python-docx操作word文件（*.docx）
阿新 • • 發佈：2019-04-25
tin comment turn spl end nta document .sh font
目錄
- 基礎操作
- 對象關系
- 添加樣式
- 中文字體微軟雅黑，西文字體Times New Roman
- 首行縮進
- 單獨設置標題樣式
- 設置超鏈接
- 參考文檔
基礎操作
from docx import Document from docx.shared import Inches # 創建空文檔 document = Document() # 添加標題，設置級別level，0為Title，1或省略為Heading 1，0<=level<=9 document.add_heading('Document Title', 0) # 添加段落，參數為text=''和style=None p = document.add_paragraph('A plain paragraph having some ') # 添加run對象，參數為text=None和style=None, # run對象有bold（加粗）和italic（斜體）這兩個屬性 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' ) # 添加圖片 document.add_picture('monty-truth.png', width=Inches(1.25)) # 添加表格 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()
對象關系
document.add_paragraph()之後，默認paragraph的內容到第一個run中。
添加樣式
中文字體微軟雅黑，西文字體Times New Roman
import docx from docx.enum.text import WD_ALIGN_PARAGRAPH from docx.oxml.ns import qn from docx.shared import Cm, Pt document = Document() # 設置一個空白樣式 style = document.styles['Normal'] # 設置西文字體 style.font.name = 'Times New Roman' # 設置中文字體 style.element.rPr.rFonts.set(qn('w:eastAsia'), '微軟雅黑')
首行縮進
# 獲取段落樣式
paragraph_format = style.paragraph_format
# 首行縮進0.74厘米，即2個字符
paragraph_format.first_line_indent = Cm(0.74)單獨設置標題樣式
# 設置標題 title_ = document.add_heading(level=0) # 標題居中 title_.alignment = WD_ALIGN_PARAGRAPH.CENTER # 添加標題內容 title_run = title_.add_run(title) # 設置標題字體大小 title_run.font.size = Pt(14) # 設置標題西文字體 title_run.font.name = 'Times New Roman' # 設置標題中文字體 title_run.element.rPr.rFonts.set(qn('w:eastAsia'), '微軟雅黑')
設置超鏈接
def add_hyperlink(paragraph, url, text, color, underline):
"""
A function that places a hyperlink within a paragraph object.
:param paragraph: The paragraph we are adding the hyperlink to.
:param url: A string containing the required url
:param text: The text displayed for the url
:return: The hyperlink object
"""
# This gets access to the document.xml.rels file and gets a new relation id value
part = paragraph.part
r_id = part.relate_to(url, docx.opc.constants.RELATIONSHIP_TYPE.HYPERLINK, is_external=True)
# Create the w:hyperlink tag and add needed values
hyperlink = docx.oxml.shared.OxmlElement('w:hyperlink')
hyperlink.set(docx.oxml.shared.qn('r:id'), r_id, )
# Create a w:r element
new_run = docx.oxml.shared.OxmlElement('w:r')
# Create a new w:rPr element
rPr = docx.oxml.shared.OxmlElement('w:rPr')
# Add color if it is given
if not color is None:
c = docx.oxml.shared.OxmlElement('w:color')
c.set(docx.oxml.shared.qn('w:val'), color)
rPr.append(c)
# Remove underlining if it is requested
if not underline:
u = docx.oxml.shared.OxmlElement('w:u')
u.set(docx.oxml.shared.qn('w:val'), 'none')
rPr.append(u)
# Join all the xml elements together add add the required text to the w:r element
new_run.append(rPr)
new_run.text = text
hyperlink.append(new_run)
paragraph._p.append(hyperlink)
return hyperlink
document = docx.Document()
p = document.add_paragraph()
#add a hyperlink with the normal formatting (blue underline)
hyperlink = add_hyperlink(p, 'http://www.google.com', 'Google', None, True)
#add a hyperlink with a custom color and no underline
hyperlink = add_hyperlink(p, 'http://www.google.com', 'Google', 'FF8822', False)
document.save('demo.docx')上面的函數是對整段內容直接添加鏈接，日常使用的時候，超鏈接多為關鍵詞，或<a>標簽的格式，用paragraph和run這兩個對象的關系來解決。
比如有文本內容如下，將其中的<a>標簽換為超鏈接：
"""I am trying to add an hyperlink in a MS Word document using docx module for <a href="python.org">Python</a>. Just do it."""
# 判斷字段是否為鏈接
def is_text_link(text):
for i in ['http', '://', 'www.', '.com', '.org', '.cn', '.xyz', '.htm']:
if i in text:
return True
else:
return False
# 對段落中的鏈接加上超鏈接
def add_text_link(document, text):
paragraph = document.add_paragraph()
# 根據<a>標簽拆分文本內容
text = re.split(r'<a href="|">|</a>',text)
keyword = None
for i in range(len(text)):
# 對非鏈接和非關鍵詞的內容，通過run直接加入段落中
if not is_text_link(text[i]):
if text[i] != keyword:
paragraph.add_run(text[i])
# 對鏈接和關鍵詞，使用add_hyperlink插入超鏈接
elif i + 1<len(text):
url=text[i]
keyword=text[i + 1]
add_hyperlink(paragraph, url, keyword, None, True)參考文檔
- https://python-docx.readthedocs.io/en/latest/index.html
- https://github.com/python-openxml/python-docx/issues/74
- http://www.warmeng.com/2018/12/02/auto_report/
python-docx操作word文件（*.docx）