User:Angeliki/Prototyping 3
Catalogying
sorting.cgi
#!/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])
sorting.html
<!DOCTYPE html>
<html>
<head>
<title></title>
<meta charset="utf-8">
</head>
<body>
<form method="get" action="cgi-bin/sorting.cgi">
<input type="submit" name="submit" value="search" >
<textarea name="text"> Type here. </textarea>
<textarea name="result"> extracts </textarea>
</form>
</body>
</html>
Most downloaded books
import csv
from collections import defaultdict, Counter
data_list = []
with open('content.csv') as csvfile:
data_list = list(csv.reader(x.replace('\0', '') for x in csvfile))
for col in data_list:
print(col[0])
id_counts = Counter()
country_counts = Counter()
with open('analyze.csv') as csvfile:
reader = csv.reader(csvfile, delimiter='\t')
booklist_br = []
booklist_nl = []
booklist_gr = []
booklist_in = []
booklist_ge = []
booklist_au = []
booklist_be = []
booklist_hu = []
booklist_ro = []
for row in reader:
if row[1] == 'Brazil':
booklist_br.append((row[0],row[2]))
if row[1] == 'Netherlands':
booklist_nl.append((row[0],row[2]))
if row[1] == 'Greece':
booklist_gr.append((row[0],row[2]))
if row[1] == 'Indonesia':
booklist_in.append((row[0],row[2]))
if row[1] == 'Germany':
booklist_ge.append((row[0],row[2]))
if row[1] == 'Austria':
booklist_au.append((row[0],row[2]))
if row[1] == 'Belgium':
booklist_be.append((row[0],row[2]))
if row[1] == 'Hungary':
booklist_hu.append((row[0],row[2]))
if row[1] == 'Romania':
booklist_ro.append((row[0],row[2]))
sorted_booklist_br = sorted(booklist_br, key=lambda x:int(x[1]), reverse=True)
sorted_booklist_nl = sorted(booklist_nl, key=lambda x:int(x[1]), reverse=True)
sorted_booklist_gr = sorted(booklist_gr, key=lambda x:int(x[1]), reverse=True)
sorted_booklist_in = sorted(booklist_in, key=lambda x:int(x[1]), reverse=True)
sorted_booklist_ge = sorted(booklist_ge, key=lambda x:int(x[1]), reverse=True)
sorted_booklist_au = sorted(booklist_au, key=lambda x:int(x[1]), reverse=True)
sorted_booklist_be = sorted(booklist_be, key=lambda x:int(x[1]), reverse=True)
sorted_booklist_hu = sorted(booklist_hu, key=lambda x:int(x[1]), reverse=True)
sorted_booklist_ro = sorted(booklist_ro, key=lambda x:int(x[1]), reverse=True)
print('10 most downloaded books in Brazil:')
for ide, downloads in sorted_booklist_br[:10]:
print(downloads+" "+data_list[int(ide)-1][1])
print("-----------------------------")
print('10 most downloaded books in the Netherlands:')
for ide, downloads in sorted_booklist_nl[:10]:
print(downloads+" "+data_list[int(ide)-1][1])
print("-----------------------------")
print('10 most downloaded books in the Greece:')
for ide, downloads in sorted_booklist_gr[:10]:
print(downloads+" "+data_list[int(ide)-1][1])
print("-----------------------------")
print('10 most downloaded books in the Indonesia:')
for ide, downloads in sorted_booklist_in[:10]:
print(downloads+" "+data_list[int(ide)-1][1])
print("-----------------------------")
print('10 most downloaded books in the Germany:')
for ide, downloads in sorted_booklist_ge[:10]:
print(downloads+" "+data_list[int(ide)-1][1])
print("-----------------------------")
print('10 most downloaded books in the Austria:')
for ide, downloads in sorted_booklist_au[:10]:
print(downloads+" "+data_list[int(ide)-1][1])
print("-----------------------------")
print('10 most downloaded books in the Belgium:')
for ide, downloads in sorted_booklist_be[:10]:
print(downloads+" "+data_list[int(ide)-1][1])
print("-----------------------------")
print('10 most downloaded books in the Hungary:')
for ide, downloads in sorted_booklist_hu[:10]:
print(downloads+" "+data_list[int(ide)-1][1])
print("-----------------------------")
print('10 most downloaded books in the Romania:')
for ide, downloads in sorted_booklist_ro[:10]:
print(downloads+" "+data_list[int(ide)-1][1])