Grab likes et al for members of a Facebook group.

fbLinksGrabber.py

#This is a really simple script:
##Grab the list of members of a Facebook group (no paging as yet...)
#Lets you do things like http://blog.ouseful.info/2012/12/05/emergent-social-interest-mapping-red-bull-racing-facebook-group/
###For each member, try to grab their Likes

#USAGE
#> python fbLinksGrabber.py -group GROUPID -typ THING -FBTOKEN ETC
#THING is one of groups, likes, books etc


import urllib,json,csv,argparse
 
#Grab a copy of a current token from an example Facebook API call. eg from clicking a keyed link on:
#https://developers.facebook.com/docs/reference/api/examples/
#Something a bit like this:
#AAAAAAITEghMBAOMYrWLBTYpf9ciZBLXaw56uOt2huS7C4cCiOiegEZBeiZB1N4ZCqHgQZDZD
 
parser = argparse.ArgumentParser(description='Generate social positioning map around a Facebook group')
 
parser.add_argument('-gid',default='2311573955',help='Facebook group ID')
#gid='2311573955'
 
parser.add_argument('-FBTOKEN',help='Facebook API token')

parser.add_argument('-typ',default='likes',help='Facebook group ID')

args=parser.parse_args()
if args.gid!=None: gid=args.gid
if args.FBTOKEN!=None: FBTOKEN=args.FBTOKEN
if args.typ!=None: typ=args.typ

import datetime
def getTimeStampedProjDirName(path,stub):
  now = datetime.datetime.now()
	ts = now.strftime("_%Y-%m-%d-%H-%M-%S")
	return path+'/'+stub+ts


#Quick test - output file is simple 2 column CSV that we can render in Gephi
#fn='fbgroupliketest_'+str(gid)+'.csv'
fn=getTimeStampedProjDirName('.','fbgroup_'+typ+'_test_'+str(gid) )
writer=csv.writer(open(fn+'.csv','wb+'),quoting=csv.QUOTE_ALL)
 
uids=[]
 
def getGroupMembers(gid):
    gurl='https://graph.facebook.com/'+str(gid)+'/members?limit=5000&access_token='+FBTOKEN
    data=json.load(urllib.urlopen(gurl))
    if "error" in data:
        print "Something seems to be going wrong - check OAUTH key?"
        print data['error']['message'],data['error']['code'],data['error']['type']
        exit(-1)
    else:
    	print data
        return data
 
def getX(X,uid,gid):
	#X: likes
    print "Get",X,"for",str(uid)
    #Should probably implement at least a simple cache here
    lurl="https://graph.facebook.com/"+str(uid)+"/"+X+"?access_token="+FBTOKEN
    ldata=json.load(urllib.urlopen(lurl))
    print ldata
     
    if len(ldata['data'])>0: 
        for i in ldata['data']:
            o=[]
            if 'name' in i:
                #writer.writerow([str(uid),i['name'].encode('ascii','ignore')])
                o.append( str(uid) )
                o.append( i['name'].encode('ascii','ignore') )
                
                print str(uid),i['name'],
                #We could colour nodes based on category, etc, though would require richer output format.
                #In the past, I have used the networkx library to construct "native" graph based representations of interest networks.
                if 'category' in i: 
                    print i['category'],
                    o.append( i['category'] )
                if 'id' in i: 
                    print i['id'],
                    o.append( i['id'] )
                writer.writerow( o )
                print ''


#For each user in the group membership list, get their likes                
def parseGroupMembers(groupData,gid):
    for user in groupData['data']:
        uid=user['id']
        #writer.writerow([str(uid),str(gid)])
        #x is just a fudge used in progress reporting
        x=0
        #Prevent duplicate fetches
        if uid not in uids:
            #getLikes(user['id'],gid)
            getX(typ,user['id'],gid)
            uids.append(uid)
            #Really crude progress reporting
            print x
            x=x+1
    #need to handle paging?
    #parse next page URL and recall this function
 
 
groupdata=getGroupMembers(gid)
parseGroupMembers(groupdata,gid)