当我运行下面的代码时，最终得到一个文件，该文件包含第二个代码块中的所有预期数据，而第一个代码块中则没有任何数据。换句话说，从EventLocation到EventURL的所有数据都存在，但是从EventArtist到EventDetails没有任何数据。我需要修改什么才能使其正常工作？
import urlparse
from scrapy.http import Request
from scrapy.spider import BaseSpider
from scrapy.selector import Selector
#from NT.items import NowTorontoItem
from scrapy.item import Item, Field
class NowTorontoItem(Item):
eventArtist = Field()
eventTitle = Field()
eventHolder = Field()
eventDetails = Field()
eventLocation = Field()
eventOrganization = Field()
eventName = Field()
eventAddress = Field()
eventLocality = Field()
eventPostalCode = Field()
eventPhone = Field()
eventURL = Field()
class MySpider(BaseSpider):
name = "NTSpider"
allowed_domains = ["nowtoronto.com"]
start_urls = ["http://www.nowtoronto.com/music/listings/"]
def parse(self, response):
selector = Selector(response)
listings = selector.css("div.listing-item0, div.listing-item1")
for listing in listings:
item = NowTorontoItem()
for body in listing.css('span.listing-body > div.List-Body'):
item ["eventArtist"] = body.css("span.List-Name::text").extract()
item ["eventTitle"] = body.css("span.List-Body-Emphasis::text").extract()
item ["eventHolder"] = body.css("span.List-Body-Strong::text").extract()
item ["eventDetails"] = body.css("::text").extract()
# yield a Request()
# so that scrapy enqueues a new page to fetch
detail_url = listing.css("div.listing-readmore > a::attr(href)")
if detail_url:
yield Request(urlparse.urljoin(response.url,
detail_url.extract()[0]),
callback=self.parse_details)
def parse_details(self, response):
self.log("parse_details: %r" % response.url)
selector = Selector(response)
listings = selector.css("div.whenwhereContent")
for listing in listings:
for body in listing.css('td.small-txt.dkgrey-txt.rightInfoTD'):
item = NowTorontoItem()
item ["eventLocation"] = body.css("span[property='v:location']::text").extract()
item ["eventOrganization"] = body.css("span[property='v:organization'] span[property='v:name']::text").extract()
item ["eventName"] = body.css("span[property='v:name']::text").extract()
item ["eventAddress"] = body.css("span[property='v:street-address']::text").extract()
item ["eventLocality"] = body.css("span[property='v:locality']::text").extract()
item ["eventPostalCode"] = body.css("span[property='v:postal-code']::text").extract()
item ["eventPhone"] = body.css("span[property='v:tel']::text").extract()
item ["eventURL"] = body.css("span[property='v:url']::text").extract()
yield item
编辑
现在它似乎正在运行，但是有一个小问题。对于每个事件，它返回两行，其中一行包含所有详细信息，而一行仅包含从第一个代码块提取的详细信息，或者返回三行，一行包含所有细节，而两行相同的行仅包含从第一个代码块提取的详细信息块。
这是第一种情况的示例
2014-03-21 11:12:40-0400 [NTSpider] DEBUG: parse_details: 'http://www.nowtoronto.com/music/listings/listing.cfm?listingid=129761&subsection=&category=&criticspicks=&date1=&date2=&locationId=0'
2014-03-21 11:12:40-0400 [NTSpider] DEBUG: Scraped from <200 http://www.nowtoronto.com/music/listings/listing.cfm?listingid=129761&subsection=&category=&criticspicks=&date1=&date2=&locationId=0>
{'eventAddress': [u'875 Bloor W'],
'eventArtist': [u'Andria Simone & Those Guys'],
'eventDetails': [u'Andria Simone & Those Guys',
u' (pop/soul) ',
u'Baltic Avenue',
u' 8 pm, $15.'],
'eventHolder': [u'Baltic Avenue'],
'eventLocality': [u'Toronto'],
'eventLocation': [u'\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t'],
'eventName': [u'\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tBaltic Avenue'],
'eventOrganization': [u'\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tBaltic Avenue'],
'eventPhone': [u'647-898-5324'],
'eventPostalCode': [u'M6G 3T6'],
'eventTitle': [],
'eventURL': []}
2014-03-21 11:12:40-0400 [NTSpider] DEBUG: Scraped from <200 http://www.nowtoronto.com/music/listings/listing.cfm?listingid=129761&subsection=&category=&criticspicks=&date1=&date2=&locationId=0>
{'eventAddress': [],
'eventArtist': [u'Andria Simone & Those Guys'],
'eventDetails': [u'Andria Simone & Those Guys',
u' (pop/soul) ',
u'Baltic Avenue',
u' 8 pm, $15.'],
'eventHolder': [u'Baltic Avenue'],
'eventLocality': [],
'eventLocation': [],
'eventName': [],
'eventOrganization': [],
'eventPhone': [],
'eventPostalCode': [],
'eventTitle': [],
'eventURL': []}
这是第二种情况的例子
2014-03-21 11:21:23-0400 [NTSpider] DEBUG: parse_details: 'http://www.nowtoronto.com/music/listings/listing.cfm?listingid=130096&subsection=&category=&criticspicks=&date1=&date2=&locationId=0'
2014-03-21 11:21:23-0400 [NTSpider] DEBUG: Scraped from <200 http://www.nowtoronto.com/music/listings/listing.cfm?listingid=130096&subsection=&category=&criticspicks=&date1=&date2=&locationId=0>
{'eventAddress': [u'11 Polson'],
'eventArtist': [u'Danny Byrd, S.P.Y., Fred V & Grafix, Marcus Visionary, Lushy '],
'eventDetails': [u'Danny Byrd, S.P.Y., Fred V & Grafix, Marcus Visionary, Lushy ',
u'Bassweek: Projek-Hospitality ',
u'Sound Academy',
u' $35 or wristband TM.'],
'eventHolder': [u'Sound Academy'],
'eventLocality': [u'Toronto'],
'eventLocation': [u'\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t'],
'eventName': [u'\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tSound Academy'],
'eventOrganization': [u'\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\tSound Academy'],
'eventPhone': [u'416-461-3625'],
'eventPostalCode': [u'M5A 1A4'],
'eventTitle': [u'Bassweek: Projek-Hospitality '],
'eventURL': [u'sound-academy.com']}
2014-03-21 11:21:23-0400 [NTSpider] DEBUG: Crawled (200) <GET http://www.nowtoronto.com/music/listings/listing.cfm?listingid=122291&subsection=&category=&criticspicks=&date1=&date2=&locationId=0> (referer: http://www.nowtoronto.com/music/listings/)
2014-03-21 11:21:24-0400 [NTSpider] DEBUG: Scraped from <200 http://www.nowtoronto.com/music/listings/listing.cfm?listingid=130096&subsection=&category=&criticspicks=&date1=&date2=&locationId=0>
{'eventAddress': [],
'eventArtist': [u'Danny Byrd, S.P.Y., Fred V & Grafix, Marcus Visionary, Lushy '],
'eventDetails': [u'Danny Byrd, S.P.Y., Fred V & Grafix, Marcus Visionary, Lushy ',
u'Bassweek: Projek-Hospitality ',
u'Sound Academy',
u' $35 or wristband TM.'],
'eventHolder': [u'Sound Academy'],
'eventLocality': [],
'eventLocation': [],
'eventName': [],
'eventOrganization': [],
'eventPhone': [],
'eventPostalCode': [],
'eventTitle': [u'Bassweek: Projek-Hospitality '],
'eventURL': []}
2014-03-21 11:21:24-0400 [NTSpider] DEBUG: Scraped from <200 http://www.nowtoronto.com/music/listings/listing.cfm?listingid=130096&subsection=&category=&criticspicks=&date1=&date2=&locationId=0>
{'eventAddress': [],
'eventArtist': [u'Danny Byrd, S.P.Y., Fred V & Grafix, Marcus Visionary, Lushy '],
'eventDetails': [u'Danny Byrd, S.P.Y., Fred V & Grafix, Marcus Visionary, Lushy ',
u'Bassweek: Projek-Hospitality ',
u'Sound Academy',
u' $35 or wristband TM.'],
'eventHolder': [u'Sound Academy'],
'eventLocality': [],
'eventLocation': [],
'eventName': [],
'eventOrganization': [],
'eventPhone': [],
'eventPostalCode': [],
'eventTitle': [u'Bassweek: Projek-Hospitality '],
'eventURL': []}
您应该在的meta参数中将项目从传递parse()给：parse_details()Request
yield Request(urlparse.urljoin(response.url,
detail_url.extract()[0]),
meta={'item': item},
callback=self.parse_details)
然后，parse_details()您可以从response.meta['item']（docs）获取项目。
另外，yield如果没有找到详细信息，您可能想要一个项目：
if detail_url:
yield Request(urlparse.urljoin(response.url,
detail_url.extract()[0]),
meta={'item': item},
callback=self.parse_details)
else:
yield item
希望能有所帮助。
本文收集自互联网，转载请注明来源。
如有侵权，请联系[email protected] 删除。
我来说两句