User:Tash/Prototyping 03
CGI & TF-IDF search engine
#!//usr/local/bin/python3
import cgi
import cgitb; cgitb.enable()
import nltk
import re
print ("Content-type:text/html;charset=utf-8")
print ()
#cgi.print_environ()
f = cgi.FieldStorage()
submit1 = f.getvalue("submit1", "")
submit2 = f.getvalue("submit2", "")
text = f.getvalue("text", "")
### SORTING
import os
import csv
import string
import pandas as pd
import sys
### SEARCHING
#input keyword you want to search
keyword = text
print ("""<!DOCTYPE html>
<html>
<head>
<title>Search</title>
<meta charset="utf-8">
</head>
<body>
<p style='font-size: 20pt; font-family: Courier'>Search by keyword</p>
<form method="get">
<textarea name="text" style="background: yellow; font-size: 10pt; width: 370px; height: 28px;" autofocus></textarea>
<input type="submit" name="submit" value="Search" style='font-size: 9pt; height: 32px; vertical-align:top;'>
</form>
<p style='font-size: 9pt; font-family: Courier'>
webring <br>
<a href="http://145.24.204.185:8000/form.html">joca</a>
<a href="http://145.24.198.145:8000/form.html">alice</a>
<a href="http://145.24.246.69:8000/form.html">michael</a>
<a href="http://145.24.165.175:8000/form.html">ange</a>
<a href="http://145.24.254.39:8000/form.html">zalan</a>
</p>
</body>
</html>""")
x = 0
if text :
#read csv, and split on "," the line
csv_file = csv.reader(open('tfidf.csv', "r"), delimiter=",")
col_names = next(csv_file)
#loop through csv list
for row in csv_file:
#if current rows value is equal to input, print that row
if keyword == row[0] :
tfidf_list = list(zip(col_names, row))
del tfidf_list[0]
sorted_by_second = sorted(tfidf_list, key=lambda x:float(x[1]), reverse=True)
print ("<p></p>")
print ("--------------------------------------------------------------------------------------")
print ("<p style='font-size: 20pt; font-family: Courier'>Results</p>")
for item in sorted_by_second:
x = x+1
print ("--------------------------------------------------------------------------------------")
print ("<br></br>")
print(x, item)
n = item[0]
f = open("cgi-bin/texts/{}".format(n), "r")
sents = nltk.sent_tokenize(f.read())
for sentence in sents:
if re.search(r'\b({})\b'.format(text), sentence):
print ("<br></br>")
print(sentence)
f.close()
print ("<br></br>")
Self directed research
Brainstorm 23.04.2018
Interface: How do you visualize that which is UNSTABLE? Serendipity? Missing data? Uncertainty? Dissent? Multiple views? On data provenance and feminist visualization: https://civic.mit.edu/feminist-data-visualization HOW can you GET data that's MISSING ?! E.G. from LibGen: where is the UPLOAD DATA? what could we do with it?
Simple test to highlight absent information: in LibGen's catalogue CSV there are row without titles How to search for blanks?
something like:
csvgrep -c Title -m "" content.csv
^ this solution matches spaces but doesn't look for empty state cells.
csvgrep -c Author -r "^$" content.csv
^ this solution finds rows with empty state cells in the 'Author' column
andre's exciting explorations of the archive.org api search: Internet Archive - Advanced search: https://archive.org/advancedsearch.php ghost in the mp3