每个scrapy输出项都放在csv中的一个单独的行中

Question

我从csv文件中删除了超过5,000个链接。

程序将每个元素放入输出csv中的单独行。

如何在每个网站上获得一行，同时包含同一行网站的所有信息？

from scrapy.spider import BaseSpider
from scrapy.contrib.linkextractors import LinkExtractor
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.utils.markup import remove_tags
from scrapy.selector import Selector
from scrapy.selector import HtmlXPathSelector
from bkstr.items import BkstrItem
from scrapy.http import Request
from scrapy.loader.processors import Join
import csv
import sys


class MySpider(CrawlSpider):
    name = "book"
    my_file = open("callnumberedited3.csv", "rb")
    reader = csv.reader(my_file)
    start_urls = my_file
    custom_settings = {'REDIRECT_ENABLED': False}
    handle_httpstatus_list = [301]
    download_delay = 0.25
    rules = [Rule(LinkExtractor(), follow=True, callback='parse_item')]

    def parse_item (self, response):
        items = []
        varx = response.xpath('//*[@id="fldset-course_1_1"]/div[2]/h2/text()')

        for sel in response.xpath('//*[@id="fldset-course_1_1"]/div[2]/h2/text()'):
            item = BkstrItem()
            item["course"] = varx.extract()[0]
            yield item

        var1 = response.xpath('//*[@id="fldset-crsmaterialgrp_1"]/div[1]/h3/text()') 
        for sel in response.xpath('//*[@id="fldset-crsmaterialgrp_1"]/div[1]/h3/text()'):
            item = BkstrItem()
            item["title1"] = var1.extract()[0]
            yield item

        var11 = response.xpath('//*[@id="materialAuthor"]/text()')
        for sel in response.xpath('//*[@id="materialAuthor"]/text()'):
            item = BkstrItem()
            item["author1"] = var11.extract() 
            yield item

        var12 = response.xpath('//*[@id="materialISBN"]/text()')
        for sel in response.xpath('//*[@id="materialISBN"]/text()'):
            item = BkstrItem()
            item["isbn1"] = var12.extract() 
            yield item

        var15 = response.xpath('//*[@id="materialCopyrightYear"]/text()')
        for sel in response.xpath('//*[@id="materialCopyrightYear"]/text()'):
            item = BkstrItem()
            item["year1"] = var15.extract() 
            yield item

        var16 = response.xpath('//*[@id="materialPublisher"]/text()')
        for sel in response.xpath('//*[@id="materialPublisher"]/text()'):
            item = BkstrItem()
            item["publisher1"] = var16.extract()                        
            yield item  

        var2 = response.xpath('//*[@id="fldset-crsmaterialgrp_2"]/div[1]/h3/text()')
        for sel in response.xpath('//*[@id="fldset-crsmaterialgrp_2"]/div[1]/h3/text()'):
            item = BkstrItem()
            item["title2"] = var2.extract()[0]
            yield item

        var3 = response.xpath('//*[@id="fldset-crsmaterialgrp_3"]/div[1]/h3/text()')
        for sel in response.xpath('//*[@id="fldset-crsmaterialgrp_3"]/div[1]/h3/text()'):
            item = BkstrItem()
            item["title3"] = var3.extract()[0]
            yield item
        print items