def process_answers(self, dbquestion_ids):
""" Get all answers for the list of question ids """
has_more = True
page = 1
base_url = self.url + '/2.2/questions/' + str(
dbquestion_ids) + '/answers?'
base_url += 'order=desc&sort=activity&site=stackoverflow&key=' + self.api_key
base_url += '&' + 'pagesize=' + str(self.pagesize)
logging.debug("Getting answers for dbquestion ids" +
str(dbquestion_ids))
dbanswers_ids = []
while has_more:
url = base_url + "&page=" + str(page)
if not self.debug:
data = self._get_api_data(url)
else:
has_more = False
data = StackSampleData.answers
parser = JSONParser(unicode(data))
parser.parse()
# [u'has_more', u'items', u'quota_max', u'quota_remaining']
has_more = parser.data['has_more']
page += 1
data = parser.data['items']
for answer in data:
dbanswer = Answers()
dbanswer.identifier = answer['answer_id']
dbanswers_ids.append(dbanswer.identifier)
# dbanswer.body = text
if 'user_id' in answer['owner']:
dbanswer.user_identifier = answer['owner']['user_id']
if dbanswer.user_identifier not in self.user_ids_answers:
self.user_ids_answers.append(dbanswer.user_identifier)
dbanswer.question_identifier = answer['question_id']
create_date = datetime.datetime.fromtimestamp(
int(answer['creation_date']))
dbanswer.submitted_on = create_date.strftime(
'%Y-%m-%d %H:%M:%S')
dbanswer.votes = answer['score']
self.session.add(dbanswer)
self.total_answers += 1
self.user_ids_answers.append(dbanswer.user_identifier)
self.session.commit()
# Time to get comments for all answers
while len(dbanswers_ids) > 0:
ids = []
for i in range(self.pagesize):
if len(dbanswers_ids) > 0:
val = dbanswers_ids.pop()
if val is not None: ids.append(val)
else: logging.info("Found None Answer")
ids = ";".join([str(x) for x in ids])
self.process_comments(ids, 'answer')
def process_answer(answer):
dbanswer = Answers()
dbanswer.identifier = answer['id']
# dbanswer.body = text
dbanswer.user_identifier = answer['user_id']
if answer['username'] not in self.user_ids_answers:
self.user_ids_answers.append(answer['username'])
dbanswer.question_identifier = question_id
dbanswer.submitted_on = answer['updated_at']
dbanswer.votes = answer['score']
dbanswer.body = answer['cooked']
self.session.add(dbanswer)
self.total_answers += 1
def process_answer(answer):
dbanswer = Answers()
dbanswer.identifier = answer['id']
# dbanswer.body = text
dbanswer.user_identifier = answer['user_id']
if answer['username'] not in self.user_ids_answers:
self.user_ids_answers.append(answer['username'])
dbanswer.question_identifier = question_id
dbanswer.submitted_on = answer['updated_at']
dbanswer.votes = answer['score']
dbanswer.body = answer['cooked']
self.session.add(dbanswer)
self.total_answers += 1
def process_answers(self, dbquestion_ids):
""" Get all answers for the list of question ids """
has_more = True
page = 1
base_url = self.url + '/2.2/questions/'+str(dbquestion_ids)+'/answers?'
base_url += 'order=desc&sort=activity&site=stackoverflow&key='+self.api_key
base_url += '&' + 'pagesize='+str(self.pagesize)
logging.debug("Getting answers for dbquestion ids" + str(dbquestion_ids))
dbanswers_ids = []
while has_more:
url = base_url + "&page="+str(page)
if not self.debug:
data = self._get_api_data(url)
else:
has_more = False
data = StackSampleData.answers
parser = JSONParser(unicode(data))
parser.parse()
# [u'has_more', u'items', u'quota_max', u'quota_remaining']
has_more = parser.data['has_more']
page += 1
data = parser.data['items']
for answer in data:
dbanswer = Answers()
dbanswer.identifier = answer['answer_id']
dbanswers_ids.append(dbanswer.identifier)
# dbanswer.body = text
if 'user_id' in answer['owner']:
dbanswer.user_identifier = answer['owner']['user_id']
if dbanswer.user_identifier not in self.user_ids_answers:
self.user_ids_answers.append(dbanswer.user_identifier)
dbanswer.question_identifier = answer['question_id']
create_date = datetime.datetime.fromtimestamp(int(answer['creation_date']))
dbanswer.submitted_on = create_date.strftime('%Y-%m-%d %H:%M:%S')
dbanswer.votes = answer['score']
self.session.add(dbanswer)
self.total_answers += 1
self.user_ids_answers.append(dbanswer.user_identifier)
self.session.commit()
# Time to get comments for all answers
while len(dbanswers_ids)>0:
ids = []
for i in range(self.pagesize):
if len(dbanswers_ids)>0:
val = dbanswers_ids.pop()
if val is not None: ids.append(val)
else: logging.info("Found None Answer")
ids = ";".join([str(x) for x in ids])
self.process_comments(ids,'answer')
