Python Scrapy-在一个Scrapy脚本中抓取不同的网页
我正在创建一个web应用程序,从不同的网站上收集一长串鞋子。 以下是我的两个单独的scrapy脚本: 我怎样才能把它们都放在一起呢?我已经阅读了这些零碎的文档,我没有看到他们提到这一点,它只是提到了如何从一个根地址中刮取两个地址。Python Scrapy-在一个Scrapy脚本中抓取不同的网页,python,scrapy,Python,Scrapy,我正在创建一个web应用程序,从不同的网站上收集一长串鞋子。 以下是我的两个单独的scrapy脚本: 我怎样才能把它们都放在一起呢?我已经阅读了这些零碎的文档,我没有看到他们提到这一点,它只是提到了如何从一个根地址中刮取两个地址。 谢谢将两个域都放在允许的\u域中并将两个URL放在开始\u URL中,然后使用简单的if-else确定要执行的代码部分 from scrapy import Spider from scrapy.http import Request class ShoesSpi
谢谢将两个域都放在
允许的\u域中
并将两个URL放在开始\u URL中
,然后使用简单的if-else确定要执行的代码部分
from scrapy import Spider
from scrapy.http import Request
class ShoesSpider(Spider):
name = "shoes"
allowed_domains = ["store.nike.com", "dickssportinggoods.com"]
start_urls = ['http://store.nike.com/us/en_us/pw/mens-clearance-soccer-shoes/47Z7puZ896Zoi3', 'http://www.dickssportinggoods.com/products/clearance-soccer-cleats.jsp']
def parse(self, response):
if "store.nike.com" in response.url:
shoes = response.xpath('//*[@class="grid-item-image-wrapper sprite-sheet sprite-index-0"]/a/@href').extract()
elif "dickssportinggoods.com" in response.url:
shoes = response.xpath('//*[@class="fplpTitle header4"]/a/@href').extract()
for shoe in shoes:
yield Request(shoe, callback=self.parse_shoes)
def parse_shoes(self, response):
url = response.url
if "store.nike.com" in response.url:
name = response.xpath('//*[@itemprop="name"]/text()').extract_first()
price = response.xpath('//*[@itemprop="price"]/text()').extract_first()
price = price.replace('$','')
shoe_type = response.css('.exp-product-subtitle::text').extract_first()
sizes = response.xpath('//*[@class="nsg-form--drop-down exp-pdp-size-dropdown exp-pdp-dropdown two-column-dropdown"]/option')
sizes = sizes.xpath('text()[not(parent::option/@class="exp-pdp-size-not-in-stock selectBox-disabled")]').extract()
sizes = [s.strip() for s in sizes]
yield {
'url': url,
'name' : name,
'price' : price,
'sizes' : sizes,
'shoe_type': shoe_type
}
elif "dickssportinggoods.com" in response.url:
sizes = response.xpath('//*[@class="swatches clearfix"]/input/@value').extract()
if sizes == []:
pass
url = response.url
name = response.xpath('.//*[@id="PageHeading_3074457345618261107"]/h1/text()').extract_first()
price = response.xpath('.//*[@itemprop="price"]/text()').extract_first()
#shoe_type = response.css('.exp-product-subtitle::text').extract_first()
yield {
'url': url,
'name' : name,
'price' : price,
'sizes' : sizes,
'shoe_type': ''
}
您不必指定允许的变量。
您可以忽略allowed_domains变量,这样就没有域限制。@tadm123太棒了!。我没有运行您的代码,如果我的代码有任何语法错误或任何其他问题,请用您的完整工作代码编辑我的答案,这样它可能会帮助未来的读者/只是
ellif
,但您现在已经修复了它。谢谢你展示了如何做到这一点,我有10个不同的脚本的鞋子试图把它们绑在一起。
from scrapy import Spider
from scrapy.http import Request
class ShoesSpider(Spider):
name = "shoes"
allowed_domains = ["dickssportinggoods.com"]
start_urls = ['http://www.dickssportinggoods.com/products/clearance-soccer-cleats.jsp']
def parse(self, response):
shoes = response.xpath('//*[@class="fplpTitle header4"]/a/@href').extract()
for shoe in shoes:
yield Request(shoe, callback=self.parse_shoes)
def parse_shoes(self, response):
sizes = response.xpath('//*[@class="swatches clearfix"]/input/@value').extract()
if sizes == []:
pass
url = response.url
name = response.xpath('.//*[@id="PageHeading_3074457345618261107"]/h1/text()').extract_first()
price = response.xpath('.//*[@itemprop="price"]/text()').extract_first()
#shoe_type = response.css('.exp-product-subtitle::text').extract_first()
yield {
'url': url,
'name' : name,
'price' : price,
'sizes' : sizes,
'shoe_type': ''
}
from scrapy import Spider
from scrapy.http import Request
class ShoesSpider(Spider):
name = "shoes"
allowed_domains = ["store.nike.com", "dickssportinggoods.com"]
start_urls = ['http://store.nike.com/us/en_us/pw/mens-clearance-soccer-shoes/47Z7puZ896Zoi3', 'http://www.dickssportinggoods.com/products/clearance-soccer-cleats.jsp']
def parse(self, response):
if "store.nike.com" in response.url:
shoes = response.xpath('//*[@class="grid-item-image-wrapper sprite-sheet sprite-index-0"]/a/@href').extract()
elif "dickssportinggoods.com" in response.url:
shoes = response.xpath('//*[@class="fplpTitle header4"]/a/@href').extract()
for shoe in shoes:
yield Request(shoe, callback=self.parse_shoes)
def parse_shoes(self, response):
url = response.url
if "store.nike.com" in response.url:
name = response.xpath('//*[@itemprop="name"]/text()').extract_first()
price = response.xpath('//*[@itemprop="price"]/text()').extract_first()
price = price.replace('$','')
shoe_type = response.css('.exp-product-subtitle::text').extract_first()
sizes = response.xpath('//*[@class="nsg-form--drop-down exp-pdp-size-dropdown exp-pdp-dropdown two-column-dropdown"]/option')
sizes = sizes.xpath('text()[not(parent::option/@class="exp-pdp-size-not-in-stock selectBox-disabled")]').extract()
sizes = [s.strip() for s in sizes]
yield {
'url': url,
'name' : name,
'price' : price,
'sizes' : sizes,
'shoe_type': shoe_type
}
elif "dickssportinggoods.com" in response.url:
sizes = response.xpath('//*[@class="swatches clearfix"]/input/@value').extract()
if sizes == []:
pass
url = response.url
name = response.xpath('.//*[@id="PageHeading_3074457345618261107"]/h1/text()').extract_first()
price = response.xpath('.//*[@itemprop="price"]/text()').extract_first()
#shoe_type = response.css('.exp-product-subtitle::text').extract_first()
yield {
'url': url,
'name' : name,
'price' : price,
'sizes' : sizes,
'shoe_type': ''
}