Python ImportError:无法导入名称爬网器

我在scrapy中创建了一个web scraper，它在同一进程中运行两个爬行器，但是当我在终端中使用命令：scrapy crawl运行代码时，我得到：ImportError:无法导入名称CrawlerRunner。 我以前尝试过同时运行多个scrapy Spider的其他方法，但无法解决这个问题。我认为也许使用twisted库可能有效，但显然可能存在一些我没有的依赖性，但我不能确定。要导入库，是否需要安装一些特殊设备？我已经安装了python twisted。爬行器的代码如下所示：

import scrapy
import re
import json
from scrapy.crawler import CrawlerProcess
from scrapy import Request
from scrapy.contrib.spiders import CrawlSpider , Rule
from scrapy.selector import HtmlXPathSelector
from scrapy.selector import Selector
from scrapy.contrib.loader import ItemLoader
from scrapy.contrib.loader import XPathItemLoader
from scrapy.contrib.loader.processor import Join, MapCompose
from concert_comparator.items import ComparatorItem, ComparatorItem2

bandname = raw_input("Enter a bandname \n")

vs_url = "http://www.vividseats.com/concerts/" + bandname + "-tickets.html"
sg_url = "http://www.seatgeek.com/" + bandname + "-tickets"

class MySpider(CrawlSpider):
    handle_httpstatus_list = [416]
    name = 'comparator'
    allowed_domains = ["www.vividseats.com"]
    start_urls = [vs_url]
    tickets_list_xpath = './/*[@itemtype="http://schema.org/Event"]'

    def parse_json(self, response):
        loader = response.meta['loader']
        jsonresponse = json.loads(response.body_as_unicode())
        ticket_info = jsonresponse.get('tickets')
        price_list = [i.get('p') for i in ticket_info]
        ticketPrice = ''.join(price_list[0])
        loader.add_value('ticketPrice', ticketPrice)
        return loader.load_item()

    def parse_price(self, response):
        loader = response.meta['loader']
        ticketsLink = loader.get_output_value("ticketsLink")
        json_id_list= re.findall(r"(\d+)[^-]*$", ticketsLink)
        json_id=  "".join(json_id_list)
        json_url = "http://www.vividseats.com/javascript/tickets.shtml?productionId=" + json_id
        yield scrapy.Request(json_url, meta={'loader': loader}, callback = self.parse_json, dont_filter = True) 

    def parse(self, response):
        """
        # """
        selector = HtmlXPathSelector(response)
        # iterate over tickets
        for ticket in selector.select(self.tickets_list_xpath):
            loader = XPathItemLoader(ComparatorItem(), selector=ticket)
            # define loader
            loader.default_input_processor = MapCompose(unicode.strip)
            loader.default_output_processor = Join()
            # iterate over fields and add xpaths to the loader
            loader.add_xpath('eventName' , './/*[@class="productionsEvent"]/text()')
            loader.add_xpath('eventLocation' , './/*[@class = "productionsVenue"]/span[@itemprop  = "name"]/text()')
            loader.add_xpath('ticketsLink' , './/*/a[@class = "btn btn-primary"]/@href')
            loader.add_xpath('eventDate' , './/*[@class = "productionsDate"]/text()')
            loader.add_xpath('eventCity' , './/*[@class = "productionsVenue"]/span[@itemprop  = "address"]/span[@itemprop  = "addressLocality"]/text()')
            loader.add_xpath('eventState' , './/*[@class = "productionsVenue"]/span[@itemprop  = "address"]/span[@itemprop  = "addressRegion"]/text()')
            loader.add_xpath('eventTime' , './/*[@class = "productionsTime"]/text()')

            print "Here is ticket link \n" + loader.get_output_value("ticketsLink")
            #sel.xpath("//span[@id='PractitionerDetails1_Label4']/text()").extract()
            ticketsURL = "concerts/" + bandname + "-tickets/" + bandname + "-" + loader.get_output_value("ticketsLink")
            ticketsURL = urljoin(response.url, ticketsURL)
            yield scrapy.Request(ticketsURL, meta={'loader': loader}, callback = self.parse_price, dont_filter = True)


class MySpider2(CrawlSpider):
    handle_httpstatus_list = [416]
    name = 'comparator2'
    allowed_domains = ["www.seatgeek.com/"]
    start_urls = [sg_url]
    tickets_list_xpath = './/*[@itemtype="http://schema.org/Event"]'

    def parse_json2(self, response):
        loader = response.meta['loader']
        jsonresponse = json.loads(response.body_as_unicode())
        listings_info = jsonresponse.get('listings')
        price_list = [i.get('pf') for i in ticket_info]
        ticketPrice = price_list[0]
        loader.add_value('ticketPrice', ticketPrice)
        return loader.load_item()

    def parse_price2(self, response):
        loader = response.meta['loader']
        ticketsLink = loader.get_output_value("ticketsLink")
        json_id= ticketsLink.split('/')[6]
        json_url = "https://seatgeek.com/listings?client_id=MTY2MnwxMzgzMzIwMTU4&id=" + json_id + "&_wt=1&&_=1436364489501"
        yield scrapy.Request(json_url, meta={'loader': loader}, callback = self.parse_json, dont_filter = True) 

    def parse2(self, response):
        """

        # """
        selector = HtmlXPathSelector(response)
        # iterate over tickets
        for ticket in selector.select(self.tickets_list_xpath):
            loader = XPathItemLoader(ComparatorItem(), selector=ticket)
            # define loader
            loader.default_input_processor = MapCompose(unicode.strip)
            loader.default_output_processor = Join()
            # iterate over fields and add xpaths to the loader
            loader.add_xpath('eventName' , './/a[@class = "event-listing-title"]/span[@itemprop = "name"]/text()')
            loader.add_xpath('eventLocation' , './/a[@class = "event-listing-venue-link"]/span[@itemprop = "name"]/text()')
            loader.add_xpath('ticketsLink' , '//a[@class = "event-listing-button"]/@href')
            loader.add_xpath('eventDate' , '//div[@class = "event-listing-date"]/text()')
            loader.add_xpath('eventCity' , './/span[@itemprop  = "addressLocality"]/text()')
            loader.add_xpath('eventState' , './/span[@itemprop  = "addressRegion"]/text()')
            loader.add_xpath('eventCountry' , './/span[@itemprop  = "addressCountry"]/text()')
            loader.add_xpath('eventTime' , '//div[@class = "event-listing-time"]/text()')

            #ticketsURL = "concerts/" + bandname + "-tickets/" + bandname + "-" + loader.get_output_value("ticketsLink")
            tickets_url = "www.seatgeek.com/" + loader.get_output_value("ticketsLink")
            #ticketsURL = urljoin(response.url, ticketsURL)
            yield scrapy.Request(tickets_url, meta={'loader': loader}, callback = self.parse_price2, dont_filter = True)

process = CrawlerProcess()
process.crawl(MySpider)
process.crawl(MySpider2)
process.start()

---

你们有安装刮刮器吗？

import scarpy

说什么？@MaximilianKindshofer是的，我安装了scrapy。导入scrapy时我没有收到错误。这个文件是否有可能名为

scrapy.py

？@Glyph在再次更新scrapy后，我不会再收到与crawlerProcess相同的错误。现在我得到了这个错误：raise error.ReactorNotRestartable（）twisted.internet.error.ReactorNotRestartable。我一直在终端中使用：命令，所以我不确定这是否会导致问题，因为从技术上讲，这是在特定情况下运行一个spider的命令。您是否应该在爬虫脚本中调用

reactor.run（）

？我假设

scrapy

命令行工具可以为您实现这一点。您是否安装了scrapy？

import scarpy

说什么？@MaximilianKindshofer是的，我安装了scrapy。导入scrapy时我没有收到错误。这个文件是否有可能名为

scrapy.py

？@Glyph在再次更新scrapy后，我不会再收到与crawlerProcess相同的错误。现在我得到了这个错误：raise error.ReactorNotRestartable（）twisted.internet.error.ReactorNotRestartable。我一直在终端中使用：命令，所以我不确定这是否会导致问题，因为从技术上讲，这是在特定情况下运行一个spider的命令。您是否应该在爬虫脚本中调用

reactor.run（）

？我假设

scrapy

命令行工具可以为您做到这一点。