Pulls data from Twitter and writes to a .csv data file for use with Witter

realData.py

from __future__ import division
import re, string, os, math, time, sys, random
from operator import itemgetter
import tweetstream

def strTimeProp(start, end, format, prop):
    """Get a time at a proportion of a range of two formatted times.

    start and end should be strings specifying times formated in the
    given format (strftime-style), giving an interval [start, end].
    prop specifies how a proportion of the interval to be taken after
    start.  The returned time will be in the specified format.
    """

    stime = time.mktime(time.strptime(start, format))
    etime = time.mktime(time.strptime(end, format))

    ptime = stime + prop * (etime - stime)

    return time.strftime(format, time.localtime(ptime))


def randomDate(start, end, prop):
    return strTimeProp(start, end, '%m/%d/%Y', prop)
def randomDateTime(start, end, prop):
    return strTimeProp(start, end, '%m/%d/%Y %I:%M %p', prop)

r = re.compile("[^a-zA-Z0-9 ]", re.UNICODE)

#Enter twitter credentials here
stream = tweetstream.SampleStream("USERNAME","PASSWORD")

f = open('names.csv', 'w')

#Generates a Userset of n users with random ids between 1-10000 and joindates between 1/1/2008 and 1/1/2012
n = 0

uids = []

for tweet in stream:
    try:
            uid = random.randint(1,10000)
            while (uid in uids):
                uid = random.randint(1,10000)
            date = randomDate("1/1/2008", "1/1/2012", random.random())  
            f.write(tweet['user']['name'].decode('ascii') + ", " + date + ", " + str(uid) + ",\n")
            print tweet['user']['name'].decode('ascii') + ", " + date + ", " + str(uid) + ","
            uids.append(uid)
            if(n<10):
                n+=1
            else:
                break
    except KeyError:
        pass
    except UnicodeDecodeError:
        pass
    except UnicodeEncodeError:
        pass

f.close()

print "IDs: " + str(uids)

#Generates a random number (between 1 and 20) of tweets per user
f = open('weets.csv','w')
wids = []
for uid in uids:
    n = random.randint(1,20)
    i = 0
    for tweet in stream:
        try: 
            wid = random.randint(1,1000000)
            while (wid in wids):
                wid = random.randint(1,1000000)
            datetime = randomDateTime("1/1/2008 1:00 AM", "1/1/2012 1:00 AM", random.random())
            message = ''.join(tweet['text'].decode('ascii').splitlines()).replace(',', ' ')
            f.write(str(wid) + ", " + str(uid) + ", " + message + ", " + datetime + "\n")
            print "[" + str(i) + "/" + str(n) + "] " + str(wid) + ", " + str(uid) + ", " + message + ", " + datetime + ", "
            wids.append(wid)
            if(i<n):
                i+=1
            else:
                break  
        except KeyError:
            pass
        except UnicodeDecodeError:
            pass
        except UnicodeEncodeError:
            pass

f.close()