Python 自动找出两份 PDF 文档的差别的方法

"""Python 自动找出两份 PDF 文档的差别"""
import PyPDF2
import os
from difflib import Differ

def extract_pdf_text(file_path):
    """提取 PDF 文档中的所有文本内容"""
    text_content = []
    try:
        with open(file_path, 'rb') as file:
            pdf_reader = PyPDF2.PdfReader(file)
            for page in pdf_reader.pages:
                text = page.extract_text()
                if text.strip():  # 忽略空页面
                    text_content.append(text)
    except Exception as e:
        print(f"读取 PDF 文件时出错: {e}")
    return text_content

def compare_pdf_documents(pdf1_path, pdf2_path, output_format='console'):
    """比较两个 PDF 文档的差异"""
    
    # 提取文本内容
    pdf1_content = extract_pdf_text(pdf1_path)
    pdf2_content = extract_pdf_text(pdf2_path)
    
    # 将内容转换为行列表以便比较
    pdf1_lines = []
    for page_text in pdf1_content:
        pdf1_lines.extend(page_text.split('\n'))
    
    pdf2_lines = []
    for page_text in pdf2_content:
        pdf2_lines.extend(page_text.split('\n'))
    
    # 使用 difflib 进行差异比较
    differ = Differ()
    diff_result = list(differ.compare(pdf1_lines, pdf2_lines))
    
    # 过滤出有差异的行
    differences = [line for line in diff_result if line.startswith(('+', '-'))]
    
    if not differences:
        print("两个 PDF 文档内容完全相同。")
        return
    
    if output_format == 'console':
        print("文档差异对比结果:")
        print("(- 表示第一个文档有但第二个文档没有)")
        print("(+ 表示第二个文档有但第一个文档没有)")
        print("-" * 50)
        
        for diff in differences:
            print(diff)
            
    elif output_format == 'file':
        output_filename = f"{os.path.splitext(pdf1_path)[0]}_vs_{os.path.splitext(pdf2_path)[0]}_diff.txt"
        
        with open(output_filename, 'w', encoding='utf-8') as output_file:
            output_file.write("PDF 文档差异对比报告\n")
            output_file.write("=" * 40 + "\n")
            output_file.write("(-) 第一个文档独有的内容\n")
            output_file.write("(+) 第二个文档独有的内容\n\n")
            
            for diff in differences:
                output_file.write(diff + '\n')
        
        print(f"差异报告已保存到: {output_filename}")
    
    else:
        print("不支持的输出格式，请选择 'console' 或 'file'")

# 使用示例
if __name__ == "__main__":
    # 比较两个 PDF 文档并在控制台显示差异
    compare_pdf_documents('document1.pdf', 'document2.pdf', output_format='console')
    
    # 或者将差异保存到文件
    # compare_pdf_documents('document1.pdf', 'document2.pdf', output_format='file')

pip install PyPDF2