Question

有没有办法在Spider类终止之前触发它？

我可以自己终止蜘蛛，就像这样：

class MySpider(CrawlSpider):
    #Config stuff goes here...

    def quit(self):
        #Do some stuff...
        raise CloseSpider('MySpider is quitting now.')

    def my_parser(self, response):
        if termination_condition:
            self.quit()

        #Parsing stuff goes here...

但我找不到任何关于如何确定蜘蛛何时会自然戒烟的信息。

Answer 1

看起来您可以通过dispatcher注册信号监听器。

我会尝试类似的事情：

from scrapy import signals
from scrapy.xlib.pydispatch import dispatcher

class MySpider(CrawlSpider):
    def __init__(self):
        dispatcher.connect(self.spider_closed, signals.spider_closed)

    def spider_closed(self, spider):
      # second param is instance of spder about to be closed.

Answer 2

只是为了更新，你可以像这样调用closed函数：

class MySpider(CrawlSpider):
    def closed(self, reason):
        do-something()

Answer 3

对于Scrapy版本 1.0.0 + （它也适用于旧版本）。

from scrapy import signals

class MySpider(CrawlSpider):
    name = 'myspider'

    @classmethod
    def from_crawler(cls, crawler, *args, **kwargs):
        spider = super(MySpider, cls).from_crawler(crawler, *args, **kwargs)
        crawler.signals.connect(spider.spider_opened, signals.spider_opened)
        crawler.signals.connect(spider.spider_closed, signals.spider_closed)
        return spider

    def spider_opened(self, spider):
        print('Opening {} spider'.format(spider.name))

    def spider_closed(self, spider):
        print('Closing {} spider'.format(spider.name))

一个很好的用法是将tqdm进度条添加到scrapy spider。

# -*- coding: utf-8 -*-
from scrapy import signals
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from tqdm import tqdm


class MySpider(CrawlSpider):
    name = 'myspider'
    allowed_domains = ['somedomain.comm']
    start_urls = ['http://www.somedomain.comm/ccid.php']

    rules = (
        Rule(LinkExtractor(allow=r'^http://www.somedomain.comm/ccds.php\?id=.*'),
             callback='parse_item',
             ),
        Rule(LinkExtractor(allow=r'^http://www.somedomain.comm/ccid.php$',
                           restrict_xpaths='//table/tr[contains(., "SMTH")]'), follow=True),
    )

    def parse_item(self, response):
        self.pbar.update()  # update progress bar by 1
        item = MyItem()
        # parse response
        return item

    @classmethod
    def from_crawler(cls, crawler, *args, **kwargs):
        spider = super(MySpider, cls).from_crawler(crawler, *args, **kwargs)
        crawler.signals.connect(spider.spider_opened, signals.spider_opened)
        crawler.signals.connect(spider.spider_closed, signals.spider_closed)
        return spider

    def spider_opened(self, spider):
        self.pbar = tqdm()  # initialize progress bar
        self.pbar.clear()
        self.pbar.write('Opening {} spider'.format(spider.name))

    def spider_closed(self, spider):
        self.pbar.clear()
        self.pbar.write('Closing {} spider'.format(spider.name))
        self.pbar.close()  # close progress bar

Answer 4

对我来说，接受的不起作用/至少对scrapy 0.19来说已经过时了。我得到它与以下工作：

from scrapy.signalmanager import SignalManager
from scrapy.xlib.pydispatch import dispatcher

class MySpider(CrawlSpider):
    def __init__(self, *args, **kwargs):
        super(MySpider, self).__init__(*args, **kwargs)
        SignalManager(dispatcher.Any).connect(
            self.closed_handler, signal=signals.spider_closed)

    def closed_handler(self, spider):
        # do stuff here

Answer 5

对于最新版本（v1.7），只需在蜘蛛类中定义<img srcset="tiger-320w.jpg 320w, tiger-480w.jpg 480w, tiger-800w.jpg 800w" sizes="(max-width: 320px) 280px, (max-width: 480px) 440px, 800px" src="tiger-800w.jpg" alt="Bengal tiger">方法即可。

closed(reason)：

在蜘蛛关闭时调用。此方法提供了一个快捷方式   signal.connect（）代表蜘蛛关闭信号。

Scrapy Doc : scrapy.spiders.Spider.closed

Answer 6

如果你有很多蜘蛛，想要在每个蜘蛛关闭之前做点什么，也许在你的项目中添加statscollector会很方便。

设置中的

：

STATS_CLASS = 'scraper.stats.MyStatsCollector'

和收藏家：

from scrapy.statscollectors import StatsCollector

class MyStatsCollector(StatsCollector):
    def _persist_stats(self, stats, spider):
        do something here

scrapy：当蜘蛛退出时调用一个函数

6 个答案: