1.jd.py
# -*- coding: utf-8 -*-
import scrapy
from copy import deepcopy
import json
import urllib
from scrapy_redis.spiders import RedisSpider
from JingDong.items import JingdongItem
class JdSpider(RedisSpider):
name = 'jd'
# allowed_domains = ['jd.com']
# start_urls = ['https://book.jd.com/booksort.html/']
redis_key = 'jingdong'
#
#解析分类
def parse(self, response):
dt_list=response.xpath('//div[@class="mc"]/dl/dt') #大分类列表
for dt in dt_list:
item=JingdongItem()
item['b_cate']=dt.xpath('./a/text()').extract_first()#当前循环大标题
em_list=dt.xpath('./following-sibling::dd[1]/em') #下小分类列表
for em in em_list:
item['s_href']=em.xpath('./a/@href').extract_first() #小分类的标题
item['s_cate']=em.xpath('./a/text()').extract_first() #小分类得到url
if item['s_href'] is not None:
item['s_href']='https:'+item['s_href']
yield scrapy.Request(item['s_href'],callback=self.parse_book_list,meta={'item':item})
#解析每个小分类下的所有图书
def parse_book_list(self,response):
item=response.meta['item']
li_list=response.xpath('//div[@id="plist"]/ul/li')
for li in li_list:
item['book_name']=li.xpath('.//div[@class="p-name"]/a/em/text()').extract_first().strip()
item['book_img']=li.xpath('.//div[@class="p-img"]//img/@src').extract_first() #封面照片连接
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
item['book_author']=li.xpath('.//span[@class="author_type_1"]/a/text()').extract() #作者
item['book_publish']=li.xpath('.//span[@class="p-bi-store"]/a/@title').extract_first() #出版社
item['book_publish_date']=li.xpath('.//span[@class="p-bi-date"]/text()').extract_first().strip() #出版日期
item['book_sku']=li.xpath('./div/@data-sku').extract_first()#书籍编号
#这边价格是去后端再次请求得到的
#因为这边后边还需要用到item,所以需要用到深拷贝,sccrapy有三级分类的都要注意是否要使用深拷贝
yield scrapy.Request('https://p.3.cn/prices/mgets?skuIds={}'.format(item['book_sku']),callback=self.parse_book_price,meta={'item':deepcopy(item)})
#列表翻页
next_url=response.xpath('//a[@class="pn-next"]/@href').extract_first()
if next_url is not None:
next_url=urllib.parse.urljoin(response.url,next_url)
yield scrapy.Request(next_url,callback=self.parse_book_list,meta={'item',item})
#解析价格函数
def parse_book_price(self,response):
item=response.meta['item']
#这边返回的json串
book_info_dict=json.loads(response.body.decode())
item['boo_price']=book_info_dict[0]['op']
print('=========',item)
2.item
import scrapy
class JingdongItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
b_cate=scrapy.Field()
s_href=scrapy.Field()
s_cate=scrapy.Field()
book_name=scrapy.Field()
book_img=scrapy.Field()
book_author=scrapy.Field()
book_publish=scrapy.Field()
book_publish_date=scrapy.Field()
book_sku=scrapy.Field()
boo_price=scrapy.Field()
3.settings
# -*- coding: utf-8 -*-
# Scrapy settings for JingDong project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# https://doc.scrapy.org/en/latest/topics/settings.html
# https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'JingDong'
SPIDER_MODULES = ['JingDong.spiders']
NEWSPIDER_MODULE = 'JingDong.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16
# Disable cookies (enabled by default)
#COOKIES_ENABLED = False
# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False
# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Language': 'en',
#}
# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'JingDong.middlewares.JingdongSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'JingDong.middlewares.JingdongDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
# 'JingDong.pipelines.JingdongPipeline': 300,
'scrapy_redis.pipelines.RedisPipeline': 400
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False
# Enable and configure HTTP caching (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
SCHEDULER = "scrapy_redis.scheduler.Scheduler"
SCHEDULER_PERSIST = True
REDIS_URL='redis://127.0.0.1:6379'