Python—docx 批量生成 docx 文件

一、文档结构

二、方法

from docx import Document
from docx.shared import Pt         # 字体磅数
from docx.oxml.ns import qn        # 中文格式
from docx.shared import Inches     # 图片尺寸
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT
from docx.shared import RGBColor
import time



today = time.strftime("%Y{y}%m{m}%d{d}",time.localtime()).format(y='年',m='月',d='日')


# 对客户或者领导的工作报告
Customer_Leader = {
    '经理1':'9：20',
    '经理2':'9：30',
    '经理3':'10：40',
    '张三': '13：20',
    '李四': '14：20',
    '王五': '15：20',
}


for key,value in Customer_Leader.items():
    document = Document()
    document.styles['Normal'].font.name = u'微软雅黑'
    document.styles['Normal'].font.size = Pt(14)
    document.styles['Normal']._element.rPr.rFonts.set(qn('w:eastAsia'), '微软雅黑')


    p = document.add_heading('关于XXX'+Customer_Leader[key]+'今日的报告', 0)      # 添加标题

    # 自定义--段落样式(样式名, 样式类型),样式类型: 1为段落样式, 2为字符样式, 3为表格样式)
    UserStyle1 = document.styles.add_style('UserStyle1', 1)
    UserStyle1.font.size = Pt(30)                                          # 字体尺寸
    UserStyle1.font.color.rgb = RGBColor(0xff, 0xde, 0x00)                 # 字体颜色
    UserStyle1.paragraph_format.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER  # 居中文本

    UserStyle1.paragraph_format.first_line_indent = Inches(0.3)            # 缩进
    UserStyle1.paragraph_format.space_before = Pt(18)                      # 段前间距
    UserStyle1.paragraph_format.space_after = Pt(12)                       # 段后间距
    UserStyle1.font.name = 'Times New Roman'                               # 西文字体
    UserStyle1._element.rPr.rFonts.set(qn('w:eastAsia'), '微软雅黑')        # 中文字体


    # 自定义--字符样式
    UserStyle2 = document.styles.add_style('UserStyle2', 2)
    UserStyle2.font.size = Pt(15)
    UserStyle2.font.color.rgb = RGBColor(0x0c, 0x8a, 0xc5)
    UserStyle2.font.name = '宋体'

    UserStyle2._element.rPr.rFonts.set(qn('w:eastAsia'), '宋体')

    # 段落-内容（依次添加段落1，段落2）
    txt_p1 = '由于天气原因导致产品价格上升%s的通知'%(today)
    p1 = document.add_paragraph(txt_p1, style=UserStyle1)

    txt_p2 = '预计2019年1-6月归属于上市公司股东的净利润盈利:7,419.218016万元至7,869.218016万元,同比上年增长约:50%至60%。'
    p2 = document.add_paragraph('').add_run(txt_p2,style=UserStyle2)

    # 添加分页符
    document.add_page_break()

    # 创建 有序列表
    document.add_paragraph('').add_run('微软财务分析人-有序列表内容').font.size = Pt(20)
    document.add_paragraph('UBS分析师', style='List Number')
    document.add_paragraph('纳德拉', style='List Number')
    document.add_paragraph('德意志银行分析师', style='List Number')

    # 创建 无序列表
    document.add_paragraph('').add_run('微软财务收入-无序列表内容').font.size = Pt(30)
    document.add_paragraph('游戏还是主要基于游戏机和个人电脑，微软对自己的定位', style='List Bullet')
    document.add_paragraph('微软会在Windows 10商务组件业务上保持两位数的增长', style='List Bullet')
    document.add_paragraph('最新的Office对Teams来说是一个全新的突破', style='List Bullet')
    document.add_paragraph('用户长期地表现出对产品的忠诚度，该产品越来越被认可了', style='List Bullet')

    # 添加分页符，插入图片（默认居左）
    document.add_page_break()
    document.add_paragraph('').add_run('详情价格单').font.size = Pt(30)
    document.add_picture('../gggg/001.png', width=Inches(1.25))

    records = (
                ('浙江东日',
                '预计2019年1-6月归属于上市公司股东的净利润盈利:7,419.218016万元至7,869.218016万元,同比上年增长约:50%至60%。',
                '因雨雪天气较多,蔬菜批发价格上涨'),
                ('长城汽车', '预计2019年1-6月归属于上市公司股东的净利润盈利:153,000万元,同比上年下降:58.6%。',
                '公司提高产品优惠额度让利消费者,并继续加大品牌推广力度及研发投入'),
                ('圣济堂', '预计2019年1-6月归属于上市公司股东的净利润亏损:1,500万元至2,500万元。',
                '甲醇市场处于持续低迷状态,医药行业受集中带量采购政策所影响,药品价格有所下降')
               )

    # 添加表
    table = document.add_table(rows=1, cols=3)
    hdr_cells = table.rows[0].cells            # 设置表首行标题
    hdr_cells[0].text = '股票简称'              # 表首行标题赋值
    hdr_cells[1].text = '业绩变动'
    hdr_cells[2].text = '业绩变动原因'
    for qty, id, desc in records:              # for循环将records内容赋值到单元格内
        row_cells = table.add_row().cells
        row_cells[0].text = str(qty)
        row_cells[1].text = id
        row_cells[2].text = desc

    document.save('./demo_'+str(key)+'.docx')  # 保存文件

三、表格批量写入数据

from docx import Document
from docx.shared import Pt         # 字体磅数
from docx.oxml.ns import qn        # 中文格式
from docx.shared import RGBColor
import time




def read_txt(txt_path):
	f = open(txt_path, "r", encoding="utf-8")
	lines = f.readlines()
	data_list = []
	for line in lines:
		data_list.append(line.strip('\n'))
	f.close()
	return data_list


def write_docx(doc_path,index,text):
    document = Document()
    document.styles['Normal'].font.name = u'宋体'
    document.styles['Normal'].font.size = Pt(10)
    document.styles['Normal']._element.rPr.rFonts.set(qn('w:eastAsia'), '宋体')

    records = (
                zip(tuple(text[:5000]),tuple(text[5000:10000]))
               )

    # 添加表(n行两列)
    table = document.add_table(rows=0, cols=2)
    for text1, text2 in records:
        row_cells = table.add_row().cells
        row_cells[0].text = text1
        row_cells[1].text = text2
    document.save(doc_path+'/medical_'+str(index)+'.docx')  # 保存文件


if __name__ == '__main__':
    txt_path = './text_local/medical.txt'
    doc_path = './test_doc'
    data_list = read_txt(txt_path)
    doc_num = len(data_list)//5000+1
    for index in range(doc_num):
        try:
            write_docx(doc_path, index,data_list[index*5000:(index+1)*10000])
        except:
            write_docx(doc_path, index,data_list[index*10000:])

四、批量修改表格文字字体大小颜色

import os
from docx import Document
from docx.shared import Pt         # 字体磅数
from docx.oxml.ns import qn
from docx.shared import RGBColor



def get_docx(docx_paths):
    docx_list = []
    for paths,dirs,filenames in os.walk(docx_paths):
        for filename in filenames:
            if filename.endswith('.docx'):
                docx_list.append(paths+'/'+filename)
    return docx_list

'''
增值税发票:深蓝色          #172194(23,33,148)
增值税电子发票:深紫黑色    #1F1023(31,16,35)
增值税发票:浅蓝色          #51557C(81,85,124)
医疗票据： 深黄黑色        #3F4537(63,69,55)
增值税电子发票: 浅黄色     #90867A(144,134,122)
'''


def rewrite_doc(docx_path,output_docx_paths):
    save_name = output_docx_paths+'/xieti_127_127_127_'+docx_path.split('/')[-1]
    document = Document(docx_path)
    table = document.tables[0]
    for row in table.rows:
        for cell in row.cells:
            paragraphs = cell.paragraphs
            paragraph = paragraphs[0]
            run_obj = paragraph.runs
            run = run_obj[0]
            # run.font.size = Pt(6.5)                                    # 字体大小
            # run.font.name = u'宋体'                                    # 字体
            # run._element.rPr.rFonts.set(qn('w:eastAsia'), '宋体')      # 字体
            # run.font.name = 'Times New Roman'
            run.font.color.rgb = RGBColor(23,33,148)                     # 字体颜色
            run.italic = True
    document.save(save_name)


if __name__ == '__main__':
    input_docx_paths = './标准轮廓宋体大小6.5副本'
    output_docx_paths = './xieti_23_33_148'
    docx_list = get_docx(input_docx_paths)
    for docx_path in docx_list:
        rewrite_doc(docx_path, output_docx_paths)

有关模板填充：https://www.cnblogs.com/cofear/p/10686299.html