Python Scraper.is_idle方法代码示例

# 需要导入模块: from scrapy.core.scraper import Scraper [as 别名]
# 或者: from scrapy.core.scraper.Scraper import is_idle [as 别名]
class ExecutionEngine(object):

    def __init__(self):
        self.configured = False
        self.closing = {} # dict (spider -> reason) of spiders being closed
        self.running = False
        self.killed = False
        self.paused = False
        self._next_request_calls = {}
        self._crawled_logline = load_object(settings['LOG_FORMATTER_CRAWLED'])

    def configure(self, spider_closed_callback):
        """
        Configure execution engine with the given scheduling policy and downloader.
        """
        self.scheduler = load_object(settings['SCHEDULER'])()
        self.downloader = Downloader()
        self.scraper = Scraper(self)
        self.configured = True
        self._spider_closed_callback = spider_closed_callback

    def start(self):
        """Start the execution engine"""
        assert not self.running, "Engine already running"
        self.start_time = time()
        send_catch_log(signal=signals.engine_started, sender=self.__class__)
        self.running = True

    def stop(self):
        """Stop the execution engine gracefully"""
        assert self.running, "Engine not running"
        self.running = False
        dfd = self._close_all_spiders()
        return dfd.addBoth(lambda _: self._finish_stopping_engine())

    def kill(self):
        """Forces shutdown without waiting for pending transfers to finish.
        stop() must have been called first
        """
        assert not self.running, "Call engine.stop() before engine.kill()"
        self.killed = True

    def pause(self):
        """Pause the execution engine"""
        self.paused = True

    def unpause(self):
        """Resume the execution engine"""
        self.paused = False

    def is_idle(self):
        return self.scheduler.is_idle() and self.downloader.is_idle() and \
            self.scraper.is_idle()

    def next_request(self, spider, now=False):
        """Scrape the next request for the spider passed.

        The next request to be scraped is retrieved from the scheduler and
        requested from the downloader.

        The spider is closed if there are no more pages to scrape.
        """
        if now:
            self._next_request_calls.pop(spider, None)
        elif spider not in self._next_request_calls:
            call = reactor.callLater(0, self.next_request, spider, now=True)
            self._next_request_calls[spider] = call
            return call
        else:
            return

        if self.paused:
            return reactor.callLater(5, self.next_request, spider)

        while not self._needs_backout(spider):
            if not self._next_request(spider):
                break

        if self.spider_is_idle(spider):
            self._spider_idle(spider)

    def _needs_backout(self, spider):
        return not self.running \
            or self.spider_is_closed(spider) \
            or self.downloader.sites[spider].needs_backout() \
            or self.scraper.sites[spider].needs_backout()

    def _next_request(self, spider):
        # Next pending request from scheduler
        request, deferred = self.scheduler.next_request(spider)
        if request:
            dwld = mustbe_deferred(self.download, request, spider)
            dwld.chainDeferred(deferred).addBoth(lambda _: deferred)
            dwld.addErrback(log.err, "Unhandled error on engine._next_request()",
                spider=spider)
            return dwld

    def spider_is_idle(self, spider):
        scraper_idle = spider in self.scraper.sites \
            and self.scraper.sites[spider].is_idle()
#.........这里部分代码省略.........

# 需要导入模块: from scrapy.core.scraper import Scraper [as 别名]
# 或者: from scrapy.core.scraper.Scraper import is_idle [as 别名]
class ExecutionEngine(object):

    def __init__(self, settings, spider_closed_callback):
        self.settings = settings
        self.closing = {} # dict (spider -> reason) of spiders being closed
        self.closing_dfds = {} # dict (spider -> deferred) of spiders being closed
        self.running = False
        self.paused = False
        self._next_request_calls = {}
        self.scheduler = load_object(settings['SCHEDULER'])()
        self.downloader = Downloader()
        self.scraper = Scraper(self, self.settings)
        self._spider_closed_callback = spider_closed_callback

    @defer.inlineCallbacks
    def start(self):
        """Start the execution engine"""
        assert not self.running, "Engine already running"
        self.start_time = time()
        yield send_catch_log_deferred(signal=signals.engine_started)
        self.running = True

    def stop(self):
        """Stop the execution engine gracefully"""
        assert self.running, "Engine not running"
        self.running = False
        dfd = self._close_all_spiders()
        return dfd.addBoth(lambda _: self._finish_stopping_engine())

    def pause(self):
        """Pause the execution engine"""
        self.paused = True

    def unpause(self):
        """Resume the execution engine"""
        self.paused = False

    def is_idle(self):
        return self.scheduler.is_idle() and self.downloader.is_idle() and \
            self.scraper.is_idle()

    def next_request(self, spider, now=False):
        """Scrape the next request for the spider passed.

        The next request to be scraped is retrieved from the scheduler and
        requested from the downloader.

        The spider is closed if there are no more pages to scrape.
        """
        if now:
            self._next_request_calls.pop(spider, None)
        elif spider not in self._next_request_calls:
            call = reactor.callLater(0, self.next_request, spider, now=True)
            self._next_request_calls[spider] = call
            return call
        else:
            return

        if self.paused:
            return reactor.callLater(5, self.next_request, spider)

        while not self._needs_backout(spider):
            if not self._next_request(spider):
                break

        if self.spider_is_idle(spider):
            self._spider_idle(spider)

    def _needs_backout(self, spider):
        return not self.running \
            or self.spider_is_closed(spider) \
            or self.downloader.sites[spider].needs_backout() \
            or self.scraper.sites[spider].needs_backout()

    def _next_request(self, spider):
        # Next pending request from scheduler
        request, deferred = self.scheduler.next_request(spider)
        if request:
            dwld = mustbe_deferred(self.download, request, spider)
            dwld.chainDeferred(deferred).addBoth(lambda _: deferred)
            dwld.addErrback(log.err, "Unhandled error on engine._next_request()",
                spider=spider)
            return dwld

    def spider_is_idle(self, spider):
        scraper_idle = spider in self.scraper.sites \
            and self.scraper.sites[spider].is_idle()
        pending = self.scheduler.spider_has_pending_requests(spider)
        downloading = spider in self.downloader.sites \
            and self.downloader.sites[spider].active
        return scraper_idle and not (pending or downloading)

    def spider_is_closed(self, spider):
        """Return True if the spider is fully closed (ie. not even in the
        closing stage)"""
        return spider not in self.downloader.sites

    def spider_is_open(self, spider):
        """Return True if the spider is fully opened (ie. not in closing
        stage)"""
#.........这里部分代码省略.........

# 需要导入模块: from scrapy.core.scraper import Scraper [as 别名]
# 或者: from scrapy.core.scraper.Scraper import is_idle [as 别名]
class ExecutionEngine(object):

    def __init__(self, settings, spider_closed_callback):
        self.settings = settings
        self.slots = {}
        self.running = False
        self.paused = False
        self._next_request_calls = {}
        self.scheduler = load_object(settings['SCHEDULER'])()
        self.downloader = Downloader()
        self.scraper = Scraper(self, self.settings)
        self._spider_closed_callback = spider_closed_callback

    @defer.inlineCallbacks
    def start(self):
        """Start the execution engine"""
        assert not self.running, "Engine already running"
        self.start_time = time()
        yield send_catch_log_deferred(signal=signals.engine_started)
        self.running = True

    def stop(self):
        """Stop the execution engine gracefully"""
        assert self.running, "Engine not running"
        self.running = False
        dfd = self._close_all_spiders()
        return dfd.addBoth(lambda _: self._finish_stopping_engine())

    def pause(self):
        """Pause the execution engine"""
        self.paused = True

    def unpause(self):
        """Resume the execution engine"""
        self.paused = False

    def is_idle(self):
        return self.scheduler.is_idle() and self.downloader.is_idle() and \
            self.scraper.is_idle()

    def next_request(self, spider, now=False):
        """Scrape the next request for the spider passed.

        The next request to be scraped is retrieved from the scheduler and
        requested from the downloader.

        The spider is closed if there are no more pages to scrape.
        """
        if now:
            self._next_request_calls.pop(spider, None)
        elif spider not in self._next_request_calls:
            call = reactor.callLater(0, self.next_request, spider, now=True)
            self._next_request_calls[spider] = call
            return call
        else:
            return

        if self.paused:
            return reactor.callLater(5, self.next_request, spider)

        while not self._needs_backout(spider):
            if not self._next_request(spider):
                break

        if self.spider_is_idle(spider):
            self._spider_idle(spider)

    def _needs_backout(self, spider):
        slot = self.slots[spider]
        return not self.running \
            or slot.closing \
            or self.spider_is_closed(spider) \
            or self.downloader.sites[spider].needs_backout() \
            or self.scraper.sites[spider].needs_backout()

    def _next_request(self, spider):
        request = self.scheduler.next_request(spider)
        if not request:
            return
        d = self._download(request, spider)
        d.addBoth(self._handle_downloader_output, request, spider)
        d.addErrback(log.msg, spider=spider)
        slot = self.slots[spider]
        d.addBoth(lambda _: slot.remove_request(request))
        d.addErrback(log.msg, spider=spider)
        d.addBoth(lambda _: self.next_request(spider))
        return d

    def _handle_downloader_output(self, response, request, spider):
        assert isinstance(response, (Request, Response, Failure)), response
        # downloader middleware can return requests (for example, redirects)
        if isinstance(response, Request):
            self.crawl(response, spider)
            return
        # response is a Response or Failure
        d = defer.Deferred()
        d.addBoth(self.scraper.enqueue_scrape, request, spider)
        d.addErrback(log.err, spider=spider)
        if isinstance(response, Failure):
            d.errback(response)
#.........这里部分代码省略.........