使用Python处理Word文件
- 安装外部模块python-docx
pip install python-docx
1. 从Python看Word文件结构
在python-docx模块中,将Word文件结构分成3层:
- Document:最高层,代表整个Word文件。
- Paragraph:一个Word文件由许多段落组成,在Python中,整份文件的定义是Document,这些段落的定义就是Paragraph对象。在Python中,一个段落代表一个
Paragraph对象,所有段落以Paragraph对象列表方式存在。 - Run:Word文件要考虑的有字号、字体样式、色彩等,统称为样式。一个Run对象指的是Paragraph对象中相同样式的连续文字,如果文字发生样式变化,Python将以新的Run对象代表。
2. 读取Word文件内容
- 读取简单word文件
# author:mlnt
# createdate:2022/8/15
import docx # 导入docx模块
# 1.创建docx对象
document = docx.Document('test.docx')
# 2.获得Paragraph和Run数量
# 使用len()方法获得Paragraph数量
paragraph_count = len(document.paragraphs)
print(f'段落数:{paragraph_count}')
for i in range(0, paragraph_count):
# 获取Paragraph的Run数量
paragraph_run_count = len(document.paragraphs[i].runs) # i为Paragraph编号
print(document.paragraphs[i].text) # 打印Paragraph内容
print(document.paragraphs[i].runs[i].text) # 打印第i段第i个Run内容
def getFile(filename):
"""读取文件与适度编辑文件"""
document = docx.Document(filename) # 建立Word文件对象
content = []
for paragraph in document.paragraphs:
print(paragraph.text) # 输出文件所读取的Paragraph内容
content.append(paragraph.text) # 将每一段Paragraph组成列表
return '\n\n'.join(content) # 将列表转成字符串并隔行输出
print(getFile('test.docx'))
# 存储文件
document.save('out_test.docx') # 将文件复制到新文件
test.docx:
out_test.docx
- 读取含表格的word文档内容
# author:mlnt
# createdate:2022/8/15
import docx # 导入docx模块
from docx.document import Document
from docx.oxml import CT_P, CT_Tbl
from docx.table import _Cell, Table, _Row
from docx.text.paragraph import Paragraph
def iter_block_items(parent):
"""
依次遍历文档内容
按文档顺序生成对父级中每个段落和表子级的引用。
每个返回值都是表或段落的实例。
父对象通常是对主文档对象的引用,但也适用于_Cell对象,它本身可以包含段落和表格。
:param parent:
:return:
"""
# 判断传入的是否为word文档对象,是则获取文档内容的全部子对象
if isinstance(parent, Document):
parent_elm = parent.element.body
# 判断传入的是否为单元格,是则获取单元格内全部子对象
elif isinstance(parent, _Cell):
parent_elm = parent.tc
# 判断是否为表格行
elif isinstance(parent, _Row):
parent_elm = parent.tr
else:
raise ValueError("something's not right")
# 遍历全部子对象
for child in parent_elm.iterchildren():
# 判断是否为段落,是则返回段落对象
if isinstance(child, CT_P):
yield Paragraph(child, parent)
# 判断是否为表格,是则返回表格对象
if isinstance(child, CT_Tbl):
yield Table(child, parent)
# 1.创建docx对象
document = docx.Document('test.docx')
# 遍历word文档,最后调用函数没有返回值时停止遍历
for block in iter_block_items(document):
# 判断是否为段落
if isinstance(block, Paragraph):
print(block.text)
# 判断是否为表格
elif isinstance(block, Table):
for row in block.rows:
row_data = []
for cell in row.cells:
for paragraph in cell.paragraphs:
row_data.append(paragraph.text)
print("\t".join(row_data))
测试文档:
读取效果:
3. 创建文件内容
- 创建docx对象
# 1.创建docx对象
document = docx.Document()
- 设置页面
# 设置页眉
run_header = document.sections[0].header.paragraphs[0].add_run("test")
document.sections[0].header.paragraphs[0].alignment = WD_PARAGRAPH_ALIGNMENT.CENTER # 居中对齐
- 添加标题
# 2.添加标题
"""
add_heading():建立标题
- document.add_heading('content_of_heading', level=n)
"""
document.add_heading('侠客行', level=1) # 标题1格式
document.add_heading('李白', level=2) # 标题2格式
- 添加段落
# 3.添加段落
# 创建段落对象
"""
add_paragraph():建立段落Paragraph内容
- document.add_paragraph('paragraph_content')
"""
paragraph_object = document.add_paragraph('赵客缦胡缨,吴钩霜雪明。')
document.add_paragraph('银鞍照白马,飒沓如流星。')
document.add_paragraph('十步杀一人,千里不留行。')
document.add_paragraph('事了拂衣去,深藏身与名。')
document.add_paragraph('闲过信陵饮,脱剑膝前横。')
document.add_paragraph('将炙啖朱亥,持觞劝侯嬴。')
document.add_paragraph('三杯吐然诺,五岳倒为轻。')
document.add_paragraph('眼花耳热后,意气素霓生。')
document.add_paragraph('救赵挥金槌,邯郸先震惊。')
document.add_paragraph('千秋二壮士,烜赫大梁城。')
document.add_paragraph('纵死侠骨香,不惭世上英。')
document.add_paragraph('谁能书阁下,白首太玄经。')
prior_paragraph_object = paragraph_object.insert_paragraph_before('') # 在paragraph前插入新段落
- 建立Run内容,设置样式
# 4.建立Run内容
"""
Paragraph是由Run组成,使用add_run()方法可以在Paragraph中插入内容,语法如下:
paragraph_object.add_run('run_content')
"""
run1 = prior_paragraph_object.add_run('*'*13)
run2 = prior_paragraph_object.add_run('%'*13)
# 设置Run的样式
"""
bold: 加粗
italic:斜体
underline:下划线
strike:删除线
"""
run1.bold = True
run2.underline = True
# 设置段落居中对齐
for i in range(len(document.paragraphs)):
document.paragraphs[i].alignment = WD_PARAGRAPH_ALIGNMENT.CENTER # 居中对齐
- 添加换页符
# 5.添加换页符
# add_page_break()
document.add_page_break()
- 插入图片
# 6.插入图片
# add_picture(),调整图片宽高需导入docx.shared模块
document.add_picture('libai.jpeg', width=Pt(200), height=Pt(300))
# 设置居中对齐
document.paragraphs[len(document.paragraphs)-1].alignment = WD_PARAGRAPH_ALIGNMENT.CENTER # 居中对齐
- 创建表格,添加数据并设置简单样式
# 7.创建表格
"""
add_table(rows=n, cols=m)
"""
table = document.add_table(rows=2, cols=5)
# 添加表格内容
# 添加第1行数据
row = table.rows[0]
row.cells[0].text = '姓名'
row.cells[1].text = '字'
row.cells[2].text = '号'
row.cells[3].text = '所处时代'
row.cells[4].text = '别称'
# 添加第2行数据
row = table.rows[1]
row.cells[0].text = '李白'
row.cells[1].text = '太白'
row.cells[2].text = '青莲居士'
row.cells[3].text = '唐朝'
row.cells[4].text = '诗仙'
# 插入行
new_row = table.add_row() # 增加表格行
new_row.cells[0].text = '白居易'
new_row.cells[1].text = '乐天'
new_row.cells[2].text = '香山居士'
new_row.cells[3].text = '唐朝'
new_row.cells[4].text = '诗魔'
# 插入列
new_column = table.add_column(width=Inches(1)) # 增加表格列
new_column.cells[0].text = '代表作'
new_column.cells[1].text = '《侠客行》、《静夜思》'
new_column.cells[2].text = '《长恨歌》、《琵琶行》'
# 计算表格的rows和cols的长度
rows = len(table.rows)
cols = len(table.columns)
print(f'rows: {rows}')
print(f'columns: {cols}')
# 打印表格内容
# for row in table.rows:
# for cell in row.cells:
# print(cell.text)
# 设置表格样式
# table.style = 'LightShading-Accent1'
# UserWarning: style lookup by style_id is deprecated. Use style name as key instead.
table.style = 'Light Shading Accent 1'
# 循环将每一行,每一列都设置为居中
for r in range(rows):
for c in range(cols):
table.cell(r, c).vertical_alignment = WD_CELL_VERTICAL_ALIGNMENT.CENTER # 垂直居中
table.cell(r, c).paragraphs[0].paragraph_format.alignment = WD_TABLE_ALIGNMENT.CENTER # 水平居中
- 设置页码并保存
# 设置页码
add_page_number(document.sections[0].footer.paragraphs[0])
# 保存文件
document.save('test2.docx')
- 设置页码的代码(page_num.py)
from docx import Document
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT
from docx.oxml import OxmlElement, ns
def create_element(name):
return OxmlElement(name)
def create_attribute(element, name, value):
element.set(ns.qn(name), value)
def add_page_number(paragraph):
paragraph.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
page_run = paragraph.add_run()
t1 = create_element('w:t')
create_attribute(t1, 'xml:space', 'preserve')
t1.text = 'Page '
page_run._r.append(t1)
page_num_run = paragraph.add_run()
fldChar1 = create_element('w:fldChar')
create_attribute(fldChar1, 'w:fldCharType', 'begin')
instrText = create_element('w:instrText')
create_attribute(instrText, 'xml:space', 'preserve')
instrText.text = "PAGE"
fldChar2 = create_element('w:fldChar')
create_attribute(fldChar2, 'w:fldCharType', 'end')
page_num_run._r.append(fldChar1)
page_num_run._r.append(instrText)
page_num_run._r.append(fldChar2)
of_run = paragraph.add_run()
t2 = create_element('w:t')
create_attribute(t2, 'xml:space', 'preserve')
t2.text = ' of '
of_run._r.append(t2)
fldChar3 = create_element('w:fldChar')
create_attribute(fldChar3, 'w:fldCharType', 'begin')
instrText2 = create_element('w:instrText')
create_attribute(instrText2, 'xml:space', 'preserve')
instrText2.text = "NUMPAGES"
fldChar4 = create_element('w:fldChar')
create_attribute(fldChar4, 'w:fldCharType', 'end')
num_pages_run = paragraph.add_run()
num_pages_run._r.append(fldChar3)
num_pages_run._r.append(instrText2)
num_pages_run._r.append(fldChar4)
- 完整代码
import docx
from docx.enum.table import WD_TABLE_ALIGNMENT, WD_CELL_VERTICAL_ALIGNMENT
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT
from docx.shared import Pt, Inches
from page_num import add_page_number
# 1.创建docx对象
document = docx.Document()
# 设置页眉
run_header = document.sections[0].header.paragraphs[0].add_run("test")
document.sections[0].header.paragraphs[0].alignment = WD_PARAGRAPH_ALIGNMENT.CENTER # 居中对齐
print(len(document.sections))
# 2.添加标题
"""
add_heading():建立标题
- document.add_heading('content_of_heading', level=n)
"""
document.add_heading('侠客行', level=1) # 标题1格式
document.add_heading('李白', level=2) # 标题2格式
# 3.添加段落
# 创建段落对象
"""
add_paragraph():建立段落Paragraph内容
- document.add_paragraph('paragraph_content')
"""
paragraph_object = document.add_paragraph('赵客缦胡缨,吴钩霜雪明。')
document.add_paragraph('银鞍照白马,飒沓如流星。')
document.add_paragraph('十步杀一人,千里不留行。')
document.add_paragraph('事了拂衣去,深藏身与名。')
document.add_paragraph('闲过信陵饮,脱剑膝前横。')
document.add_paragraph('将炙啖朱亥,持觞劝侯嬴。')
document.add_paragraph('三杯吐然诺,五岳倒为轻。')
document.add_paragraph('眼花耳热后,意气素霓生。')
document.add_paragraph('救赵挥金槌,邯郸先震惊。')
document.add_paragraph('千秋二壮士,烜赫大梁城。')
document.add_paragraph('纵死侠骨香,不惭世上英。')
document.add_paragraph('谁能书阁下,白首太玄经。')
prior_paragraph_object = paragraph_object.insert_paragraph_before('') # 在paragraph前插入新段落
# 4.建立Run内容
"""
Paragraph是由Run组成,使用add_run()方法可以在Paragraph中插入内容,语法如下:
paragraph_object.add_run('run_content')
"""
run1 = prior_paragraph_object.add_run('*'*13)
run2 = prior_paragraph_object.add_run('%'*13)
# 设置Run的样式
"""
bold: 加粗
italic:斜体
underline:下划线
strike:删除线
"""
run1.bold = True
run2.underline = True
# 设置段落居中对齐
for i in range(len(document.paragraphs)):
document.paragraphs[i].alignment = WD_PARAGRAPH_ALIGNMENT.CENTER # 居中对齐
# 5.添加换页符
# add_page_break()
document.add_page_break()
# print(len(document.paragraphs))
# 6.插入图片
# add_picture(),调整图片宽高需导入docx.shared模块
document.add_picture('libai.jpeg', width=Pt(200), height=Pt(300))
# 设置居中对齐
document.paragraphs[len(document.paragraphs)-1].alignment = WD_PARAGRAPH_ALIGNMENT.CENTER # 居中对齐
# 7.创建表格
"""
add_table(rows=n, cols=m)
"""
table = document.add_table(rows=2, cols=5)
# 添加表格内容
# 添加第1行数据
row = table.rows[0]
row.cells[0].text = '姓名'
row.cells[1].text = '字'
row.cells[2].text = '号'
row.cells[3].text = '所处时代'
row.cells[4].text = '别称'
# 添加第2行数据
row = table.rows[1]
row.cells[0].text = '李白'
row.cells[1].text = '太白'
row.cells[2].text = '青莲居士'
row.cells[3].text = '唐朝'
row.cells[4].text = '诗仙'
# 插入行
new_row = table.add_row() # 增加表格行
new_row.cells[0].text = '白居易'
new_row.cells[1].text = '乐天'
new_row.cells[2].text = '香山居士'
new_row.cells[3].text = '唐朝'
new_row.cells[4].text = '诗魔'
# 插入列
new_column = table.add_column(width=Inches(1)) # 增加表格列
new_column.cells[0].text = '代表作'
new_column.cells[1].text = '《侠客行》、《静夜思》'
new_column.cells[2].text = '《长恨歌》、《琵琶行》'
# 计算表格的rows和cols的长度
rows = len(table.rows)
cols = len(table.columns)
print(f'rows: {rows}')
print(f'columns: {cols}')
# 打印表格内容
# for row in table.rows:
# for cell in row.cells:
# print(cell.text)
# 设置表格样式
# table.style = 'LightShading-Accent1'
# UserWarning: style lookup by style_id is deprecated. Use style name as key instead.
table.style = 'Light Shading Accent 1'
# 循环将每一行,每一列都设置为居中
for r in range(rows):
for c in range(cols):
table.cell(r, c).vertical_alignment = WD_CELL_VERTICAL_ALIGNMENT.CENTER # 垂直居中
table.cell(r, c).paragraphs[0].paragraph_format.alignment = WD_TABLE_ALIGNMENT.CENTER # 水平居中
# 设置页码
add_page_number(document.sections[0].footer.paragraphs[0])
# 保存文件
document.save('test2.docx')
效果:
参考:
- https://www.cnpython.com/qa/1290238
- python-docx官方文档:https://python-docx.readthedocs.io/en/latest/
- https://qa.1r1g.com/sf/ask/2046849521/