def collect(self):
#with tweetstream.FilterStream(self.twitterUser, self.twitterPass, track=self.words) as stream:
with tweetstream.SampleStream(self.twitterUser,
self.twitterPass) as stream:
for tweet in stream:
#print tweet.get('text')
if self.count and self.count % 100 == 0:
print "done with %d tweets in %s" % (self.count,
datetime.now())
if (self.count >= self.limit):
raise Exception('done')
if tweet.get('text'):
if 'rt' in tweet.get('text').lower():
continue
self.queue.put(tweet)
self.count += 1
#GetSearch(self, term=None, geocode=None, since_id=None, max_id=None, until=None, count=15, lang=None, locale=None, result_type='mixed', include_entities=None)
#Return twitter search results for a given term.
#36.35,-86.92
#polygon 8mi
#Nashville 30mi
#<onset>2013-09-10T15:31:00-05:00</onset> <expires>2013-09-10T16:00:00-05:00</expires>
#statuses = api.GetSearch(term = "FEMA", count = 100, geocode=("36.350000","-86.920000","3000mi"))
#statuses = api.GetSearch(geocode="36.35,-86.92,3000mi", until="2013-09-11", count = 10)
#statuses = api.GetSearch(until="2013-09-11", count = 10)
#statuses = api.GetSearch(term = "snow", count = 100000, geocode=("45.023513", "-109.915807", "100mi"), result_type="recent")
#print statuses
#dumpfile = open("statuses_100000_recent_geocode_snow.pkl", "wb")
#pickle.dump(statuses, dumpfile)
#dumpfile.close()
#for status in statuses:
# print status.text
# print "\n\n"
stream = tweetstream.SampleStream("*****@*****.**", "karidola")
for tweet in stream:
print tweet
#!/usr/bin/env python
import tweetstream, twitter
stream = tweetstream.SampleStream("*****@*****.**", "825123")
api = twitter.Api(
consumer_key='NINW6eFEgEAOUAFAX5bVpQ',
consumer_secret='SjJDB2Bpk0IjiEWlptCUkJsluq17tockkAQqJCSs',
access_token_key='SjJDB2Bpk0IjiEWlptCUkJsluq17tockkAQqJCSs',
access_token_secret='QxwE8socZx7gxcNJlrKMveDYWeyhIir3cvh2KgO5wHI')
print api.VerifyCredentials()
# statuses = api.GetUserTimeline('gsm1011')
# print [s.user.name for s in statuses]
users = api.GetFriends()
print[u.name for u in users]
def create_stream():
return tweetstream.SampleStream(tpconf.USERNAME, tpconf.PASSWORD)
def send_tweets(server, user, password):
stream = tweetstream.SampleStream(user, password)
for tweet in stream:
broadcast_msg(server, '/tweets', 'tweet', tweet)
parser.add_argument('-s', '--s', dest='s', action='store', type=float, required=True,
help='Minimum frequency')
parser.add_argument('-c', '--credentials', dest='credentials', action='store',
default="./.tpass",
help='File with Twitter credentials (username and password, separated by a space)')
args = parser.parse_args()
return args
args = parse_command_line_arguments()
username,password = open(args.credentials).read().strip().split()
stream = tweetstream.SampleStream(username,password)
lc = LossyCounter(args.s)
N=0
while True:
try:
t = stream.next()
except Exception, e:
print e
break
if t.has_key("text"):
tags = re.findall("#[A-Za-z0-9]+", t["text"])
if len(tags) > 0:
for tag in tags:
print tag
N+=1
import tweetstream
import codecs
stream = tweetstream.SampleStream("ID", "password");
f = codecs.open("dumpfile", "w", encoding="UTF-8");
counter=0;
for tweet in stream:
counter=counter+1;
try:
f.write(counter+" TEXT: "+tweet["text"]);
except KeyError:
print "No text field";
try:
g=tweet["geo"]; #try to print the geographical location of the twitter
try:
if(not g is None):
print counter," LOCATION: ",g;
except AttributeError:
g=None; #print "AttributeError, g=|",g,"|";
except KeyError:
g=None;
# Connect to Mongo
try:
c = Connection(host="localhost", port=27017)
print "Connected successfully"
except ConnectionFailure, e:
sys.stderr.write("Could not connect to MongoDB: %s" % e)
sys.exit(1)
db = c['haiku']
# Open connection to Twitter's public timeline, build haikus
failed = True
while failed:
failed = False
try:
with tweetstream.SampleStream(USER, PASS) as stream:
for tweet in stream:
if 'text' in tweet and len(tweet['text']) > 0:
screen_name = tweet['user']['screen_name']
hashes = [
j for j in set([
i for i in tweet['text'].split()
if i.startswith('#')
])
]
# Strip out urls, punctuation, RTs, and @'s
tweet_stripped = urlre.sub('', tweet['text'])
tweet_stripped = punctre.sub('', tweet_stripped)
tweet_stemmed = [
porter_stemmer.stem_word(i.lower())
for i in tweet_stripped.split()
def tweetFilter(uname, psswd): stream = tweetstream.SampleStream(uname, psswd) for tweet in stream: if 'user' in tweet.keys() and tweet['user']['lang'] == 'en': yield tweet
from pymongo.errors import ConnectionFailure
import tweetstream
import string
def normalize(s):
ret = s
for p in string.punctuation:
ret = ret.replace(p, '')
return ret
""" Connect to MongoDB """
try:
c = Connection(host="localhost", port=27017)
except ConnectionFailure, e:
sys.stderr.write("Could not connect to MongoDB: %s" % e)
sys.exit(1)
db = c['nba_tweets']
with open('nba_queries.txt') as f:
queries = [i.strip() for i in f.readlines()]
with tweetstream.SampleStream('username', 'pass') as stream:
for tweet in stream:
if 'text' in tweet.keys() and len(tweet['text']) > 0:
if True in [i.lower() in queries for i in tweet['text'].split()]:
print tweet['text']
db.tweets.insert(tweet)
ret = ret.replace(p, '')
return ret
def is_english_word(word):
return word.lower() in english_words
afinn = dict(
map(lambda (k, v): (k, int(v)),
[line.split('\t') for line in open("AFINN/AFINN-111.txt")]))
if __name__ == '__main__':
romney_count = 0
obama_count = 0
with tweetstream.SampleStream(sys.argv[1], sys.argv[2]) as stream:
for tweet in stream:
if 'text' in tweet.keys() and len(tweet['text']) > 0:
try:
no_punct = normalize(tweet['text'])
if no_punct != None:
val = sum([
afinn[i] if i in afinn else 0
for i in no_punct.split()
])
if val < -2 or val > 2:
if any([
i in ['romney', 'mitt']
for i in no_punct.split()
]):
romney_count += 1