analyzeRetweet.py

import sys, csv, pprint, json
import networkx as nx
import matplotlib.pyplot as plt
import community as community_louvain
import matplotlib.cm as cm
from community import generate_dendrogram, best_partition, partition_at_level
from pymongo import MongoClient
from networkx.readwrite import json_graph

# Connecting to the db
collection= db['tweets']

# Creating empty graph
G= nx.Graph()

# Options while creating the graphs
options = {
    'node_color': 'blue',
    'node_size': 20,
    'width': 1
}

# Keep track of tweets counted
mapOriginal= {}

''' TODO: Add edges to the graph '''
def addToGraph(src, dest):
    global G
    if G.has_edge(src, dest):
        G[src][dest]['weight']+=1
    else:
        G.add_edge(src, dest, weight=1)

# Iterating in each record
for item in collection.find():

    ifRetweeted= True if item.get('retweeted_status') is not None else False
    ifQuoted= True if item.get('quoted_status') is not None else False

    # If the tweet is original tweet itself (i.e. no retweet or not a quoted one)
    if (not ifRetweeted) and (not ifQuoted):
        
        # do nothing...
        pass

    # In case it's just a retweet
    elif (ifRetweeted) and (not ifQuoted):
        
        if mapOriginal.get(item['retweeted_status']['id']) is None:
            mapOriginal[item['retweeted_status']['id']]= 1
            
            addToGraph(item['user']['screen_name'], item['retweeted_status']['user']['screen_name'])

    # In case it's just a quoted one
    elif ifQuoted:
        
        if mapOriginal.get(item['quoted_status']['id']) is None:
            
            # Get the original tweeter & mentions in that post
            mapOriginal[item['quoted_status']['id']]= 1

            addToGraph(item['user']['screen_name'], item['quoted_status']['user']['screen_name'])

with open('retweeters.csv', 'w', newline='') as fileSave:
    writer= csv.writer(fileSave)
    for u,v in G.edges():
        writer.writerow([u, v, G[u][v]['weight']])