所以最近我开始在scrapy docs网站上学习scrapy。我尝试了一些网站。 现在,如果我想使用Scrapy Shell,那么大多数情况下我会得到空数组。
import scrapy
class rebuySpider(scrapy.Spider):
name = "rebuy"
allowed_domains = ['rebuy.de']
start_urls = [
'https://www.rebuy.de/kaufen/handy',
'https://www.rebuy.de/kaufen/handy?page=2'
]
def parse(self, response):
page = response.url.split("=")[-1]
filename = 'rebuy-%s.html' % page
with open(filename, 'wb') as f:
f.write(response.body)
def parse(self, response):
for product in response.css("div.ry-product__item"):
yield {
"product" : product.css("div.ry-product-item-content__name::text").getall(),
"preis" : product.css("strong.ry-price__amount::text").getall(),
}