Last active
December 17, 2015 23:59
-
-
Save mdeous/5693631 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env python | |
| # -*- coding: utf-8 -*- | |
| import sys | |
| from threading import Thread | |
| from Queue import Empty, Queue | |
| from urlparse import urlparse | |
| todo = Queue() | |
| done = Queue() | |
| incoming_data = True | |
| finished_processing = False | |
| class Parsing(Thread): | |
| def __init__(self, queue): | |
| self.queue = queue | |
| super(Parsing, self).__init__() | |
| def run(self): | |
| global finished_processing | |
| while incoming_data or not todo.empty(): | |
| try: | |
| url = todo.get_nowait() | |
| except Empty: | |
| continue | |
| parsed = urlparse(url) | |
| done.put(parsed.netloc) | |
| finished_processing = True | |
| class Storage(Thread): | |
| def __init__(self, queue, outfile): | |
| self.queue = queue | |
| self.outfile = outfile | |
| super(Storage, self).__init__() | |
| def run(self): | |
| with open(self.outfile, 'w') as of: | |
| while not finished_processing or not done.empty(): | |
| try: | |
| data = done.get_nowait() | |
| except Empty: | |
| continue | |
| of.write(data + '\n') | |
| parser = Parsing(todo) | |
| store = Storage(done, 'output.txt') | |
| parser.start() | |
| store.start() | |
| for line in sys.stdin: | |
| line = line.strip() | |
| if not line: | |
| continue | |
| todo.put(line) | |
| incoming_data = False | |
| parser.join() | |
| store.join() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment