Getting Data In

How to integrate facebook python script to splunk?


Greetings, I'm new to splunk and I'm trying to get data from facebook: posts, likes, reactions... I have a python script that saves that information to a JSON file. I would like to use that script as an input for Splunk but I don't know how to address it.

This is the script:

import urllib2
import json
import datetime
import csv
import time

#app_id = "<FILL IN>"
#app_secret = "<FILL IN>" # DO NOT SHARE WITH ANYONE!
page_id = raw_input("Please Paste Public Page Name:")

#access_token = app_id + "|" + app_secret

access_token = raw_input("Please Paste Your Access Token:")

def request_until_succeed(url):
    req = urllib2.Request(url)
    success = False
    while success is False:
            response = urllib2.urlopen(req)
            if response.getcode() == 200:
                success = True
        except Exception, e:
            print e

            print "Error for URL %s: %s" % (url,
            print "Retrying."


# Needed to write tricky unicode correctly to csv
def unicode_normalize(text):
    return text.translate({ 0x2018:0x27, 0x2019:0x27, 0x201C:0x22, 0x201D:0x22,
                            0xa0:0x20 }).encode('utf-8')

def getFacebookPageFeedData(page_id, access_token, num_statuses):

    # Construct the URL string; see for
    # Reactions parameters
    base = ""
    node = "/%s/posts" % page_id 
    fields = "/?fields=message,link,permalink_url,created_time,type,name,id," + \
            "comments.limit(0).summary(true),shares,reactions" + \
    parameters = "&limit=%s&access_token=%s" % (num_statuses, access_token)
    url = base + node + fields + parameters

    # retrieve data
    data = json.loads(request_until_succeed(url))

    return data

def getReactionsForStatus(status_id, access_token):

    # See for Reactions parameters
        # Reactions are only accessable at a single-post endpoint

    base = ""
    node = "/%s" % status_id
    reactions = "/?fields=" \
            "reactions.type(LIKE).limit(0).summary(total_count).as(like)" \
            ",reactions.type(LOVE).limit(0).summary(total_count).as(love)" \
            ",reactions.type(WOW).limit(0).summary(total_count).as(wow)" \
            ",reactions.type(HAHA).limit(0).summary(total_count).as(haha)" \
            ",reactions.type(SAD).limit(0).summary(total_count).as(sad)" \
    parameters = "&access_token=%s" % access_token
    url = base + node + reactions + parameters

    # retrieve data
    data = json.loads(request_until_succeed(url))

    return data

def processFacebookPageFeedStatus(status, access_token):

    # The status is now a Python dictionary, so for top-level items,
    # we can simply call the key.

    # Additionally, some items may not always exist,
    # so must check for existence first

    status_id = status['id']
    status_message = '' if 'message' not in status.keys() else \
    link_name = '' if 'name' not in status.keys() else \
    status_type = status['type']
    status_link = '' if 'link' not in status.keys() else \
    status_permalink_url = '' if 'permalink_url' not in status.keys() else \
    # Time needs special care since a) it's in UTC and
    # b) it's not easy to use in statistical programs.

    status_published = datetime.datetime.strptime(
    status_published = status_published + \
            datetime.timedelta(hours=-5) # EST
    status_published = status_published.strftime(
            '%Y-%m-%d %H:%M:%S') # best time format for spreadsheet programs

    # Nested items require chaining dictionary keys.

    num_reactions = 0 if 'reactions' not in status else \
    num_comments = 0 if 'comments' not in status else \
    num_shares = 0 if 'shares' not in status else status['shares']['count']

    # Counts of each reaction separately; good for sentiment
    # Only check for reactions if past date of implementation:

    reactions = getReactionsForStatus(status_id, access_token) if \
            status_published > '2016-02-24 00:00:00' else {}

    num_likes = 0 if 'like' not in reactions else \

    # Special case: Set number of Likes to Number of reactions for pre-reaction
    # statuses

    num_likes = num_reactions if status_published < '2016-02-24 00:00:00' \
            else num_likes

    def get_num_total_reactions(reaction_type, reactions):
        if reaction_type not in reactions:
            return 0
            return reactions[reaction_type]['summary']['total_count']

    num_loves = get_num_total_reactions('love', reactions)
    num_wows = get_num_total_reactions('wow', reactions)
    num_hahas = get_num_total_reactions('haha', reactions)
    num_sads = get_num_total_reactions('sad', reactions)
    num_angrys = get_num_total_reactions('angry', reactions)

    # Return a tuple of all processed data

    return (status_id, status_message, link_name, status_type, status_link, status_permalink_url,
            status_published, num_reactions, num_comments, num_shares,
            num_likes, num_loves, num_wows, num_hahas, num_sads, num_angrys)

def scrapeFacebookPageFeedStatus(page_id, access_token):
    with open('%s_facebook_statuses.csv' % page_id, 'wb') as file:
        w = csv.writer(file)
        w.writerow(["status_id", "status_message", "link_name", "status_type",
                    "status_link", "permalink_url", "status_published", "num_reactions", 
                    "num_comments", "num_shares", "num_likes", "num_loves", 
                    "num_wows", "num_hahas", "num_sads", "num_angrys"])

        has_next_page = True
        num_processed = 0   # keep a count on how many we've processed
        scrape_starttime =

        print "Scraping %s Facebook Page: %s\n" % (page_id, scrape_starttime)

        statuses = getFacebookPageFeedData(page_id, access_token, 100)

        while has_next_page:
            for status in statuses['data']:

                # Ensure it is a status with the expected metadata
                if 'reactions' in status:

                # output progress occasionally to make sure code is not
                # stalling
                num_processed += 1
                if num_processed % 100 == 0:
                    print "%s Statuses Processed: %s" % \

            # if there is no next page, we're done.
            if 'paging' in statuses.keys():
                statuses = json.loads(request_until_succeed(
                has_next_page = False

        print "\nDone!\n%s Statuses Processed in %s" % \
                (num_processed, - scrape_starttime)

if __name__ == '__main__':
    scrapeFacebookPageFeedStatus(page_id, access_token)
0 Karma

New Member


I don't know if u got a solution or not, but did u check the documentation about "Setting up a scripted input"?

0 Karma


I have the idea that run a script calling the previous code and uploading the file to splunk, like this:

service = client.connect(host='localhost', port=8089, username='admin', password='changeme')

inputs = service.inputs

mynewindex = service.indexes.create("index")


myindex = service.indexes["index"]
uploadme = "/filepath/file"

It works fine outside splunk but when I import the script as data input doesn't work.

0 Karma
Register for .conf21 Now! Go Vegas or Go Virtual!

How will you .conf21? You decide! Go in-person in Las Vegas, 10/18-10/21, or go online with .conf21 Virtual, 10/19-10/20.