加速scrapy

def parse(self, response):
# Get the next index URLs and yield Requests
next_sel = response.xpath('//*[contains(@class,"next")]//@href') for url in next_sel.extract():
yield Request(urlparse.urljoin(response.url, url))

# Iterate through products and create PropertiesItems selectors = response.xpath(
'//*[@itemtype="http://schema.org/Product"]') for selector in selectors:
yield self.parse_item(selector, response)

 

转载于:https://www.cnblogs.com/realmonkeykingsun/p/8031447.html