There doesn’t seem to be a (simple) way to terminate a thread in Python.
Here is a simple example of running multiple HTTP requests in parallel:
import threading
def crawl():
import urllib2
data = urllib2.urlopen("http://www.google.com/").read()
print "Read google.com"
threads = []
for n in range(10):
thread = threading.Thread(target=crawl)
thread.start()
threads.append(thread)
# to wait until all three functions are finished
print "Waiting..."
for thread in threads:
thread.join()
print "Complete."
With additional overhead, you can use a multi-process aproach that’s more powerful and allows you to terminate thread-like processes.
I’ve extended the example to use that. I hope this will be helpful to you:
import multiprocessing
def crawl(result_queue):
import urllib2
data = urllib2.urlopen("http://news.ycombinator.com/").read()
print "Requested..."
if "result found (for example)":
result_queue.put("result!")
print "Read site."
processs = []
result_queue = multiprocessing.Queue()
for n in range(4): # start 4 processes crawling for the result
process = multiprocessing.Process(target=crawl, args=[result_queue])
process.start()
processs.append(process)
print "Waiting for result..."
result = result_queue.get() # waits until any of the proccess have `.put()` a result
for process in processs: # then kill them all off
process.terminate()
print "Got result:", result