tweetTSVtoGEXF.py

import csv
from os import listdir
import re
from gexf import *


gexf = Gexf("Twitter Mentions Network", "Test")
graph = gexf.addGraph("directed", "static", "Twitter network")



subcounter = 0 #needed to enumerate edges

for filename in listdir("output/"): #folder for output files
    print("opening " + filename)
    with open("output/" + filename, "r") as currentFile:
        tweettsv = csv.reader(currentFile, delimiter='\t')

        for t in tweettsv:
            source = t[11]
            print(source) #
            graph.addNode(source, source)
            targetlist = (t[12].split())
            for tl in targetlist:
                if tl.startswith("@"):
                    target = re.sub(r'[^A-Za-z0-9]+',r'',tl)
                    print("\t" + source)
                    print("\t\t" + target)
                    graph.addNode(target, target)
                    subcounter += 1
                    graph.addEdge(subcounter, source, target)


gexf_file = open("twitternetwork.gexf", "wb")
gexf.write(gexf_file)
print("Subcounter has looped " + str(subcounter) + " times")


"""
# The values in the TSV file:
['URL', 'Keywords', 'Keyword Count', 'DateTime', 'Favorite Count', 'Retweet', 'Lang',
'LinkCount', 'Link1', 'Link2', 'Link3', 'Author', 'Text', 'Followers', 'Friends',
'Location', 'Timezone', 'UTC Offset']
"""