python（二）——word处理（20201029）

目录

2、例程

3、程序

4、函数

（1）paragraph.runs() 

更多处理

---

1、包安装

pip install python-docx

pip install docx之后都是报错。。

2、例程

指路官网：

https://python-docx.readthedocs.io/en/latest/index.html

官网给出的例程，注释掉加入图片之后可以正常运行。

from docx import Document
from 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 = True
p.add_run(' and some ')
p.add_run('italic.').italic = True

document.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('monty-truth.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')

3、程序

功能：BIOE的txt根据标签转换为word，不同标签的文本具有不同的颜色。

from random import randint
from docx import Document
from docx.shared import RGBColor
from docx.oxml.ns import qn
import re

readfile_path = 'test.txt'


def tagColor(tag_str):
    if tag_str.find('BX') != -1:  # 表现
        color_str = '7030A0'
    elif tag_str.find('BJ') != -1:  # 病机
        color_str = 'FFC000'
    elif tag_str.find('ZM') != -1:  # 证
        color_str = '00B0F0'
    elif tag_str.find('BZ') != -1:  # 病证
        color_str = 'FFFF00'
    elif tag_str.find('BM') != -1:   # 别名
        color_str = '00B050'
    else:  # （O）
        color_str = '000000'
    return color_str


if __name__ == "__main__":
    sentence = ''
    sen_tag_list = []
    doc = Document()
    doc.styles['Normal'].font.name = u'宋体'
    doc.styles['Normal']._element.rPr.rFonts.set(qn('w:eastAsia'), u'宋体')
    p = doc.add_paragraph()
    with open(readfile_path, 'r', encoding='utf-8') as f:
        try:
            while True:
                line = f.readline()
                # print(line)
                if (line != '\n'):
                    line = line.split(' ')
                    sentence += line[0]
                    sen_tag_list.append(line[1])
                else:
                    sentence += '\n'
                    sen_tag_list.append(' ')
        except:
            f.close()


    for i in range(len(sen_tag_list)):
        #p = doc.add_paragraph()

        color = tagColor(sen_tag_list[i])

        #print(sen_tag_list[i], color)
        run = p.add_run(sentence[i:i + 1])
        run.font.color.rgb = RGBColor.from_string(color)
    doc.save('final.docx')

4、函数

（1）paragraph.runs() 

paragaph objects

Sequence of Run instances corresponding to the <w:r> elements in this paragraph.

原始文本格式如图所示：

分为两段，代码中p[0]即指第一段。 

from docx import Document
document = Document('1.docx')
p = document.paragraphs
for n in p[0].runs:
    print('=====')
    rgb = n.font.color.rgb
    text = n.text
    print('text:' + text)
    print('rgb' + str(n.font.color.rgb))
'''
=====
text: 工作中会
rgb:None
=====
text: 遇到需要读
rgb:FF0000
=====
text: 取一个有几百页的word文档并从中整理出一些信息的需求，比如产品的API文档一般是word格式的。
rgb:None
'''

更多处理

https://www.jb51.net/article/180546.htm