def parseRawTracerouteResults(results, fnMakePath, *prune):
'''parseRawTracerouteResults:
Parses RIPE Atlas traceroute results into path sets, grouping on probe IDs.
@param results List of raw traceroute results.
@param fnMakePath Function that returns a path's set representation; it
accepts a traceroute.ip_path object as input, and optionally
a list *prune that contains locations to exclude. Refer to
ripeh.makePath and caidah.makePath for examples.
@param prune List of strings to exclude from our AS paths.
@ret 1 List of probe IDs to pruned AS paths.
@ret 2 List of probe IDs to fail counters.
'''
logging.info(
'Parsing raw traceroute results using filter: {}'.format(prune))
p2r, p2f = {}, {}
for result in results:
tr = TracerouteResult(result)
if tr.is_success:
path = fnMakePath(tr.ip_path, *prune)
p2r.setdefault(tr.probe_id, [])
p2r[tr.probe_id].append(path)
else:
p2f.setdefault(tr.probe_id, 0)
p2f[tr.probe_id] += 1
return p2r, p2f
def return_path(self, result):
'''
Returns the ith ip path from a ripe measurement.
Input:
a) result: Dictionary containing the ith traceroute.
Output:
a) src_ip: A string with the source IP address.
b) dst_ip: A string with the destination IP address.
c) ip_path: A list containing the IPs of the traceroute path.
d) delays: A list containing the delays of the traceroute path.
'''
trace_res = TracerouteResult(result)
all_replies = trace_res.hops
src_ip = result['from']
ip_path = []
delays = []
dst_ip = '*'
if 'error' not in result['result'][0]:
dst_ip = trace_res.destination_address
for node in all_replies:
packet = node.packets
if node.index != 255:
[ip, delay] = self.choose_ip(packet)
ip_path.append(ip)
delays.append(delay)
return (src_ip, dst_ip, ip_path, delays)
def compare_results(probe_table):
for probe_id in probe_table:
if debug:
print('Parsing probe_id: %s' % probe_id)
r4 = TracerouteResult(probe_table[probe_id][4], on_error=TracerouteResult.ACTION_IGNORE)
r6 = TracerouteResult(probe_table[probe_id][6], on_error=TracerouteResult.ACTION_IGNORE)
if r4.is_success and r6.is_success:
probe = None
if r6.total_hops - r4.total_hops > hop_threshold:
probe = get_probe_details(probe_id)
more_hops = r6.total_hops - r4.total_hops
print('AS%s - %s hop count:%s vs %s hop count:%s - IPv6 has %s more hops'
% (probe['asn_v6'], probe['prefix_v6'], r6.total_hops,
probe['prefix_v4'], r4.total_hops, more_hops))
elif r4.total_hops - r6.total_hops > hop_threshold:
probe = get_probe_details(probe_id)
more_hops = r4.total_hops - r6.total_hops
print('AS%s - %s hop count:%s vs %s hop count:%s - IPv4 has %s more hops'
% (probe['asn_v4'], probe['prefix_v4'], r4.total_hops,
probe['prefix_v6'], r6.total_hops, more_hops))
if r6.last_median_rtt - r4.last_median_rtt > rtt_threshold:
if probe is None:
probe = get_probe_details(probe_id)
percent = int(((r6.last_median_rtt - r4.last_median_rtt) / r4.last_median_rtt) * 100)
print('AS%s - %s RTT:%s vs %s RTT:%s - IPv6 is %s%% worse'
% (probe['asn_v6'], probe['prefix_v6'], r6.last_median_rtt,
probe['prefix_v4'], r4.last_median_rtt, percent))
elif r4.last_median_rtt - r6.last_median_rtt > rtt_threshold:
if probe is None:
probe = get_probe_details(probe_id)
percent = int(((r4.last_median_rtt - r6.last_median_rtt) / r6.last_median_rtt) * 100)
print('AS%s - %s RTT:%s vs %s RTT:%s - IPv4 is %s%% worse'
% (probe['asn_v4'], probe['prefix_v4'], r4.last_median_rtt,
probe['prefix_v6'], r6.last_median_rtt, percent))
else:
if debug:
if r6.destination_ip_responded is False or r6.last_hop_responded is False:
print('Probe:%s could not trace to %s' % (r6.probe_id, r6.destination_address))
elif r4.destination_ip_responded is False or r4.last_hop_responded is False:
print('Probe:%s could not trace to %s' % (r4.probe_id, r4.destination_address))
pass
def processMeasurement(mID, dic, asndb):
#mID = '3703242' has two results in one measurement
source = "https://atlas.ripe.net/api/v1/measurement-latest/" + mID
response = requests.get(source).json()
ip_set = set()
for probe_id, result in response.items():
result = result[0] # There's only one result for each probe
parsed_result = TracerouteResult(result)
source_ip = parsed_result.origin
dest_ip = parsed_result.destination_address
# convert source_ip to ASN
(source_asn, source_prefix) = asndb.lookup(source_ip)
if source_asn is None:
continue
# get inner dict
# create if it doesn't exist
if source_asn not in dic:
dic[source_asn] = {}
inner_dic = dic[source_asn]
# get ip set
# create if it doesn't exist
if dest_ip not in inner_dic:
inner_dic[dest_ip] = set()
as_path_set = inner_dic[dest_ip]
ip_path_set = set()
# Make set of IPs before converting to ASNs
ip_path = parsed_result.ip_path
for triple in ip_path:
for ip in triple:
if ip is not None:
ip_path_set.add(ip)
# Explicity ADD source_ip and dest_ip to ip_path_set
ip_path_set.add(source_ip)
ip_path_set.add(dest_ip)
# remove destination IP from IP set before converting
#ip_path_set.discard(dest_ip)
# remove source_ip from IP set
#ip_path_set.discard(source_ip)
# convert to AS and add ASes to set
for ip in ip_path_set:
(asn, prefix) = asndb.lookup(ip)
#print asn
if asn is not None:
as_path_set.add(asn)
def print_nicely(self, limit):
with open(self.filename) as results:
i = 0
for result in results.readlines():
if limit is not None:
if i >= limit:
return
parsed_result = TracerouteResult.get(result)
print("PROBE ID: "+str(parsed_result.probe_id))
print("firmware: "+str(parsed_result.firmware))
print("origin: "+parsed_result.origin)
print("measurement type: "+self.measurement_type)
self._print_traceroute_nicely(parsed_result)
print("\n")
i +=1
def print_nicely(self, limit):
with open(self.filename) as results:
i = 0
for result in results.readlines():
if limit is not None:
if i >= limit:
return
parsed_result = TracerouteResult.get(result)
print("PROBE ID: "+str(parsed_result.probe_id))
print("firmware: "+str(parsed_result.firmware))
print("origin: "+parsed_result.origin)
print("measurement type: "+self.measurement_type)
self._print_traceroute_nicely(parsed_result)
print("\n")
i +=1
def index(family):
exp_id = bottle.request.query.id
res_blob = exp_config[exp_id][family]
# Read the data
G = nx.DiGraph()
hop_cnt = defaultdict(int)
hop_idx = defaultdict(int)
origin_asn = None
seq = []
for res_set in res_blob:
sagan_res = TracerouteResult(res_set)
asn = get_addr_as(sagan_res.origin)
prev_asn = asn
origin_asn = asn
hop_cnt[asn] += 1
for hop in sagan_res.hops:
hop_addr = set()
for packet in hop.packets:
if packet.origin is None:
continue
hop_addr.add(packet.origin)
for a in hop_addr:
asn = get_addr_as(a)
if asn is not None:
hop_cnt[asn] += 1
hop_idx[asn] = hop.index
addr2as[a] = asn
else:
hop_cnt[prev_asn] += 1
hop_idx[prev_asn] = hop.index
addr2as[a] = prev_asn
if asn is not None and prev_asn != asn:
G.add_edge(prev_asn, asn, rtt=hop.median_rtt)
prev_asn = asn
for n in G.nodes_iter():
G.node[n]['hops'] = hop_cnt[n]
G.node[n]['index'] = hop_idx[n]
n, e = transform_graph(G, origin_asn, asn)
# Return an object
return {'nodes': n, 'edges': e}
def make_probe_to_interval_results(msm_id, start_datetime):
"""
Retreive a single interval of traceroute results. Only returns results
where the traceroute successfully made it to the destination.
"""
probe_to_interval_results = dict()
msm_meta = query_msm_meta(msm_id)
msm_interval = msm_meta.interval
msm_target_ip_addr = msm_meta.target_ip
stop_datetime = start_datetime + datetime.timedelta(seconds=msm_interval)
measurements = query_msm(msm_id, int(start_datetime.timestamp()),
int(stop_datetime.timestamp()))
for msm in measurements:
tracert_msm = TracerouteResult(msm)
if not tracert_is_clean(tracert_msm, msm_target_ip_addr):
continue
probe_result = {
"origin_addr": tracert_msm.origin,
"stop_timestamp": tracert_msm.end_time.timestamp(),
"ip_path": tracert_msm.ip_path
}
if tracert_msm.probe_id not in probe_to_interval_results:
probe_to_interval_results[tracert_msm.probe_id] = probe_result
else:
current_result = probe_to_interval_results[tracert_msm.probe_id]
if (probe_result["stop_timestamp"] <
current_result["stop_timestamp"]):
probe_to_interval_results[tracert_msm.probe_id] = probe_result
return probe_to_interval_results
__author__ = 'secastro'
import json
import random
from ripe.atlas.sagan import TracerouteResult
from collections import Counter
with open('data/final_test_1/results.json', 'rb') as res_fd:
res_blob = random.sample(json.load(res_fd), 50)
for res in res_blob:
print "=" * 30
sagan_res = TracerouteResult(res)
for h in reversed(sagan_res.hops):
rtt_sum = Counter()
rtt_cnt = Counter()
for p in h.packets:
if p.origin is None:
continue
if p.rtt is not None:
rtt_sum[p.origin] += p.rtt
rtt_cnt[p.origin] += 1
print p.origin, p.rtt
for a in rtt_cnt:
print "** ", a, rtt_sum[a] / rtt_cnt[a]
print "\n"
traceroute_dict[measurement][
"target_lon"] = longitude # set target longiyude
traceroute_dict[measurement][
"target_address"] = target_address # set target geo address
traceroute_dict[measurement][
"target_isanchor"] = is_anchor # True if probe is anchor
probes = {
} # initialise all the probes dictionaries within this measurement
i = 0
for result in results: # get all the results of the pings from landmarks to target
print("Reading measurement data, ", measurement, "from probes ", i,
" one moment")
print("this is result ", i, "of measuremnt ", measurement)
result = TracerouteResult(result)
print(result)
if not result.is_error: # if no error in handling/parsing this result
p = result.probe_id
probe = Probe(
id=p
) # Get all the properties of the individual probe used in this individual measurement
print('Probe ', p)
a = probe.geometry[
'coordinates'] # Create a list of Coordinates
probe_x = a[0] # Probes X coordinate
probe_y = a[1] # Probes Y coordinate
probe_id = result.probe_id # get the probe_id for this individual measurement
if probe_id == '1000492':
print("HERE ITS IS *************************", probe_id,
probe_x, probe_y)
def trace(start_time):
# set end time
end_time = str(int(start_time) + 86400)
# initialize data structures
uniqueTrace = set()
uniqueIP = set()
uniqueEdge = set()
allTrace = []
allIP = []
nodeList = []
# initialize edge count
edgecount = 0
# open node list
with open("RipeNodeList") as f:
for line in f:
for word in line.split():
nodeList.append(word)
# iterate through each of 195 nodes
for node in nodeList:
# open working files
with open("/home/jay/Desktop/Trace_01/ripe-temp/traceList.txt", "w") as f:
try:
# download page from internet and store in filesystem **I changed this to run on desktop. For server, uncomment the next line and comment out 63-68
#urllib.urlretrieve("https://atlas.ripe.net/api/v2/measurements/" + node + "/results?start=" + str(start_time) + "&stop=" + str(end_time) + "&format=json", "/home/jay/Desktop/Trace_01/ripe-temp/ripe.json")
req = urllib.request.Request("https://atlas.ripe.net/api/v2/measurements/" + node + "/results?start=" + str(start_time) + "&stop=" + str(end_time) + "&format=json")
with urllib.request.urlopen(req) as response:
the_page = response.read()
outfile = open("/home/jay/Desktop/Trace_01/ripe-temp/ripe.json", "wb")
outfile.write(the_page)
outfile.close()
try:
# Import file to db
os.system("mongoimport --db RipeNode --collection mapping --type json --file /home/jay/Desktop/Trace_01/ripe-temp/ripe.json --jsonArray")
except:
print ("Error--problem loading data to MongoDB")
# Create client
client = MongoClient()
# Assign the local variable db to the database named primer
db = client.RipeNode
# Access collection object
db.mapping
# Create object variable for later use
coll = db.mapping
index_i = 0
index_j = 1
# iterate through all documents in a collection
cursor = coll.find()#[index_i:index_j]
# use mongo to parse data
try:
for post in coll.find():
#record = convert(post) # made a change here to get this to run on my desktop...for server, uncomment this and comment out the next line
record = post
my_result = TracerouteResult.get(record)
newLine = []
flag = 0
ip = my_result.ip_path
if(my_result.is_success == 1):
# set value of source and destination
source = my_result.source_address
destination = my_result.destination_address
# push src and dst to ip lists
allIP.append(source)
allIP.append(destination)
uniqueIP.add(source)
uniqueIP.add(destination)
# add source:dest and hop-0 to newLine
newLine.append(source + ':' + destination + '\t')
#newLine.append(source + ',' + '0' + '\t')
# set initial value of hop
hop = 1
# iterate to get all addresses
for x in ip:
sublist = x
for y in sublist:
# take only the first of the three
while flag == 0:
# if 'None', add '0' to newLine
if(y == None):
newLine.append('0' + ',' + str(hop) + '\t')
hop += 1
# if ! 'None, add address to newLine'
else:
newLine.append(y + ',' + str(hop) + '\t')
allIP.append(y)
uniqueIP.add(y)
hop += 1
flag = 1
flag = 0
# remove last tab in string
newLine[-1].replace('\t', '')
# convert list to string
newLine = ''.join(newLine)
# add string to file
f.write(newLine)
f.write('\n')
else:
pass
except:
pass
except:
pass
# Unique traces
with open("/home/jay/Desktop/Trace_01/ripe-temp/traceList.txt", "r") as f:
trace = []
for line in f:
uniqueTrace.add(line)
allTrace.append(line)
# get edges
#edgeList = set()
starCounter = 1
count = 1
for item in uniqueTrace:
# set list so it will reset
trace = []
# split trace and push to list
#for item in item.split(): # changed this for Abdullah to make parsing easier
for item in item.split('\t'):
if (':' in item):
pass
else:
#item = item.split('-') # changed this for Abdullah to make parsing easier
item = item.split(',')
trace.append(item[0])
# find length of list
length = len(trace)
# set iterator variable so it will reset
i = 0
# iterate through trace list for pairs
while i < length - 1:
first = trace[i]
second = trace[i+1]
# set incrementing value for 0's
if first == '0':
first = count
count += 1
if second == '0':
second = count
count += 1
#uniqueEdge.add(str(first) + ' ' + str(second)) # changed this for Abdullah to make parsing easier
uniqueEdge.add(str(first) + '\t' + str(second))
i += 1
# Drop Collection
result = db.mapping.drop()
# all traces
with open("/home/jay/Desktop/Trace_01/RipeData/all_trace_" + start_time + ".txt", "w") as f:
for item in allTrace:
f.write(item)
# all ips
with open("/home/jay/Desktop/Trace_01/RipeData/all_ip_" + start_time + ".txt", "w") as f:
for item in allIP:
f.write(item + '\n')
# unique traces
with open("/home/jay/Desktop/Trace_01/RipeData/unique_trace_" + start_time + ".txt", "w") as f:
for item in uniqueTrace:
f.write(item)
# unique ip addresses
with open("/home/jay/Desktop/Trace_01/RipeData/unique_ip_" + start_time + ".txt", "w") as f:
for item in uniqueIP:
f.write(item + '\n')
# unique edges (w/o '0's counted)
with open("/home/jay/Desktop/Trace_01/RipeData/unique_edge_" + start_time + ".txt", "w") as f:
for item in uniqueEdge:
f.write(item + '\n')
#item = item.split(' ') # changed this for Abdullah to make parsing easier
item = item.split('\t')
if (('.' in item[0]) and ('.' in item[1])):
edgecount += 1
# write totals to file
with open("/home/jay/Desktop/Trace_01/RipeData/stats_" + start_time + ".txt", "w") as f:
f.write("Total IPs: " + str(len(allIP)) + '\n')
f.write("Total Traces: " + str(len(allTrace)) + '\n')
f.write("Total Unique IPs: " + str(len(uniqueIP)) + '\n')
f.write("Total Unique Traces: " + str(len(uniqueTrace)) + '\n')
f.write("Total Unique Edges: " + str(edgecount) + '\n')
def trace():
# global variables
global start_time
traceCount3 = 0
ipCount3 = 0
srcCount3 = 0
dstCount3 = 0
privateIP = 0
edgeCount = 0
target = 0
uniqueTrace = set()
uniqueIP = set()
uniqueSrc = set()
uniqueDst = set()
uniqueEdge = set()
nodeList = []
with open("RipeNodeList") as f:
for line in f:
for word in line.split():
nodeList.append(word)
for line in open("start_time.txt"):
if line.strip():
start_time = int(line)
end_time = start_time + 86400
for node in nodeList:
traceCount1 = 0
srcCount1 = 0
dstCount1 = 0
ipCount1 = 0
traceCount2 = 0
srcCount2 = 0
dstCount2 = 0
ipCount2 = 0
flag = 0
privateIP = 0
edgeCount1 = 0
if not os.path.exists("/home/jay/RipeData/" + str(start_time) + "/all_nodes"):
os.makedirs("/home/jay/RipeData/" + str(start_time) + "/all_nodes")
if not os.path.exists("/home/jay/RipeData/" + str(start_time) + "/per_node/" + node):
os.makedirs("/home/jay/RipeData/" + str(start_time) + "/per_node/" + node)
# open working files
of1 = open("traceList.txt", "w")
of2 = open("ipList.txt", "w")
of3 = open("src.txt", "w")
of4 = open("dst.txt", "w")
of5 = open("/home/jay/RipeData/" + str(start_time) + "/per_node/" + node + "/stats.txt", "w")
of6 = open("/home/jay/RipeData/" + str(start_time) + "/per_node/" + node + "/trace.txt", "w")
of7 = open("/home/jay/RipeData/" + str(start_time) + "/per_node/" + node + "/ip.txt", "w")
of8 = open("/home/jay/RipeData/" + str(start_time) + "/per_node/" + node + "/src.txt", "w")
of9 = open("/home/jay/RipeData/" + str(start_time) + "/per_node/" + node + "/dst.txt", "w")
of10 = open("/home/jay/RipeData/" + str(start_time) + "/per_node/" + node + "/traceCount.txt", "w")
of11 = open("/home/jay/RipeData/" + str(start_time) + "/per_node/" + node + "/edgeList.txt", "w")
of15 = open("/home/jay/RipeData/" + str(start_time) + "/per_node/" + node + "/ipCount.txt", "w")
ofx = open("/home/jay/RipeData/" + str(start_time) + "/all_nodes/stats.txt", "w")
try:
# download page from internet and store in filesystem
urllib.urlretrieve("https://atlas.ripe.net/api/v2/measurements/" + node + "/results?start=" + str(start_time) + "&stop=" + str(end_time) + "&format=json", "/home/jay/RipeGraph/ripe.json")
try:
# Import file to db
os.system("mongoimport --db RipeNode --collection mapping --type json --file ripe.json --jsonArray")
except:
print "Error--problem loading data to MongoDB"
# Create client
client = MongoClient()
# Assign the local variable db to the database named primer
db = client.RipeNode
# Access collection object
db.mapping
# Create object variable for later use
coll = db.mapping
index_i = 0
index_j = 1
# iterate through all documents in a collection
cursor = coll.find()#[index_i:index_j]
# use mongo to parse data
try:
for post in coll.find():
record = convert(post)
my_result = TracerouteResult.get(record)
newLine = []
srcList = []
dstList = []
flag = 0
ip = my_result.ip_path
if(my_result.is_success == 1):
#newLine.append(my_result.source_address)
source = my_result.source_address
destination = my_result.destination_address
srcList.append(my_result.source_address)
dstList.append(my_result.destination_address)
for x in ip:
sublist = x
for y in sublist:
while flag == 0:
if(y == None):
newLine.append('0')
else:
newLine.append(y)
flag = 1
flag = 0
else:
pass
# write parsed data to file
# trace strings and ip addresses
of1.write(source + ':' + destination + ' ')
hop = 1
for address in newLine:
of1.write(address + '-' + str(hop))
of2.write(address)
of1.write(' ')
of2.write('\n')
ipCount1 += 1
hop += 1
if (len(newLine) != 0):
of1.write('\n')
traceCount1 += 1
# source ip addresses
for address in srcList:
of3.write(address)
of3.write('\n')
srcCount1 += 1
# destination ip addresses
for address in dstList:
of4.write(address)
of4.write('\n')
dstCount1 += 1
except:
print "Could not process document"
except:
of5.write("ERROR -- Could not download node " + node)
# Close files
of1.close()
of2.close()
of3.close()
of4.close()
# write per node data to file
# Unique Traces
with open("traceList.txt", "r") as f:
trace = []
for line in f:
if line not in trace:
trace.append(line)
uniqueTrace.add(line)
f.close()
for item in trace:
of6.write(item)
traceCount2 += 1
of6.close()
# Trace Counts
# initialize variables
allTraceList = []
uniqueTraceList = []
uniqueIpList = []
# open traceList file
with open("traceList.txt", "r") as f:
for line in f:
# make list of traces
allTraceList.append(line)
if line not in uniqueTraceList:
# make list of unique traces
uniqueTraceList.append(line)
f.close()
# for each unique trace, count number of occurances in total list
for item in uniqueTraceList:
num = allTraceList.count(item)
# write count and trace to new file
of10.write(str(num) + " " + item)
# close file
of10.close()
# ip counts
with open("ipList.txt", "r") as f:
# create lists for all and unique
ips = []
uips = set()
# fill both lists
for item in f:
ips.append(item)
uips.add(item)
# compare unique to all and count all
for item in uips:
num = ips.count(item)
# write out to file
of15.write(str(num) + " " + item)
# close files
of15.close()
f.close()
# initialize lists
edgeList = set()
starCounter = 1
count = 1
for item in uniqueTraceList:
# set list so it will reset
trace = []
# split trace and push to list
for item in item.split():
if (':' in item):
pass
else:
item = item.split('-')
trace.append(item[0])
# find length of list
length = len(trace)
# set iterator variable so it will reset
i = 0
# iterate through trace list for pairs
while i < length - 1:
first = trace[i]
second = trace[i+1]
# set incrementing value for 0's
if first == '0':
first = count
count += 1
if second == '0':
second = count
count += 1
# add to edgeList set (unique values only)
edgeList.add(str(first) + ' ' + str(second))
uniqueEdge.add(str(first) + ' ' + str(second))
i += 1
# write edgeList to file
for item in edgeList:
of11.write(item + '\n')
edgeCount1 += 1
# close file
of11.close()
# Unique IPs
with open("ipList.txt", "r") as f:
ip = []
for line in f:
if line not in ip:
ip.append(line)
uniqueIP.add(line)
f.close()
#for item in ip:
for item in uniqueIP:
of7.write(item)
if (('10.0' in item) or ('192.168' in item) or ('172.16' in item)):
privateIP += 1
ipCount2 += 1
of7.close()
# Unique Source IPs
with open("src.txt", "r") as f:
src = []
for line in f:
if line not in src:
src.append(line)
uniqueSrc.add(line)
f.close()
for item in src:
of8.write(item)
srcCount2 += 1
of8.close()
# Unique Destination IPs
with open("dst.txt", "r") as f:
dst = []
for line in f:
if line not in dst:
dst.append(line)
uniqueDst.add(line)
f.close()
for item in dst:
of9.write(item)
dstCount2 += 1
of9.close()
# Drop Collection
result = db.mapping.drop()
# write individual node totals to file
of5.write("Node: " + node + '\n')
of5.write("Total Traces: " + str(traceCount1) + '\n')
of5.write("Total IPs: " + str(ipCount1) + '\n')
of5.write("Total Source IPs: " + str(srcCount1) + '\n')
of5.write("Total Destination IPs: " + str(dstCount1) + '\n')
of5.write("Unique Traces: " + str(traceCount2) + '\n')
of5.write("Unique IPs: " + str(ipCount2) + '\n')
of5.write("Private IPs: " + str(privateIP) + '\n')
of5.write("Unique Source IPs: " + str(srcCount2) + '\n')
of5.write("Unique Destination IPs: " + str(dstCount2) + '\n')
of5.write("Unique Edges: " + str(edgeCount1) + '\n')
of5.write("*************************************" + '\n')
of5.close()
# Write Totals To File
# unique traces
of11 = open("/home/jay/RipeData/" + str(start_time) + "/all_nodes/traces.txt", "w")
for item in uniqueTrace:
of11.write(item)
traceCount3 += 1
of11.close()
# unique ip addresses
of12 = open("/home/jay/RipeData/" + str(start_time) + "/all_nodes/ips.txt", "w")
for item in uniqueIP:
of12.write(item)
ipCount3 += 1
of12.close()
# unique source ip addresses
of13 = open("/home/jay/RipeData/" + str(start_time) + "/all_nodes/src.txt", "w")
for item in uniqueSrc:
of13.write(item)
srcCount3 += 1
of13.close()
# unique destination ip addresses
of14 = open("/home/jay/RipeData/" + str(start_time) + "/all_nodes/dst.txt", "w")
for item in uniqueDst:
of14.write(item)
dstCount3 += 1
of14.close()
# unique edges (w/o '0's counted)
of15 = open("/home/jay/RipeData/" + str(start_time) + "/all_nodes/edges.txt", "w")
for item in uniqueEdge:
of15.write(item + '\n')
item = item.split(' ')
if (('.' in item[0]) and ('.' in item[1])):
edgeCount += 1
of15.close()
# write totals to file
ofx.write("Total Unique Traces: " + str(traceCount3) + '\n')
ofx.write("Total Unique IPs: " + str(ipCount3) + '\n')
ofx.write("Total Unique Source IPs: " + str(srcCount3) + '\n')
ofx.write("Total Unique Destination IPs: " + str(dstCount3) + '\n')
ofx.write("Total Unique Edges: " + str(edgeCount) + '\n')
ofx.close()
# update start_time.txt
f = open("start_time.txt", "w")
f.write(str(end_time))
f.close()
def atlas_api_result_call(msm_idvar, start_date, stop_date, count):
kwargs = {
"msm_id": msm_idvar,
"start": start_date,
"stop": stop_date,
}
is_success, results = AtlasResultsRequest(**kwargs).create()
pathlist = []
hopslist = []
timelist = []
IPlistcomp = []
if is_success:
for result in results:
parsed_result = TracerouteResult.get(result)
pathlist.append(parsed_result.ip_path)
hopslist.append(parsed_result.total_hops)
timelist.append(parsed_result.end_time)
for i in range(0, len(pathlist)):
for k in range(0, hopslist[i]):
try:
IPlistcomp.append(pathlist[i][k][0])
except:
IPlistcomp.append("0.0.0.0")
reader = geoip2.database.Reader(
"/home/csg/Downloads/GeoLite2-Country.mmdb")
h = open('countries.txt', 'w')
for i in range(0, len(IPlistcomp)):
try:
response = reader.country(IPlistcomp[i])
except:
h.write("none" + "\n")
else:
if response.country.name is None:
h.write("none" + "\n")
else:
new = (response.country.name).encode('ascii', 'ignore')
h.write(new + "\n")
h.close()
with open("countries.txt") as f:
content = f.readlines()
f.close()
content = map(lambda s: s.strip(), content)
counter = collections.Counter(content)
sum = 0
for key, value in counter.iteritems():
sum = sum + value
counter[key] = [counter[key]]
for key, value in counter.iteritems():
var1 = (int((counter[key])[0]) / sum) * 100
counter[key].append(var1)
key = "sum"
counter.setdefault(key, [])
counter[key].append(sum)
#key = "loss data"
#counter.setdefault(key, [])
#var2=(int((counter["none"])[0])/sum)*100
#counter[key].append(var2)
counter1 = collections.OrderedDict(sorted(counter.items()))
json.dump(counter1, open("countries_stat.txt", 'w'))
def fetchResult(response, start_time, stop_time, fileName):
pathOfTheFile = "/ldc/mdata/atlas/atlas." + str(fileName)
dataLine = open(pathOfTheFile, "a")
if len(response) != 0:
for y in range(len(response)):
res_ponse = response[y]
mr = TracerouteResult(res_ponse)
source_address = mr.source_address
destination_address = mr.destination_address
res = mr.ip_path
if destination_address == None or source_address == None:
continue
ip_path = destination_address + ' ' + source_address
for z in range(len(res)):
if len(res[z]) < 1:
continue
elif len(res[z]) == 1:
if res[z][0] == None:
ip_path = ip_path + ' ' + 'q'
else:
ip_path = ip_path + ' ' + res[z][0]
elif len(res[z]) == 2:
if res[z][0] == res[z][1] == None:
ip_path = ip_path + ' ' + 'q'
elif res[z][0] == res[z][1]:
ip_path = ip_path + ' ' + res[z][1]
elif res[z][0] == None:
ip_path = ip_path + ' ' + res[z][1]
else:
ip_path = ip_path + ' ' + res[z][0]
elif res[z][0] == res[z][1] == res[z][2] and res[z][0] != None:
ip_path = ip_path + ' ' + res[z][0]
elif res[z][0] == res[z][1] == res[z][2] == None:
ip_path = ip_path + ' ' + 'q'
else:
list_of_badhop_ip = []
for badhop in range(len(res[z])):
if res[z][badhop] == None:
continue
list_of_badhop_ip.append(res[z][badhop])
if len(list_of_badhop_ip) == 1:
ip_path = ip_path + ' ' + list_of_badhop_ip[0]
elif len(list_of_badhop_ip) == 2:
if list_of_badhop_ip[0] == list_of_badhop_ip[1]:
ip_path = ip_path + ' ' + list_of_badhop_ip[0]
else:
ip_path = ip_path + ' ' + list_of_badhop_ip[
0] + ',' + list_of_badhop_ip[1]
else:
if list_of_badhop_ip[0] != list_of_badhop_ip[
1] and list_of_badhop_ip[
1] != list_of_badhop_ip[
2] and list_of_badhop_ip[
0] != list_of_badhop_ip[2]:
ip_path = ip_path + ' ' + list_of_badhop_ip[
0] + ',' + list_of_badhop_ip[
1] + ',' + list_of_badhop_ip[2]
elif list_of_badhop_ip[0] == list_of_badhop_ip[1]:
ip_path = ip_path + ' ' + list_of_badhop_ip[
0] + ',' + list_of_badhop_ip[2]
elif list_of_badhop_ip[0] == list_of_badhop_ip[2]:
ip_path = ip_path + ' ' + list_of_badhop_ip[
0] + ',' + list_of_badhop_ip[1]
elif list_of_badhop_ip[1] == list_of_badhop_ip[2]:
ip_path = ip_path + ' ' + list_of_badhop_ip[
0] + ',' + list_of_badhop_ip[1]
dataLine.writelines(ip_path + "\n")
dataLine.close()
def do(self):
all_target = Target.objects.all()
for tar in all_target:
kwargs = {
"msm_id": tar.msm_id,
"start": DT.date.today() - DT.timedelta(days=7),
"stop": DT.date.today(),
}
is_success, results = AtlasResultsRequest(**kwargs).create()
pathlist = []
hopslist = []
timelist = []
IPlistcomp = []
if is_success:
for result in results:
parsed_result = TracerouteResult.get(result)
pathlist.append(parsed_result.ip_path)
hopslist.append(parsed_result.total_hops)
timelist.append(parsed_result.end_time)
for i in range(0, len(pathlist)):
for k in range(0, hopslist[i]):
try:
IPlistcomp.append(pathlist[i][k][0])
except:
IPlistcomp.append("0.0.0.0")
reader = geoip2.database.Reader(
"/home/csg/Downloads/GeoLite2-Country.mmdb")
h = open('countriescron.txt', 'w')
for i in range(0, len(IPlistcomp)):
try:
response = reader.country(IPlistcomp[i])
except:
h.write("OO" + "\n")
else:
if response.country.name is None:
h.write("OO" + "\n")
else:
new = (response.country.iso_code).encode(
'ascii', 'ignore')
h.write(new + "\n")
h.close()
with open("countriescron.txt") as f:
countrylist = f.readlines()
f.close()
countrylist = map(lambda s: s.strip(), countrylist)
desc = tar.description
rel = int(filter(str.isdigit, str(desc)))
desc = desc.replace(" ", "")
desc = str(desc)
rel = "Relation" + str(rel)
m = 0
for i in range(0, len(hopslist)):
tar1 = eval(desc)(timestamp=timelist[i])
tar1.save()
for k in range(0, hopslist[i]):
b = Countries.objects.get(country=countrylist[m])
eval(rel).objects.create(traceroutemeasurement_id=int(
tar1.id),
countries_id=int(b.id))
m = m + 1
def trace():
# global variables
global start_time
traceCount3 = 0
ipCount3 = 0
srcCount3 = 0
dstCount3 = 0
privateIP = 0
edgeCount = 0
target = 0
uniqueTrace = set()
uniqueIP = set()
uniqueSrc = set()
uniqueDst = set()
uniqueEdge = set()
nodeList = []
with open("RipeNodeList") as f:
for line in f:
for word in line.split():
nodeList.append(word)
for line in open("start_time.txt"):
if line.strip():
start_time = int(line)
end_time = start_time + 86400
for node in nodeList:
traceCount1 = 0
srcCount1 = 0
dstCount1 = 0
ipCount1 = 0
traceCount2 = 0
srcCount2 = 0
dstCount2 = 0
ipCount2 = 0
flag = 0
privateIP = 0
edgeCount1 = 0
if not os.path.exists("/home/jay/Desktop/Data_Collector/RipeData/" +
str(start_time) + "/all_nodes"):
os.makedirs("/home/jay/Desktop/Data_Collector/RipeData/" +
str(start_time) + "/all_nodes")
if not os.path.exists("/home/jay/Desktop/Data_Collector/RipeData/" +
str(start_time) + "/per_node/" + node):
os.makedirs("/home/jay/Desktop/Data_Collector/RipeData/" +
str(start_time) + "/per_node/" + node)
# open working files
of1 = open("traceList.txt", "w")
of2 = open("ipList.txt", "w")
of3 = open("src.txt", "w")
of4 = open("dst.txt", "w")
of5 = open(
"/home/jay/Desktop/Data_Collector/RipeData/" + str(start_time) +
"/per_node/" + node + "/stats.txt", "w")
of6 = open(
"/home/jay/Desktop/Data_Collector/RipeData/" + str(start_time) +
"/per_node/" + node + "/trace.txt", "w")
of7 = open(
"/home/jay/Desktop/Data_Collector/RipeData/" + str(start_time) +
"/per_node/" + node + "/ip.txt", "w")
of8 = open(
"/home/jay/Desktop/Data_Collector/RipeData/" + str(start_time) +
"/per_node/" + node + "/src.txt", "w")
of9 = open(
"/home/jay/Desktop/Data_Collector/RipeData/" + str(start_time) +
"/per_node/" + node + "/dst.txt", "w")
of10 = open(
"/home/jay/Desktop/Data_Collector/RipeData/" + str(start_time) +
"/per_node/" + node + "/traceCount.txt", "w")
of11 = open(
"/home/jay/Desktop/Data_Collector/RipeData/" + str(start_time) +
"/per_node/" + node + "/edgeList.txt", "w")
of15 = open(
"/home/jay/Desktop/Data_Collector/RipeData/" + str(start_time) +
"/per_node/" + node + "/ipCount.txt", "w")
ofx = open(
"/home/jay/Desktop/Data_Collector/RipeData/" + str(start_time) +
"/all_nodes/stats.txt", "w")
try:
# download page from internet and store in filesystem
urllib.urlretrieve(
"https://atlas.ripe.net/api/v2/measurements/" + node +
"/results?start=" + str(start_time) + "&stop=" +
str(end_time) + "&format=json",
"/home/jay/Desktop/Data_Collector/ripe.json")
try:
# Import file to db
os.system(
"mongoimport --db RipeNode --collection mapping --type json --file ripe.json --jsonArray"
)
except:
print "Error--problem loading data to MongoDB"
# Create client
client = MongoClient()
# Assign the local variable db to the database named primer
db = client.RipeNode
# Access collection object
db.mapping
# Create object variable for later use
coll = db.mapping
index_i = 0
index_j = 1
# iterate through all documents in a collection
cursor = coll.find() #[index_i:index_j]
# use mongo to parse data
try:
for post in coll.find():
record = convert(post)
my_result = TracerouteResult.get(record)
newLine = []
srcList = []
dstList = []
flag = 0
ip = my_result.ip_path
if (my_result.is_success == 1):
#newLine.append(my_result.source_address)
source = my_result.source_address
destination = my_result.destination_address
srcList.append(my_result.source_address)
dstList.append(my_result.destination_address)
for x in ip:
sublist = x
for y in sublist:
while flag == 0:
if (y == None):
newLine.append('0')
else:
newLine.append(y)
flag = 1
flag = 0
else:
pass
# write parsed data to file
# trace strings and ip addresses
of1.write(source + ':' + destination + ' ')
hop = 1
for address in newLine:
of1.write(address + '-' + str(hop))
of2.write(address)
of1.write(' ')
of2.write('\n')
ipCount1 += 1
hop += 1
if (len(newLine) != 0):
of1.write('\n')
traceCount1 += 1
# source ip addresses
for address in srcList:
of3.write(address)
of3.write('\n')
srcCount1 += 1
# destination ip addresses
for address in dstList:
of4.write(address)
of4.write('\n')
dstCount1 += 1
except:
print "Could not process document"
except:
of5.write("ERROR -- Could not download node " + node)
# Close files
of1.close()
of2.close()
of3.close()
of4.close()
# write per node data to file
# Unique Traces
with open("traceList.txt", "r") as f:
trace = []
for line in f:
if line not in trace:
trace.append(line)
uniqueTrace.add(line)
f.close()
for item in trace:
of6.write(item)
traceCount2 += 1
of6.close()
# Trace Counts
# initialize variables
allTraceList = []
uniqueTraceList = []
uniqueIpList = []
# open traceList file
with open("traceList.txt", "r") as f:
for line in f:
# make list of traces
allTraceList.append(line)
if line not in uniqueTraceList:
# make list of unique traces
uniqueTraceList.append(line)
f.close()
# for each unique trace, count number of occurances in total list
for item in uniqueTraceList:
num = allTraceList.count(item)
# write count and trace to new file
of10.write(str(num) + " " + item)
# close file
of10.close()
# ip counts
with open("ipList.txt", "r") as f:
# create lists for all and unique
ips = []
uips = set()
# fill both lists
for item in f:
ips.append(item)
uips.add(item)
# compare unique to all and count all
for item in uips:
num = ips.count(item)
# write out to file
of15.write(str(num) + " " + item)
# close files
of15.close()
f.close()
# initialize lists
edgeList = set()
starCounter = 1
count = 1
for item in uniqueTraceList:
# set list so it will reset
trace = []
# split trace and push to list
for item in item.split():
if (':' in item):
pass
else:
item = item.split('-')
trace.append(item[0])
# find length of list
length = len(trace)
# set iterator variable so it will reset
i = 0
# iterate through trace list for pairs
while i < length - 1:
first = trace[i]
second = trace[i + 1]
# set incrementing value for 0's
if first == '0':
first = count
count += 1
if second == '0':
second = count
count += 1
# add to edgeList set (unique values only)
edgeList.add(str(first) + ' ' + str(second))
uniqueEdge.add(str(first) + ' ' + str(second))
i += 1
# write edgeList to file
for item in edgeList:
of11.write(item + '\n')
edgeCount1 += 1
# close file
of11.close()
# Unique IPs
with open("ipList.txt", "r") as f:
ip = []
for line in f:
if line not in ip:
ip.append(line)
uniqueIP.add(line)
f.close()
#for item in ip:
for item in uniqueIP:
of7.write(item)
if (('10.0' in item) or ('192.168' in item) or ('172.16' in item)):
privateIP += 1
ipCount2 += 1
of7.close()
# Unique Source IPs
with open("src.txt", "r") as f:
src = []
for line in f:
if line not in src:
src.append(line)
uniqueSrc.add(line)
f.close()
for item in src:
of8.write(item)
srcCount2 += 1
of8.close()
# Unique Destination IPs
with open("dst.txt", "r") as f:
dst = []
for line in f:
if line not in dst:
dst.append(line)
uniqueDst.add(line)
f.close()
for item in dst:
of9.write(item)
dstCount2 += 1
of9.close()
# Drop Collection
result = db.mapping.drop()
# write individual node totals to file
of5.write("Node: " + node + '\n')
of5.write("Total Traces: " + str(traceCount1) + '\n')
of5.write("Total IPs: " + str(ipCount1) + '\n')
of5.write("Total Source IPs: " + str(srcCount1) + '\n')
of5.write("Total Destination IPs: " + str(dstCount1) + '\n')
of5.write("Unique Traces: " + str(traceCount2) + '\n')
of5.write("Unique IPs: " + str(ipCount2) + '\n')
of5.write("Private IPs: " + str(privateIP) + '\n')
of5.write("Unique Source IPs: " + str(srcCount2) + '\n')
of5.write("Unique Destination IPs: " + str(dstCount2) + '\n')
of5.write("Unique Edges: " + str(edgeCount1) + '\n')
of5.write("*************************************" + '\n')
of5.close()
# Write Totals To File
# unique traces
of11 = open(
"/home/jay/Desktop/Data_Collector/RipeData/" + str(start_time) +
"/all_nodes/traces.txt", "w")
for item in uniqueTrace:
of11.write(item)
traceCount3 += 1
of11.close()
# unique ip addresses
of12 = open(
"/home/jay/Desktop/Data_Collector/RipeData/" + str(start_time) +
"/all_nodes/ips.txt", "w")
for item in uniqueIP:
of12.write(item)
ipCount3 += 1
of12.close()
# unique source ip addresses
of13 = open(
"/home/jay/Desktop/Data_Collector/RipeData/" + str(start_time) +
"/all_nodes/src.txt", "w")
for item in uniqueSrc:
of13.write(item)
srcCount3 += 1
of13.close()
# unique destination ip addresses
of14 = open(
"/home/jay/Desktop/Data_Collector/RipeData/" + str(start_time) +
"/all_nodes/dst.txt", "w")
for item in uniqueDst:
of14.write(item)
dstCount3 += 1
of14.close()
# unique edges (w/o '0's counted)
of15 = open(
"/home/jay/Desktop/Data_Collector/RipeData/" + str(start_time) +
"/all_nodes/edges.txt", "w")
for item in uniqueEdge:
of15.write(item + '\n')
item = item.split(' ')
if (('.' in item[0]) and ('.' in item[1])):
edgeCount += 1
of15.close()
# write totals to file
ofx.write("Total Unique Traces: " + str(traceCount3) + '\n')
ofx.write("Total Unique IPs: " + str(ipCount3) + '\n')
ofx.write("Total Unique Source IPs: " + str(srcCount3) + '\n')
ofx.write("Total Unique Destination IPs: " + str(dstCount3) + '\n')
ofx.write("Total Unique Edges: " + str(edgeCount) + '\n')
ofx.close()
# update start_time.txt
f = open("start_time.txt", "w")
f.write(str(end_time))
f.close()
