def reviewp(self):
if self.parent=="true":
survey_id=[self.survey_id]
for obj in AspectQ.objects(parent=self.survey_id):
survey_id.append(obj.survey_id)
print("survey_id",survey_id)
task= Status.objects(unique_identifier=survey_id[0]+self.provider)
else:
survey_id= self.survey_id
task= Status.objects(unique_identifier=survey_id+self.provider)
print ("task",task)
try:
status= task.scraped_status
if task.scraped_status=="success" and task.reviewp_status!="success":
# ReviewP(self.survey_id,self.provider).run()
task.update(reviewp_status="success")
else:
print ("ReviewP job ignored for ",self.survey_id,"provider",self.provider)
except Exception as e:
print ("ReviewP Exception Occured ***",e,"*** for",self.survey_id,self.provider)
if task.scraped_status=="success" and task.reviewp_status!="success":
ReviewP(self.survey_id,self.provider).run()
task.update(reviewp_status="success")
else:
print ("ReviewP job ignored for ",self.survey_id,"provider",self.provider)
def reviewp(self):
if self.parent == "true":
survey_id = [self.survey_id]
for obj in AspectQ.objects(parent=self.survey_id):
survey_id.append(obj.survey_id)
print("survey_id", survey_id)
task = Status.objects(unique_identifier=survey_id[0] +
self.provider)
else:
survey_id = self.survey_id
task = Status.objects(unique_identifier=survey_id + self.provider)
print("task", task)
try:
status = task.scraped_status
if task.scraped_status == "success" and task.reviewp_status != "success":
# ReviewP(self.survey_id,self.provider).run()
task.update(reviewp_status="success")
else:
print("ReviewP job ignored for ", self.survey_id, "provider",
self.provider)
except Exception as e:
print("ReviewP Exception Occured ***", e, "*** for",
self.survey_id, self.provider)
if task.scraped_status == "success" and task.reviewp_status != "success":
ReviewP(self.survey_id, self.provider).run()
task.update(reviewp_status="success")
else:
print("ReviewP job ignored for ", self.survey_id, "provider",
self.provider)
def get_data(self):
if isinstance(self.sid, list):
print("Zomato ignored", self.sid)
pass
# parent_id= self.sid[0]
# for i in range(len(self.sid)):
# if i==0:
# pass
# else:
# objects=Reviews.objects(survey_id= self.sid[i],provider=self.p)
# for obj in objects:
# Reviews()
# pass
else:
rid = self.get_id()
total = self.get_total()
turn = int(total / 5) + 1
print(turn)
# 1/0
if len(Record.objects(survey_id=self.sid, rid=str(rid))) != 0:
print("Already Review Collected")
else:
pool = Pool()
ids = list(range(0, turn))
print(ids)
# 1/0
# for i in ids:
# self.sub_get(i)
pool.map(self.sub_get, ids)
Record(provider="zomato", survey_id=self.sid,
rid=str(rid)).save()
Status(unique_identifier=self.sid + provider,
scraped_status="success").save()
def sentiment(self):
task= Status.objects(unique_identifier=self.survey_id+self.provider)
if task.scraped_status=="success" and task.reviewp_status=="success" and task.sentiment_status!="success":
Sentiment(self.survey_id,self.provider).run()
task.update(sentiment_status="success")
else:
print ("Sentiment job ignored for ",self.survey_id,"provider",self.provider)
def sentiment(self):
task = Status.objects(unique_identifier=self.survey_id + self.provider)
if task.scraped_status == "success" and task.reviewp_status == "success" and task.sentiment_status != "success":
Sentiment(self.survey_id, self.provider).run()
task.update(sentiment_status="success")
else:
print("Sentiment job ignored for ", self.survey_id, "provider",
self.provider)
def aspectr(self):
if self.parent=="true":
pass
else:
task= Status.objects(unique_identifier=self.survey_id+self.provider)
if task.scraped_status=="success" and task.reviewp_status=="success" and task.sentiment_status=="success":
# AspectR(self.survey_id,self.provider)
task.update(aspectr_status="success")
else:
print ("AspectR job ignored for ",self.survey_id,"provider",self.provider)
def aspectr(self):
if self.parent == "true":
pass
else:
task = Status.objects(unique_identifier=self.survey_id +
self.provider)
if task.scraped_status == "success" and task.reviewp_status == "success" and task.sentiment_status == "success":
# AspectR(self.survey_id,self.provider)
task.update(aspectr_status="success")
else:
print("AspectR job ignored for ", self.survey_id, "provider",
self.provider)
def scrap(self):
if self.parent == "true":
print(self.survey_id, "is a parent survey")
try:
task = Status(unique_identifier=self.survey_id +
self.provider).count()
if task == 0:
Status(unique_identifier=self.survey_id + self.provider,
scraped_status="success").save()
else:
pass
except Exception as e:
print("Exception", e, "for", self.survey_id)
try:
Status(unique_identifier=self.survey_id + self.provider,
scraped_status="success").save()
except:
pass
else:
task = Status.objects(unique_identifier=self.survey_id +
self.provider).count()
if task == 1:
print(self.survey_id, "ignored for provider", self.provider)
pass
else:
if self.provider == "zomato":
try:
print("Scraping", self.survey_id)
# Zomato(self.base_url,self.survey_id,self.provider).get_data()
Status(unique_identifier=self.survey_id +
self.provider,
scraped_status="success").save()
except Exception as e:
print("Exception occured for ", e, "***********",
self.survey_id, "provider", self.provider)
with open("log.txt", "a") as f:
f.write(str(e) + "****** \n")
elif self.provider == "tripadvisor":
try:
TripAdvisor(self.base_url, self.survey_id,
self.provider).get_data()
Status(unique_identifier=self.survey_id +
self.provider,
scraped_status="success").save()
except:
print("Exception occured for ", self.survey_id,
"provider", self.provider)
else:
print("Bad Provider: ", self.provider)
def scrap(self):
if self.parent=="true":
print (self.survey_id,"is a parent survey")
try:
task=Status(unique_identifier=self.survey_id+self.provider).count()
if task==0:
Status(unique_identifier= self.survey_id+self.provider,scraped_status="success").save()
else:pass
except Exception as e:
print("Exception",e,"for",self.survey_id)
try:Status(unique_identifier= self.survey_id+self.provider,scraped_status="success").save()
except:pass
else:
task= Status.objects(unique_identifier=self.survey_id+self.provider).count()
if task==1:
print(self.survey_id,"ignored for provider",self.provider)
pass
else:
if self.provider=="zomato":
try:
print ("Scraping",self.survey_id)
# Zomato(self.base_url,self.survey_id,self.provider).get_data()
Status(unique_identifier=self.survey_id+self.provider,scraped_status="success").save()
except Exception as e:
print("Exception occured for ",e,"***********",self.survey_id,"provider",self.provider)
with open("log.txt","a") as f:
f.write(str(e)+"****** \n")
elif self.provider=="tripadvisor":
try:
TripAdvisor(self.base_url,self.survey_id,self.provider).get_data()
Status(unique_identifier=self.survey_id+self.provider,scraped_status="success").save()
except:
print("Exception occured for ",self.survey_id,"provider",self.provider)
else:
print("Bad Provider: ",self.provider)
def wordcloud(self):
if isinstance(self.survey_id, list):
survey_id = self.survey_id[0]
else:
survey_id = self.survey_id
task = Status.objects(unique_identifier=survey_id + self.provider)
def wordcloud(self):
if isinstance(self.survey_id,list):
survey_id=self.survey_id[0]
else:survey_id=self.survey_id
task= Status.objects(unique_identifier=survey_id+self.provider)
