学习笔记(44):21天通关Python（仅视频课）-Scrapy开发爬虫的步骤（下）

立即学习:https://edu.youkuaiyun.com/course/play/24797/282246?utm_source=blogtoedu

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class ZhipinspiderItem(scrapy.Item):
    # 款式
    design = scrapy.Field()
    # 购买时间
    buy_date = scrapy.Field()
    # 地址
    buy_addr = scrapy.Field()
    # 裸车价
    real_price = scrapy.Field()
    # 指导价
    original_price = scrapy.Field()

 

 

 

# -*- coding: utf-8 -*-
import scrapy
from ZhipinSpider.items import ZhipinspiderItem


# 页数1-61页
# http://luochejia.yiche.com/yiqifengtianrav4/price/?page=1
class TestScrapySpider(scrapy.Spider):
    # 蜘蛛的名字
    name = 'test_scrapy'
    # 定义蜘蛛只爬取哪写域名
    allowed_domains = ['luochejia.yiche.com']
    # 从哪个页面开始爬
    urls = ['http://luochejia.yiche.com/yiqifengtianrav4/price/?page=%s' % i for i in range(1, 62)]
    start_urls = urls

    # 该response就代表Scrapy下载器所获取的目标响应
    def parse(self, response):
        # 每个job_primary元素包含一个工作信息
        for car_primary in response.xpath('//div[@class="price-list-box"]'):
            item = ZhipinspiderItem()
            # 款式
            item['design'] = car_primary.xpath('./div[@class="con-box"]/div[@class="tit"]/text()').extract_first()
            # 购买时间
            item['buy_date'] = car_primary.xpath('./div[@class="con-box"]/p[@class="other"]/text()').extract_first()
            # 地址
            item['buy_addr'] = car_primary.xpath('./div[@class="con-box"]/p[@class="other"]/text()').extract_first()
            # 裸车价
            item['real_price'] = car_primary.xpath(
                './div[@class="con-box"]/div[@class="price"]/p[@class="luochejia"]/em/text()').extract_first()
            # 指导价
            item['original_price'] = car_primary.xpath(
                './div[@class="con-box"]/div[@class="price"]/p[@class="zhidaojia"]/text()').extract_first()
            yield item