Scrapyで処理を中断して例外をスローする

def parse_page(self, response):
    if 'Bandwidth exceeded' in response.body:
        raise CloseSpider('bandwidth_exceeded')

from scrapy.exceptions import DropItem

class PricePipeline:

    vat_factor = 1.15

    def process_item(self, item, spider):
        if item.get('price'):
            if item.get('price_excludes_vat'):
                item['price'] = item['price'] * self.vat_factor
            return item
        else:
            raise DropItem("Missing price in %s" % item)

import scrapy
from scrapy.exceptions import CloseSpider

class QuotesSpider(scrapy.Spider):
    name = "quotes"
    start_urls = [
        'http://quotes.toscrape.com/page/1/',
    ]

    def parse(self, response):
        raise CloseSpider("Force Close!!!!!!")
        for quote in response.css('div.quote'):
            yield {
                'text': quote.css('span.text::text').get(),
                'author': quote.css('small.author::text').get(),
                'tags': quote.css('div.tags a.tag::text').getall(),
            }

        next_page = response.css('li.next a::attr(href)').get()
        if next_page is not None:
            next_page = response.urljoin(next_page)
            yield scrapy.Request(next_page, callback=self.parse)

import scrapy

from scrapy.spidermiddlewares.httperror import HttpError
from twisted.internet.error import DNSLookupError
from twisted.internet.error import TimeoutError, TCPTimedOutError

class ErrbackSpider(scrapy.Spider):
    name = "errback_example"
    start_urls = [
        "http://www.httpbin.org/",              # HTTP 200 expected
        "http://www.httpbin.org/status/404",    # Not found error
        "http://www.httpbin.org/status/500",    # server issue
        "http://www.httpbin.org:12345/",        # non-responding host, timeout expected
        "http://www.httphttpbinbin.org/",       # DNS error expected
    ]

    def start_requests(self):
        for u in self.start_urls:
            yield scrapy.Request(u, callback=self.parse_httpbin,
                                    errback=self.errback_httpbin,
                                    dont_filter=True)

    def parse_httpbin(self, response):
        self.logger.info('Got successful response from {}'.format(response.url))
        # do something useful here...

    def errback_httpbin(self, failure):
        # log all failures
        self.logger.error(repr(failure))

        # in case you want to do something special for some errors,
        # you may need the failure's type:

        if failure.check(HttpError):
            # these exceptions come from HttpError spider middleware
            # you can get the non-200 response
            response = failure.value.response
            self.logger.error('HttpError on %s', response.url)

        elif failure.check(DNSLookupError):
            # this is the original request
            request = failure.request
            self.logger.error('DNSLookupError on %s', request.url)

        elif failure.check(TimeoutError, TCPTimedOutError):
            request = failure.request
            self.logger.error('TimeoutError on %s', request.url)

# -*- coding: utf-8 -*-
import scrapy
from scrapy_splash import SplashRequest
from scrapy_splash_tutorial.items import QuoteItem
from scrapy.spidermiddlewares.httperror import HttpError
from scrapy.exceptions import CloseSpider

_login_script = """
function main(splash, args)
  assert(splash:go(args.url))
  assert(splash:wait(0.5))

  --  例外発生
  error("Force Splash Error")

  return {
    url = splash:url(),
    html = splash:html(),
  }
end
"""

class QuotesjsSpider(scrapy.Spider):
    name = 'quotesjs'
    allowed_domains = ['quotes.toscrape.com']
    start_urls = ['http://quotes.toscrape.com/js/']

    def start_requests(self):
        for url in self.start_urls:
            yield SplashRequest(
                url,
                callback=self.parse,
                errback=self.errback_httpbin,
                endpoint='execute',
                cache_args=['lua_source'],
                args={ 'timeout': 60, 'wait': 5, 'lua_source': _login_script, },
            )

    def parse(self, response):
        for q in response.css(".container .quote"):
            quote = QuoteItem()
            quote["author"] = q.css(".author::text").extract_first()
            quote["quote"] = q.css(".text::text").extract_first()
            yield quote

    def errback_httpbin(self, failure):
        # log all failures
        self.logger.error(repr(failure))

        # in case you want to do something special for some errors,
        # you may need the failure's type:

        if failure.check(HttpError):
            # these exceptions come from HttpError spider middleware
            # you can get the non-200 response
            response = failure.value.response
            self.logger.error('HttpError on %s', response.url)
            raise CloseSpider("Force Close!!!!!!")