You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
35 lines
819 B
Python
35 lines
819 B
Python
3 years ago
|
import nltk
|
||
|
|
nltk.download('punkt')
|
||
|
|
|
||
|
|
with open('speech.txt','r') as result:
|
||
|
|
r = result.read()
|
||
|
|
|
||
|
|
r = r.replace('<span class="interim"></span>','').replace('\n','. ')
|
||
|
|
|
||
|
|
l=nltk.word_tokenize(r)
|
||
|
|
pos = nltk.pos_tag(l)
|
||
|
|
|
||
|
|
html = '''
|
||
|
|
<html>
|
||
|
|
<head>
|
||
|
|
<meta name="viewport" content="width=device-width, initial-scale=1">
|
||
|
|
<link rel="stylesheet" href="pagedjs_files/interface.css">
|
||
|
|
<script src="pagedjs_files/paged.polyfill.js"></script>
|
||
|
|
<link rel="stylesheet" href="styles/1.css">
|
||
|
|
<meta charset="utf-8"/>
|
||
|
|
<title>Booklet</title>
|
||
|
|
</head>
|
||
|
|
<body>
|
||
|
|
'''
|
||
|
|
|
||
|
|
for x in pos:
|
||
|
|
if x[0] == '.':
|
||
|
|
html += "<span class='dot'>.<span><br> "
|
||
|
|
else:
|
||
|
|
html += "<span class='"+x[1]+"'>"+x[0]+"<span> "
|
||
|
|
|
||
|
|
html = '''</body>
|
||
|
|
</html>'''
|
||
|
|
|
||
|
|
with open('index.html','w') as index:
|
||
|
|
index.write(html)
|