linecount = 0 #keeps a line count
plagper = 0 #finds the plagiarism percentage
for contentline in content: #going through each line in the user data
if (contentline != "\n"): #get rid of unrequired lines read
linecount += 1 #keep a count of content lines
URLsToCheck = None #variable to store url found
URLsToCheck = getURL1.URLFinder(contentline) #finds the url
somevar = 0 #a flag variable
if (URLsToCheck != None):
webSearch.searchResults(URLsToCheck) #scraps from the url
somevar = comparefuzzy.check(
contentline) #compares with the scraped data
if (somevar > 85):
plagper += 100 #kept a threshold value of 85% as per the performance of the algo seen before...for Levenshtein Distance
matched.write("Line-" + str(linecount) + "::" + URLsToCheck +
"\n") #writing for matched sources
# highlight.write("<font color=\"red\"><b>"+contentline+"</b></font>\n") #writing for highlighting
highlight.write(contentline.upper() + "Source::{" +
URLsToCheck + "}\n")
else:
plagper += somevar
highlight.write(contentline) #writing non-highlighted
#NOTE: But to decide whether a Document is Plagiarised or Not, we have kept a threshold value of 70%...or as per the user...
for contentline in content: #going through each line in the user data
if (contentline != "\n"): #get rid of unrequired lines read
linecount += 1
URLsToCheck = [None] * 3 #For checking first 3 URLs
URLsToCheck = getURL3.URLFinder(contentline)
maxval = 0 #a flag variable
for j in range(3): #for all 3 urls
if (URLsToCheck[j] != None):
webSearch.searchResults(URLsToCheck[j])
tempval = comparefuzzy.check(contentline)
if (tempval > maxval):
maxval = tempval
maxurl = URLsToCheck[j]
tempval = 0
if (maxval > 85):
break
if (maxval > 85): #85%...a threshold value for Levenshtein Distance...
plagper += 100 #kept a threshold value of 85% as per the performance of the algo seen before
matched.write("Line-" + str(linecount) + "::" + maxurl +
"\n") #writing for matched sources
# highlight.write("<font color=\"red\"><b>"+contentline+"</b></font>\n") #writing for highlighting
highlight.write(contentline.upper() + "Source::{" + maxurl + "}\n")
else:
# URLsToCheck = [None]*3 #For checking first 3 URLs
URLsToCheck = None
URLsToCheck = getURL.URLFinder(contentline)
# for j in range(3):
# if(URLsToCheck[j]!=None):
if (URLsToCheck != None):
# print("Checking: "+URLsToCheck[j]+"\n")
# webSearch.searchResults(URLsToCheck[j])
webSearch.searchResults(URLsToCheck)
# print("Scrapped Text from "+URLsToCheck[j]+"\n")
# if(compareContent.check(contentline)):
# # print("A Plag Found!!!...\n")
# plagflag+=1
# break
somevar = comparefuzzy.check(contentline)
# if(somevar>75):
# plagper += 100 #kept a threshold value of 75% as per the performance of the algo seen before
# else:
plagper += somevar
if (
somevar > 75
): #kept 75 so as to compensate for the errors generated by common words and sentences
matched.write("Line-" + str(linecount) + "::" + URLsToCheck +
"\n") #writing for matched sources
highlight.write("<font color=\"red\"><b>" + contentline +
"</b></font>\n") #writing for highlighting
else:
highlight.write(contentline) #writing non-highlighted