mirror of
https://github.com/laramies/theHarvester.git
synced 2024-09-22 08:16:35 +08:00
45 lines
1.3 KiB
Python
45 lines
1.3 KiB
Python
import httplib
|
|
import myparser
|
|
import time
|
|
import sys
|
|
|
|
|
|
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.userAgent = "(Mozilla/5.0 (Windows; U; Windows NT 6.0;en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6"
|
|
self.limit = limit
|
|
self.counter = 0
|
|
|
|
def do_search(self):
|
|
h = httplib.HTTP(self.server)
|
|
|
|
h.putrequest('GET', "/search?p=\"%40" + self.word
|
|
+ "\"&b=" + str(self.counter) + "&pz=10")
|
|
h.putheader('Host', self.hostname)
|
|
h.putheader('User-agent', self.userAgent)
|
|
h.endheaders()
|
|
returncode, returnmsg, headers = h.getreply()
|
|
|
|
self.total_results += h.getfile().read()
|
|
|
|
def process(self):
|
|
while self.counter <= self.limit and self.counter <= 1000:
|
|
self.do_search()
|
|
time.sleep(1)
|
|
|
|
print "\tSearching " + str(self.counter) + " results..."
|
|
self.counter += 10
|
|
|
|
def get_emails(self):
|
|
rawres = myparser.parser(self.total_results, self.word)
|
|
return rawres.emails()
|
|
|
|
def get_hostnames(self):
|
|
rawres = myparser.parser(self.total_results, self.word)
|
|
return rawres.hostnames()
|