11、一个简单的更美APP美购项目爬虫

import scrapy


class QuotesSpider(scrapy.Spider):
    name = "quotes"
    start_urls = [
        'http://www.gmei.com/promotion_list/province_268?page=1',
    ]

    def parse(self, response):
        for quote in response.css('a.commodity'):
            yield {
                'title': quote.css('p.commodity-title::text').extract(),
                'yuyue':quote.css('div.commodity-num span').re(r'[1-9]\d*'),
                'riji':quote.css('span.diary-num').re(r'[1-9]\d*'),
                'xianjia':quote.css('h3.commodity-price').re(r'[1-9]\d*')[1],
                'yuanjia':quote.css('h3.commodity-price').re(r'[1-9]\d*')[2],
                'address':quote.css('p.commodity-address::text').extract(),
                'url': quote.css('a.commodity::attr(href)').extract(),
            }

        next_page = response.css('li.next-page a::attr(href)').extract_first()
        if next_page is not None:
             next_page = response.urljoin(next_page)
        yield scrapy.Request(next_page, callback=self.parse)