some improvements and fixes to scrapy.service

This commit is contained in:
Pablo Hoffman 2010-06-10 11:51:46 -03:00
parent 6a33d6c4d0
commit 075b59f4af
1 changed files with 37 additions and 29 deletions

View File

@ -1,7 +1,7 @@
import sys, os
from twisted.python import log
from twisted.internet import reactor, protocol, error
from twisted.internet import reactor, defer, protocol, error
from twisted.application.service import Service
from scrapy.utils.py26 import cpu_count
@ -11,50 +11,58 @@ from scrapy.conf import settings
class ScrapyService(Service):
def startService(self):
reactor.callWhenRunning(self.start_processes)
reactor.callWhenRunning(self.spawn_processes)
def start_processes(self):
for i in range(cpu_count()):
self.start_process(i+1)
def spawn_processes(self):
for settings_module, count in settings['PROJECTS'].items():
for i in range(count or cpu_count()):
self.spawn_process(settings_module, i)
def start_process(self, id):
args = [sys.executable, '-m', 'scrapy.service']
def spawn_process(self, settings_module, position):
args = [sys.executable, '-m', 'scrapy.cmdline', 'start']
env = os.environ.copy()
self.set_log_file(env, id)
pp = ScrapyProcessProtocol(self, id, env.get('SCRAPY_LOG_FILE'))
botname = self.get_bot_name(settings_module)
logfile = self.get_log_file(settings_module, position)
env['SCRAPY_SETTINGS_MODULE'] = settings_module
env['SCRAPY_LOG_FILE'] = logfile
pp = ScrapyProcessProtocol(self, botname, settings_module, logfile)
reactor.spawnProcess(pp, sys.executable, args=args, env=env)
pp.deferred.addCallback(self.respawn_process, args, env)
def set_log_file(self, env, suffix):
logfile = settings['LOG_FILE']
if logfile:
file, ext = os.path.splitext(logfile)
env['SCRAPY_LOG_FILE'] = "%s-%s%s" % (file, suffix, ext)
def respawn_process(self, pp, args, env):
reactor.callLater(5, reactor.spawnProcess, pp, sys.executable, \
args=args, env=env)
def get_log_file(self, settings_module, position):
botname = self.get_bot_name(settings_module)
basename = "%s-%s" % (botname, position) if position else botname
return os.path.join(settings['LOG_DIR'], "%s.log" % basename)
def get_bot_name(self, settings_module):
mod = __import__(settings_module, {}, {}, [''], -1)
return mod.BOT_NAME
class ScrapyProcessProtocol(protocol.ProcessProtocol):
def __init__(self, service, id, logfile):
def __init__(self, service, botname, settings_module, logfile):
self.service = service
self.id = id
self.botname = botname
self.settings_module = settings_module
self.logfile = logfile
self.pid = None
self.deferred = defer.Deferred()
def connectionMade(self):
self.pid = self.transport.pid
log.msg("Process %r started: pid=%r logfile=%r" % (self.id, self.pid, \
self.logfile))
log.msg("Crawler %r started: pid=%r settings=%r log=%r" % \
(self.botname, self.pid, self.settings_module, self.logfile))
def processEnded(self, status):
if isinstance(status.value, error.ProcessDone):
log.msg("Process %r finished: pid=%r logfile=%r" % (self.id, \
self.pid, self.logfile))
log.msg("Crawler %r finished: pid=%r settings=%r log=%r" % \
(self.botname, self.pid, self.settings_module, self.logfile))
else:
log.msg("Process %r died: exitstatus=%r pid=%r logfile=%r" % \
(self.id, status.value.exitCode, self.pid, self.logfile))
reactor.callLater(5, self.service.start_process, self.id)
if __name__ == '__main__':
from scrapy.core.manager import scrapymanager
scrapymanager.configure()
scrapymanager.start(keep_alive=True)
log.msg("Crawler %r died: exitstatus=%r pid=%r settings=%r log=%r" % \
(self.botname, status.value.exitCode, self.pid, self.settings_module, \
self.logfile))
self.deferred.callback(self)