Example #1
0
 def __init__(self, restart, browser, ext_port, proxy_file, proxy_scheme, 
              log_q):
     self.restart = restart
     self.browser_name = browser
     self.browser_inst = None
     if self.browser_name == 'Firefox':
         self.__class__ = FirefoxCrawlerProcess
         # May want to just ignore ext_port for other browsers.
         self.ext_port = ext_port 
     self.logger = mplogging.setupSubProcessLogger("Crawler", log_q)
     self.proxy = Proxy(proxy_file, proxy_scheme, self.logger)
     # To make sure the process doesn't take more than 15 min to complete
     #     a single visit. Kill the process if it does.
     signal.signal(signal.SIGALRM, self.alarm_handler)
     # We would like to restart browser every so many visits.
     self.num_visits = 0
Example #2
0
 def __init__(self, restart, browser, ext_port, proxy_file, proxy_scheme,
              log_q):
     self.restart = restart
     self.browser_name = browser
     self.browser_inst = None
     if self.browser_name == 'Firefox':
         self.__class__ = FirefoxCrawlerProcess
         # May want to just ignore ext_port for other browsers.
         self.ext_port = ext_port
     self.logger = mplogging.setupSubProcessLogger("Crawler", log_q)
     self.proxy = Proxy(proxy_file, proxy_scheme, self.logger)
     # To make sure the process doesn't take more than 15 min to complete
     #     a single visit. Kill the process if it does.
     signal.signal(signal.SIGALRM, self.alarm_handler)
     # We would like to restart browser every so many visits.
     self.num_visits = 0
Example #3
0
 def __init__(self, log_q):
     """log_q is the multiprocessing queue that we place records on for
     logging. These are processed by LogQueueReader thread in mplogging.
     """
     self.cleanup = False
     self.logger = mplogging.setupSubProcessLogger("QController", log_q)