mirror of
https://github.com/laramies/theHarvester.git
synced 2024-11-12 02:16:59 +08:00
58 lines
2 KiB
Python
58 lines
2 KiB
Python
import requests
|
|
import myparser
|
|
from discovery.constants import *
|
|
import time
|
|
|
|
class search_trello:
|
|
|
|
def __init__(self, word, limit):
|
|
self.word = word.replace(' ', '%20')
|
|
self.results = ""
|
|
self.totalresults = ""
|
|
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&meta=&q=site%3Atrello.com%20" + self.word
|
|
except Exception as e:
|
|
print(e)
|
|
headers = {'User-Agent': googleUA}
|
|
try:
|
|
r = requests.get(urly, headers=headers)
|
|
time.sleep(getDelay())
|
|
except Exception as e:
|
|
print(e)
|
|
self.results = r.text
|
|
self.totalresults += self.results
|
|
|
|
def get_emails(self):
|
|
rawres = myparser.parser(self.totalresults, self.word)
|
|
return rawres.emails()
|
|
|
|
def get_urls(self):
|
|
print('\tSearching Trello Urls..')
|
|
try:
|
|
rawres = myparser.parser(self.totalresults, "trello.com")
|
|
trello_urls = rawres.urls()
|
|
visited = set()
|
|
for url in trello_urls:
|
|
# iterate through trello urls gathered and visit them, append text to totalresults
|
|
if url not in visited: # make sure visiting unique urls
|
|
visited.add(url)
|
|
self.totalresults += requests.get(url=url, headers={'User-Agent': googleUA}).text
|
|
rawres = myparser.parser(self.totalresults, self.word)
|
|
return rawres.hostnames(), trello_urls
|
|
except Exception as e:
|
|
print("Error occurred: " + str(e))
|
|
|
|
def process(self):
|
|
while (self.counter < self.limit):
|
|
self.do_search()
|
|
time.sleep(getDelay())
|
|
self.counter += 100
|
|
print("\tSearching " + str(self.counter) + " results..")
|