Python合并两个PDF文件的两种实现方案

pip install pypdf2

from PyPDF2 import PdfFileMerger

def merge_pdfs(pdf_list, output_path):
    merger = PdfFileMerger()
    
    for pdf in pdf_list:
        try:
            with open(pdf, 'rb') as f:
                merger.append(f)
        except Exception as e:
            print(f"处理文件 {pdf} 时出错: {str(e)}")
    
    with open(output_path, 'wb') as outfile:
        merger.write(outfile)
    merger.close()

# 使用示例
merge_pdfs(['file1.pdf', 'file2.pdf'], 'merged.pdf')

pip install pdfplumber

import pdfplumber

def merge_pdfs_advanced(input_paths, output_path):
    with pdfplumber.PDF.open(input_paths[0]) as first_pdf:
        writer = first_pdf.copy()
        
        for path in input_paths[1:]:
            with pdfplumber.PDF.open(path) as pdf:
                for page in pdf.pages:
                    writer.add_page(page)
        
        with open(output_path, 'wb') as outfile:
            writer.write(outfile)

# 使用示例
merge_pdfs_advanced(['doc1.pdf', 'doc2.pdf'], 'combined.pdf')

# PyPDF2示例
merger.append(pdf_path, password='your_password')

# 需要使用PyPDF2的Bookmark特性
merger.addBookmark("Chapter 1", 0)

try:
    # 合并操作
except PyPDF2.utils.PdfMetricsError as e:
    print("页面尺寸不匹配:", e)
except Exception as e:
    print("未知错误:", e)