利用Python操作Word文档页码的实际应用

from docx import Document
from docx.oxml.shared import qn
from docx.oxml import parse_xml

def process_word_document(doc_path, output_path):
    # 打开Word文档
    doc = Document(doc_path)
    
    # 获取文档中的所有节
    sections = doc.sections
    
    print(f"文档共有 {len(sections)} 个节")
    
    # 处理第一节（特殊处理，不链接到前一节）
    first_section = sections[0]
    first_footer = first_section.footer
    
    # 清除第一节页脚内容
    for paragraph in list(first_footer.paragraphs):
        p = paragraph._element
        p.getparent().remove(p)
    
    for table in list(first_footer.tables):
        t = table._element
        t.getparent().remove(t)
    
    print("已处理第1节")
    
    # 处理其他节
    for i, section in enumerate(sections[1:], 1):
        footer = section.footer
        
        # 清除页脚内容
        for paragraph in list(footer.paragraphs):
            p = paragraph._element
            p.getparent().remove(p)
        
        for table in list(footer.tables):
            t = table._element
            t.getparent().remove(t)
        
        # 设置页脚链接到前一节
        footer.is_linked_to_previous = True
        
        # 设置页码为续前节
        sectPr = section._sectPr
        pgNumType = sectPr.find(qn('w:pgNumType'))
        
        if pgNumType is None:
            pgNumType = parse_xml(r'<w:pgNumType xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"/>')
            sectPr.append(pgNumType)
        
        # 移除start属性以确保续前节
        start_attr = qn('w:start')
        if pgNumType.get(start_attr) is not None:
            pgNumType.attrib.pop(start_attr, None)
        
        # 每处理100节打印一次进度
        if (i + 1) % 100 == 0:
            print(f"已处理 {i + 1} 个节")
    
    # 保存文档
    doc.save(output_path)
    print(f"处理完成! 共处理了 {len(sections)} 个节")
    print("所有节的页脚已清除，设置为链接到前一节，且页码设置为续前节")

# 使用示例
if __name__ == "__main__":
    input_file = r"d:\wgx\ok\a619.docx"  # 输入文件路径
    output_file = r"d:\wgx\ok\a6190.docx"  # 输出文件路径
    process_word_document(input_file, output_file)
    

pip install python-docx