def Advanced(self,string,html,link):
start_time = time.time()
global i
global j
global data2
global class2
if(i==0):
stemmed_text,link_stemmed_text,c = ContentAnalyzer_Utils(string,html,link).read_text()
path = directory.path()
doc = open(path+'/text/'+'news.txt', 'r').read()
self.news_list = Stemming().stem(doc)
doc = open(path+'/text/'+'games.txt', 'r').read()
self.games_list = Stemming().stem(doc)
doc = open(path+'/text/'+'medicine.txt', 'r').read()
self.med_list = Stemming().stem(doc)
pickle.dump(stemmed_text, open('pfile_text.p','wb'))
pickle.dump(link_stemmed_text,open('pfile_link.p','wb'))
region_text,region_link,length_list_link_text,length_link_text = Bayesian(i,c).learning()
p = Content_Classifier_2(region_text,region_link,length_list_link_text,length_link_text)
k = 0
sitecounter = 0
for u in range(1,7):
data2[k] = p.classify_text(u)
k = k + 1
data2[k] = p.classify_link(u)
k = k + 1
i = 1
elif(i==1):
stemmed_text,link_stemmed_text,c = ContentAnalyzer_Utils(string,html,link).read_text()
pickle.dump(stemmed_text, open('pfile_text.p','wb'))
pickle.dump(link_stemmed_text,open('pfile_link.p','wb'))
region_text,region_link,length_list_link_text,length_link_text = Bayesian(i,c).learning()
p = Content_Classifier_2(region_text,region_link,length_list_link_text,length_link_text )
k = 0
sitecounter = 0
for u in range(1,7):
data2[k] = p.classify_text(u)
k = k + 1
data2[k] = p.classify_link(u)
k = k + 1
s = []
s[:] = data2
value = self.check_advanced(data2,stemmed_text)
if(sum(data2) !=12):
value = value + ' ' +self.reason(data2)
elif(sum(data2) == 12):
value = 'SAFE'
if sum(data2)==0 and len(stemmed_text) <=20: value = "Not-Enough-Text-on-Site"
elif len(stemmed_text)==0 : value = "ERROR"
return s, value
def openandstem(self,file1):
path = directory.path()
doc = open(path+'/text/'+file1, 'r').read()
return Stemming().stem(doc)