Last active
June 14, 2020 23:07
-
-
Save 0187773933/3e7189aa1db7038593916f61cd7abfbd to your computer and use it in GitHub Desktop.
Microsoft Word Progress Bar on Word Count
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys, re, os, argparse | |
from docx import Document | |
import subprocess as sub | |
import time | |
from tqdm import tqdm | |
from pprint import pprint | |
import re | |
# https://raw.githubusercontent.com/SyntaxOverflowByte/word_count/master/word_count.py | |
# python3 -m pip install docx | |
# python3 -m pip install python-docx | |
class WordCount: | |
def __init__( self , options={} ): | |
self.options = options | |
if "file_path" not in self.options: | |
print( "you have to pass a file_path" ) | |
return False | |
if "word_count" not in self.options: | |
self.options["word_count"] = 500 | |
if "time_interval" not in self.options: | |
self.options["time_interval"] = 3 | |
self.bar = tqdm( total=int( self.options["word_count"] ) , desc="Word Count" ) | |
#self.bar = tqdm( total=100 , desc="Word Count" ) | |
self.checking = True | |
self.last_update_count = 0 | |
self.start_check_interval() | |
def load_document( self ): | |
self.document = Document( self.options["file_path"] ) | |
def get_word_count_update( self ): | |
words = [] | |
for index , paragraph in enumerate( self.document.paragraphs ): | |
original_text = self.document.paragraphs[ index ].text | |
cleaned = re.sub( ' +' , ' ' , original_text ) | |
cleaned_list = cleaned.split( " " ) | |
words = words + cleaned_list | |
words = [ x for x in words if x ] | |
self.words = words | |
self.current_word_count = len( words ) | |
self.percent_complete = ( ( self.current_word_count / self.options["word_count"] ) * 100 ) | |
# print( f'Total Words = {self.current_word_count}' ) | |
# print( f'Perecent Complete = {self.percent_complete}' ) | |
if self.current_word_count != self.last_update_count: | |
self.bar = tqdm( total=int( self.options["word_count"] ) , desc="Word Count" ) | |
self.bar.update( self.current_word_count ) | |
self.bar.refresh() | |
self.last_update_count = self.current_word_count | |
def start_check_interval( self ): | |
while self.checking == True: | |
self.load_document() | |
self.get_word_count_update() | |
time.sleep( self.options["time_interval"] ) | |
def stop_check_interval( self ): | |
self.checking = False | |
if __name__ == '__main__': | |
parser = argparse.ArgumentParser(description='Counts the words in a Microsoft Word document.') | |
parser.add_argument('input_file', action='store', type=str, help='Enter the name of the file you want to perform the word count on.') | |
parser.add_argument('word_count', action='store', type=int ) | |
args = parser.parse_args() | |
word_counter = WordCount({ | |
"file_path": args.input_file , | |
"word_count": args.word_count | |
}) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment