View difference between Paste ID: 12rLXQaz and J4Rd3NhA
SHOW: | | - or go back to the newest paste.
1
import re,requests,string,random,threading,os,inspect,gc,pdb,urllib2,urllib
2
def load(filename):
3
    with open(filename) as f:
4
        return [line.rstrip() for line in f]
5
def getpage():
6
    try:
7
        curl = urls.pop(0)
8
        print "working on " +str(curl)
9
        thepage1 = requests.get(curl).text
10
        global ctot
11
        if "Contact Us" in thepage1:
12
            slist.write("\n" +curl)
13
            ctot = ctot + 1
14
    except:
15
        pass
16
    finally:
17
        if len(urls)>0 :
18
            getpage()       
19
urls = load('res\urls.txt')
20
slist = open('res\output.txt', 'a+')
21
totallinks = len(urls)
22
global ctot
23
ctot = 0
24
tarray=[]
25
noofthreads = input("Enter the Number of Threads : ")
26
tout = input("Enter TimeOut Value : ")
27
if (totallinks<noofthreads) :
28
    noofthreads = totallinks
29
if totallinks>0 :
30
    for xd in range(0,noofthreads):
31
        t = threading.Thread(target=getpage)
32
        t.daemon = True
33
        t.start()
34
        tarray.append(t)
35
for t in tarray:
36
    t.join()
37
slist.close()
38
print "Program Completed Its Execution"
39
raw_input("Press ENTER to Exit the Program")