from ftplib import parse150
import os, sys
def paragraph_parser(contents):
paragraph_end = ['.\n', '?\n', '!\n', '"\n']
paragraph_index = [0]
paragraph_number = 1
paragraph = []
x = 0
while len(paragraph_end) > 1:
while x in range (len(paragraph_end)):
if contents[paragraph_index[paragraph_number-1]:].find(paragraph_end[x]) == -1:
paragraph_end.pop(x)
else:
x += 1
minimum = contents[paragraph_index[paragraph_number-1]:].index(paragraph_end[0])+paragraph_index[paragraph_number-1]
x = 1
for x in range (len(paragraph_end)):
if contents[paragraph_index[paragraph_number-1]:].index(paragraph_end[x]) < minimum:
minimum = contents[paragraph_index[paragraph_number-1]:].index(paragraph_end[x])+paragraph_index[paragraph_number-1]
paragraph_index.append(minimum)
print(minimum)
#paragraph.append(contents[paragraph_index[paragraph_number-1]: paragraph_index[paragraph_number]+1])
#print(paragraph_index[paragraph_number])
paragraph_number +=1
def txthandler(path, htmlfile):
filename = path[path.rfind('/')+1: path.rfind('.')]
f = open(path, "r")
contents = f.read()
title = filename
main_header = contents[0:contents.find('\n')]
paragraph_parser(contents)
htmlfile.write(''
''
''
'' +title+ ''
''
''
''
''
''
'' +main_header+ '
'
''
' Introduction
'
'''
'
''
''
'')
print(f.read())
return 0
def pdfhandler(path):
f = open(path)
print(f.read())
return 0
def dochandler(path):
f = open(path)
print(f.read())
return 0
#Attempting to pass txt file in path
path = 'C:/Users/a big fuck/Documents/beansandtoast.txt'
extension = path[path.rfind('.')+1: len(path)]
filename = path[path.rfind('/')+1: path.rfind('.')]
if os.path.exists(filename+".html") == True:
os.remove(filename+".html")
htmlfile = open(filename+".html", "x")
if extension =='txt':
txthandler(path, htmlfile)
elif extension == 'pdf':
pdfhandler(path)
elif extension == 'doc' or 'docx':
dochandler(path)
else:
print("Extension not recognized")
sys.exit()