def get_tweet_from_user(self, userlist, field='id'):
# return a list of tweets made by users in userlist
duplicateFinder = dupefilter.DupInfo(prefix=self.prefix)
return duplicateFinder.get_tweet(collection=util.loadjson(
self.sourcefile),
userlist=userlist,
field=field)
def print_metadata(self):
# return metadata of one collection
# including total number of tweets, total
duplicateFinder = dupefilter.DupInfo(prefix=self.prefix)
data = duplicateFinder.get_metadata()
print data['num_tweet']
print data['end_time'] - data['start_time']
print data['start_time']
def get_suspicious_user_group(self,
startover=False,
filter_function=all_groups):
duplicateFinder = dupefilter.DupInfo(prefix=self.prefix,
startover=startover)
duplicateFinder.find_duplicate_tweet(
collection=util.loadjson(self.sourcefile),
collect_url_only=self.collect_url_only)
botty_groups = duplicateFinder.get_suspicious_user_group(
filter_function=filter_function, url_based=self.url_based)
return botty_groups
def get_percent_of_spam(self):
spam_user = self.get_spam_user_info(variable='spam_user')
duplicateFinder = dupefilter.DupInfo(prefix=self.prefix)
total_user = duplicateFinder.get_metadata(variable='num_user')
print 'Start time is ', duplicateFinder.get_metadata(
variable='start_time')
print 'End time is ', duplicateFinder.get_metadata(variable='end_time')
print 'Total number of account is %d' % (total_user)
print 'Total number of spam account is %d' % (len(spam_user))
print 'Percent of spam account is %f' % (float(len(spam_user)) /
float(total_user))
total_tweet = duplicateFinder.get_metadata(variable='num_tweet')
print 'Total number of tweets is %d' % (total_tweet)
num_spam_tweet = duplicateFinder.get_tweet(collection=util.loadjson(
self.sourcefile),
userlist=spam_user,
only_number=True)
print 'Total number of spam tweets is %d' % (num_spam_tweet)
print 'Percent of spam tweets is %f' % (float(num_spam_tweet) /
float(total_tweet))
def save_user_info(self):
duplicateFinder = dupefilter.DupInfo(prefix=self.prefix)
duplicateFinder.save_user_info(
collection=util.loadjson(self.sourcefile))
def get_url_per_user(self):
duplicateFinder = dupefilter.DupInfo(prefix=self.prefix)
return duplicateFinder.get_url_per_user(
collection=util.loadjson(self.sourcefile))
def get_num_tweet(self):
# return total number of tweets in one collection
duplicateFinder = dupefilter.DupInfo(prefix=self.prefix)
num_tweet = duplicateFinder.get_metadata(variable='num_tweet')
return num_tweet