mirror of
https://github.com/laramies/theHarvester.git
synced 2026-09-22 17:44:57 +02:00
Moved search method to constants.py also made it so it notifies user if google is blocking incoming requests, added search method to trello.
This commit is contained in:
+12
-1
@@ -237,12 +237,23 @@ user_agents = [
|
||||
"Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
|
||||
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.19 (KHTML, like Gecko) Ubuntu/11.10 Chromium/18.0.1025.142 Chrome/18.0.1025.142 Safari/535.19",
|
||||
"Mozilla/5.0 (Windows NT 5.1; U; de; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6 Opera 11.00"
|
||||
]
|
||||
]
|
||||
|
||||
googleUA = "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36"
|
||||
|
||||
|
||||
def getDelay():
|
||||
return random.randint(1, 3) - .5
|
||||
|
||||
|
||||
def getUserAgent():
|
||||
return random.choice(user_agents)
|
||||
|
||||
|
||||
def search(text):
|
||||
# helper function to check if google has blocked traffic
|
||||
for line in text.strip().splitlines():
|
||||
if 'This page appears when Google automatically detects requests coming from your computer network' in line:
|
||||
print('\tGoogle is blocking your iP due too many automated request, wait or change your IP')
|
||||
return True
|
||||
return False
|
||||
|
||||
@@ -3,6 +3,7 @@ import time
|
||||
import requests
|
||||
from discovery.constants import *
|
||||
|
||||
|
||||
class search_google:
|
||||
|
||||
def __init__(self, word, limit, start):
|
||||
@@ -29,7 +30,7 @@ class search_google:
|
||||
except Exception as e:
|
||||
print(e)
|
||||
self.results = r.text
|
||||
if (self.search(self.results)):
|
||||
if (search(self.results)):
|
||||
time.sleep(getDelay() * 5) # sleep for a longer time
|
||||
else:
|
||||
time.sleep(getDelay())
|
||||
@@ -47,7 +48,7 @@ class search_google:
|
||||
except Exception as e:
|
||||
print(e)
|
||||
self.results = r.text
|
||||
if (self.search(self.results)):
|
||||
if (search(self.results)):
|
||||
time.sleep(getDelay() * 5) # sleep for a longer time
|
||||
else:
|
||||
time.sleep(getDelay())
|
||||
@@ -73,8 +74,6 @@ class search_google:
|
||||
if google_dorking == False:
|
||||
while self.counter <= self.limit and self.counter <= 1000:
|
||||
self.do_search()
|
||||
#more = self.check_next()
|
||||
time.sleep(1.5)
|
||||
print("\tSearching " + str(self.counter) + " results...")
|
||||
self.counter += 100
|
||||
else: # google dorking is true
|
||||
@@ -143,17 +142,10 @@ class search_google:
|
||||
link = self.links[i] # get link from dork list
|
||||
req = requests.get(link, headers=headers)
|
||||
self.results = req.text
|
||||
if (self.search(self.results)):
|
||||
if (search(self.results)):
|
||||
time.sleep(getDelay() * 5) # sleep for a longer time
|
||||
else:
|
||||
time.sleep(getDelay())
|
||||
self.totalresults += self.results
|
||||
except:
|
||||
continue
|
||||
|
||||
def search(self, text):
|
||||
# helper function to check if google has blocked traffic
|
||||
for line in text.strip().splitlines():
|
||||
if 'This page appears when Google automatically detects requests coming from your computer network' in line:
|
||||
return True
|
||||
return False
|
||||
|
||||
+4
-1
@@ -53,6 +53,9 @@ class search_trello:
|
||||
def process(self):
|
||||
while (self.counter < self.limit):
|
||||
self.do_search()
|
||||
time.sleep(getDelay())
|
||||
if search(self.results):
|
||||
time.sleep(getDelay() * 5)
|
||||
else:
|
||||
time.sleep(getDelay())
|
||||
self.counter += 100
|
||||
print("\tSearching " + str(self.counter) + " results..")
|
||||
|
||||
Reference in New Issue
Block a user