def give_cluster(url):
try:
#print('URL name is :',url)
# for key in final_dict.keys():
# for value in final_dict[key]:
# if(url==value):
# return key
content = preprocess(get_text_content(url))
#print("line 1")
new_url_vector=sent_vectorizer(content,modelg)
#print("line 2")
#print(kmeans.predict([new_url_vector])[0])
return kmeans.predict([new_url_vector])[0]
except Exception as e:
return e
def giveUrlInfo(url):
try:
urlInfo = checkUrlInDb(url)
if(len(urlInfo['new_url_vector'])!=0):
print("url in databse")
cluster_no = urlInfo['cluster_no']
new_url_vector = urlInfo['new_url_vector']
else:
print("url not in database")
content = preprocess(get_text_content(url))
new_url_vector=sent_vectorizer(content,modelg)
cluster_no=kmeans.predict([new_url_vector])[0]
print("cluster",cluster_no)
# print("cluster_no")
# print(new_url_vector)
return dict({"cluster_no":cluster_no,"urlvector":new_url_vector})
except Exception as e:
print('giveUrlInfo error',e)
return e
def getVectorOfUrl(url):
try:
content = preprocess(get_text_content(url))
return sent_vectorizer(content,modelg)
except Exception as e:
return e