我刚尝试使用the new scrapy documentation在同一进程中运行多个蜘蛛，但我得到了：AttributeError：＆＃39; CrawlerProcess＆＃39;对象没有属性＆＃39;抓取＆＃39;
我发现this SO post有同样的问题，所以我尝试使用0.24 documentation中的代码并得到：runspider：错误：无法加载＆＃39; price_comparator.py＆＃39;：没有模块命名为testspiders.spiders.followall
对于我导入的1.0：
from scrapy.crawler import CrawlerProcess
和0.24我导入：
from twisted.internet import reactor
from scrapy.crawler import Crawler
from scrapy import log
from testspiders.spiders.followall import FollowAllSpider
from scrapy.utils.project import get_project_settings
基于0.24 doc，似乎代码通过多个域运行一个蜘蛛，这似乎与1.0 doc代码的作用相同，但无论如何我都运行了两个。我确实有代码在我的蜘蛛定义的文件中运行两个蜘蛛，这可能是一个问题。新版本的代码是否存在内部问题，或者我的程序中是否存在某些依赖项或代码？我的文件包含以下两个文档的代码（我没有同时运行这两个版本）。
蜘蛛类定义
底部的相关代码
import re
import json
import scrapy
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
from twisted.internet import reactor
from scrapy.crawler import CrawlerProcess
#from scrapy.crawler import Crawler
from scrapy import log
#from testspiders.spiders.followall import FollowAllSpider
from scrapy.utils.project import get_project_settings
from urlparse import urljoin
bandname = raw_input("Enter a bandname \n")
#location = raw_input("Enter a city \n")
vs_url = "http://www.vividseats.com/concerts/" + bandname + "-tickets.html"
sg_url = "http://www.seatgeek.com/" + bandname + "-tickets"
#sh_url = "http://www.stubhub.com/" + bandname + "-tickets/"
#print sh_url
#rules = (Rule(LinkExtractor(allow=("concerts/" + bandname + "-tickets/" + bandname + "-" + item["ticketsLink"]),restrict_xpaths=('.//*/td[3]/a/@href',))callback = "parse_tickets" , follow = True,))
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)
#0.24 code
# def setup_crawler(domain):
# spider = FollowAllSpider(domain=domain)
# settings = get_project_settings()
# crawler = Crawler(settings)
# crawler.configure()
# crawler.crawl(spider)
# crawler.start()
# for domain in [vs_url, sg_url]:
# setup_crawler(domain)
# log.start()
# reactor.run()
#1.0 code
process = CrawlerProcess(get_project_settings())
process = CrawlerProcess({
'USER_AGENT' : 'Mozilla/4.0 (compartible; MSIE 7.0; Windows NT 5.1)'
})
process.crawl(MySpider)
process.crawl(MySpider2)
process.start()