WEBDIENSTE/theHarvester
1
0
Fork 0
mirror of https://github.com/laramies/theHarvester.git synced 2026-09-28 20:44:53 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #156 from leebaird/master

Browse Source 
Removed dbl quotes.
This commit is contained in:
Matt
2019-01-23 03:47:02 +00:00
committed by GitHub
parent 208ab14558 e92e9ea2f1
commit efe73e20ae
32 changed files with 237 additions and 250 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.gitignore
+2 -2
View File
@@ -4,7 +4,7 @@
.html
.vscode
.xml
api-keys.yaml
debug_results.txt
tests/myparser.py
venv
api-keys.yaml
venv
README.md
+1 -1
View File
@@ -6,7 +6,7 @@
* | |_| | | | __/ / __ / (_| | | \ V / __/\__ \ || __/ | *
* \__|_| |_|\___| \/ /_/ \__,_|_| \_/ \___||___/\__\___|_| *
* *
* theHarvester 3.0.6 v206 *
* theHarvester 3.0.6 v213 *
* Coded by Christian Martorella *
* Edge-Security Research *
* cmartorella@edge-security.com *
discovery/censys.py
+13 -13
View File
@@ -14,7 +14,7 @@ class SearchCensys:
self.resultcerts = ""
self.total_resultshosts = ""
self.total_resultscerts = ""
self.server = "censys.io"
self.server = 'censys.io'
self.ips = []
self.hostnamesall = []
self.limit = limit
@@ -39,8 +39,8 @@ class SearchCensys:
def process(self):
try:
self.urlhost = "https://" + self.server + "/ipv4/_search?q=" + str(self.word) + "&page=1"
self.urlcert = "https://" + self.server + "/certificates/_search?q=" + str(self.word) + "&page=1"
self.urlhost = 'https://' + self.server + '/ipv4/_search?q=' + str(self.word) + '&page=1'
self.urlcert = 'https://' + self.server + '/certificates/_search?q=' + str(self.word) + '&page=1'
self.do_searchhosturl()
self.do_searchcertificateurl()
counter = 2
@@ -51,9 +51,9 @@ class SearchCensys:
while counter <= totalpages:
try:
self.page = str(counter)
self.urlhost = "https://" + self.server + "/ipv4/_search?q=" + str(self.word) + "&page=" + str(
self.urlhost = 'https://' + self.server + '/ipv4/_search?q=' + str(self.word) + '&page=' + str(
self.page)
print("\tSearching Censys IP results page " + self.page + ".")
print('\tSearching Censys IP results page ' + self.page + '.')
self.do_searchhosturl()
counter += 1
except Exception as e:
@@ -62,9 +62,9 @@ class SearchCensys:
while counter <= pagestosearch:
try:
self.page = str(counter)
self.urlhost = "https://" + self.server + "/ipv4/_search?q=" + str(self.word) + "&page=" + str(
self.urlhost = 'https://' + self.server + '/ipv4/_search?q=' + str(self.word) + '&page=' + str(
self.page)
print(f'\tSearching Censys IP results page {self.page} ...')
print(f'\tSearching results page {self.page}.')
self.do_searchhosturl()
counter += 1
except Exception as e:
@@ -75,9 +75,9 @@ class SearchCensys:
while counter <= totalpages:
try:
self.page = str(counter)
self.urlhost = "https://" + self.server + "/certificates/_search?q=" + str(
self.word) + "&page=" + str(self.page)
print(f'\tSearching Censys certificates results page {self.page} ...')
self.urlhost = 'https://' + self.server + '/certificates/_search?q=' + str(
self.word) + '&page=' + str(self.page)
print(f'\tSearching Censys certificates results page {self.page}.')
self.do_searchcertificateurl()
counter += 1
except Exception as e:
@@ -86,9 +86,9 @@ class SearchCensys:
while counter <= pagestosearch:
try:
self.page = str(counter)
self.urlhost = "https://" + self.server + "/ipv4/_search?q=" + str(self.word) + "&page=" + str(
self.urlhost = 'https://' + self.server + '/ipv4/_search?q=' + str(self.word) + '&page=' + str(
self.page)
print("\tSearching Censys IP results page " + self.page + ".")
print('\tSearching Censys IP results page ' + self.page + '.')
self.do_searchhosturl()
counter += 1
except Exception as e:
@@ -101,7 +101,7 @@ class SearchCensys:
try:
ips = self.get_ipaddresses()
headers = {'user-agent': Core.get_user_agent(), 'Accept': '*/*', 'Referer': self.urlcert}
response = requests.post("https://censys.io/ipv4/getdns", json={"ips": ips}, headers=headers)
response = requests.post('https://censys.io/ipv4/getdns', json={'ips': ips}, headers=headers)
responsejson = response.json()
domainsfromcensys = []
for key, jdata in responsejson.items():
discovery/constants.py
+3 -3
View File
@@ -1,7 +1,7 @@
import random
googleUA = "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36"
googleUA = 'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36'
def filter(lst):
@@ -42,9 +42,9 @@ class MissingKey(Exception):
def __init__(self, identity_flag):
if identity_flag:
self.message = '\n\033[93m[!] Missing API key.\n \033[0m'
self.message = '\n\033[93m[!] Missing API key. \033[0m'
else:
self.message = '\n\033[93m[!] Missing CSE id.\n \033[0m'
self.message = '\n\033[93m[!] Missing CSE id. \033[0m'
def __str__(self):
return self.message
discovery/crtsh.py
+3 -3
View File
@@ -11,8 +11,8 @@ class search_crtsh:
self.word = word.replace(' ', '%20')
self.results = ""
self.totalresults = ""
self.server = "https://crt.sh/?q="
self.quantity = "100"
self.server = 'https://crt.sh/?q='
self.quantity = '100'
self.counter = 0
def do_search(self):
@@ -64,4 +64,4 @@ class search_crtsh:
def process(self):
self.do_search()
print("\tSearching CRT.sh results.")
print('\tSearching results.')
discovery/cymon.py
+3 -3
View File
@@ -11,7 +11,7 @@ class search_cymon:
self.word = word
self.url = ""
self.results = ""
self.server = "cymon.io"
self.server = 'cymon.io'
def do_search(self):
try:
@@ -24,8 +24,8 @@ class search_cymon:
def process(self):
try:
self.url = "https://" + self.server + "/domain/" + str(self.word)
print('\tSearching Cymon results.')
self.url = 'https://' + self.server + '/domain/' + str(self.word)
print('\tSearching results.')
self.do_search()
except Exception as e:
print(f'Error occurred: {e}')
discovery/dnssearch.py
+54 -54
View File
@@ -12,10 +12,10 @@ class dns_reverse():
self.results = []
self.verbose = verbose
try:
DNS.ParseResolvConf("/etc/resolv.conf")
DNS.ParseResolvConf('/etc/resolv.conf')
nameserver = DNS.defaults['server'][0]
except:
print("Error in DNS resolvers")
print('Error in DNS resolvers')
sys.exit()
def run(self, host):
@@ -27,20 +27,20 @@ class dns_reverse():
if self.verbose:
ESC = chr(27)
sys.stdout.write(ESC + '[2K' + ESC + '[G')
sys.stdout.write("\r\t" + host)
sys.stdout.write('\r\t' + host)
sys.stdout.flush()
try:
name = DNS.Base.DnsRequest(b, qtype='ptr').req().answers[0]['data']
return host + ":" + name
return host + ':' + name
except:
pass
def get_ip_list(self, ips):
"""Generates the list of ips to reverse"""
"""Generates the list of IPs to reverse"""
try:
list = IPy.IP(ips)
except:
print("Error in IP format, check the input and try again. (Eg. 192.168.1.0/24)")
print('Error in IP format, check the input and try again. (Eg. 192.168.1.0/24)')
sys.exit()
name = []
for x in list:
@@ -64,7 +64,7 @@ class dns_force():
def __init__(self, domain, dnsserver, verbose=False):
self.domain = domain
self.nameserver = dnsserver
self.file = "wordlists/dns-big.txt"
self.file = 'wordlists/dns-big.txt'
self.subdo = False
self.verbose = verbose
try:
@@ -73,21 +73,21 @@ class dns_force():
with open(res_path) as f:
self.resolvers = f.read().splitlines()
except Exception:
print("Resolvers file can't be open")
print("Resolvers file can't be open.")
try:
f = open(self.file, "r")
f = open(self.file, 'r')
except:
print("Error opening dns dictionary file")
print('Error opening DNS dictionary file.')
sys.exit()
self.list = f.readlines()
def getdns(self, domain):
DNS.ParseResolvConf("/etc/resolv.conf")
DNS.ParseResolvConf('/etc/resolv.conf')
dom = domain
if self.subdo is True:
dom = domain.split(".")
dom = domain.split('.')
dom.pop(0)
rootdom = ".".join(dom)
rootdom = '.'.join(dom)
else:
rootdom = dom
if self.nameserver == "":
@@ -107,26 +107,26 @@ class dns_force():
# Check if variable is defined.
test
except NameError:
print("Error, test is not defined")
print('Error, test is not defined.')
sys.exit()
if test.header['status'] != "NOERROR":
print("Error")
if test.header['status'] != 'NOERROR':
print('[!] Error')
sys.exit()
self.nameserver = test.answers[0]['data']
elif self.nameserver == "local":
elif self.nameserver == 'local':
self.nameserver = nameserver
return self.nameserver
def run(self, host):
if self.nameserver == "":
self.nameserver = self.getdns(self.domain)
print("\n\033[94m[-] Using DNS server: " + self.nameserver + "\033[1;33;40m\n")
print('\n\033[94m[-] Using DNS server: ' + self.nameserver + '\033[1;33;40m\n')
hostname = str(host.split("\n")[0]) + "." + str(self.domain)
hostname = str(host.split('\n')[0]) + '.' + str(self.domain)
if self.verbose:
ESC = chr(27)
sys.stdout.write(ESC + '[2K' + ESC + '[G')
sys.stdout.write("\r" + hostname)
sys.stdout.write('\r' + hostname)
sys.stdout.flush()
try:
test = DNS.Request(
@@ -136,7 +136,7 @@ class dns_force():
)
# TODO FIX test is sometimes not getting answers and leads to an indexing error.
hostip = test.answers[0]['data']
return hostname + ":" + hostip
return hostname + ':' + hostip
except Exception:
pass
@@ -145,7 +145,7 @@ class dns_force():
for x in self.list:
host = self.run(x)
if host is not None:
print(" : " + host.split(":")[1])
print(' : ' + host.split(':')[1])
results.append(host)
return results
@@ -159,37 +159,37 @@ class dns_tld():
self.verbose = verbose
# Updated from http://data.iana.org/TLD/tlds-alpha-by-domain.txt
self.tlds = [
"ac", "academy", "ad", "ae", "aero", "af", "ag", "ai", "al", "am", "an", "ao", "aq", "ar", "arpa", "as",
"asia", "at", "au", "aw", "ax", "az", "ba", "bb", "bd", "be", "bf", "bg", "bh", "bi", "bike", "biz", "bj",
"bm", "bn", "bo", "br", "bs", "bt", "builders", "buzz", "bv", "bw", "by", "bz", "ca", "cab", "camera",
"camp", "careers", "cat", "cc", "cd", "center", "ceo", "cf", "cg", "ch", "ci", "ck", "cl", "clothing",
"cm", "cn", "co", "codes", "coffee", "com", "company", "computer", "construction", "contractors", "coop",
"cr", "cu", "cv", "cw", "cx", "cy", "cz", "de", "diamonds", "directory", "dj", "dk", "dm", "do",
"domains", "dz", "ec", "edu", "education", "ee", "eg", "email", "enterprises", "equipment", "er", "es",
"estate", "et", "eu", "farm", "fi", "fj", "fk", "florist", "fm", "fo", "fr", "ga", "gallery", "gb", "gd",
"ge", "gf", "gg", "gh", "gi", "gl", "glass", "gm", "gn", "gov", "gp", "gq", "gr", "graphics", "gs", "gt",
"gu", "guru", "gw", "gy", "hk", "hm", "hn", "holdings", "holiday", "house", "hr", "ht", "hu", "id", "ie",
"il", "im", "immobilien", "in", "info", "institute", "int", "international", "io", "iq", "ir", "is", "it",
"je", "jm", "jo", "jobs", "jp", "kaufen", "ke", "kg", "kh", "ki", "kitchen", "kiwi", "km", "kn", "kp",
"kr", "kw", "ky", "kz", "la", "land", "lb", "lc", "li", "lighting", "limo", "lk", "lr", "ls", "lt", "lu",
"lv", "ly", "ma", "management", "mc", "md", "me", "menu", "mg", "mh", "mil", "mk", "ml", "mm", "mn", "mo",
"mobi", "mp", "mq", "mr", "ms", "mt", "mu", "museum", "mv", "mw", "mx", "my", "mz", "na", "name", "nc",
"ne", "net", "nf", "ng", "ni", "ninja", "nl", "no", "np", "nr", "nu", "nz", "om", "onl", "org", "pa", "pe",
"pf", "pg", "ph", "photography", "photos", "pk", "pl", "plumbing", "pm", "pn", "post", "pr", "pro", "ps",
"pt", "pw", "py", "qa", "re", "recipes", "repair", "ro", "rs", "ru", "ruhr", "rw", "sa", "sb", "sc", "sd",
"se", "sexy", "sg", "sh", "shoes", "si", "singles", "sj", "sk", "sl", "sm", "sn", "so", "solar",
"solutions", "sr", "st", "su", "support", "sv", "sx", "sy", "systems", "sz", "tattoo", "tc", "td",
"technology", "tel", "tf", "tg", "th", "tips", "tj", "tk", "tl", "tm", "tn", "to", "today", "tp", "tr",
"training", "travel", "tt", "tv", "tw", "tz", "ua", "ug", "uk", "uno", "us", "uy", "uz", "va", "vc",
"ve", "ventures", "vg", "vi", "viajes", "vn", "voyage", "vu", "wang", "wf", "wien", "ws", "xxx", "ye",
"yt", "za", "zm", "zw"]
'ac', 'academy', 'ad', 'ae', 'aero', 'af', 'ag', 'ai', 'al', 'am', 'an', 'ao', 'aq', 'ar', 'arpa', 'as',
'asia', 'at', 'au', 'aw', 'ax', 'az', 'ba', 'bb', 'bd', 'be', 'bf', 'bg', 'bh', 'bi', 'bike', 'biz', 'bj',
'bm', 'bn', 'bo', 'br', 'bs', 'bt', 'builders', 'buzz', 'bv', 'bw', 'by', 'bz', 'ca', 'cab', 'camera',
'camp', 'careers', 'cat', 'cc', 'cd', 'center', 'ceo', 'cf', 'cg', 'ch', 'ci', 'ck', 'cl', 'clothing',
'cm', 'cn', 'co', 'codes', 'coffee', 'com', 'company', 'computer', 'construction', 'contractors', 'coop',
'cr', 'cu', 'cv', 'cw', 'cx', 'cy', 'cz', 'de', 'diamonds', 'directory', 'dj', 'dk', 'dm', 'do',
'domains', 'dz', 'ec', 'edu', 'education', 'ee', 'eg', 'email', 'enterprises', 'equipment', 'er', 'es',
'estate', 'et', 'eu', 'farm', 'fi', 'fj', 'fk', 'florist', 'fm', 'fo', 'fr', 'ga', 'gallery', 'gb', 'gd',
'ge', 'gf', 'gg', 'gh', 'gi', 'gl', 'glass', 'gm', 'gn', 'gov', 'gp', 'gq', 'gr', 'graphics', 'gs', 'gt',
'gu', 'guru', 'gw', 'gy', 'hk', 'hm', 'hn', 'holdings', 'holiday', 'house', 'hr', 'ht', 'hu', 'id', 'ie',
'il', 'im', 'immobilien', 'in', 'info', 'institute', 'int', 'international', 'io', 'iq', 'ir', 'is', 'it',
'je', 'jm', 'jo', 'jobs', 'jp', 'kaufen', 'ke', 'kg', 'kh', 'ki', 'kitchen', 'kiwi', 'km', 'kn', 'kp',
'kr', 'kw', 'ky', 'kz', 'la', 'land', 'lb', 'lc', 'li', 'lighting', 'limo', 'lk', 'lr', 'ls', 'lt', 'lu',
'lv', 'ly', 'ma', 'management', 'mc', 'md', 'me', 'menu', 'mg', 'mh', 'mil', 'mk', 'ml', 'mm', 'mn', 'mo',
'mobi', 'mp', 'mq', 'mr', 'ms', 'mt', 'mu', 'museum', 'mv', 'mw', 'mx', 'my', 'mz', 'na', 'name', 'nc',
'ne', 'net', 'nf', 'ng', 'ni', 'ninja', 'nl', 'no', 'np', 'nr', 'nu', 'nz', 'om', 'onl', 'org', 'pa', 'pe',
'pf', 'pg', 'ph', 'photography', 'photos', 'pk', 'pl', 'plumbing', 'pm', 'pn', 'post', 'pr', 'pro', 'ps',
'pt', 'pw', 'py', 'qa', 're', 'recipes', 'repair', 'ro', 'rs', 'ru', 'ruhr', 'rw', 'sa', 'sb', 'sc', 'sd',
'se', 'sexy', 'sg', 'sh', 'shoes', 'si', 'singles', 'sj', 'sk', 'sl', 'sm', 'sn', 'so', 'solar',
'solutions', 'sr', 'st', 'su', 'support', 'sv', 'sx', 'sy', 'systems', 'sz', 'tattoo', 'tc', 'td',
'technology', 'tel', 'tf', 'tg', 'th', 'tips', 'tj', 'tk', 'tl', 'tm', 'tn', 'to', 'today', 'tp', 'tr',
'training', 'travel', 'tt', 'tv', 'tw', 'tz', 'ua', 'ug', 'uk', 'uno', 'us', 'uy', 'uz', 'va', 'vc',
've', 'ventures', 'vg', 'vi', 'viajes', 'vn', 'voyage', 'vu', 'wang', 'wf', 'wien', 'ws', 'xxx', 'ye',
'yt', 'za', 'zm', 'zw']
def getdns(self, domain):
dom = domain
if self.subdo is True:
dom = domain.split(".")
dom = domain.split('.')
dom.pop(0)
rootdom = ".".join(dom)
rootdom = '.'.join(dom)
else:
rootdom = dom
if self.nameserver is False:
@@ -197,21 +197,21 @@ class dns_tld():
primary, email, serial, refresh, retry, expire, minimum = r.answers[
0]['data']
test = DNS.Request(rootdom, qtype='NS', server=primary, aa=1).req()
if test.header['status'] != "NOERROR":
print("Error")
if test.header['status'] != 'NOERROR':
print('Error')
sys.exit()
self.nameserver = test.answers[0]['data']
elif self.nameserver == "local":
elif self.nameserver == 'local':
self.nameserver = nameserver
return self.nameserver
def run(self, tld):
self.nameserver = self.getdns(self.domain)
hostname = self.domain.split(".")[0] + "." + tld
hostname = self.domain.split('.')[0] + '.' + tld
if self.verbose:
ESC = chr(27)
sys.stdout.write(ESC + '[2K' + ESC + '[G')
sys.stdout.write("\r\tSearching for: " + hostname)
sys.stdout.write('\r\tSearching for: ' + hostname)
sys.stdout.flush()
try:
test = DNS.Request(
@@ -220,7 +220,7 @@ class dns_tld():
server=self.nameserver).req(
)
hostip = test.answers[0]['data']
return hostip + ":" + hostname
return hostip + ':' + hostname
except Exception:
pass
discovery/dogpilesearch.py
+2 -2
View File
@@ -10,8 +10,8 @@ class SearchDogpile:
def __init__(self, word, limit):
self.word = word
self.total_results = ""
self.server = "www.dogpile.com"
self.hostname = "www.dogpile.com"
self.server = 'www.dogpile.com'
self.hostname = 'www.dogpile.com'
self.limit = limit
self.counter = 0
discovery/duckduckgosearch.py
+6 -6
View File
@@ -14,9 +14,9 @@ class SearchDuckDuckGo:
self.totalresults = ""
self.dorks = []
self.links = []
self.database = "https://duckduckgo.com/?q="
self.api = "https://api.duckduckgo.com/?q=x&format=json&pretty=1" # Currently using API.
self.quantity = "100"
self.database = 'https://duckduckgo.com/?q='
self.api = 'https://api.duckduckgo.com/?q=x&format=json&pretty=1' # Currently using API.
self.quantity = '100'
self.limit = limit
def do_search(self):
@@ -39,9 +39,9 @@ class SearchDuckDuckGo:
def crawl(self, text):
"""
function parses json and returns urls
Function parses json and returns URLs.
:param text: formatted json
:return: set of urls
:return: set of URLs
"""
urls = set()
try:
@@ -51,7 +51,7 @@ class SearchDuckDuckGo:
if isinstance(val, int) or isinstance(val, dict) or val is None:
continue
if isinstance(val, list):
if len(val) == 0: # Make sure not indexing an empty list
if len(val) == 0: # Make sure not indexing an empty list.
continue
val = val[0] # First value should be dict.
if isinstance(val, dict): # Sanity check.
discovery/exaleadsearch.py
+10 -10
View File
@@ -10,20 +10,20 @@ class search_exalead:
def __init__(self, word, limit, start):
self.word = word
self.files = "pdf"
self.files = 'pdf'
self.results = ""
self.totalresults = ""
self.server = "www.exalead.com"
self.hostname = "www.exalead.com"
self.server = 'www.exalead.com'
self.hostname = 'www.exalead.com'
self.limit = limit
self.counter = start
def do_search(self):
url = 'http:// ' + self.server + '/search/web/results/?q=%40' + self.word \
+ "&elements_per_page=50&start_index=" + str(self.counter)
+ '&elements_per_page=50&start_index=' + str(self.counter)
headers = {
'Host': self.hostname,
'Referer': ("http://" + self.hostname + "/search/web/results/?q=%40" + self.word),
'Referer': ('http://' + self.hostname + '/search/web/results/?q=%40' + self.word),
'User-agent': Core.get_user_agent()
}
h = requests.get(url=url, headers=headers)
@@ -32,10 +32,10 @@ class search_exalead:
def do_search_files(self, files):
url = 'http:// ' + self.server + '/search/web/results/?q=%40' + self.word \
+ "filetype:" + self.files + "&elements_per_page=50&start_index=" + str(self.counter)
+ 'filetype:' + self.files + '&elements_per_page=50&start_index=' + str(self.counter)
headers = {
'Host': self.hostname,
'Referer': ("http://" + self.hostname + "/search/web/results/?q=%40" + self.word),
'Referer': ('http://' + self.hostname + '/search/web/results/?q=%40' + self.word),
'User-agent': Core.get_user_agent()
}
h = requests.get(url=url, headers=headers)
@@ -46,10 +46,10 @@ class search_exalead:
renext = re.compile('topNextUrl')
nextres = renext.findall(self.results)
if nextres != []:
nexty = "1"
nexty = '1'
print(str(self.counter))
else:
nexty = "0"
nexty = '0'
return nexty
def get_emails(self):
@@ -75,7 +75,7 @@ class search_exalead:
self.do_search_files(files)
time.sleep(getDelay())
more = self.check_next()
if more == "1":
if more == '1':
self.counter += 50
else:
break
discovery/googleCSE.py
+16 -16
View File
@@ -11,13 +11,13 @@ class SearchGoogleCSE:
def __init__(self, word, limit, start):
self.word = word
self.files = "pdf"
self.files = 'pdf'
self.results = ""
self.totalresults = ""
self.server = "www.googleapis.com"
self.hostname = "www.googleapis.com"
self.userAgent = "(Mozilla/5.0 (Windows; U; Windows NT 6.0;en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6"
self.quantity = "10"
self.server = 'www.googleapis.com'
self.hostname = 'www.googleapis.com'
self.userAgent = '(Mozilla/5.0 (Windows; U; Windows NT 6.0;en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6'
self.quantity = '10'
self.limit = limit
self.counter = 1
self.api_key = Core.google_cse_key()['key']
@@ -30,9 +30,9 @@ class SearchGoogleCSE:
self.highRange = start + 100
def do_search(self):
url = 'https://' + self.server + "/customsearch/v1?key=" + self.api_key + "&highrange=" + str(self.highRange) \
+ '&lowrange=' + str(self.lowRange) + '&cx=' + self.cse_id + "&start=" + str(self.counter) + \
"&q=" + self.word
url = 'https://' + self.server + '/customsearch/v1?key=' + self.api_key + '&highrange=' + str(self.highRange) \
+ '&lowrange=' + str(self.lowRange) + '&cx=' + self.cse_id + '&start=' + str(self.counter) + \
'&q=' + self.word
headers = {
'Host': self.server,
'User-agent': self.userAgent
@@ -43,9 +43,9 @@ class SearchGoogleCSE:
self.totalresults += self.results
def do_search_files(self, files):
url = 'https://' + self.server + "/customsearch/v1?key=" + self.api_key + "&highRange=" + str(self.highRange) \
+ '&lowRange=' + str(self.lowRange) + '&cx=' + self.cse_id + "&start=" + str(self.counter) + \
"&q=filetype:" + files + "%20site:" + self.word
url = 'https://' + self.server + '/customsearch/v1?key=' + self.api_key + '&highRange=' + str(self.highRange) \
+ '&lowRange=' + str(self.lowRange) + '&cx=' + self.cse_id + '&start=' + str(self.counter) + \
'&q=filetype:' + files + '%20site:' + self.word
headers = {
'Host': self.server,
'User-agent': self.userAgent
@@ -58,9 +58,9 @@ class SearchGoogleCSE:
renext = re.compile('> Next <')
nextres = renext.findall(self.results)
if nextres != []:
nexty = "1"
nexty = '1'
else:
nexty = "0"
nexty = '0'
return nexty
def get_emails(self):
@@ -81,7 +81,7 @@ class SearchGoogleCSE:
self.do_search()
ESC = chr(27)
sys.stdout.write(ESC + '[2K' + ESC + '[G')
sys.stdout.write("\r\t" + "Searching " + str(self.counter + self.lowRange) + " results.")
sys.stdout.write('\r\t' + 'Searching ' + str(self.counter + self.lowRange) + ' results.')
sys.stdout.flush()
if self.counter == 101:
self.counter = 1
@@ -92,7 +92,7 @@ class SearchGoogleCSE:
tracker = self.counter + self.lowRange
def store_results(self):
filename = "debug_results.txt"
filename = 'debug_results.txt'
file = open(filename, 'w')
file.write(self.totalresults)
@@ -101,4 +101,4 @@ class SearchGoogleCSE:
self.do_search_files(files)
time.sleep(1)
self.counter += 100
print("\tSearching " + str(self.counter) + " results.")
print('\tSearching ' + str(self.counter) + ' results.')
discovery/googlecertificates.py
+4 -4
View File
@@ -9,14 +9,14 @@ class SearchGoogleCertificates:
self.word = word
self.results = ""
self.totalresults = ""
self.server = "www.google.com"
self.quantity = "100"
self.server = 'www.google.com'
self.quantity = '100'
self.limit = limit
self.counter = start
def do_search(self):
try:
urly = "https://" + self.server + "/transparencyreport/api/v3/httpsreport/ct/certsearch?include_expired=true&include_subdomains=true&domain=" + self.word
urly = 'https://' + self.server + '/transparencyreport/api/v3/httpsreport/ct/certsearch?include_expired=true&include_subdomains=true&domain=' + self.word
except Exception as e:
print(e)
try:
@@ -29,7 +29,7 @@ class SearchGoogleCertificates:
def get_domains(self):
domains = []
rawres = json.loads(self.totalresults.split("\n", 2)[2])
rawres = json.loads(self.totalresults.split('\n', 2)[2])
for array in rawres[0][1]:
domains.append(array[1])
return list(set(domains))
discovery/googlesearch.py
+23 -23
View File
@@ -10,18 +10,18 @@ class search_google:
self.word = word
self.results = ""
self.totalresults = ""
self.server = "www.google.com"
self.server = 'www.google.com'
self.dorks = []
self.links = []
self.database = "https://www.google.com/search?q="
self.quantity = "100"
self.database = 'https://www.google.com/search?q='
self.quantity = '100'
self.limit = limit
self.counter = start
def do_search(self):
try: # Do normal scraping.
urly = "http://" + self.server + "/search?num=" + self.quantity + "&start=" + str(
self.counter) + "&hl=en&meta=&q=%40\"" + self.word + "\""
urly = 'http://' + self.server + '/search?num=' + self.quantity + '&start=' + str(
self.counter) + '&hl=en&meta=&q=%40\"' + self.word + '\"'
except Exception as e:
print(e)
try:
@@ -38,8 +38,8 @@ class search_google:
def do_search_profiles(self):
try:
urly = "http://" + self.server + "/search?num=" + self.quantity + "&start=" + str(
self.counter) + "&hl=en&meta=&q=site:www.google.com%20intitle:\"Google%20Profile\"%20\"Companies%20I%27ve%20worked%20for\"%20\"at%20" + self.word + "\""
urly = 'http://' + self.server + '/search?num=' + self.quantity + '&start=' + str(
self.counter) + '&hl=en&meta=&q=site:www.google.com%20intitle:\"Google%20Profile\"%20\"Companies%20I%27ve%20worked%20for\"%20\"at%20' + self.word + '\"'
except Exception as e:
print(e)
try:
@@ -79,7 +79,7 @@ class search_google:
else: # Google dorking is true.
self.counter = 0 # Reset counter.
print('\n')
print("[-] Searching with Google Dorks: ")
print('[-] Searching with Google Dorks: ')
while self.counter <= self.limit and self.counter <= 200: # Only 200 dorks in list.
self.googledork() # Call Google dorking method if user wanted it!
print(f'\tSearching {self.counter} results.')
@@ -102,27 +102,27 @@ class search_google:
def construct_dorks(self):
# Format is: site:targetwebsite.com + space + inurl:admindork
colon = "%3A"
plus = "%2B"
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"
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'
pipe = '%7C'
# Replace links with html encoding.
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('*', 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).replace('|', pipe)
.replace('&', ampersand).replace('(', left_peren).replace(')', right_peren).replace('|', pipe)
for dork in self.dorks]
def googledork(self):
discovery/googlesets.py
+5 -5
View File
@@ -8,19 +8,19 @@ class search_google_labs:
def __init__(self, list):
self.results = ""
self.totalresults = ""
self.server = "labs.google.com"
self.hostname = "labs.google.com"
self.server = 'labs.google.com'
self.hostname = 'labs.google.com'
id = 0
self.set = ""
for x in list:
id += 1
if id == 1:
self.set = self.set + "q" + str(id) + "=" + str(x)
self.set = self.set + 'q' + str(id) + '=' + str(x)
else:
self.set = self.set + "&q" + str(id) + "=" + str(x)
self.set = self.set + '&q' + str(id) + '=' + str(x)
def do_search(self):
url = 'http://' + self.server + "/sets?hl-en&" + self.set
url = 'http://' + self.server + '/sets?hl-en&' + self.set
headers = {
'Host': self.server,
'User-agent': Core.get_user_agent()
discovery/huntersearch.py
+2 -2
View File
@@ -16,7 +16,7 @@ class SearchHunter:
self.results = ""
self.totalresults = ""
self.counter = start
self.database = "https://api.hunter.io/v2/domain-search?domain=" + word + "&api_key=" + self.key + "&limit=" + str(self.limit)
self.database = 'https://api.hunter.io/v2/domain-search?domain=' + word + '&api_key=' + self.key + '&limit=' + str(self.limit)
def do_search(self):
try:
@@ -28,7 +28,7 @@ class SearchHunter:
def process(self):
self.do_search() # Only need to do it once.
print('\tDone Searching Results')
print('\tSearching results.')
def get_emails(self):
rawres = myparser.Parser(self.totalresults, self.word)
discovery/linkedinsearch.py
+4 -4
View File
@@ -11,15 +11,15 @@ class SearchLinkedin:
self.word = word.replace(' ', '%20')
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.quantity = "100"
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.quantity = '100'
self.limit = int(limit)
self.counter = 0
def do_search(self):
try:
urly = "http://" + self.server + "/search?num=100&start=" + str(self.counter) + "&hl=en&meta=&q=site%3Alinkedin.com/in%20" + self.word
urly = 'http://' + self.server + '/search?num=100&start=' + str(self.counter) + '&hl=en&meta=&q=site%3Alinkedin.com/in%20' + self.word
except Exception as e:
print(e)
try:
discovery/netcraft.py
+5 -5
View File
@@ -9,14 +9,14 @@ class SearchNetcraft:
self.word = word.replace(' ', '%20')
self.results = ""
self.totalresults = ""
self.server = "www.google.com"
self.hostname = "www.google.com"
self.quantity = "100"
self.server = 'www.google.com'
self.hostname = 'www.google.com'
self.quantity = '100'
self.counter = 0
def do_search(self):
try:
urly = "https://searchdns.netcraft.com/?restriction=site+ends+with&host=" + self.word
urly = 'https://searchdns.netcraft.com/?restriction=site+ends+with&host=' + self.word
except Exception as e:
print(e)
headers = {'User-Agent': Core.get_user_agent()}
@@ -33,4 +33,4 @@ class SearchNetcraft:
def process(self):
self.do_search()
print("\tSearching Netcraft results.")
print('\tSearching results.')
discovery/pgpsearch.py
+5 -5
View File
@@ -8,13 +8,13 @@ class SearchPgp:
def __init__(self, word):
self.word = word
self.results = ""
self.server = "pgp.mit.edu"
self.hostname = "pgp.mit.edu"
self.server = 'pgp.mit.edu'
self.hostname = 'pgp.mit.edu'
def process(self):
print("\tSearching PGP results.")
print('\tSearching results.')
try:
url = 'http://' + self.server + "/pks/lookup?search=" + self.word + "&op=index"
url = 'http://' + self.server + '/pks/lookup?search=' + self.word + '&op=index'
headers = {
'Host': self.hostname,
'User-agent': Core.get_user_agent()
@@ -23,7 +23,7 @@ class SearchPgp:
self.results = h.text
self.results += self.results
except Exception as e:
print("Unable to connect to PGP server: ", str(e))
print('Unable to connect to PGP server: ', str(e))
def get_emails(self):
rawres = myparser.Parser(self.results, self.word)
discovery/s3_scanner.py
+8 -8
View File
@@ -8,21 +8,21 @@ class s3_scanner:
self.host = host
self.results = ""
self.totalresults = ""
self.fingerprints = ["www.herokucdn.com/error-pages/no-such-app.html", "<title>Squarespace - No Such Account</title>", "<p> If you're trying to publish one, <a href=\"https://help.github.com/pages/\">read the full documentation</a> to learn how to set up <strong>GitHub Pages</strong> for your repository, organization, or user account. </p>","<p> If you\'re trying to publish one, <a href=\"https://help.github.com/pages/\">read the full documentation</a> to learn how to set up <strong>GitHub Pages</strong> for your repository, organization, or user account. </p>","<span class=\"title\">Bummer. It looks like the help center that you are trying to reach no longer exists.</span>","<head> <title>The page you\'re looking for could not be found (404)</title> <style> body { color: #666; text-align: center; font-family: \"Helvetica Neue\", Helvetica, Arial, sans-serif; margin: 0; width: 800px; margin: auto; font-size: 14px; } h1 { font-size: 56px; line-height: 100px; font-weight: normal; color: #456; } h2 { font-size: 24px; color: #666; line-height: 1.5em; } h3 { color: #456; font-size: 20px; font-weight: normal; line-height: 28px; } hr { margin: 18px 0; border: 0; border-top: 1px solid #EEE; border-bottom: 1px solid white; } </style> </head>"]
self.fingerprints = ['www.herokucdn.com/error-pages/no-such-app.html', '<title>Squarespace - No Such Account</title>', "<p> If you're trying to publish one, <a href=\"https://help.github.com/pages/\">read the full documentation</a> to learn how to set up <strong>GitHub Pages</strong> for your repository, organization, or user account. </p>","<p> If you\'re trying to publish one, <a href=\"https://help.github.com/pages/\">read the full documentation</a> to learn how to set up <strong>GitHub Pages</strong> for your repository, organization, or user account. </p>","<span class=\"title\">Bummer. It looks like the help center that you are trying to reach no longer exists.</span>","<head> <title>The page you\'re looking for could not be found (404)</title> <style> body { color: #666; text-align: center; font-family: \"Helvetica Neue\", Helvetica, Arial, sans-serif; margin: 0; width: 800px; margin: auto; font-size: 14px; } h1 { font-size: 56px; line-height: 100px; font-weight: normal; color: #456; } h2 { font-size: 24px; color: #666; line-height: 1.5em; } h3 { color: #456; font-size: 20px; font-weight: normal; line-height: 28px; } hr { margin: 18px 0; border: 0; border-top: 1px solid #EEE; border-bottom: 1px solid white; } </style> </head>"]
def __check_http(self, bucket_url):
check_response = self.session.head(
S3_URL, timeout=3, headers={"Host": bucket_url})
S3_URL, timeout=3, headers={'Host': bucket_url})
# if not ARGS.ignore_rate_limiting\
# and (check_response.status_code == 503 and check_response.reason == "Slow Down"):
# and (check_response.status_code == 503 and check_response.reason == 'Slow Down'):
# self.q.rate_limited = True
# add it back to the bucket for re-processing
# Add it back to the bucket for re-processing.
# self.q.put(bucket_url)
if check_response.status_code == 307: # valid bucket, lets check if its public
new_bucket_url = check_response.headers["Location"]
new_bucket_url = check_response.headers['Location']
bucket_response = requests.request(
"GET" if ARGS.only_interesting else "HEAD", new_bucket_url, timeout=3)
'GET' if ARGS.only_interesting else 'HEAD', new_bucket_url, timeout=3)
if bucket_response.status_code == 200\
and (not ARGS.only_interesting or
@@ -32,13 +32,13 @@ class s3_scanner:
def do_s3(self):
try:
print("\t Searching takeovers for " + self.host)
print('\t Searching takeovers for ' + self.host)
r = requests.get('https://' + self.host, verify=False)
for x in self.fingerprints:
take_reg = re.compile(x)
self.temp = take_reg.findall(r.text)
if self.temp != []:
print("\t\033[91m Takeover detected! - " + self.host + "\033[1;32;40m ")
print('\t\033[91m Takeover detected! - ' + self.host + '\033[1;32;40m')
except Exception as e:
print(e)
discovery/securitytrailssearch.py
+2 -2
View File
@@ -15,7 +15,7 @@ class search_securitytrail:
raise MissingKey(True)
self.results = ""
self.totalresults = ""
self.database = "https://api.securitytrails.com/v1/"
self.database = 'https://api.securitytrails.com/v1/'
self.info = ()
def authenticate(self):
@@ -53,7 +53,7 @@ class search_securitytrail:
parser = securitytrailsparser.Parser(word=self.word, text=self.totalresults)
self.info = parser.parse_text()
# Create parser and set self.info to tuple returned from parsing text.
print('\tDone Searching Results')
print('\tSearching results.')
def get_ips(self):
return self.info[0]
discovery/shodansearch.py
+3 -3
View File
@@ -34,10 +34,10 @@ class search_shodan:
str(results.get('org')), str(servicesports).replace('\'', '').strip('[]'),
str(technologies).replace('\'', '').strip('[]')]
except exception.APIError:
print(f'{ipaddress}: Not in Shodan')
self.hostdatarow = [ipaddress, "Not in Shodan", "Not in Shodan", "Not in Shodan", "Not in Shodan"]
print(f'{ipaddress}: Not in Shodan.')
self.hostdatarow = [ipaddress, 'Not in Shodan', 'Not in Shodan', 'Not in Shodan', 'Not in Shodan']
except Exception as e:
print(f'Error occurred in the Shodan IP search module: {e}')
print(f'[!] Error occurred in the Shodan IP search module: {e}')
finally:
return self.hostdatarow
discovery/takeover.py
+14 -14
View File
@@ -8,25 +8,25 @@ class take_over:
self.host = host
self.results = ""
self.totalresults = ""
self.fingerprints = ["<title>Squarespace - Domain Not Claimed</title>"
,"www.herokucdn.com/error-pages/no-such-app.html",
"<title>Squarespace - No Such Account</title>",
self.fingerprints = ["<title>Squarespace - Domain Not Claimed</title>",
'www.herokucdn.com/error-pages/no-such-app.html',
'<title>Squarespace - No Such Account</title>',
"<p> If you're trying to publish one, <a href=\"https://help.github.com/pages/\">read the full documentation</a> to learn how to set up <strong>GitHub Pages</strong> for your repository, organization, or user account. </p>",
"<p> If you\'re trying to publish one, <a href=\"https://help.github.com/pages/\">read the full documentation</a> to learn how to set up <strong>GitHub Pages</strong> for your repository, organization, or user account. </p>",
"<span class=\"title\">Bummer. It looks like the help center that you are trying to reach no longer exists.</span>",
"<head> <title>The page you\'re looking for could not be found (404)</title> <style> body { color: #666; text-align: center; font-family: \"Helvetica Neue\", Helvetica, Arial, sans-serif; margin: 0; width: 800px; margin: auto; font-size: 14px; } h1 { font-size: 56px; line-height: 100px; font-weight: normal; color: #456; } h2 { font-size: 24px; color: #666; line-height: 1.5em; } h3 { color: #456; font-size: 20px; font-weight: normal; line-height: 28px; } hr { margin: 18px 0; border: 0; border-top: 1px solid #EEE; border-bottom: 1px solid white; } </style> </head>",
"The specified bucket does not exist",
"Bad Request: ERROR: The request could not be satisfied",
"Fastly error: unknown domain:",
'The specified bucket does not exist',
'Bad Request: ERROR: The request could not be satisfied',
'Fastly error: unknown domain:',
"There isn't a Github Pages site here.",
"No such app",
"Unrecognized domain",
"Sorry, this shop is currently unavailable.",
'No such app',
'Unrecognized domain',
'Sorry, this shop is currently unavailable.',
"Whatever you were looking for doesn't currently exist at this address",
"The requested URL was not found on this server.",
"This UserVoice subdomain is currently available!",
"Do you want to register *.wordpress.com?",
"Help Center Closed"]
'The requested URL was not found on this server.',
'This UserVoice subdomain is currently available!',
'Do you want to register *.wordpress.com?',
'Help Center Closed']
def do_take(self):
try:
@@ -36,7 +36,7 @@ class take_over:
take_reg = re.compile(x)
self.temp = take_reg.findall(r.text)
if self.temp != []:
print(f"\t\033[91m Takeover detected! - {self.host} \033[1;32;40m")
print(f'\t\033[91m Takeover detected! - {self.host} \033[1;32;40m')
except Exception as e:
print(e)
discovery/threatcrowd.py
+5 -5
View File
@@ -9,14 +9,14 @@ class search_threatcrowd:
self.word = word.replace(' ', '%20')
self.results = ""
self.totalresults = ""
self.server = "www.google.com"
self.hostname = "www.google.com"
self.quantity = "100"
self.server = 'www.google.com'
self.hostname = 'www.google.com'
self.quantity = '100'
self.counter = 0
def do_search(self):
try:
urly = "https://www.threatcrowd.org/searchApi/v2/domain/report/?domain=" + self.word
urly = 'https://www.threatcrowd.org/searchApi/v2/domain/report/?domain=' + self.word
except Exception as e:
print(e)
headers = {'User-Agent': Core.get_user_agent()}
@@ -33,4 +33,4 @@ class search_threatcrowd:
def process(self):
self.do_search()
print('\tSearching Threatcrowd results.')
print('\tSearching results.')
discovery/trello.py
+7 -7
View File
@@ -10,16 +10,16 @@ class search_trello:
self.word = word.replace(' ', '%20')
self.results = ""
self.totalresults = ""
self.server = "www.google.com"
self.hostname = "www.google.com"
self.quantity = "100"
self.server = 'www.google.com'
self.hostname = 'www.google.com'
self.quantity = '100'
self.limit = limit
self.counter = 0
def do_search(self):
try:
urly = "https://" + self.server + "/search?num=100&start=" + str(
self.counter) + "&hl=en&q=site%3Atrello.com%20" + self.word
urly = 'https://' + self.server + '/search?num=100&start=' + str(
self.counter) + '&hl=en&q=site%3Atrello.com%20' + self.word
except Exception as e:
print(e)
headers = {'User-Agent': googleUA}
@@ -36,9 +36,9 @@ class search_trello:
return rawres.emails()
def get_urls(self):
print('\tSearching Trello URLs.')
print('\tSearching URLs.')
try:
rawres = myparser.Parser(self.totalresults, "trello.com")
rawres = myparser.Parser(self.totalresults, 'trello.com')
trello_urls = rawres.urls()
visited = set()
for url in trello_urls:
discovery/twittersearch.py
+4 -4
View File
@@ -11,15 +11,15 @@ class search_twitter:
self.word = word.replace(' ', '%20')
self.results = ""
self.totalresults = ""
self.server = "www.google.com"
self.hostname = "www.google.com"
self.quantity = "100"
self.server = 'www.google.com'
self.hostname = 'www.google.com'
self.quantity = '100'
self.limit = int(limit)
self.counter = 0
def do_search(self):
try:
urly = "https://" + self.server + "/search?num=100&start=" + str(self.counter) + "&hl=en&meta=&q=site%3Atwitter.com%20intitle%3A%22on+Twitter%22%20" + self.word
urly = 'https://' + self.server + '/search?num=100&start=' + str(self.counter) + '&hl=en&meta=&q=site%3Atwitter.com%20intitle%3A%22on+Twitter%22%20' + self.word
except Exception as e:
print(e)
headers = {'User-Agent': Core.get_user_agent()}
discovery/virustotal.py
+5 -5
View File
@@ -9,14 +9,14 @@ class search_virustotal:
self.word = word.replace(' ', '%20')
self.results = ""
self.totalresults = ""
self.server = "www.google.com"
self.hostname = "www.google.com"
self.quantity = "100"
self.server = 'www.google.com'
self.hostname = 'www.google.com'
self.quantity = '100'
self.counter = 0
def do_search(self):
try:
urly = "https://www.virustotal.com/en/domain/" + self.word + "/information/"
urly = 'https://www.virustotal.com/en/domain/' + self.word + '/information/'
except Exception as e:
print(e)
headers = {'User-Agent': Core.get_user_agent()}
@@ -33,4 +33,4 @@ class search_virustotal:
def process(self):
self.do_search()
print('\tSearching Virustotal results.')
print('\tSearching results.')
discovery/wfuzz_search.py
+1 -1
View File
@@ -14,7 +14,7 @@ class search_wfuzz:
def do_search(self):
print('elo')
try:
for r in wfuzz.fuzz(url="https://"+self.host+"/FUZZ", hc=[404], payloads=[("file", dict(fn="wordlists/general/common.txt"))]):
for r in wfuzz.fuzz(url='https://'+self.host+'/FUZZ', hc=[404], payloads=[('file', dict(fn='wordlists/general/common.txt'))]):
print(r)
self.results += r
except Exception as e:
discovery/yahoosearch.py
+4 -5
View File
@@ -10,14 +10,13 @@ class search_yahoo:
def __init__(self, word, limit):
self.word = word
self.total_results = ""
self.server = "search.yahoo.com"
self.hostname = "search.yahoo.com"
self.server = 'search.yahoo.com'
self.hostname = 'search.yahoo.com'
self.limit = limit
self.counter = 0
def do_search(self):
url = 'http://' + self.server + "/search?p=\"%40" + self.word \
+ "\"&b=" + str(self.counter) + "&pz=10"
url = 'http://' + self.server + '/search?p=\"%40' + self.word + '\"&b=' + str(self.counter) + '&pz=10'
headers = {
'Host': self.hostname,
'User-agent': Core.get_user_agent()
@@ -29,7 +28,7 @@ class search_yahoo:
while self.counter <= self.limit and self.counter <= 1000:
self.do_search()
time.sleep(getDelay())
print(f'\tSearching {self.counter} results.')
print(f'\tSearching {self.counter} results.')
self.counter += 10
def get_emails(self):
discovery/yandexsearch.py
+6 -6
View File
@@ -12,13 +12,13 @@ class search_yandex:
self.word = word
self.results = ""
self.totalresults = ""
self.server = "yandex.com"
self.hostname = "yandex.com"
self.server = 'yandex.com'
self.hostname = 'yandex.com'
self.limit = limit
self.counter = start
def do_search(self):
url = 'http://' + self.server + "/search?text=%40" + self.word + "&numdoc=50&lr=" + str(self.counter)
url = 'http://' + self.server + '/search?text=%40' + self.word + '&numdoc=50&lr=' + str(self.counter)
headers = {
'Host': self.hostname,
'User-agent': Core.get_user_agent()
@@ -29,7 +29,7 @@ class search_yandex:
print(self.results)
def do_search_files(self, files): # TODO
url = 'http://' + self.server + "/search?text=%40" + self.word + "&numdoc=50&lr=" + str(self.counter)
url = 'http://' + self.server + '/search?text=%40' + self.word + '&numdoc=50&lr=' + str(self.counter)
headers = {
'Host': self.hostname,
'User-agent': Core.get_user_agent()
@@ -42,10 +42,10 @@ class search_yandex:
renext = re.compile('topNextUrl')
nextres = renext.findall(self.results)
if nextres != []:
nexty = "1"
nexty = '1'
print(str(self.counter))
else:
nexty = "0"
nexty = '0'
return nexty
def get_emails(self):
lib/core.py
+4 -8
View File
@@ -1,11 +1,6 @@
# coding=utf-8
#from discovery import *
# from lib import stash
import os
import random
# import re
import sys
import yaml
@@ -49,7 +44,7 @@ class Core:
print("* | |_| | | | __/ / __ / (_| | | \ V / __/\__ \ || __/ | *")
print("* \__|_| |_|\___| \/ /_/ \__,_|_| \_/ \___||___/\__\___|_| *")
print('* *')
print('* theHarvester 3.0.6 v206 *')
print('* theHarvester 3.0.6 v213 *')
print('* Coded by Christian Martorella *')
print('* Edge-Security Research *')
print('* cmartorella@edge-security.com *')
@@ -321,8 +316,9 @@ class Core:
return random.choice(user_agents)
# TODO use this method when -b all is called to replace lines 383-635 in theHarvester.py
# TODO and to find the best approch of getting the
# word, limit and start etc vars from the arguments and importing libs that are needed
# TODO and to find the best approach of getting the word, limit, and start etc vars from
# the arguments and importing libs that are needed.
#
# @staticmethod
# def engine_all_search():
# print(('Full harvest on ' + word))
requirements.txt
+1 -1
View File
@@ -1,7 +1,7 @@
beautifulsoup4>=4.7.1
plotly>=3.5.0
PyYaml==3.13
pytest>=4.1.1
PyYaml==3.13
requests>=2.21.0
shodan>=1.10.0
texttable>=1.6.0
theHarvester.py
+12 -20
View File
@@ -14,6 +14,7 @@ import datetime
import ipaddress
import re
import time
import sys
try:
import bs4
@@ -80,7 +81,7 @@ def start():
word = args.domain
engines = set(args.source.split(','))
if set(engines).issubset(Core.get_supportedengines()):
print(f'\033[94m[*] Target domain: {word} \n \033[0m')
print(f'\033[94m[*] Target: {word} \n \033[0m')
for engineitem in engines:
if engineitem == 'baidu':
print('\033[94m[*] Searching Baidu. \033[0m')
@@ -656,7 +657,7 @@ def start():
else:
print('\n[*] IPs found: ' + str(len(all_ip)))
print('-------------------')
ips = sorted(ipaddress.ip_address(line.strip()) for line in all_ip)
ips = sorted(ipaddress.ip_address(line.strip()) for line in set(all_ip))
print('\n'.join(map(str, ips)))
if len(all_emails) == 0:
@@ -669,8 +670,8 @@ def start():
if len(all_hosts) == 0:
print('\n[*] No hosts found.\n\n')
else:
print('\n[*] Hosts found: ' + str(len(all_hosts)))
print('---------------------')
print('\n[*] Resolving hosts found: ' + str(len(all_hosts)))
print('-------------------------------')
all_hosts = sorted(list(set(all_hosts)))
full_host = hostchecker.Checker(all_hosts)
full = full_host.check()
@@ -748,7 +749,7 @@ def start():
s = '.'
range = s.join(range)
if not analyzed_ranges.count(range):
print('[*] Performing reverse lookup in ' + range)
print('[*] Performing a reverse lookup on ' + range)
a = dnssearch.dns_reverse(range, True)
a.list()
res = a.process()
@@ -760,8 +761,8 @@ def start():
dnsrev.append(x)
if x not in full:
full.append(x)
print('Hosts found after reverse lookup (in target domain):')
print('----------------------------------------------------')
print('[*] Hosts found after reverse lookup:')
print('-------------------------------------')
for xh in dnsrev:
print(xh)
@@ -819,7 +820,7 @@ def start():
time.sleep(2)
tab.add_row(rowdata)
printedtable = tab.draw()
print('\n [*] Shodan results:')
print('\n[*] Shodan results:')
print('-------------------')
print(printedtable)
except Exception as e:
@@ -873,20 +874,11 @@ def start():
Html_file.close()
print('NEW REPORTING FINISHED!')
print('[*] Saving files.')
html = htmlExport.htmlExport(
all_emails,
full,
vhost,
dnsres,
dnsrev,
filename,
word,
shodanres,
dnstldres)
html = htmlExport.htmlExport(all_emails, full, vhost, dnsres, dnsrev, filename, word, shodanres, dnstldres)
save = html.writehtml()
except Exception as e:
print(e)
print('Error creating the file.')
print('[!] Error creating the file.')
try:
filename = filename.split('.')[0] + '.xml'
file = open(filename, 'w')
@@ -944,7 +936,7 @@ if __name__ == '__main__':
try:
start()
except KeyboardInterrupt:
print('\n\n\033[93m[!] ctrl+c detected from user, quitting.\n\n \033[0m')
print('\n\n\033[93m[!] ctrl+c detected, stopping program.\n\n \033[0m')
except Exception:
import traceback
print(traceback.print_exc())