Python使用python-docx庫復制Word文檔樣式的實現(xiàn)方法

更新時間：2025年05月18日 08:58:58 作者：東方佑

在日常辦公中,我們經(jīng)常需要處理Word文檔的格式調(diào)整、內(nèi)容更新等任務,本文將介紹如何使用python-docx庫來復制一個Word文檔的內(nèi)容及樣式,并展示如何利用此方法進行文檔內(nèi)容的自動化處理,需要的朋友可以參考下

引言

在日常辦公中，我們經(jīng)常需要處理Word文檔的格式調(diào)整、內(nèi)容更新等任務。對于那些希望通過編程手段自動完成這些工作的開發(fā)者來說，Python及其豐富的第三方庫提供了強大的支持。本文將介紹如何使用python-docx庫來復制一個Word文檔的內(nèi)容及樣式，并展示如何利用此方法進行文檔內(nèi)容的自動化處理。

環(huán)境準備

首先，確保你已經(jīng)安裝了python-docx庫。如果尚未安裝，可以通過以下命令進行安裝：

pip install python-docx

主要功能實現(xiàn)

復制段落和文本框樣式：通過定義copy_paragraph_style函數(shù)，我們可以復制舊段落或文本框的樣式到新創(chuàng)建的段落或文本框上。
識別分頁符：is_page_break函數(shù)幫助我們在文檔元素之間識別是否含有分頁符，這對于保持文檔布局的一致性非常重要。
克隆段落和表格：通過clone_paragraph和clone_table函數(shù)，我們可以根據(jù)舊文檔中的段落或表格創(chuàng)建新的段落或表格，并且保留原有的樣式設置。
復制單元格邊框：為了使新生成的表格看起來與原表格一致，我們實現(xiàn)了copy_cell_borders函數(shù)來復制每個單元格的邊框樣式。
完整文檔復制：最后，通過clone_document函數(shù)，我們可以復制整個文檔的內(nèi)容和樣式到一個新的Word文檔中。

示例代碼

以下是簡化版的核心代碼示例，展示了如何從舊文檔中提取內(nèi)容并創(chuàng)建一個新的文檔：

from docx import Document
# 假設其他必需的導入已包含在此處

def clone_document(old_doc_path, new_doc_path, out_text_list):
    try:
        # 加載舊文檔和創(chuàng)建新文檔
        old_doc = Document(old_doc_path)
        new_doc = Document()
        
        # 復制主體內(nèi)容
        elements = old_doc.element.body
        para_index = 0
        table_index = 0
        index = 0
        
        while index < len(elements):
            element = elements[index]
            if element.tag.endswith('p'):
                # 處理段落...
                para_index += 1
            elif element.tag.endswith('tbl'):
                # 處理表格...
                table_index += 1
            index += 1
        
        # 保存新文檔
        new_doc.save(new_doc_path)
        print(f"文檔已成功保存至：{new_doc_path}")
    except Exception as e:
        print(f"復制文檔時發(fā)生錯誤：{e}")

結(jié)論

通過上述方法，我們可以高效地復制Word文檔的內(nèi)容和樣式，這為文檔處理自動化提供了一種有效的解決方案。當然，根據(jù)實際需求的不同，你可以進一步擴展和完善這個基礎(chǔ)框架，比如添加對更多樣式的支持、優(yōu)化性能等。

希望這篇文章能為你提供有價值的參考，幫助你在日常工作中更高效地處理Word文檔。

生成文件代碼

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_list


def copy_paragraph_style(run_from, run_to):
    """復制 run 的樣式"""
    run_to.bold = run_from.bold
    run_to.italic = run_from.italic
    run_to.underline = run_from.underline
    run_to.font.size = run_from.font.size
    run_to.font.color.rgb = run_from.font.color.rgb
    run_to.font.name = run_from.font.name
    run_to.font.all_caps = run_from.font.all_caps
    run_to.font.strike = run_from.font.strike
    run_to.font.shadow = run_from.font.shadow


def is_page_break(element):
    """判斷元素是否為分頁符（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 True
    elif element.tag.endswith('tbl'):
        # 表格后可能有分頁符（通過下一個元素判斷）
        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 True
    return False


def clone_paragraph(old_para, new_doc, out_text_list):
    """根據(jù)舊段落創(chuàng)建新段落"""
    new_para = new_doc.add_paragraph()
    if old_para.style:
        new_para.style = old_para.style
    for 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.alignment
    return new_para


def copy_cell_borders(old_cell, new_cell):
    """復制單元格的邊框樣式"""
    old_tc = old_cell._tc
    new_tc = new_cell._tc

    old_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):
    """根據(jù)舊表格創(chuàng)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.style

    for 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.alignment
            copy_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.width

    return new_table


def clone_document(old_doc_path, new_doc_path, out_text_list ):
    # global out_text_list

    try:
        old_doc = Document(old_doc_path)
        new_doc = Document()

        # # 復制分節(jié)符及頁眉頁腳
        # 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
        #     # 其他分節(jié)符屬性...
        #
        #     # 頁眉
        #     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
        #
        #     # 頁腳
        #     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

        # 復制主體內(nèi)容
        elements = old_doc.element.body
        para_index = 0
        table_index = 0
        index = 0

        while 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 += 1
                index += 1
            elif element.tag.endswith('tbl'):
                old_table = old_doc.tables[table_index]
                clone_table(old_table, new_doc, out_text_list)
                table_index += 1
                index += 1
            elif 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 += 1
            else:
                index += 1

            # 檢查分頁符
            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 += 1
        if new_doc_path:
            new_doc.save(new_doc_path)
            print(f"文檔已成功保存至：{new_doc_path}")
        else:
            return out_text_list
    except Exception as e:
        print(f"復制文檔時發(fā)生錯誤：{e}")


# 使用示例
if __name__ == "__main__":
    out = gen_to_list('.docx', '')
    if out:
        print("文檔內(nèi)容:\n", out, """按照順序的文檔內(nèi)容請根據(jù)用戶要求更改文檔內(nèi)容，而不改變順序，且不改變內(nèi)容個數(shù)，最后將內(nèi)容list 輸出為到給定的json中
         ```json
         {"輸出":[]}
         ```
         用戶輸入:請潤色
         """)

        print("請求llm")
        print("提取json")
    print("填入模版")

    out = clone_document('.docx', 'only_text.docx',out)

生成文本列表代碼

from docx import Document
from docx.enum.text import  WD_BREAK
from docx.oxml import OxmlElement
from docx.oxml.shared import qn




def copy_paragraph_style(run_from, run_to):
    """復制 run 的樣式"""
    run_to.bold = run_from.bold
    run_to.italic = run_from.italic
    run_to.underline = run_from.underline
    run_to.font.size = run_from.font.size
    run_to.font.color.rgb = run_from.font.color.rgb
    run_to.font.name = run_from.font.name
    run_to.font.all_caps = run_from.font.all_caps
    run_to.font.strike = run_from.font.strike
    run_to.font.shadow = run_from.font.shadow


def is_page_break(element):
    """判斷元素是否為分頁符（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 True
    elif element.tag.endswith('tbl'):
        # 表格后可能有分頁符（通過下一個元素判斷）
        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 True
    return False


def clone_paragraph(old_para, new_doc,out_text_list):
    """根據(jù)舊段落創(chuàng)建新段落"""
    new_para = new_doc.add_paragraph()
    if old_para.style:
        new_para.style = old_para.style
    for 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.alignment
    return new_para


def copy_cell_borders(old_cell, new_cell):
    """復制單元格的邊框樣式"""
    old_tc = old_cell._tc
    new_tc = new_cell._tc

    old_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):
    """根據(jù)舊表格創(chuàng)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.style

    for 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.alignment
            copy_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.width

    return new_table


def clone_document(old_doc_path, new_doc_path):
    # global out_text_list
    out_text_list = []
    try:
        old_doc = Document(old_doc_path)
        new_doc = Document()

        # # 復制分節(jié)符及頁眉頁腳
        # 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
        #     # 其他分節(jié)符屬性...
        #
        #     # 頁眉
        #     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
        #
        #     # 頁腳
        #     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

        # 復制主體內(nèi)容
        elements = old_doc.element.body
        para_index = 0
        table_index = 0
        index = 0

        while 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 += 1
                index += 1
            elif element.tag.endswith('tbl'):
                old_table = old_doc.tables[table_index]
                clone_table(old_table, new_doc,out_text_list)
                table_index += 1
                index += 1
            elif 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 += 1
            else:
                index += 1

            # 檢查分頁符
            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 += 1
        if new_doc_path:
            new_doc.save(new_doc_path)
            print(f"文檔已成功保存至：{new_doc_path}")
        else:
            return out_text_list
    except Exception as e:
        print(f"復制文檔時發(fā)生錯誤：{e}")


# 使用示例
if __name__ == "__main__":
    out=clone_document('南山三防工作專報.docx', '')
    if out:
        print("文檔內(nèi)容:\n",out,"""按照順序的文檔內(nèi)容請根據(jù)用戶要求更改文檔內(nèi)容，而不改變順序，且不改變內(nèi)容個數(shù)，最后將內(nèi)容list 輸出為到給定的json中
         ```json
         {"輸出":[]}
         ```
         用戶輸入:請潤色
         """)

        print("請求llm")
        print("提取json")
    print("填入模版")

到此這篇關(guān)于Python使用python-docx庫復制Word文檔樣式的實現(xiàn)方法的文章就介紹到這了,更多相關(guān)Python python-docx庫復制Word樣式內(nèi)容請搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家！

您可能感興趣的文章: