使用Python和`python-docx`库复制Word文档样式

在日常办公中，我们经常需要处理Word文档的格式调整、内容更新等任务。对于那些希望通过编程手段自动完成这些工作的开发者来说，Python及其丰富的第三方库提供了强大的支持。本文将介绍如何使用python-docx库来复制一个Word文档的内容及样式，并展示如何利用此方法进行文档内容的自动化处理。

环境准备

首先，确保你已经安装了python-docx库。如果尚未安装，可以通过以下命令进行安装：

pip install python-docx

主要功能实现

1. 复制段落和文本框样式：通过定义copy_paragraph_style函数，我们可以复制旧段落或文本框的样式到新创建的段落或文本框上。

2. 识别分页符：is_page_break函数帮助我们在文档元素之间识别是否含有分页符，这对于保持文档布局的一致性非常重要。

3. 克隆段落和表格：通过clone_paragraph和clone_table函数，我们可以根据旧文档中的段落或表格创建新的段落或表格，并且保留原有的样式设置。

4. 复制单元格边框：为了使新生成的表格看起来与原表格一致，我们实现了copy_cell_borders函数来复制每个单元格的边框样式。

5. 完整文档复制：最后，通过clone_document函数，我们可以复制整个文档的内容和样式到一个新的Word文档中。

示例代码

以下是简化版的核心代码示例，展示了如何从旧文档中提取内容并创建一个新的文档：

from docx import Document
# 假设其他必需的导入已包含在此处def clone_document(old_doc_path, new_doc_path, out_text_list):try:# 加载旧文档和创建新文档old_doc = Document(old_doc_path)new_doc = Document()# 复制主体内容elements = old_doc.element.bodypara_index = 0table_index = 0index = 0while index < len(elements):element = elements[index]if element.tag.endswith('p'):# 处理段落...para_index += 1elif element.tag.endswith('tbl'):# 处理表格...table_index += 1index += 1# 保存新文档new_doc.save(new_doc_path)print(f"文档已成功保存至：{new_doc_path}")except Exception as e:print(f"复制文档时发生错误：{e}")

结论

通过上述方法，我们可以高效地复制Word文档的内容和样式，这为文档处理自动化提供了一种有效的解决方案。当然，根据实际需求的不同，你可以进一步扩展和完善这个基础框架，比如添加对更多样式的支持、优化性能等。

希望这篇文章能为你提供有价值的参考，帮助你在日常工作中更高效地处理Word文档。

生成文件代码

from docx import Document
from docx.enum.text import WD_BREAK
from docx.oxml import OxmlElement
from docx.oxml.shared import qn
from copy_word_only_text_json import clone_document as gen_to_listdef copy_paragraph_style(run_from, run_to):"""复制 run 的样式"""run_to.bold = run_from.boldrun_to.italic = run_from.italicrun_to.underline = run_from.underlinerun_to.font.size = run_from.font.sizerun_to.font.color.rgb = run_from.font.color.rgbrun_to.font.name = run_from.font.namerun_to.font.all_caps = run_from.font.all_capsrun_to.font.strike = run_from.font.strikerun_to.font.shadow = run_from.font.shadowdef is_page_break(element):"""判断元素是否为分页符（段落或表格后）"""if element.tag.endswith('p'):for child in element:if child.tag.endswith('br') and child.get(qn('type')) == 'page':return Trueelif element.tag.endswith('tbl'):# 表格后可能有分页符（通过下一个元素判断）if element.getnext() is not None:next_element = element.getnext()if next_element.tag.endswith('p'):for child in next_element:if child.tag.endswith('br') and child.get(qn('type')) == 'page':return Truereturn Falsedef clone_paragraph(old_para, new_doc, out_text_list):"""根据旧段落创建新段落"""new_para = new_doc.add_paragraph()if old_para.style:new_para.style = old_para.stylefor old_run in old_para.runs:new_run = new_para.add_run(out_text_list.pop(0))copy_paragraph_style(old_run, new_run)new_para.alignment = old_para.alignmentreturn new_paradef copy_cell_borders(old_cell, new_cell):"""复制单元格的边框样式"""old_tc = old_cell._tcnew_tc = new_cell._tcold_borders = old_tc.xpath('.//w:tcBorders')if old_borders:old_border = old_borders[0]new_border = OxmlElement('w:tcBorders')border_types = ['top', 'left', 'bottom', 'right', 'insideH', 'insideV']for border_type in border_types:old_element = old_border.find(f'.//w:{border_type}', namespaces={'w': 'http://schemas.openxmlformats.org/wordprocessingml/2006/main'})if old_element is not None:new_element = OxmlElement(f'w:{border_type}')for attr, value in old_element.attrib.items():new_element.set(attr, value)new_border.append(new_element)tc_pr = new_tc.get_or_add_tcPr()tc_pr.append(new_border)def clone_table(old_table, new_doc, out_text_list):"""根据旧表格创建新表格"""new_table = new_doc.add_table(rows=len(old_table.rows), cols=len(old_table.columns))if old_table.style:new_table.style = old_table.stylefor i, old_row in enumerate(old_table.rows):for j, old_cell in enumerate(old_row.cells):new_cell = new_table.cell(i, j)for paragraph in new_cell.paragraphs:new_cell._element.remove(paragraph._element)for old_paragraph in old_cell.paragraphs:new_paragraph = new_cell.add_paragraph()for old_run in old_paragraph.runs:new_run = new_paragraph.add_run(out_text_list.pop(0))copy_paragraph_style(old_run, new_run)new_paragraph.alignment = old_paragraph.alignmentcopy_cell_borders(old_cell, new_cell)for i, col in enumerate(old_table.columns):if col.width is not None:new_table.columns[i].width = col.widthreturn new_tabledef clone_document(old_doc_path, new_doc_path, out_text_list ):# global out_text_listtry:old_doc = Document(old_doc_path)new_doc = Document()# # 复制分节符及页眉页脚# for old_section in old_doc.sections:#     new_section = new_doc.add_section(start_type=old_section.start_type)#     new_section.left_margin = old_section.left_margin#     new_section.right_margin = old_section.right_margin#     # 其他分节符属性...##     # 页眉#     for para in old_section.header.paragraphs:#         new_para = new_section.header.add_paragraph()#         for run in para.runs:#             new_run = new_para.add_run(run.text)#             copy_paragraph_style(run, new_run)#         new_para.alignment = para.alignment##     # 页脚#     for para in old_section.footer.paragraphs:#         new_para = new_section.footer.add_paragraph()#         for run in para.runs:#             new_run = new_para.add_run(run.text)#             copy_paragraph_style(run, new_run)#         new_para.alignment = para.alignment# 复制主体内容elements = old_doc.element.bodypara_index = 0table_index = 0index = 0while index < len(elements):element = elements[index]if element.tag.endswith('p'):old_para = old_doc.paragraphs[para_index]clone_paragraph(old_para, new_doc, out_text_list)para_index += 1index += 1elif element.tag.endswith('tbl'):old_table = old_doc.tables[table_index]clone_table(old_table, new_doc, out_text_list)table_index += 1index += 1elif element.tag.endswith('br') and element.get(qn('type')) == 'page':if index > 0:new_doc.add_paragraph().add_run().add_break(WD_BREAK.PAGE)index += 1else:index += 1# 检查分页符if index < len(elements) and is_page_break(elements[index]):if index > 0:new_doc.add_paragraph().add_run().add_break(WD_BREAK.PAGE)index += 1if new_doc_path:new_doc.save(new_doc_path)print(f"文档已成功保存至：{new_doc_path}")else:return out_text_listexcept Exception as e:print(f"复制文档时发生错误：{e}")# 使用示例
if __name__ == "__main__":out = gen_to_list('.docx', '')if out:print("文档内容:\n", out, """按照顺序的文档内容请根据用户要求更改文档内容，而不改变顺序，且不改变内容个数，最后将内容list 输出为到给定的json中```json{"输出":[]}```用户输入:请润色""")print("请求llm")print("提取json")print("填入模版")out = clone_document('.docx', 'only_text.docx',out)

生成文本列表代码

from docx import Document
from docx.enum.text import  WD_BREAK
from docx.oxml import OxmlElement
from docx.oxml.shared import qndef copy_paragraph_style(run_from, run_to):"""复制 run 的样式"""run_to.bold = run_from.boldrun_to.italic = run_from.italicrun_to.underline = run_from.underlinerun_to.font.size = run_from.font.sizerun_to.font.color.rgb = run_from.font.color.rgbrun_to.font.name = run_from.font.namerun_to.font.all_caps = run_from.font.all_capsrun_to.font.strike = run_from.font.strikerun_to.font.shadow = run_from.font.shadowdef is_page_break(element):"""判断元素是否为分页符（段落或表格后）"""if element.tag.endswith('p'):for child in element:if child.tag.endswith('br') and child.get(qn('type')) == 'page':return Trueelif element.tag.endswith('tbl'):# 表格后可能有分页符（通过下一个元素判断）if element.getnext() is not None:next_element = element.getnext()if next_element.tag.endswith('p'):for child in next_element:if child.tag.endswith('br') and child.get(qn('type')) == 'page':return Truereturn Falsedef clone_paragraph(old_para, new_doc,out_text_list):"""根据旧段落创建新段落"""new_para = new_doc.add_paragraph()if old_para.style:new_para.style = old_para.stylefor old_run in old_para.runs:out_text_list.append(old_run.text)new_run = new_para.add_run(old_run.text)copy_paragraph_style(old_run, new_run)new_para.alignment = old_para.alignmentreturn new_paradef copy_cell_borders(old_cell, new_cell):"""复制单元格的边框样式"""old_tc = old_cell._tcnew_tc = new_cell._tcold_borders = old_tc.xpath('.//w:tcBorders')if old_borders:old_border = old_borders[0]new_border = OxmlElement('w:tcBorders')border_types = ['top', 'left', 'bottom', 'right', 'insideH', 'insideV']for border_type in border_types:old_element = old_border.find(f'.//w:{border_type}', namespaces={'w': 'http://schemas.openxmlformats.org/wordprocessingml/2006/main'})if old_element is not None:new_element = OxmlElement(f'w:{border_type}')for attr, value in old_element.attrib.items():new_element.set(attr, value)new_border.append(new_element)tc_pr = new_tc.get_or_add_tcPr()tc_pr.append(new_border)def clone_table(old_table, new_doc,out_text_list):"""根据旧表格创建新表格"""new_table = new_doc.add_table(rows=len(old_table.rows), cols=len(old_table.columns))if old_table.style:new_table.style = old_table.stylefor i, old_row in enumerate(old_table.rows):for j, old_cell in enumerate(old_row.cells):new_cell = new_table.cell(i, j)for paragraph in new_cell.paragraphs:new_cell._element.remove(paragraph._element)for old_paragraph in old_cell.paragraphs:new_paragraph = new_cell.add_paragraph()for old_run in old_paragraph.runs:out_text_list.append(old_run.text)new_run = new_paragraph.add_run(old_run.text)copy_paragraph_style(old_run, new_run)new_paragraph.alignment = old_paragraph.alignmentcopy_cell_borders(old_cell, new_cell)for i, col in enumerate(old_table.columns):if col.width is not None:new_table.columns[i].width = col.widthreturn new_tabledef clone_document(old_doc_path, new_doc_path):# global out_text_listout_text_list = []try:old_doc = Document(old_doc_path)new_doc = Document()# # 复制分节符及页眉页脚# for old_section in old_doc.sections:#     new_section = new_doc.add_section(start_type=old_section.start_type)#     new_section.left_margin = old_section.left_margin#     new_section.right_margin = old_section.right_margin#     # 其他分节符属性...##     # 页眉#     for para in old_section.header.paragraphs:#         new_para = new_section.header.add_paragraph()#         for run in para.runs:#             new_run = new_para.add_run(run.text)#             copy_paragraph_style(run, new_run)#         new_para.alignment = para.alignment##     # 页脚#     for para in old_section.footer.paragraphs:#         new_para = new_section.footer.add_paragraph()#         for run in para.runs:#             new_run = new_para.add_run(run.text)#             copy_paragraph_style(run, new_run)#         new_para.alignment = para.alignment# 复制主体内容elements = old_doc.element.bodypara_index = 0table_index = 0index = 0while index < len(elements):element = elements[index]if element.tag.endswith('p'):old_para = old_doc.paragraphs[para_index]clone_paragraph(old_para, new_doc,out_text_list)para_index += 1index += 1elif element.tag.endswith('tbl'):old_table = old_doc.tables[table_index]clone_table(old_table, new_doc,out_text_list)table_index += 1index += 1elif element.tag.endswith('br') and element.get(qn('type')) == 'page':if index > 0:new_doc.add_paragraph().add_run().add_break(WD_BREAK.PAGE)index += 1else:index += 1# 检查分页符if index < len(elements) and is_page_break(elements[index]):if index > 0:new_doc.add_paragraph().add_run().add_break(WD_BREAK.PAGE)index += 1if new_doc_path:new_doc.save(new_doc_path)print(f"文档已成功保存至：{new_doc_path}")else:return out_text_listexcept Exception as e:print(f"复制文档时发生错误：{e}")# 使用示例
if __name__ == "__main__":out=clone_document('南山三防工作专报.docx', '')if out:print("文档内容:\n",out,"""按照顺序的文档内容请根据用户要求更改文档内容，而不改变顺序，且不改变内容个数，最后将内容list 输出为到给定的json中```json{"输出":[]}```用户输入:请润色""")print("请求llm")print("提取json")print("填入模版")