mirror of
https://github.com/laramies/theHarvester.git
synced 2025-02-24 06:22:57 +08:00
Removed google dork class, added more dorks, and added boolean to indicate if user wants google dorks in google search.
This commit is contained in:
NotoriousRebel
parent
c2f86f7c54
commit
568ace4419
4 changed files with 86 additions and 125 deletions
|
|
@ -1,91 +0,0 @@
|
|||
import myparser
|
||||
import time
|
||||
import requests
|
||||
import random
|
||||
|
||||
class google_dork:
|
||||
|
||||
def __init__(self, word, limit, start):
|
||||
self.word = word
|
||||
self.results = ""
|
||||
self.totalresults = ""
|
||||
self.dorks = []
|
||||
self.links = []
|
||||
self.database = "https://www.google.com/search?q="
|
||||
#create list of userAgents to shuffle through
|
||||
self.userAgent = ["(Mozilla/5.0 (Windows; U; Windows NT 6.0;en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6",
|
||||
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36"
|
||||
,("Mozilla/5.0 (Linux; Android 7.0; SM-G892A Build/NRD90M; wv) " +
|
||||
"AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/60.0.3112.107 Mobile Safari/537.36"),
|
||||
("Mozilla/5.0 (Windows Phone 10.0; Android 6.0.1; Microsoft; RM-1152) " +
|
||||
"AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Mobile Safari/537.36 Edge/15.15254")]
|
||||
self.quantity = "100"
|
||||
self.limit = limit
|
||||
self.counter = start
|
||||
|
||||
def append_dorks(self):
|
||||
try: #wrap in try-except incase filepaths are messed up
|
||||
with open('../theHarvester/wordlists/dorks.txt',mode='r') as fp:
|
||||
self.dorks = [dork.strip() for dork in fp]
|
||||
except IOError as error:
|
||||
print(error)
|
||||
|
||||
def construct_dorks(self):
|
||||
#format is: site:targetwebsite.com + space + inurl:admindork
|
||||
colon = "%3A"
|
||||
plus = "%2B"
|
||||
space = '+'
|
||||
period = "%2E"
|
||||
double_quote = "%22"
|
||||
asterick = "%2A"
|
||||
left_bracket = "%5B"
|
||||
right_bracket = "%5D"
|
||||
question_mark = "%3F"
|
||||
slash = "%2F"
|
||||
single_quote = "%27"
|
||||
ampersand = "%26"
|
||||
left_peren = "%28"
|
||||
right_peren = "%29"
|
||||
#populate links list required that we need correct html encoding to work properly
|
||||
self.links = [self.database + space + self.word + space +
|
||||
str(dork).replace(':', colon).replace('+', plus).replace('.', period).replace('"', double_quote)
|
||||
.replace("*", asterick).replace('[', left_bracket).replace(']', right_bracket)
|
||||
.replace('?', question_mark).replace(' ', space).replace('/', slash).replace("'", single_quote)
|
||||
.replace("&", ampersand).replace('(', left_peren).replace(')', right_peren)
|
||||
for dork in self.dorks]
|
||||
|
||||
def do_search(self):
|
||||
for link in self.links:
|
||||
try:
|
||||
params = {
|
||||
'User-Agent': random.choice(self.userAgent) #grab random User-Agent to avoid google blocking ip
|
||||
}
|
||||
req = requests.get(link, params=params)
|
||||
time.sleep(0.2)
|
||||
self.results = req.content
|
||||
self.totalresults += self.results
|
||||
except Exception: #if something happens just continue
|
||||
continue
|
||||
|
||||
def get_emails(self):
|
||||
rawres = myparser.parser(self.totalresults, self.word)
|
||||
return rawres.emails()
|
||||
|
||||
def get_hostnames(self):
|
||||
rawres = myparser.parser(self.totalresults, self.word)
|
||||
return rawres.hostnames()
|
||||
|
||||
def get_files(self):
|
||||
rawres = myparser.parser(self.totalresults, self.word)
|
||||
return rawres.fileurls(self.files)
|
||||
|
||||
def get_profiles(self):
|
||||
rawres = myparser.parser(self.totalresults, self.word)
|
||||
return rawres.profiles()
|
||||
|
||||
def process(self):
|
||||
while self.counter <= self.limit and self.counter <= 1000:
|
||||
self.do_search()
|
||||
time.sleep(0.8)
|
||||
print "\tSearching " + str(self.counter) + " results..."
|
||||
self.counter += 100
|
||||
|
|
@ -4,32 +4,52 @@
|
|||
import re
|
||||
import time
|
||||
import requests
|
||||
|
||||
import random
|
||||
|
||||
class search_google:
|
||||
|
||||
def __init__(self, word, limit, start):
|
||||
def __init__(self, word, limit, start,google_dorking):
|
||||
self.word = word
|
||||
self.results = ""
|
||||
self.totalresults = ""
|
||||
self.server = "www.google.com"
|
||||
self.userAgent = "(Mozilla/5.0 (Windows; U; Windows NT 6.0;en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6"
|
||||
self.dorks = []
|
||||
self.links = []
|
||||
self.database = "https://www.google.com/search?q="
|
||||
self.userAgent = ["(Mozilla/5.0 (Windows; U; Windows NT 6.0;en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6",
|
||||
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36"
|
||||
, ("Mozilla/5.0 (Linux; Android 7.0; SM-G892A Build/NRD90M; wv) " +
|
||||
"AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/60.0.3112.107 Mobile Safari/537.36"),
|
||||
("Mozilla/5.0 (Windows Phone 10.0; Android 6.0.1; Microsoft; RM-1152) " +
|
||||
"AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Mobile Safari/537.36 Edge/15.15254")]
|
||||
self.quantity = "100"
|
||||
self.limit = limit
|
||||
self.counter = start
|
||||
|
||||
def do_search(self):
|
||||
try:
|
||||
urly="http://" + self.server + "/search?num=" + self.quantity + "&start=" + str(self.counter) + "&hl=en&meta=&q=%40\"" + self.word + "\""
|
||||
except Exception, e:
|
||||
print e
|
||||
try:
|
||||
r=requests.get(urly)
|
||||
except Exception,e:
|
||||
print e
|
||||
self.results = r.content
|
||||
self.totalresults += self.results
|
||||
self.google_dorking = google_dorking
|
||||
|
||||
def do_search(self):
|
||||
if self.google_dorking == False:
|
||||
try:
|
||||
urly="http://" + self.server + "/search?num=" + self.quantity + "&start=" + str(self.counter) + "&hl=en&meta=&q=%40\"" + self.word + "\""
|
||||
except Exception, e:
|
||||
print e
|
||||
try:
|
||||
r=requests.get(urly)
|
||||
except Exception,e:
|
||||
print e
|
||||
self.results = r.content
|
||||
self.totalresults += self.results
|
||||
else: #google_dorking is true
|
||||
for link in self.links:
|
||||
try:
|
||||
params = {'User-Agent': random.choice(self.userAgent)}
|
||||
#grab random User-Agent to avoid google blocking ip
|
||||
req = requests.get(link, params=params)
|
||||
time.sleep(0.2)
|
||||
self.results = req.content
|
||||
self.totalresults += self.results
|
||||
except Exception: #if something happens just continue
|
||||
continue
|
||||
|
||||
def do_search_profiles(self):
|
||||
try:
|
||||
|
|
@ -76,3 +96,34 @@ def process_profiles(self):
|
|||
time.sleep(0.3)
|
||||
self.counter += 100
|
||||
print "\tSearching " + str(self.counter) + " results..."
|
||||
|
||||
def append_dorks(self):
|
||||
try: # wrap in try-except incase filepaths are messed up
|
||||
with open('../theHarvester/wordlists/dorks.txt', mode='r') as fp:
|
||||
self.dorks = [dork.strip() for dork in fp]
|
||||
except IOError as error:
|
||||
print(error)
|
||||
|
||||
def construct_dorks(self):
|
||||
#format is: site:targetwebsite.com + space + inurl:admindork
|
||||
colon = "%3A"
|
||||
plus = "%2B"
|
||||
space = '+'
|
||||
period = "%2E"
|
||||
double_quote = "%22"
|
||||
asterick = "%2A"
|
||||
left_bracket = "%5B"
|
||||
right_bracket = "%5D"
|
||||
question_mark = "%3F"
|
||||
slash = "%2F"
|
||||
single_quote = "%27"
|
||||
ampersand = "%26"
|
||||
left_peren = "%28"
|
||||
right_peren = "%29"
|
||||
#populate links list required that we need correct html encoding to work properly
|
||||
self.links = [self.database + space + self.word + space +
|
||||
str(dork).replace(':', colon).replace('+', plus).replace('.', period).replace('"', double_quote)
|
||||
.replace("*", asterick).replace('[', left_bracket).replace(']', right_bracket)
|
||||
.replace('?', question_mark).replace(' ', space).replace('/', slash).replace("'", single_quote)
|
||||
.replace("&", ampersand).replace('(', left_peren).replace(')', right_peren)
|
||||
for dork in self.dorks]
|
||||
|
|
|
|||
|
|
@ -8,7 +8,6 @@
|
|||
import re
|
||||
import getopt
|
||||
import stash
|
||||
from discovery import googledork
|
||||
|
||||
try:
|
||||
import requests
|
||||
|
|
@ -46,7 +45,6 @@ def usage():
|
|||
print """ -b: data source: baidu, bing, bingapi, dogpile, google, googleCSE,
|
||||
googleplus, google-profiles, linkedin, pgp, twitter, vhost,
|
||||
virustotal, threatcrowd, crtsh, netcraft, yahoo, all\n"""
|
||||
print " -g: perform google dorking"
|
||||
print " -s: start in result number X (default: 0)"
|
||||
print " -v: verify host name via dns resolution and search for virtual hosts"
|
||||
print " -f: save the results into an HTML and XML file (both)"
|
||||
|
|
@ -58,6 +56,7 @@ def usage():
|
|||
print " -l: limit the number of results to work with(bing goes from 50 to 50 results,"
|
||||
print " google 100 to 100, and pgp doesn't use this option)"
|
||||
print " -h: use SHODAN database to query discovered hosts"
|
||||
print " -g: perform google dorking"
|
||||
print "\nExamples:"
|
||||
print " " + comm + " -d microsoft.com -l 500 -b google -h myresults.html"
|
||||
print " " + comm + " -d microsoft.com -b pgp"
|
||||
|
|
@ -70,7 +69,7 @@ def start(argv):
|
|||
usage()
|
||||
sys.exit()
|
||||
try:
|
||||
opts, args = getopt.getopt(argv, "l:d:b:s:vf:nghcpte:")
|
||||
opts, args = getopt.getopt(argv, "l:d:b:s:vf:nhcgpte:")
|
||||
except getopt.GetoptError:
|
||||
usage()
|
||||
sys.exit()
|
||||
|
|
@ -100,7 +99,6 @@ def start(argv):
|
|||
elif opt == '-d':
|
||||
word = arg
|
||||
elif opt == '-g':
|
||||
print 'google dorking is true'
|
||||
google_dorking = True
|
||||
elif opt == '-s':
|
||||
start = int(arg)
|
||||
|
|
@ -131,7 +129,7 @@ def start(argv):
|
|||
print "[-] Starting harvesting process for domain: " + word + "\n"
|
||||
if engine == "google":
|
||||
print "[-] Searching in Google:"
|
||||
search = googlesearch.search_google(word, limit, start)
|
||||
search = googlesearch.search_google(word, limit, start, google_dorking)
|
||||
search.process()
|
||||
all_emails = search.get_emails()
|
||||
all_hosts = search.get_hostnames()
|
||||
|
|
@ -532,19 +530,6 @@ def start(argv):
|
|||
else:
|
||||
pass
|
||||
|
||||
# Google Dorking####################################################
|
||||
if google_dorking == True:
|
||||
print "Starting Google Dorking: "
|
||||
search = googledork.google_dork(word,limit,start)
|
||||
search.append_dorks()
|
||||
search.construct_dorks()
|
||||
emails = search.get_emails()
|
||||
hosts = search.get_hostnames()
|
||||
print emails
|
||||
print hosts
|
||||
else:
|
||||
pass
|
||||
|
||||
#Reporting#######################################################
|
||||
if filename != "":
|
||||
try:
|
||||
|
|
|
|||
|
|
@ -31,4 +31,20 @@ administrator/account.%XT%
|
|||
Database_Administration/
|
||||
phpSQLiteAdmin/
|
||||
0admin/
|
||||
super_login%XT%
|
||||
super_login%XT%
|
||||
/spid/lang/lang.php?lang_path=
|
||||
allinurl:.br/index.php?loc=
|
||||
PSUser/
|
||||
secrets/
|
||||
login_admin%XT%
|
||||
loginerror/
|
||||
superuser%XT%
|
||||
authenticate.%XT%
|
||||
authentication.%XT%
|
||||
auth.%XT%
|
||||
authuser.%XT%
|
||||
authadmin.%XT%
|
||||
cp.%XT%
|
||||
modelsearch/login.%XT%
|
||||
moderator.%XT%
|
||||
moderator/
|
||||
Loading…
Reference in a new issue