[python]裁剪文件夹中所有pdf文档并按名称保存到指定的文件夹

徐心兰2024-01-20 5:09

最近在写论文的实验部分，由于latex需要pdf格式的文档，审稿专家需要对pdf图片进行裁剪放大，以保证图片质量。

原图：

裁剪后的图像：

代码粘贴如下。将input_folder和output_folder替换即可。(x1, y1)，

(x2, y2) 分别代表裁剪框的像素位置。

bash 复制代码

import os
import PyPDF2
from PIL import Image

def crop_and_save_pdf(input_folder, output_folder, x1, y1, x2, y2):
    # Ensure output folder exists
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)

    # Process each PDF file in the input folder
    for filename in os.listdir(input_folder):
        if filename.endswith(".pdf"):
            input_pdf_path = os.path.join(input_folder, filename)
            output_png_path = os.path.join(output_folder, os.path.splitext(filename)[0] + ".png")
            output_pdf_path = os.path.join(output_folder, os.path.splitext(filename)[0] + ".pdf")
            with open(input_pdf_path, 'rb') as file:
                pdf_reader = PyPDF2.PdfReader(file)
                pdf_writer = PyPDF2.PdfWriter()

                for page_num in range(len(pdf_reader.pages)):
                    page = pdf_reader.pages[page_num]
                    page.cropbox.lower_left = (x1, y1)
                    page.cropbox.upper_right = (x2, y2)

                    pdf_writer.add_page(page)

                with open(output_pdf_path, 'wb') as output_file:
                    pdf_writer.write(output_file)

            # Convert the first page to PNG format for visualization
            # first_page = Image.open(output_pdf_path)
            # first_page.save(output_png_path, 'PNG')

# Specify input and output folders, and crop coordinates
input_folder = '/home/lxy/data_link2/evaluate/clip/HU_Compare'
output_folder = '/home/lxy/data_link2/evaluate/clip/HU_Compare2'
x1, y1 = 50, 400  # Left bottom coordinates
x2, y2 = 130, 550  # Right top coordinates

# Call the function to crop and save PDF pages as PNG
crop_and_save_pdf(input_folder, output_folder, x1, y1, x2, y2)