blob: 601f509bfe2c4cd92ff8dac24cdb6548925e5b0e (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
|
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('<!DOCTYPE html>'
'<html lang ="en">'
'<head>'
'<title>' +title+ '</title>'
'<link rel="stylesheet" type="text/css" href="stylesheet.css">'
'<link rel="icon" type="image/x-icon" href="images/favicon.ico">'
'<meta charset="utf-8"/>'
'</head>'
'<body>'
'<h1>' +main_header+ '</h1>'
'<article class="introduction">'
'<h2>  Introduction  </h2>'
'<p>''</p>'
'</article>'
'</body>'
'</html>')
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()
|
