Question

我正在使用scrapy构建一个刮刀，我收到以下错误消息，我无法弄清楚原因。我看过scrapy文档，但我不确定是否遗漏了什么。我正在尝试使用说明从网站下载图像。我希望将描述下载到CSV并将图像下载到名为IMG的文件夹中。

蜘蛛

from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from NSIscrape.items import NsiscrapeItem
from scrapy.http import Request
from scrapy.contrib.pipeline.images import ImagesPipeline


class NsiscrapeSpider(BaseSpider):
    name = "Nsiscrape"
    allowed_domain = ["yachtauctions.com"]
    start_urls = [
    "http://www.yachtauctions.com/inventory/"
    ]

def parse(self, response):
    hxs = HtmlXPathSelector(response)
    sites = hxs.select('//tr')
    items = []
    for site in sites:
        item = NsiscrapeItem()
        item['location'] = site.select('td[2]/text()').extract()
        item['stock_number'] = site.select('td[3]/a/text()').extract()
        item['year'] = site.select('td[4]/text()').extract()
        item['manufacturer'] = site.select('td[5]/text()').extract()
        item['model'] = site.select('td[6]/text()').extract()
        item['length'] = site.select('td[7]/text()').extract()
        item['price'] = site.select('td[8]/text()').extract()
        item['status'] = site.select('td[10]/img/@src').extract()
        item['url'] = site.select('td[1]/a/@href').extract()
        item['images'] = site.select('td/a[3]/img/@data-original').extract()
        item['image_urls'] = item['images']
        yield Request(item['url'][0],
        meta={'item':item},
        callback=self.product_detail_page)

def product_detail_page(self, response):
    hxs = HtmlXPathSelector(response)
    item = response.request.meta['item']
    #add all images url in the item['image_urls']
    yield item

这是我在运行刮刀时遇到的错误

raise TypeError('Request url must be str or unicode, got %s:' % type
(url).__name__)
exceptions.TypeError: Request url must be str or unicode, got list:

Scrapy TypeError：请求url必须是str或unicode

0 个答案: