python自動化之word文檔

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

'''

.docx文件有很多結構,有3種不同的類型來表示

在最高一層,Document對象表示整個文檔

Document對象包含一個Paragraph對象的列表,表示文檔中的段落,以回車鍵為准

每個Paragraph對象包含一個Run對象的列表

'''

#########################讀取Word文檔########################

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

########################從.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:

                   #########每一段有縮進#############

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

                   fullText.append(para.text)

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

         return '\n'.join(fullText)

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

import readDocx

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

########################設置Paragraph和Run對象的樣式########################

'''

對於Word文檔,有3種類型的樣式：

段落樣式可以應用於Paragraph對象,字符樣式可以應用於Run對象

鏈接的樣式可以應用於這兩種對象

默認Word樣式的字符串如下：

'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對象的text屬性

屬性                                     描述

bold                             文本以粗體出現

italic                                      文本以斜體出現

underline                    文本帶下划線

strike                                    文本帶刪除線

double_strike            文本帶雙刪除線

all_caps                      文本以大寫首字母出現

small_caps                          文本以大寫首字母出現,小寫字母小兩個點

shadow                                文本帶陰影

outline                                  文本以輪廓線出現,而不是實心

rtl                                          文本從右至左書寫

imprint                                 文本以刻入頁面的方式出現

emboss                                文本以凸出頁面的方式出現

'''

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

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')

#################################寫入Word文檔################################

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')

#################################添加換行符和換頁符################################

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()  ###換行

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

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

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

#################################定制邀請函################################

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/