python - Scrapy 管道以正确的格式导出 csv 文件

Question

我根据下面alexce的建议做了改进。我需要的是如下图。但是，每一行/行应该是一条评论:包含日期、评级、评论文本和链接。

我需要让项目处理器处理每个页面的每个评论。
目前 TakeFirst() 只接受页面的第一次审查。所以 10 页，我只有 10 行/行，如下图所示。

爬虫代码如下:

import scrapy
from amazon.items import AmazonItem

class AmazonSpider(scrapy.Spider):
   name = "amazon"
   allowed_domains = ['amazon.co.uk']
   start_urls = [
    'http://www.amazon.co.uk/product-reviews/B0042EU3A2/'.format(page) for      page in xrange(1,114)

]

def parse(self, response):
    for sel in response.xpath('//*[@id="productReviews"]//tr/td[1]'):
        item = AmazonItem()
        item['rating'] = sel.xpath('div/div[2]/span[1]/span/@title').extract()
        item['date'] = sel.xpath('div/div[2]/span[2]/nobr/text()').extract()
        item['review'] = sel.xpath('div/div[6]/text()').extract()
        item['link'] = sel.xpath('div/div[7]/div[2]/div/div[1]/span[3]/a/@href').extract()

        yield item

Answer 1

我从头开始，下面的蜘蛛应该运行

scrapy crawl amazon -t csv -o Amazon.csv --loglevel=INFO

以便为我显示用电子表格打开 CSV 文件

希望这有帮助:-)

import scrapy

class AmazonItem(scrapy.Item):
    rating = scrapy.Field()
    date = scrapy.Field()
    review = scrapy.Field()
    link = scrapy.Field()

class AmazonSpider(scrapy.Spider):

    name = "amazon"
    allowed_domains = ['amazon.co.uk']
    start_urls = ['http://www.amazon.co.uk/product-reviews/B0042EU3A2/' ]

    def parse(self, response):

        for sel in response.xpath('//table[@id="productReviews"]//tr/td/div'):

            item = AmazonItem()
            item['rating'] = sel.xpath('./div/span/span/span/text()').extract()
            item['date'] = sel.xpath('./div/span/nobr/text()').extract()
            item['review'] = sel.xpath('./div[@class="reviewText"]/text()').extract()
            item['link'] = sel.xpath('.//a[contains(.,"Permalink")]/@href').extract()
            yield item

        xpath_Next_Page = './/table[@id="productReviews"]/following::*//span[@class="paging"]/a[contains(.,"Next")]/@href'
        if response.xpath(xpath_Next_Page):
            url_Next_Page = response.xpath(xpath_Next_Page).extract()[0]
            request = scrapy.Request(url_Next_Page, callback=self.parse)
            yield request