def results(filename): image = app.config['UPLOAD_FOLDER']+ "/" + filename h1 = pHash.avhash(image) os.remove(image) reader = csv.reader(open(CATALOG, "rb"), delimiter=";") body = "" list = [] list_count = 0 for author, life, title, date, hash, technique, location, url, form, type in reader: h2 = int(hash) distance = pHash.hamming(h1,h2) document = {'author':author,'life':life,'title':title,'date':date, 'hash':hash, \ 'technique':technique, 'location':location, 'url':url, 'form':url,\ 'type':type, 'distance':distance} if distance < 9: confidence = (100 - int(distance)*5) document = {'author':author,'life':life,'title':title,'date':date, 'hash':hash, \ 'technique':technique, 'location':location, 'url':url, 'form':url,\ 'type':type, 'confidence':confidence, 'distance':distance} list.append(document) list_count = list_count + 1 list = sorted(list, key=lambda v: v['distance']) counter = 0 if list_count > 0: while (counter < 5 ) and counter != list_count: document = list[counter] body += htmlify( document) counter = counter + 1 return head + body + foot else: return render_template('not_found.html')
import csv import pHash import os reader = csv.reader(open("test.csv", "rb"), delimiter=";") writer = csv.writer(open("testcat.csv","wb"), delimiter=";") fields = reader.next() for author, life, title, date, technique, location, url, form, type, school, time in reader: url = url.replace(".html",".jpg") url = url.replace("/html","/art") words = url.split("/") image = words.pop() os.system("wget " + url) hash = pHash.avhash(image) hashed = str(hash) os.remove(image) writer.writerow([author, life, title, date, hash, technique, location, url, form, type]) print "Done!"