为PDF，保持原始质量
            with open(self.output_pdf, "wb") as f:
                f.write(img2pdf.convert([str(img) for img in image_paths]))
                
            print(f"无损质量PDF已成功保存为 '{self.output_pdf}'")
            return self.output_pdf
            
        except Exception as e:
            print(f"转换过程中出错: {e}")
            return None


def main():
    """主函数"""
    # 使用示例
    image_folder = 'path_to_your_images'  # 替换为实际图片文件夹路径
    output_pdf = 'output.pdf'  # 输出PDF文件名
    
    converter = ImageToPdfConverter(image_folder, output_pdf)
    converter.convert()


if __name__ == "__main__":
    main()

image_to_pdf_PIL.py

from PIL import Image
import os
import re

# 设置图片文件夹路径
image_folder = 'path_to_your_images'  # 替换为你的文件夹路径
output_pdf = 'output.pdf'  # 输出的PDF文件名

# 正则提取括号内的数字
def extract_number(filename):
    match = re.search(r'\((\d+)\)', filename)
    return int(match.group(1)) if match else float('inf')

# 获取所有jpg文件，按括号内数字排序
image_files = sorted(
    [f for f in os.listdir(image_folder) if f.endswith('.jpg')],
    key=extract_number
)

# 打开所有图片
images = []
for file in image_files:
    img_path = os.path.join(image_folder, file)
    img = Image.open(img_path)
    if img.mode != 'RGB':
        img = img.convert('RGB')
    images.append(img)

# 保存成PDF
images[0].save(output_pdf, save_all=True, append_images=images[1:])
print(f"PDF已保存为 {output_pdf}")