PDF转JPG（并去除多余的白边）

首先，手动下载一个软件（poppler for Windows），下载地址：https://github.com/oschwartz10612/poppler-windows/releases/tag/v24.08.0-0

否则会出现以下错误：

PDFInfoNotInstalledError: Unable to get page count. Is poppler installed and in PATH?

下载完了之后解压并配置下环境变量并确认是否安装成功：

比如：解压到C:\software\poppler-24.08.0；添加系统环境变量：C:\software\poppler-24.08.0\Library\bin；打开cmd命令行验证：输入pdfinfo -v

完整代码：

#!/user/bin/env python3
# -*- coding: utf-8 -*-
import os
from pdf2image import convert_from_path
from PIL import Image
import numpy as np


def pdf_to_jpg(folder_path, output_path):
    for root, dirs, files in os.walk(folder_path):
        # 创建输出目录
        if not os.path.exists(output_path):
            os.makedirs(output_path)
        for file in files:
            if not file.endswith(".pdf"):
                continue
            if len(dirs) < 1:
                images = convert_from_path(os.path.join(root, file),
                                           dpi=600,
                                           poppler_path=r'C:\software\poppler-24.08.0\Library\bin')
                # 将每一页图像保存为JPEG文件
                for i, image in enumerate(images):
                    # 还可以指定宽度或高度，调整图像大小
                    # if width or height:
                    #     image = image.resize((width, height))
                    gray_image = image.convert("L")  # 将图片转为8位灰度图，“L”表示luminance
                    gray_array = np.array(gray_image)
                    threshold = 240
                    mask = gray_array < threshold  # 用阈值来获取图片中非白色部分
                    coords = np.column_stack(np.where(mask))
                    y0, x0 = coords.min(axis=0)  # 获取非白色区域的坐标
                    y1, x1 = coords.max(axis=0)
                    cropped_image = image.crop((x0, y0, x1+1, y1+1))
                    jpg_file = os.path.join(output_path, f"{file.split('.')[0]}.jpg")
                    cropped_image.save(jpg_file, 'JPEG')
                    print(f'Saved {output_path}')
            else:
                for d in dirs:
                    images = convert_from_path(os.path.join(root, d))
                    # 创建输出目录
                    output_path_d = os.path.join(output_path, d)
                    if not os.path.exists(output_path_d):
                        os.makedirs(output_path_d)
                    # 将每一页图像保存为JPEG文件
                    for i, image in enumerate(images):
                        # 还可以指定宽度或高度，调整图像大小
                        # if width or height:
                        #     image = image.resize((width, height))
                        jpg_file = os.path.join(output_path_d, f"{file.split('.')[0]}.jpg")
                        image.save(jpg_file, 'JPEG')
                        print(f'Saved {output_path_d}')

if __name__ == '__main__':
    # PDF文件路径
    pdf_path = r'C:\datasets\D94_pdf'
    pdf_to_jpg(pdf_path, r'C:\datasets\D94_jpg')
    # 转换为图像

参考链接：

python 去除图片白边_mob649e8167c4a3的技术博客_51CTO博客

Python学习笔记：PDF转图片 - Hider1214 - 博客园