User:Angeliki/Prototyping 3: Difference between revisions
(Created page with "<code> #!/usr/bin/env python3 import cgi import cgitb; cgitb.enable() #for seeing at errors in the code import pandas as pd import csv import sys, os, re, nltk, glob prin...") |
No edit summary |
||
| Line 1: | Line 1: | ||
< | <syntaxhighlight lang="python"> | ||
#!/usr/bin/env python3 | #!/usr/bin/env python3 | ||
import cgi | import cgi | ||
import cgitb; cgitb.enable() #for seeing at errors in the code | import cgitb; cgitb.enable() #for seeing at errors in the code | ||
| Line 7: | Line 6: | ||
import csv | import csv | ||
import sys, os, re, nltk, glob | import sys, os, re, nltk, glob | ||
print ("Content-type:text/html;charset=utf-") | print ("Content-type:text/html;charset=utf-") | ||
| Line 50: | Line 48: | ||
extract.append(sentence) | extract.append(sentence) | ||
searchfile.close() | searchfile.close() | ||
print (""" | print (""" | ||
| Line 81: | Line 77: | ||
print (output[1]) | print (output[1]) | ||
print (extract[1]) | print (extract[1]) | ||
</ | </syntaxhighlight> | ||
Revision as of 12:35, 18 June 2018
#!/usr/bin/env python3
import cgi
import cgitb; cgitb.enable() #for seeing at errors in the code
import pandas as pd
import csv
import sys, os, re, nltk, glob
print ("Content-type:text/html;charset=utf-")
print ()
output= "type here"
extract= ""
f = cgi.FieldStorage()
text = f.getvalue("text", "")
#read csv, and split on "," the line
csv_file = csv.reader(open('tfidf.csv', "r"), delimiter=",")
# Read the header, put all labels into a list
header = next(csv_file)
#print(header)
#loop through csv list
for row in csv_file :
#if current rows 2nd value is equal to input, print that row
if text == row[0]:
scores = row
#print(row)
# Zip the scores and the labels, remove the first item with the query
result = list(zip(header, scores))
del result[0]
# print(result)
# Sort the results
output = sorted(result, key=lambda tup: tup[1], reverse=True)
extract=[]
os.chdir("texts")
for file in glob.glob("*.txt"):
# print(file)
searchfile = open(file, "r")
sents = nltk.sent_tokenize(searchfile.read())
for sentence in sents:
if re.search(r'\b({})\b'.format(text), sentence):
extract.append(sentence)
searchfile.close()
print ("""
<!DOCTYPE html>
<html>
<head>
<title></title>
<meta charset="utf-8">
</head>
<body>
<form method="get">
<input type="submit" name="submit" value="search" >
<textarea name="text"> {2} </textarea>
<textarea name="result"> </textarea></br></br>
{1}</br></br>
{0}
</form>
</body>
</html>""".format(output, extract, text))
# i=0
# for i>=0:
# print (output[i])
# print (extract[i])
# i++1
print (output[0])
print (extract[0])
print (output[1])
print (extract[1])