Python使用Spire.PDF轻松实现压缩PDF文件的大小

pip install Spire.PDF

from spire.pdf.common import *
from spire.pdf import *
# 定义输入和输出文件路径
inputFile = "/input/示例文档.pdf"
outputFile = "/output/压缩.pdf"
# 加载 PDF 文档
doc = PdfDocument()
doc.LoadFromFile(inputFile)
# 禁用增量更新，确保压缩生效
doc.FileInfo.IncrementalUpdate = False
# 设置压缩级别为最佳压缩
doc.CompressionLevel = PdfCompressionLevel.Best
# 再次确认禁用增量更新
doc.FileInfo.IncrementalUpdate = False
# 遍历所有页面，压缩其中的图像
imageHelper = PdfImageHelper()
for i in range(doc.Pages.Count):
    page = doc.Pages[i]
    if page is not None:
        # 获取页面中的所有图像信息
        imagesInfo = imageHelper.GetImagesInfo(page)
        if len(imagesInfo) > 0:
            # 尝试压缩每个图像
            for j in range(len(imagesInfo)):
                imagesInfo[j].TryCompressImage()
# 保存压缩后的文档
doc.SaveToFile(outputFile)
doc.Close()

from spire.pdf.common import *
from spire.pdf import *
import os
def CompressPdfFolder(input_folder: str, output_folder: str):
    """压缩文件夹中的所有 PDF 文件"""
    # 如果输出文件夹不存在则创建
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)
    # 统计信息
    total_original = 0
    total_compressed = 0
    # 遍历输入文件夹中的所有文件
    for filename in os.listdir(input_folder):
        if filename.endswith(".pdf"):
            # 构建完整的文件路径
            input_path = os.path.join(input_folder, filename)
            output_filename = filename
            output_path = os.path.join(output_folder, output_filename)
            # 获取原始文件大小
            original_size = os.path.getsize(input_path)
            total_original += original_size
            # 执行压缩
            doc = PdfDocument()
            doc.LoadFromFile(input_path)
            doc.FileInfo.IncrementalUpdate = False
            doc.CompressionLevel = PdfCompressionLevel.Best
            # 压缩图像
            imageHelper = PdfImageHelper()
            for i in range(doc.Pages.Count):
                page = doc.Pages[i]
                if page is not None:
                    imagesInfo = imageHelper.GetImagesInfo(page)
                    if len(imagesInfo) > 0:
                        for j in range(len(imagesInfo)):
                            imagesInfo[j].TryCompressImage()
            doc.SaveToFile(output_path)
            doc.Close()
            # 获取压缩后文件大小
            compressed_size = os.path.getsize(output_path)
            total_compressed += compressed_size
            # 计算压缩率
            ratio = (1 - compressed_size / original_size) * 100
            print(f"已压缩: {filename}")
            print(f"  原始大小: {original_size / 1024:.2f} KB")
            print(f"  压缩后: {compressed_size / 1024:.2f} KB")
            print(f"  压缩率: {ratio:.1f}%\n")
    # 输出总体统计
    overall_ratio = (1 - total_compressed / total_original) * 100
    print("=" * 50)
    print(f"总计:")
    print(f"  原始总大小: {total_original / 1024 / 1024:.2f} MB")
    print(f"  压缩后总大小: {total_compressed / 1024 / 1024:.2f} MB")
    print(f"  整体压缩率: {overall_ratio:.1f}%")
# 使用示例
input_folder = "./PDF文档"
output_folder = "./压缩后PDF"
CompressPdfFolder(input_folder, output_folder)