check_url_status.py

# -*- coding: utf-8 -*-


from twisted.internet import reactor
from twisted.web import client
from twisted.internet.defer import DeferredList


def check_url(url, status_handler):
    def _page_fail(reason):
        status_handler(url, False)

    def _page_ok(data):
        status_handler(url, True)

    def _handle_page(data):
        if factory.status == '200':
            return _page_ok(data)
        return _page_fail(factory.status)

    scheme, host, port, path = client._parse(url)
    factory = client.HTTPClientFactory(url, method='HEAD')
    reactor.connectTCP(host, port, factory)
    factory.deferred.addCallback(_handle_page).addErrback(_page_fail)
    return factory.deferred


def printer(url, status):
    print status, url

def main():
    urls = [
        'http://google.pl',
        'http://does_not_exist.foo.bar.com',
        ]
    deferreds = [check_url(url, printer) for url in urls]
    DeferredList(deferreds).addCallback(lambda x: reactor.stop())
    reactor.run()


if __name__ == '__main__':
    main()