crunchbase to network

networkx.py

# Crunchbase to NetworkX network builder
#
# Builds a network from the Crunchbase database and outputs it in graphml format.
#
# Required modules:
#    simplejson (http://undefined.org/python/#simplejson)
#    networkx (http://networkx.lanl.gov/)

import urllib2, simplejson as json, networkx as nx

def getCBinfo(namespace, permalink):
    api_url = "http://api.crunchbase.com/v/1/%s/%s.js" % (namespace, permalink)
    return json.loads(urllib2.urlopen(api_url).read())

def add_clique(G,investors):
    # Take a set of investors and add them to the graph, along with edges
    # between them all. Where an edge already exists, increment its weight.
    l_inv = len(investors)
    if l_inv > 1:
        # add nodes
        for inv, typ in investors:
            G.add_node(inv, inv_type = typ)
        # add edges
        for i in range(0,l_inv-1):
            for j in range(i+1,l_inv):
                if G.edge[investors[i][0]].has_key(investors[j][0]):
                    G.edge[investors[i][0]][investors[j][0]]['weight'] += 1
                else:
                    G.add_edge(investors[i][0],investors[j][0],weight=1)
    return G

# Main.
# Get the list of companies Crunchbase has data on
company_names = json.loads(urllib2.urlopen("http://api.crunchbase.com/v/1/companies.js").read())

# initialize Graph
G = nx.Graph()

# Iterate through companies, getting CB data on each
for company in company_names:
    try:
        co_info = getCBinfo('company', company['permalink'])
    except:
        continue

    # For each company make a set of all investors
    investors = set()
    if co_info.has_key('funding_rounds') and co_info['funding_rounds']:
        for iround in co_info['funding_rounds']:           
            for investment in iround['investments']:
                for i_type in ['financial_org','person','company']:
                    if investment[i_type]:
                        investors.add((investment[i_type]['permalink'],i_type))

    # Add investors and edges between them to the graph
    G = add_clique(G,list(investors))

# Write the network to a graphml file /projects/cb_graph.graphml
# NetworkX supports many other formats as well, check the docs.
nx.write_graphml(G,"/projects/cb_graph.graphml")