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
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
|
from email import header
from ftplib import parse150
import os, sys, docx, PyPDF2
from string import punctuation
from PyPDF2 import PdfReader
def process_text(string):
string = remove_non_ascii(string)
string = remove_line_break(string)
return string
def remove_non_ascii(string):
return string.encode('ascii', errors='xmlcharrefreplace').decode()
def remove_line_break(string):
return string.replace("- ","")
def html_file_generator(path, page_header, page_contents):
filename = path[path.rfind('/')+1: path.rfind('.')]
if os.path.exists(filename+".html") == True:
os.remove(filename+".html")
htmlfile = open(filename+".html", "x")
htmlfile.write('<!DOCTYPE html>'
'<html lang ="en">'
'<head>'
'<title>' +filename+ '</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>' +page_header+ '</h1>')
htmlfile.write(process_text(page_contents))
htmlfile.write('</body>'
'</html>')
htmlfile.close()
return 0
#Text file handler
def paragraph_parser(contents):
punctuation = [".", "?", "!", '"']
paragraph_end = [".\n\n", "?\n\n", "!\n\n", '"\n\n', "|E"]
article_end = '\n'
paragraph_index = [0]
article_index = [0]
paragraph_number = 1
paragraph=[]
article=[]
x = 0
contents=contents.strip()
contents+="|E\n"
while x in range (len(paragraph_end)):
if contents.find(paragraph_end[x]) == -1:
paragraph_end.pop(x)
else:
x += 1
while paragraph_end:
minimum = contents[paragraph_index[paragraph_number-1]:].index(paragraph_end[0]) +paragraph_index[paragraph_number-1]
for x in paragraph_end:
if contents[paragraph_index[paragraph_number-1]:].index(x)+paragraph_index[paragraph_number-1]+1 < minimum:
minimum = contents[paragraph_index[paragraph_number-1]:].index(x)+paragraph_index[paragraph_number-1]
paragraph_index.append(minimum+1)
paragraph.append(contents[paragraph_index[paragraph_number-1]:paragraph_index[paragraph_number]]+'</p>')
for x in paragraph_end:
if contents[paragraph_index[paragraph_number]:].find(x) == -1:
paragraph_end.remove(x)
first_nl =contents[paragraph_index[paragraph_number-1]+2:paragraph_index[paragraph_number]].index(article_end)+paragraph_index[paragraph_number-1]+2
if contents[first_nl-1:first_nl] not in punctuation:
article_index.append(contents[paragraph_index[paragraph_number-1]+2:paragraph_index[paragraph_number]].index(article_end)+paragraph_index[paragraph_number-1])
paragraph_number +=1
paragraph_number = 0
for x in range(1,len(article_index)):
if contents[article_index[x-1]:article_index[x]-2].rfind('\n') != -1:
article.append(contents[contents[:article_index[x]].rfind('\n')+1:article_index[x]+2])
elif x==1:
article.append(contents[contents[:article_index[x]].rfind('\n')+1:article_index[x]+2])
for x in article_index[1:]:
while x not in range(paragraph_index[paragraph_number],paragraph_index[paragraph_number+1]):
paragraph[paragraph_number]="<p>"+paragraph[paragraph_number]
paragraph_number +=1
paragraph[paragraph_number]=paragraph[paragraph_number].replace("\n"," ")
paragraph[paragraph_number]=paragraph[paragraph_number].strip()
paragraph[paragraph_number]="<h2>"+article[article_index.index(x)-1]+"</h2>\n<p>"+paragraph[paragraph_number][len(article[article_index.index(x)-1]):]
print("Header "+str(x)+" is in paragraph "+str(paragraph_number))
paragraph[-1] = paragraph[-1][:-5]+paragraph[-1][-4:]
return ''.join(paragraph)
#Document file Handler
def dochandler(path):
doc = docx.Document(path)
header_styles= ["Subtitle","Heading 1", "Heading 2"]
paragraph_style= ["Normal","No Spacing"]
title = (path[path.rfind('/')+1: path.rfind('.')]).capitalize()
if doc.paragraphs[0].style.name == "Title":
title = doc.paragraphs[0].text
fullText = ""
for para in doc.paragraphs:
if para.style.name in header_styles:
fullText+="<h2>"+para.text
fullText+="</h2>\n"
elif para.style.name in paragraph_style:
fullText+="<p>"+para.text
fullText+="</p>\n"
html_file_generator(path, title, fullText)
return '\n'.join(path)
def txthandler(path):
f = open(path, "r")
contents = f.read()
main_header = contents[0:contents.find('\n')]
paragraphs = paragraph_parser(contents[contents.find('\n'):])
html_file_generator(path,main_header,paragraphs)
print(f.read())
return 0
#def header_footer_remover(page_text):
#same_header, same_footer = []
#for same_header
#return(page_text)
#def html_file_generator(path, page_header, page_contents):
def pdfhandler(path):
reader = PdfReader(path)
number_of_pages = len(reader.pages)
page_text = []
#print(number_of_pages)
for x in range(number_of_pages -1):
page = reader.pages[x]
page_text.append(page.extract_text())
#print(page_text[4])
html_file_generator(path, "penis", paragraph_parser("".join(page_text)))
return 0
#Attempting to pass txt file in path
#path = 'C:/Code/texttohtml/kac.pdf'
path = 'C:/Users/Josh/Desktop/porkandbeans/texttohtml/memes.docx'
extension = path[path.rfind('.')+1: len(path)]
if extension =='txt':
txthandler(path)
elif extension == 'pdf':
pdfhandler(path)
elif extension == 'doc' or 'docx':
dochandler(path)
else:
print("Extension not recognized")
sys.exit()
|
