!pip install python-docx

from docx import Documentfrom docx.shared import Inches

document = Document()

document.add_heading('Document Title', 0)

p = document.add_paragraph('A plain paragraph having some ')
p.add_run('bold').bold = Truep.add_run(' and some ')
p.add_run('italic.').italic = Truedocument.add_heading('Heading, level 1', level=1)
document.add_paragraph('Intense quote', style='Intense Quote')

document.add_paragraph(    'first item in unordered list', style='List Bullet')
document.add_paragraph(    'first item in ordered list', style='List Number')

document.add_picture('imgs/13523736-c694e2233a8d0bb6.png', width=Inches(1.25))

records = (
    (3, '101', 'Spam'),
    (7, '422', 'Eggs'),
    (4, '631', 'Spam, spam, eggs, and spam')
)

table = document.add_table(rows=1, cols=3)
hdr_cells = table.rows[0].cells
hdr_cells[0].text = 'Qty'hdr_cells[1].text = 'Id'hdr_cells[2].text = 'Desc'for qty, id, desc in records:
    row_cells = table.add_row().cells
    row_cells[0].text = str(qty)
    row_cells[1].text = id
    row_cells[2].text = desc

document.add_page_break()

document.save('demo.docx')

document = Document('新闻稿_带格式.docx')

# 查看第1个段落的结构格式print(document.paragraphs[0].style.name)# 查看第1个段落的文本内容print(document.paragraphs[0].text)

# 查看第2个段落的结构格式print(document.paragraphs[1].style.name)# 查看第2个段落的文本内容print(document.paragraphs[1].text)

# 查看第4个段落的结构格式print(document.paragraphs[3].style.name)# 查看第4个段落的文本内容print(document.paragraphs[3].text)

def get_paragraphs_text(path):
    """
    获取所有段落的文本
    :param path: word路径
    :return: list类型，如：
        ['Test', 'hello world', ...]
    """
    document = Document(path)
    all_paragraphs = document.paragraphs
    paragraphs_text = []    for paragraph in all_paragraphs:        # 拼接一个list,包括段落的结构和内容
        paragraphs_text.append([paragraph.style.name,paragraph.text])    return paragraphs_text

# 提取文档信息text = get_paragraphs_text('新闻稿_带格式.docx')

# 随机查看一个封装后段落的信息text[9]

import osimport paddlehub as hub

text = get_paragraphs_text('新闻稿_带格式.docx')

model = hub.Module(name='transformer_zh-en', beam_size=5)
new_document = Document()for item in text:
    src_style = item[0]
    src_texts = [item[1]]    print('标题层级：', src_style)    print(src_texts)
    n_best = 1  # 每个输入样本的输出候选句子数量
    trg_texts = model.predict(src_texts, n_best=n_best)    print(trg_texts)    if src_style == 'Title':
        new_document.add_heading(trg_texts, 0)    elif src_style[:7:] == 'Heading':
        new_document.add_heading(trg_texts, level=int(src_style[-1]))    else:
        new_document.add_paragraph(trg_texts)
new_document.save('translate_news.docx')

标题层级： text_align-justify
['身处数字时代的浪潮中，你我的数字生活有哪些新生态？']
['In the digital age wave, what new ecology do you and I have in digital life?']
标题层级： Heading 1['数字化转型的浪潮已开启']
['The tide of digital transformation has started']
标题层级： text_align-justify
['截至2021年6月，我国网民规模为10.11亿，较2020年12月新增网民2175万，互联网普及率达71.6%。其中，我国手机网民规模为10.07亿，网民中使用手机上网的比例为99.6%。']
["By June 2021, the number of China's Internet users was 1.011 billion, an increase of 21.75 million since December 2020, and 71.6 percent of the Internet population."]

text = get_paragraphs_text('092016_cfpb_CreditReportingDisputeLetter.docx')

model = hub.Module(name='transformer_en-de', beam_size=5)
new_document = Document()for item in text:
    src_style = item[0]
    src_texts = [item[1]]    print('标题层级：', src_style)    print(src_texts)
    n_best = 1  # 每个输入样本的输出候选句子数量
    trg_texts = model.predict(src_texts, n_best=n_best)    print(trg_texts)    if src_style == 'Title':
        new_document.add_heading(trg_texts, 0)    elif src_style[:7:] == 'Heading':
        new_document.add_heading(trg_texts, level=int(src_style[-1]))    else:
        new_document.add_paragraph(trg_texts)
new_document.save('translate_en2de.docx')

def doc_translate(input_file, output_file, modelname):
    # 提取docx文档信息
    text = get_paragraphs_text(input_file)    # 指定模型
    model = hub.Module(name=modelname, beam_size=5)    # 准备生成转换后的文档
    new_document = Document()    for item in text:
        src_style = item[0]
        src_texts = [item[1]]        print('标题层级：', src_style)        print(src_texts)
        n_best = 1  # 每个输入样本的输出候选句子数量
        trg_texts = model.predict(src_texts, n_best=n_best)        print(trg_texts)        # 匹配转换后文档的标题层级
        if src_style == 'Title':
            new_document.add_heading(trg_texts, 0)        elif src_style[:7:] == 'Heading':
            new_document.add_heading(trg_texts, level=int(src_style[-1]))        else:
            new_document.add_paragraph(trg_texts)
    new_document.save(output_file)

word_folder = './word'files = os.listdir(word_folder)  
for fi in files:
    input_file = os.path.join(word_folder,fi)
    output_file = os.path.join(word_folder,'translate_' + os.path.basename(input_file))
    doc_translate(input_file, output_file, 'transformer_zh-en')

'''
全局内容替换
请确保要替换的内容样式一致

Args:
    doc: 文档对象
    old_text: 要被替换的文本
    new_text: 要替换成的文本
'''def replace_text(doc, old_text, new_text):
    # 遍历每个段落
    for p in doc.paragraphs:        # 如果要搜索的内容在该段落
        if old_text in p.text:            # 使用 runs 替换内容但不改变样式
            # 注意！runs 会根据样式分隔内容，确保被替换内容的样式一致
            for run in p.runs:                if old_text in run.text:
                    run.text = run.text.replace(old_text, new_text)

# 导入from docx import Document# 从文件创建文档对象document = Document('./word/translate_赛题介绍.docx')# 显示每段的内容replace_text(document, 'No', '')# 保存清洗后的文档document.save('word/translate_clean_赛题介绍.docx')