Python中Word文件自动化操作小结

pip install python-docx

from docx import Document

# 读取Word文档，需要替换成你本地文件路径
document = Document('example.docx')

# 打印展示文档内容
for paragraph in document.paragraphs:
    print(paragraph.text)

from docx import Document
from docx.shared import RGBColor, Pt

# 打开Word文档
document = Document('example.docx')

# 获取第一个段落
paragraph = document.paragraphs[0]

# 修改段落文本样式
run = paragraph.add_run("Hello, World!")
run.font.size = Pt(20)
run.bold = True
run.font.color.rgb = RGBColor(255, 0, 0)


# 将修改后的内容写回原始文件
document.save('example.docx')

# 展示文档内容
for paragraph in document.paragraphs:
    print(paragraph.text)

from docx import Document

def modify_document(file_path):
    document = Document(file_path)

    # 添加文本
    document.add_paragraph('这是一个新的段落一。')
    document.add_paragraph('这是一个新的段落二。')
    document.add_paragraph('这是一个新的段落三：旧文本将被替换。')

    # 删除文本
    document.paragraphs[0].text = ""

    # 替换文本
    for paragraph in document.paragraphs:
        paragraph.text = paragraph.text.replace("旧文本", "新文本")

    # 将修改后的内容写回原始文件
    document.save(file_path)

# 调用函数来修改文档
modify_document('example.docx')

from docx import Document
from docx.shared import Inches

# 创建新文档
document = Document()

document.add_heading('欢迎使用Word自动化处理', level=1)
document.add_paragraph('这是一个新的段落。')
document.add_picture('image.jpg', width=Inches(1.25))

# 保存文件
document.save('新文档.docx')

from docx import Document
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT
from docx.shared import Inches
from docx.oxml.ns import nsdecls
from docx.oxml import parse_xml
from docx.enum.section import WD_ORIENT

def set_layout_header_footer(file_path):
    document = Document(file_path)

    # 设置页面布局
    sections = document.sections
    for section in sections:
        section.orientation = WD_ORIENT.LANDSCAPE
        section.page_width = Inches(11)
        section.page_height = Inches(8.5)

    # 设置页眉
    for section in document.sections:
        header = section.header
        header_paragraph = header.paragraphs[0]
        header_paragraph.text = "这是页眉"

    # 设置页脚
    for section in document.sections:
        footer = section.footer
        footer_paragraph = footer.paragraphs[0]
        footer_paragraph.text = "这是页脚"

    # 设置页码
    for section in document.sections:
        footer = section.footer
        footer.is_linked_to_previous = False
        footer_page_num_paragraph = footer.add_paragraph()
        footer_page_num_paragraph.text = "页码："
        footer_page_num_paragraph.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
        footer_page_num_run = footer_page_num_paragraph.add_run()
        fld_simple = parse_xml(
            r'<w:fldSimple xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" w:instr="PAGE"><w:r><w:t>1</w:t></w:r></w:fldSimple>')
        footer_page_num_run._r.append(fld_simple)

    document.save(file_path)

# 调用函数设置页面布局、页眉页脚和页码
set_layout_header_footer('新文档.docx')

from docx import Document
from docx.shared import Pt, Inches

def add_content(file_path):
    document = Document(file_path)

    # 添加标题
    title = document.add_heading('这是一个标题', level=1)

    # 添加段落
    paragraph1 = document.add_paragraph('这是第一个段落。')
    paragraph2 = document.add_paragraph('这是第二个段落。')

    # 设置字体样式和格式
    title_run = title.runs[0]
    title_run.bold = True
    title_run.italic = True
    title_run.font.size = Pt(18)

    paragraph1_run = paragraph1.runs[0]
    paragraph1_run.bold = True
    paragraph1_run.italic = False
    paragraph1_run.font.size = Pt(12)
    
    paragraph2_run = paragraph2.runs[0]
    paragraph2_run.bold = False
    paragraph2_run.italic = True
    paragraph2_run.font.size = Pt(10)

    # 添加图像
    document.add_picture('image.jpg', width=Inches(4), height=Inches(3))

    document.save(file_path)

# 调用函数添加标题、段落和图像等内容
add_content('新文档.docx')

from docx import Document
from docx.shared import Pt
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT

def adjust_font(file_path):
    document = Document(file_path)

    paragraph = document.add_paragraph('这是一个段落。')

    run = paragraph.runs[0]
    run.text = '这是调整字体样式和格式的例子。'
    run.font.name = '宋体'
    run.font.size = Pt(12)
    run.font.bold = True
    run.font.italic = True
    run.font.underline = True

    paragraph.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER

    document.save(file_path)

# 调用函数调整字体样式和格式
adjust_font('新文档.docx')

pip install python-docx

from docx import Document

folder_path = 'path/to/your/folder'  # 替换为实际的文件夹路径

def process_document(file_path):
    document = Document(file_path)
    print(f"处理文档：{file_path}")
    
    # 打印标题
    for title in document.paragraphs:
        if title.style.name.lower().startswith('heading'):
            print(f"标题: {title.text}")
            break  # 打印第一个标题即可

    # 打印段落
    for paragraph in document.paragraphs:
        print(f"段落: {paragraph.text}")
    
    print()  # 用于区分不同文档之间的输出

# 遍历文件夹下的所有 Word 文档并处理
import os

for file_name in os.listdir(folder_path):
    if file_name.endswith('.docx'):
        file_path = os.path.join(folder_path, file_name)
        process_document(file_path)

from docx import Document

# 合并多个文档
def merge_documents(file_paths, output_path):
    merged_document = Document()
    
    for file_path in file_paths:
        document = Document(file_path)
        for element in document.element.body:
            merged_document.element.body.append(element)
    
    merged_document.save(output_path)
    print("文档合并完成！")

# 拆分一个文档为多个部分
def split_document(source_path):
    document = Document(source_path)
    
    for i, section in enumerate(document.sections):
        new_document = Document()
        
        for element in section._sectPr:
            new_document._element.append(element)
        
        output_path = f"output_{i}.docx"
        new_document.save(output_path)
        print(f"已保存拆分的文档：{output_path}")

# 合并文档示例
file_paths = ['path/to/your/doc1.docx', 'path/to/your/doc2.docx', 'path/to/your/doc3.docx']
merge_documents(file_paths, 'merged_documents.docx')

# 拆分文档示例
split_document('path/to/your/source_document.docx')

from docx import Document

def replace_text_and_style(file_path, old_text, new_text, old_style, new_style):
    document = Document(file_path)
    
    for paragraph in document.paragraphs:
        if old_text in paragraph.text:
            paragraph.text = paragraph.text.replace(old_text, new_text)
        
        for run in paragraph.runs:
            if run.bold and old_style in run.style.name:
                run.style = new_style
    
    document.save(file_path)
    print(f"替换完成：{file_path}")

# 替换文本和样式示例
replace_text_and_style('path/to/your/document.docx', '老标题', '新标题', 'Bold', 'Heading 1')

from docx import Document

# 添加表格
def add_table(file_path, rows, cols):
    document = Document(file_path)
    table = document.add_table(rows, cols)

    # 添加表格内容
    for row in table.rows:
        for cell in row.cells:
            cell.text = "单元格"

    document.save(file_path)
    print("表格添加成功！")

# 删除表格
def delete_table(file_path, table_index):
    document = Document(file_path)
    tables = document.tables

    if table_index < len(tables):
        table = tables[table_index]
        table._element.getparent().remove(table._element)
        document.save(file_path)
        print("表格删除成功！")
    else:
        print("表格索引超出范围！")

# 示例：在文档中添加一个2行3列的表格
add_table('document.docx', 2, 3)
print("表格添加成功！")

# 示例：删除文档中的第一个表格
delete_table('document.docx', 0)
print("表格删除成功！")

from docx import Document

# 读取表格数据
def read_table_data(file_path, table_index, row_index, col_index):
    document = Document(file_path)
    tables = document.tables

    if table_index < len(tables):
        table = tables[table_index]
        cell_value = table.cell(row_index, col_index).text
        return cell_value
    else:
        print("表格索引超出范围！")
        return None

# 编辑表格数据
def edit_table_data(file_path, table_index, row_index, col_index, new_value):
    document = Document(file_path)
    tables = document.tables

    if table_index < len(tables):
        table = tables[table_index]
        table.cell(row_index, col_index).text = new_value
        document.save(file_path)
        print("表格数据已更新！")
    else:
        print("表格索引超出范围！")

# 示例：读取表格中第二行第三列的数据
data = read_table_data('doc1.docx', 0, 1, 2)
if data is not None:
    print("表格中的数据：", data)

# 示例：将表格中第三行第四列的数据修改为"新数据"
edit_table_data('doc1.docx', 0, 1, 2, "新数据")

from docx import Document
from docx.shared import Inches

# 插入图像
def insert_image(file_path, image_path):
    document = Document(file_path)
    document.add_picture(image_path, width=Inches(2), height=Inches(3))
    document.save(file_path)
    print("图像插入成功！")

# 调整图像大小
def resize_image(file_path, image_index, width, height):
    document = Document(file_path)
    images = document.inline_shapes

    if image_index < len(images):
        image = images[image_index]
        image.width = Inches(width)
        image.height = Inches(height)
        document.save(file_path)
        print("图像大小已调整！")
    else:
        print("图像索引超出范围！")

# 删除图像
def delete_image(file_path, image_index):
    document = Document(file_path)
    images = document.inline_shapes

    if image_index < len(images):
        image = images[image_index]
        image._inline.getparent().remove(image._inline)
        document.save(file_path)
        print("图像删除成功！")
    else:
        print("图像索引超出范围！")

# 示例：在文档中插入一张图像
insert_image('document.docx', 'image.jpg')
print("图像插入成功！")

# 示例：将文档中第二个图像的大小调整为3英寸宽，4英寸高
resize_image('document.docx', 1, 3, 4)
print("图像大小已调整！")

# 示例：删除文档中的第三个图像
delete_image('document.docx', 2)
print("图像删除成功！")

from docx import Document

document = Document()

# 添加目录页
document.add_page_break()

# 生成目录
document.add_heading("目录", level=1)
document.add_paragraph("一、简介")
document.add_paragraph("二、方法")
document.add_paragraph("三、结果")

document.save('report.docx')