WEBDIENSTE/theHarvester
1
0
Fork 0
mirror of https://github.com/laramies/theHarvester.git synced 2026-08-17 19:35:40 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #107 from NotoriousRebel/master

Browse Source 
Modified discovery/crtsh.py to properly do searches.
This commit is contained in:
Christian Martorella
2018-11-29 22:24:51 +01:00
committed by GitHub
parent 05feda73e7 fcbca16ab1
commit eae4fe5927
3 changed files with 55 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
discovery/crtsh.py
+52 -9
View File
@@ -1,5 +1,7 @@
import requests
import myparser
import time
import random
class search_crtsh:
@@ -7,28 +9,69 @@ class search_crtsh:
self.word = word.replace(' ', '%20')
self.results = ""
self.totalresults = ""
self.server = "www.google.com"
self.hostname = "www.google.com"
self.userAgent = "(Mozilla/5.0 (Windows; U; Windows NT 6.0;en-US; rv:1.9.2) Gecko/20100116 Firefox/3.7"
self.server = "https://crt.sh/?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"),
"Mozilla/5.0 (SMART-TV; X11; Linux armv7l) AppleWebKit/537.42 (KHTML, like Gecko) Chromium/25.0.1349.2 Chrome/25.0.1349.2 Safari/537.42",
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36 OPR/43.0.2442.991",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36 OPR/48.0.2685.52",
"Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko",
"Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko",
"Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/6.0)"]
self.quantity = "100"
self.counter = 0
def do_search(self):
try:
urly = "https://crt.sh/?q=%25" + self.word
urly = self.server + self.word
except Exception as e:
print(e)
headers = {'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:34.0) Gecko/20100101 Firefox/34.0'}
try:
r=requests.get(urly,headers=headers)
params = {'User-Agent': random.choice(self.userAgent)}
r=requests.get(urly,headers=params)
except Exception as e:
print(e)
self.results = r.text
self.totalresults += self.results
links = self.get_info(r.text)
for link in links:
params = {'User-Agent': random.choice(self.userAgent)}
r = requests.get(link, headers=params)
time.sleep(1)
self.results = r.text
self.totalresults += self.results
"""
Function goes through text from base request and parses it for links
@param text requests text
@return list of links
"""
def get_info(self,text):
lines = []
for line in str(text).splitlines():
line = line.strip()
if 'id=' in line:
lines.append(line)
links = []
for i in range(len(lines)):
if i % 2 == 0: #way html is formatted only care about every other one
current = lines[i]
current = current[43:] #43 is not an arbitrary number, the id number always starts at 43rd index
link = ''
for ch in current:
if ch == '"':
break
else:
link += ch
links.append(('https://crt.sh?id=' + str(link)))
return links
def get_hostnames(self):
rawres = myparser.parser(self.results, self.word)
rawres = myparser.parser(self.totalresults, self.word)
return rawres.hostnames()
def process(self):
myparser.py
-1
View File
@@ -1,4 +1,3 @@
import string
import re
theHarvester.py
+3 -3
View File
@@ -356,13 +356,13 @@ def start(argv):
db.store_all(word,all_hosts,'host','threatcrowd')
except Exception: pass
"""print("[-] Searching in CRTSH server..")
print("[-] Searching in CRTSH server..")
search = crtsh.search_crtsh(word)
search.process()
hosts = search.get_hostnames()
all_hosts.extend(hosts)
db=stash.stash_manager()
db.store_all(word,all_hosts,'host','CRTsh')"""
db.store_all(word,all_hosts,'host','CRTsh')
print("[-] Searching in Virustotal server..")
search = virustotal.search_virustotal(word)
@@ -416,7 +416,7 @@ def start(argv):
# pass
#Results############################################################
print("\n\033[1;32;40m Harvesting results")
print("\n\033[1;32;40mHarvesting results")
print("\n\n[+] Emails found:")
print("------------------")