scrapy中的请求错误回调函数errback

在处理请求时引发任何异常时将调用的函数。这包括因404 HTTP错误而失败的页面等。

它接收 Twisted Failure实例作为第一个参数。

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)

再举一个简单实用的例子（部分代码）：

from scrapy.spidermiddlewares.httperror import HttpError
from twisted.internet.error import TimeoutError, TCPTimedOutError, ConnectionRefusedError
from twisted.web._newclient import ResponseFailed, ResponseNeverReceived
from scrapy.spidermiddlewares.httperror import HttpError
from scrapy.utils.response import response_status_message # 获取错误代码信息


def request_errback(self, failure):
        request = failure.request

        if failure.check(HttpError):
            response = failure.value.response
            self.logger.error(
                'errback <%s> %s , response status:%s' %
                (request.url, failure.value, response_status_message(response.status))
            )
        elif failure.check(ResponseFailed):
            self.logger.error('errback <%s> ResponseFailed' % request.url)

        elif failure.check(ConnectionRefusedError):
            self.logger.error('errback <%s> ConnectionRefusedError' % request.url)

        elif failure.check(ResponseNeverReceived):
            self.logger.error('errback <%s> ResponseNeverReceived' % request.url)

        elif failure.check(TCPTimedOutError, TimeoutError):
            self.logger.error('errback <%s> TimeoutError' % request.url)

        else:
            self.logger.error('errback <%s> OtherError' % request.url)