redis-crawlspider

1，建立项目

Scrapy startproject book
cd book
scrapy genspider -t crawl amazon amazon.cn

2， 与scrapy_redis不同的是继承的类不同

from scrapy_redis.spiders import RedisCrawlSpider   
from scrapy.spiders import CrawlSpider, Rule
        
class AmazonSpider(RedisCrawlSpider):
    name = 'amazon'
    allowed_domains = ['amazon.cn']
    # start_urls = ['https://www.amazon.cn/b/?&node=116169071&tag=baiduiclickcn-23&ref=DEP_190527_lhb_06']
    redis_key = 'amazon'

rules = (
    # 匹配大分类的url地址和小分类的url地址
    Rule(LinkExtractor(
        restrict_xpaths=("//ul[@class='a-unordered-list a-nostyle a-vertical s-ref-indent-two']/ul/li"), ),
         follow=True),
    # 匹配图书
    Rule(LinkExtractor(restrict_xpaths=("//div[@id='mainResults']/ul/li//h2/.."), ), callback='parse_book_detail'),
    # 翻页
    Rule(LinkExtractor(restrict_xpaths=("//div[@id='pagn']"), ), follow=True)

)

def parse_book_detail(self, response):
    item = {}
    item["book_title"] = response.xpath("//span[@id='productTitle']/text()").extract_first()
    item["book_author"] = response.xpath("//div[@id='bylineInfo']/span[1]/a/text()").extract_first()
    item["book_img"] = response.xpath("//div[@id='ebooks-img-canvas']/img/@src").extract_first()
    item["book_price"] = response.xpath("//span[@class='a-color-base']/span/text()").extract_first()

crawlspider rule完善：