python自动化之word文档

#########################docx文件############################

'''

.docx文件有很多结构,有3种不同的类型来表示

在最高一层,Document对象表示整个文档

Document对象包含一个Paragraph对象的列表,表示文档中的段落,以回车键为准

每个Paragraph对象包含一个Run对象的列表

'''

#########################读取Word文档########################

import docx

doc=docx.Document(r'C:\Users\shenlu\Desktop\demo.docx')

len(doc.paragraphs)

doc.paragraphs[0].text

doc.paragraphs[1].text

len(doc.paragraphs[1].runs)

doc.paragraphs[1].runs[0].text

doc.paragraphs[1].runs[1].text

doc.paragraphs[1].runs[2].text

doc.paragraphs[1].runs[3].text

########################从.docx文件中取得完整的文本########################

import docx

def getText(filename):

doc=docx.Document(filename)

fullText=[]

for para in doc.paragraphs:

#########每一段有缩进#############

###fullText.append(' '+para.text)

fullText.append(para.text)

###段落之间增加空行,return '\n\n'.join(fullText)

return '\n'.join(fullText)

########################从.docx文件中取得完整的文本########################

import readDocx

print (readDocx.getText('demo.docx'))

########################设置Paragraph和Run对象的样式########################

'''

对于Word文档,有3种类型的样式：

段落样式可以应用于Paragraph对象,字符样式可以应用于Run对象

链接的样式可以应用于这两种对象

默认Word样式的字符串如下：

'Normal' 'BodyText' 'BodyText2' 'BodyText3' 'Caption' 'Heading1' 'Heading2' 'Heading3' 'Heading4'

'Heading5' 'Heading6' 'Heading7' 'Heading8' 'Heading9' 'IntenseQuote' 'List' 'List2' 'List3'

'ListBullet' 'ListBullet2' 'ListBullet3' 'ListContinue' 'ListContinue2' 'ListContinue3' 'ListNumber' 'ListNumber2' 'ListNumber3'

'ListParagraph'         'MacroText'      'NoSpacing'      'Quote'     'Subtitle'  'TOCHeading'  'Title'

'''

'''

Run对象的text属性

属性                                     描述

bold                             文本以粗体出现

italic                                      文本以斜体出现

underline                    文本带下划线

strike                                    文本带删除线

double_strike            文本带双删除线

all_caps                      文本以大写首字母出现

small_caps                          文本以大写首字母出现,小写字母小两个点

shadow                                文本带阴影

outline                                  文本以轮廓线出现,而不是实心

rtl                                          文本从右至左书写

imprint                                 文本以刻入页面的方式出现

emboss                                文本以凸出页面的方式出现

'''

########################################################################

import docx

doc=docx.Document(r'C:\Users\shenlu\Desktop\demo.docx')

doc.paragraphs[0].text

doc.paragraphs[0].style

doc.save(r'C:\Users\shenlu\Desktop\demo.docx')

doc.paragraphs[0].style='Heading 1'

>>> doc.paragraphs[1].style

_ParagraphStyle('No Spacing') id: 124515664

doc.paragraphs[1].text

(doc.paragraphs[1].runs[0].text,doc.paragraphs[1].runs[1].text,doc.paragraphs[1].runs[2].text,doc.paragraphs[1].runs[3].text)

doc.paragraphs[1].runs[1].underline=True

doc.paragraphs[1].runs[3].underline=True

doc.save(r'C:\Users\shenlu\Desktop\demo.docx')

#################################写入Word文档################################

import docx

doc=docx.Document()

doc.add_heading('Header 0',0)

doc.add_heading('Header 1',1)

doc.add_heading('Header 2',2)

doc.add_heading('Header 3',3)

doc.add_heading('Header 4',4)

doc.add_paragraph('Hello world!')

doc.add_picture(r'C:\Users\shenlu\Desktop\DSCN0859.jpg',width=docx.shared.Inches(1),height=docx.shared.Cm(4))

paraObj1=doc.add_paragraph('This is a second paragraph.')

paraObj2=doc.add_paragraph('This is a yet another paragraph.')

paraObj1.add_run('This text is being added to the second paragraph.')

doc.save(r'C:\Users\shenlu\Desktop\helloworld.docx')

#################################添加换行符和换页符################################

import docx

from docx.enum.text import WD_BREAK

doc=docx.Document()

doc.add_paragraph('This is on the first page!')

#doc.paragraphs[0].runs[0].add_break()  ###换行

doc.paragraphs[0].runs[0].add_break(WD_BREAK.PAGE)  ###换页

doc.add_paragraph('This is on the second page!')

doc.save(r'C:\Users\shenlu\Desktop\twoPage.docx')

#################################定制邀请函################################

import docx,os

txtcontent=open(r'C:\Users\shenlu\Desktop\guests.txt','rb')

lines=txtcontent.readlines()

for line in lines:

print line

line=line.replace('\r\n','')

doc=docx.Document()

doc.add_paragraph('It would be a pleasure to have the company of')

doc.add_paragraph(line)

doc.add_paragraph('at 11010 memory laue on the euening of')

doc.add_paragraph('April lst')

doc.add_paragraph('at 7 o\'clock')

doc.save(os.path.join(r'C:\Users\shenlu\Desktop',line+'.docx'))

txtcontent.close()

#############################################################################

http://nostarch.com/automatestuff/