pptx_analyzer.py

from pptx import Presentation
import argparse
import re
from termcolor import colored as c

# Bash one liner version to get a similar thing: 
#   unzip -p presenation.pptx | sed -e 's/<[^>]*>//g' | tr '\r' '\n' | egrep --colour '[0-9]*$'


def parse_args():
    parser = argparse.ArgumentParser(description='Analyze powerpoint')
    parser.add_argument('pptx',
                        type=argparse.FileType('r'),
                        help='Powerpoint file to be analyzed')
    parser.add_argument('-c',
                        action='store_true',
                        help='Count each note length & cumalitive')
    parser.add_argument('-b',
                        type=int,
                        default=1,
                        help='Begin at slide b')
    parser.add_argument('-e',
                        type=int,
                        help='End at slide e')
    parser.add_argument('-d',
                        action='store_false',
                        default=True,
                        help='Skip divider') 
    parser.add_argument('-s',
                        action='store_false',
                        default=True,
                        help='Skip slides') 
    parser.add_argument('-n',
                        action='store_false',
                        default=True,
                        help='Skip notes')
    parser.add_argument('-l',
                        action='store_false',
                        help='Skip total notes length')
    
    return parser.parse_args()

def strip_extra(s):
    return re.sub(r'\n$', '', re.sub(r'\n\n', '\n', s, re.MULTILINE))

def count(s):
    c = len(re.findall(r'\w+', s))
    return round(c / 140.0, 1)

if __name__ == "__main__":
    args = parse_args()
    p = Presentation(args.pptx)

    total = 0

    for relative_index, s in enumerate(list(p.slides)[args.b - 1:]):
        i = relative_index + args.b # i is 1 indexed slide number (like in ppt)

        if args.d:
            print c("------ " + str(i) + " ------", 'red')

        slide_text = ''.join([h.text for h in s.shapes if hasattr(h, 'text')])
        if args.s:
            print c(strip_extra(slide_text), 'blue')
    
        notes_text = s.notes_slide.notes_text_frame.text
        if args.n:
            print strip_extra(notes_text)
    
        if args.c:
            notes_length = count(notes_text)
            total = total + notes_length
            print c(str(notes_length), 'green'), " cumal:", c(str(total), 'green')
    
        if args.e and args.e == i:
            break

    if args.l:
        all_notes_text = [s.notes_slide.notes_text_frame.text for s in p.slides]
        print 'Total for deck:', c(count(' '.join(all_notes_text)), 'green')