Powerpoint to PDF Converter

pptToPdf

import sys
import argparse
import os
import fnmatch
import win32com

from Tkinter import *
from tkFileDialog import *

from win32com.client import Dispatch

def main(directory):
    """Publish Powerpoints to PDFs

    This program looks for any Excel files in its subdirectories. It reads them
    expecting each row to have a format of (PptFile, PageRange, PDFOutput,
    OutputDirectory). Then assuming that each Powerpoint file is in the same
    folder as the Excel file, it will print a PDF of that range of slides from
    the Powerpoint to the output folder with the PDFOutput name specified.
    """
    files = []
    excel_dispatch = Dispatch('Excel.Application')
    ppt_dispatch = Dispatch('Powerpoint.Application')
    for root, dirnames, filenames in os.walk(directory):
        # [!~] in filter is for Windows temporary files
        for filename in fnmatch.filter(filenames, '[!~]*.xls*'):
            print('Reading data from {}'.format(filename))
            files.append(read_excel_file(os.path.join(root, filename),
                        excel_dispatch, root))
    excel_dispatch.Quit()
    for f in files:
        for entry in f:
            print_file(entry, ppt_dispatch)
    ppt_dispatch.Quit()

def print_file(entry, dispatch):
    pptFileName, slideRange, outputFileName, rootDirectory, outputDirectory = entry
    ppt = dispatch.Presentations.Open(os.path.join(rootDirectory, pptFileName),
                                        True, True, False)
    pdf_name = os.path.join(outputDirectory, outputFileName) + '.pdf'
    if slideRange:
        slides_to_keep = ranges_to_list(slideRange)
        for slide in list(range(1, ppt.Slides.Count + 1))[::-1]:
            if slide not in slides_to_keep:
                ppt.Slides(slide).Delete()
    if not os.path.exists(outputDirectory):
        os.makedirs(outputDirectory)
    print('Printing slides {} from {} to {}'.format(slideRange, pptFileName, outputFileName))
    # PpFixedFormatType for PDFs is 32
    ppt.SaveAs(pdf_name, 32)
    ppt.Close()

def read_excel_file(filename, dispatch, root):
    wb = dispatch.Workbooks.Open(filename)
    sheet = wb.Sheets(1)
    row = 1
    data = []
    while sheet.Cells(row, 1).Value:
        data.append((sheet.Cells(row, 1).Value, sheet.Cells(row, 2).Value,
                    sheet.Cells(row, 3).Value, root, sheet.Cells(row, 4).Value))
        row += 1
    wb.Close()
    return data

def ranges_to_list(s):
    """Return each integer from a complex range string like "1-9,12, 15-20,23"

    >>> list(hyphen_range('1-9,12, 15-20,23'))
    [1, 2, 3, 4, 5, 6, 7, 8, 9, 12, 15, 16, 17, 18, 19, 20, 23]

    >>> list(hyphen_range('1-9,12, 15-20,2-3-4'))
    Traceback (most recent call last):
        ...
    ValueError: format error in 2-3-4
    """
    ret = []
    for x in s.split(','):
        elem = x.split('-')
        if len(elem) == 1: # a number
            ret.append(int(elem[0]))
        elif len(elem) == 2: # a range inclusive
            start, end = map(int, elem)
            for i in xrange(start, end+1):
                ret.append(i)
        else: # more than one hyphen
            raise ValueError('format error in {}'.format(x))
    return ret

if __name__ == '__main__':
    master = Tk()
    b = Label(master, text='Close the command prompt to stop the program')
    b.pack()
    fileName = askdirectory()
    if not fileName:
        exit()
    fileName = os.path.normpath(fileName)
    main(fileName)