python-docx:将excel爬取题库转化为word格式便于浏览-Toy模板网

这篇具有很好参考价值的文章主要介绍了python-docx:将excel爬取题库转化为word格式便于浏览。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

新的改变

POE的GPT4.0错误太多难以吐槽。
似乎段落和运行的删除一直是失败的，所以在第一次添加的时候设置好所有格式
大纲等级设置失败了文章来源地址https://www.toymoban.com/news/detail-517295.html

代码实例

import os
import openpyxl
from docx import Document
from docx.enum.text import WD_BREAK
from docx.shared import Pt, Inches
from docx.shared import RGBColor

def bold_keywords(paragraph,text, keywords):
    str=[text]
    for keyword in keywords:
        tmp=[]
        for s in str:
            text_parts = s.split(keyword)
            for index, part in enumerate(text_parts):
                if index > 0:
                    tmp.append(keyword)
                tmp.append(part)
        str=tmp
    #print(str)
    for s in str:
        if s in keywords:
            run=paragraph.add_run(s)
            run.bold=True
        else:
            run = paragraph.add_run(s)
def replace_consecutive_line_breaks(paragraph):
    """
    将段落中连续的两个换行符替换为一个。
    """
    for run in paragraph.runs:
        run.text = run.text.replace('\n\n', '\n')

def sheet2docx(path,file,suffix='.xlsx'):
    # 读取 Excel 表格
    excel_file = path+'\\'+file+suffix
    wb = openpyxl.load_workbook(excel_file)
    ws = wb.active

    # 创建 Word 文档
    doc = Document()

    # 设置 Word 文档的默认字体和字体大小
    style = doc.styles['Normal']
    font = style.font
    font.name = '微软雅黑'
    font.size = Pt(12)

    # 定义题目之间的间距
    spacing_between_questions = Inches(0)

    # 将题目添加到 Word 文档中
    index = 0
    while index < ws.max_row:
        qp=doc.add_paragraph()
        # 获取题目内容
        question1 = ws.cell(row=index + 2, column=3).value
        analysis = ws.cell(row=index + 2, column=4).value
        answer1 = ws.cell(row=index + 2, column=5).value
        if question1 is not None:
            # 添加第一道题
            run=qp.add_run(question1)
            qp._element.attrib['{http://schemas.openxmlformats.org/wordprocessingml/2006/main}outlineLvl'] = '1'  # 使用字符串表示，注意从0开始，0表示大纲级别1
            qp.add_run().add_break(WD_BREAK.LINE)
            run.bold = True
            run.font.color.rgb = RGBColor(0, 0, 255)
            current_paragraph = doc.add_paragraph()
            bold_keywords(current_paragraph,analysis, ['粉笔审题', '审题点'])

            current_paragraph.add_run().add_break(WD_BREAK.LINE)
            doc.add_paragraph().add_run().add_break(WD_BREAK.PAGE)
            # 设置段落间距
            current_paragraph_format = current_paragraph.paragraph_format
            current_paragraph_format.space_after = spacing_between_questions
            #replace_consecutive_line_breaks(current_paragraph)

            second_paragraph = doc.add_paragraph()
            bold_keywords(second_paragraph,answer1, ['粉笔示例'])
            doc.add_paragraph().add_run().add_break(WD_BREAK.PAGE)

            index += 1

        else:
            break


    # 保存 Word 文档
    doc.save(path+'\\'+file+'.docx')
path='F:\huang\Desktop\草稿本'
for file in os.listdir(path):
    filename=os.path.splitext(file)[0]
    suffix=os.path.splitext(file)[1]
    #result=re.match('~$',filename,0)
    if suffix=='.xlsx':
        sheet2docx(path,filename,suffix)