test.py

gistfile1.txt

#!/usr/bin/env python
# coding: utf8

from docx import *
import urllib2

 
# filename = "template.docx"
# document = opendocx(filename)
document = newdocument()



relationships = relationshiplist()
body = document.xpath('/w:document/w:body', namespaces=nsprefixes)[0]
# body = getdocumenttext(document)


pages = open("titles.txt", 'r').read().split('\n')[0:-1]
# collect titles
titles = {}

for t in pages:
    try:
        pagetitle = t[2:-2]
        filename = "pages/" + t[2:-2].lower() + ".txt"

        temp = open(filename, 'r').read().split('\n')[0:-1]

        l = temp[0]
        h = l.replace("======", '')
        h = h[1:-1]
        titles[pagetitle] = h
        print pagetitle
    except:
        # print filename + " not found"
        titles[pagetitle] = "leer"



pages = pages[17:19]

import sys
#sys.exit()

# isComment = False
showComments = True




for f in pages:
        filename = "pages/" + f[2:-2].lower() + ".txt"
        # print "====" + f

        # title = filename  # ".".join(f.split('.')[1:-1])
        # body.append(heading(title, 1))

        try:
            temp = open(filename, 'r').read().split('\n')[0:-1]

            # temp = temp.split("======")
            for l in temp:
                # replace links
                # if "[[" in l:
                #     for t in titles:
                #         l = l.replace(c,t)
                #         # print l

                if "======" in l:
                    h = l.replace("======", '')
                    body.append(heading(h, 2))
                    # body.append(paragraph(h, style='EUHeading2'))

                elif "=====" in l:
                    h = l.replace("=====", '')
                    body.append(heading(h, 3))
                    # body.append(paragraph(h, style='EUHeading3'))
                elif "====" in l:
                    h = l.replace("====", '')
                    body.append(heading(h, 4))
                    # body.append(paragraph(h, style='EUHeading4'))
                elif "===" in l:
                    h = l.replace("===", '')
                    body.append(heading(h, 5))
                    # body.append(paragraph(h, style='EUHeading5'))

                elif "{{" in l[0:2]:
                    l = l.replace("{{", '')
                    l = l.replace("}}", '')
                    l = l.strip()

                    l = l.split('|')[0].strip('|')
                    l = l.split('?')

                    if l[0][0] == ":": l[0] = l[0][1:]
                    if l[0][0:4] == "http":
                        picfilename = l[0].split('/')[-1]

                        picfile = urllib2.urlopen(l[0])
                        # print l[0] + '<------'
                        # print l[0].split('/')[-1]
                        output = open(picfilename,'wb')
                        output.write(picfile.read())
                        output.close() 
                        l[0] = picfilename

                    if  len(l) < 2: l.append('')                   

                    relationships, picpara = picture(relationships, l[0], l[1])
                    # relationships, picpara = picture(relationships, l[0], l[1], pixelwidth=400, pixelheight=400)
                    body.append(picpara)

                elif "//" in l[0:2]:
                    # isComment = not isComment
                    if showComments:
                        body.append(paragraph( [ (l, 'i')] ) )

                elif l and l[0:3] == '  *':
                    body.append(paragraph(''+l[4:], style='ListBullet'))
                elif l and l[0:5] == '    *':
                    body.append(paragraph('-->'+l[6:], style='Liste2'))

                elif "    " in l[0:4]:
                    body.append(paragraph("." + l, style='EUCode'))

                else:


                    pass
                    # print l
                    c = unicode(l, "utf-8")
                    # print c

                    for i in titles:
                        # print "trying " + i
                        c = c.replace(i, titles[i])


                    body.append(paragraph( [ (c, '')] ) )

            body.append(pagebreak(type='page', orient='portrait'))
        except:
            print filename + " not found."
            pass


# Create our properties, contenttypes, and other support files
title    = 'Python docx demo'
subject  = 'A practical example of making docx from Python'
creator  = 'Mike MacCana'
keywords = ['python', 'Office Open XML', 'Word']

coreprops = coreproperties(title=title, subject=subject, creator=creator,
                           keywords=keywords)
appprops = appproperties()
contenttypes = contenttypes()

websettings = websettings()
wordrelationships = wordrelationships(relationships)

savedocx(document, coreprops, appprops, contenttypes, websettings,
             wordrelationships, 'test2.docx')


from subprocess import call
call(["open", "test2.docx"])


# unzip test.docx
# find .  | zip file.zip -@