scrapy ---项目运行

import scrapy


class SpiderHouseSpider(scrapy.Spider):
    name = 'spider_house'
    allowed_domains = ['douguo.com']
    start_urls = ['https://www.douguo.com/caipu/%E5%AE%B6%E5%B8%B8%E8%8F%9C']

    def parse(self, response, **kwargs):
        data_list = response.xpath('//ul[@class="cook-list"]//li')
        for data in data_list:
            title = data.xpath("./div[1]/a/text()").extract_first().replace('㊙','')
            ingredients = data.xpath("./div[1]/p/text()").extract_first()
            rating = data.xpath("./div[1]/div[1]/span//text()").extract_first()
            author = data.xpath("./div[1]/div[2]/a[1]/text()").extract_first()
            print(title,ingredients,rating,author)

打开cmd ,cd 到项目路径下,使用 scrapy crawl 代码文件(注意:不加  .py)运行文件