jd.py

# -*- coding: utf-8 -*-
import scrapy
from JD.items import JdItem
import json
from copy import deepcopy


# //div[@class="m m0"]/div[2]/dl/dd[1]/em[1]/a/@href
class JdSpider(scrapy.Spider):
    name = 'jd'
    allowed_domains = ['jd.com','p.3.cn']
    start_urls = ['https://book.jd.com/booksort.html']

    def parse(self, response):
        dt_list = response.xpath('//div[@class="m m0"]/div[2]/dl/dt')  # 大分类列表
        for dt in dt_list:
            item = JdItem()
            item['book_category'] = dt.xpath('./a/text()').extract_first()
            em_list = dt.xpath('./following-sibling::dd[1]/em')  # 小分类列表
            for em in em_list:
                item['s_href'] = em.xpath("./a/@href").extract_first()
                item["s_category"] = em.xpath("./a/text()").extract_first()
                # 下载的页面数量
                # for num in range(1, 2):
                item['s_href'] = 'https:' + item['s_href']  # + '&page='   + str(num + 1)
                yield scrapy.Request(url=item['s_href'], meta={"item": deepcopy(item)}, callback=self.parse_two)

    def parse_two(self, response):
        item = response.meta['item']
        li_list = response.xpath('//div[@id="plist"]/ul/li')
        # 遍历所有书籍所在的<li>标签
        for li in li_list:
            book_href = li.xpath('.//div[@class="p-img"]/a/@href').extract_first()
            # 书籍详情页
            item['book_href'] = 'http:' + book_href
            # 书名
            item['book_name'] = li.xpath('.//div[@class="p-name"]/a/em/text()').extract_first().strip()
            # 书籍图片
            item["book_img"] = li.xpath(".//div[@class='p-img']//img/@src").extract_first()
            if item["book_img"] is None:
                item["book_img"] = li.xpath(".//div[@class='p-img']//img/@data-lazy-img").extract_first()
            item["book_img"] = "https:" + item["book_img"] if item["book_img"] is not None else None
            # 作者
            item['book_author'] = li.xpath('.//span[@class="author_type_1"]/a/text()').extract_first()
            # 出版社
            item['book_press'] = li.xpath('.//span[@class="p-bi-store"]/a/text()').extract_first()
            # 出版时间
            item['book_publication_time'] = li.xpath('.//span[@class="p-bi-date"]/text()').extract_first().strip()
            # print(item)
            book_sku = li.xpath("./div/@data-sku").extract_first()
            # response = requests.get("https://p.3.cn/prices/mgets?skuIds=J_{}".format(book_sku))
            # item["book_price"] = json.loads(response.content.decode())[0]["op"]
            # print(item)
            yield scrapy.Request(
                "https://p.3.cn/prices/mgets?skuIds=J_{}".format(book_sku),
                meta={"item": deepcopy(item)},
                callback=self.parse_book_price)

    def parse_book_price(self, response):
        item = response.meta["item"]
        item["book_price"] = json.loads(response.body.decode())[0]["op"]
        print(item)

items.py