"""
Extracting the text of a simple docx file.
"""
import os
import sys
# adding the parent directory to PATH
path = os.path.abspath(os.path.join(os.path.dirname(__file__),".."))
sys.path.append(path)
from docx.document import DocxDocument
if __name__ == '__main__':
try:
doc = DocxDocument(sys.argv[1])
newfile = open(sys.argv[2],'w')
except:
print('Please supply an input and output file. For example:')
print(''' extract_text.py 'My Office 2007 extract.docx' 'outputfile.txt' ''')
exit()
## Fetch all the text out of the document we just created
paragraphs = doc.get_text()
# Make explicit unicode version
paragraphs_encoded = []
for p in paragraphs:
paragraphs_encoded.append(p.encode("utf-8"))
## Print our documnts test with two newlines under each paragraph
newfile.write('\n\n'.join(paragraphs_encoded))
"""
import os
import sys
# adding the parent directory to PATH
path = os.path.abspath(os.path.join(os.path.dirname(__file__),".."))
sys.path.append(path)
from docx.document import DocxDocument
from docx.elements import *
from docx.meta import CoreProperties, WordRelationships
if __name__ == '__main__':
# creating a new document with a template dir specified
template_path = os.path.abspath(os.path.join(os.path.dirname(__file__),'template'))
doc = DocxDocument(template_dir=template_path)
# appending various elements to the newly created document.
doc.add(heading('''Welcome to Python's docx module''',1) )
doc.add(heading('Make and edit docx in 200 lines of pure Python',2))
doc.add(paragraph('The module was created when I was looking for a Python support for MS Word .doc files on PyPI and Stackoverflow. Unfortunately, the only solutions I could find used:'))
# Add a numbered list
for point in ['''COM automation''','''.net or Java''','''Automating OpenOffice or MS Office''']:
doc.add(paragraph(point,style='ListNumber'))
doc.add(paragraph('''For those of us who prefer something simpler, I made docx.'''))
doc.add(heading('Making documents',2))
doc.add(paragraph('''The docx module has the following features:'''))
# Add some bullets
Creating a docx document from scratch and adding some elements to it.
"""
import os
import sys
import re
# adding the parent directory to PATH
path = os.path.abspath(os.path.join(os.path.dirname(__file__),".."))
sys.path.append(path)
from docx.document import DocxDocument
from docx.elements import *
from docx.meta import CoreProperties, WordRelationships
#doc = DocxDocument('modify.docx')
doc = DocxDocument('modify.docx')
# Replacing a string of text with another one.
doc.replace('This is a sample document', 'This is a modified document')
# replacing placeholder with picture
pic_paragraph = picture(doc,'python_logo.png','This is a test description')
doc.replace('IMAGE', pic_paragraph)
# Adding something to the end of the document.
doc.add(heading('Adding another element to the end of this document.',1))
# saving the new document
doc.save('modified_document.docx')