1、创建Scrapy项目
scrapy startproject PosProductRedis2.进入项目目录，使用命令genspider创建Spider
scrapy genspider posproductredis XXXX.com3、定义要抓取的数据（处理items.py文件）
# -*- coding: utf-8 -*-
import scrapy
class PosproductredisItem(scrapy.Item):
# 获取序号
number_list = scrapy.Field()
# 获取ID
id_list = scrapy.Field()
# 获取商家名称
qiye_list = scrapy.Field()
# 获取分类
product_list = scrapy.Field()
# 获取产品名称
product_name_list = scrapy.Field()
# 获取销售情况
sale_list = scrapy.Field()
# 销售标题（有空格）
sales_title = scrapy.Field()
# 获取销售区域
sales_area = scrapy.Field()
# 获取规格
product_size = scrapy.Field()
# 获取起订量
product_quantity = scrapy.Field()
# 获取零售价
retail_price = scrapy.Field()
# 获取零售促销价
promotion_price = scrapy.Field()
# 获取skuid，可以不写
# skuid = scrapy.Field()
4、编写提取item数据的Spider（在spiders文件夹下：posproductredis.py）
# -*- coding: utf-8 -*-
# 利用scrapy_redis将pos后台数据包含价格、规格、起订量、销售区域等信息全部保存到excel中
import scrapy
from PosProductRedis.items import PosproductredisItem
from scrapy_redis.spiders import RedisSpider
import re
class PosproductredisSpider(RedisSpider):
name = 'posproductredis'
allowed_domains = ['XXXX.com']
redis_key = "PosproductredisSpider:start_urls"
# lpush PosproductredisSpider:start_urls https://pos.XXX.com/item/itemonlist.html?d-49489-p=1
login_page = "https://pos.XXXX.com/login.html"
def start_requests(self):
yield scrapy.Request(url=self.login_page,callback=self.login)
def login(self, response):
self.username = input("请输入账号：")
self.password = input("请输入密码：")
yield scrapy.FormRequest.from_response(
response,
formdata={"j_username":self.username, "j_password":self.password},
callback = self.parse_page
)
# 获取登录成功的状态，访问需要登录后才能访问的页面
def parse_page(self, response):
if "loginerror" in response.body.decode('utf-8'):
print("登录失败，错误的手机号或密码！")
if "</span>首页" in response.body.decode('utf-8'):
print("欢迎您'%s',成功登录POS管理系统！" % (self.username))
print("请在slaver端（爬虫程序执行端）输入：lpush %s 爬取列表页网址"%(self.redis_key))
# 登录成功后获取在线产品的列表页，并回调parse()函数处理数据
# yield scrapy.Request(response.url, callback=self.parse)
def parse(self, response):
# print("数据处理中......")
items =[]
# 获取下一页的链接地址,列表，需要和“https://pos.XXXX.com/item/itemonlist.html”进行拼接
next_url_list = response.xpath('//body//div//div/span/span[@class="paginate_button"]/a/@href').extract()
for each in response.xpath('//div[@class="dataTables_wrapper"]'):
# 序号
number_list = each.xpath('.//td[1]/text()').extract()
# 获取ID
id_list = each.xpath('.//tbody//tr//td//input[@onclick="homeShow(this)"]/@value').extract()
# 获取商家名称
qiye_list = each.xpath('.//td[2]/text()').extract()
# 获取分类
product_list = each.xpath('.//td[4]/text()').extract()
# 获取产品名称
product_name_list = each.xpath('.//td[3]/a/text()').extract()
for i in range(len(id_list)):
item = PosproductredisItem()
item['number_list'] = number_list[i].strip()
item['id_list'] = id_list[i]
item['qiye_list'] = qiye_list[i].strip()
item['product_list'] = product_list[i].strip()
item['product_name_list'] = product_name_list[i].strip()
# yield item
items.append(item)
for item in items:
id_url = "https://pos.XXXX.com/item/showitem.html?item.id="+ item['id_list']
yield scrapy.Request(url=id_url,meta={'meta_1':item},callback=self.parse_id)
pattern = re.compile(r"/?d-49489-p=(\d+)")
for url in next_url_list:
i =pattern.search(url).group(1)
print("第%s页数据处理中...."%i)
fullurl = 'https://pos.XXXX.com/item/itemonlist.html'+ str(url)
yield scrapy.Request(url=fullurl,callback=self.parse)
# 处理id链接，获取价格、规格、起订量等信息
def parse_id(self,response):
# 提取每次response的meta数据
meta_1 = response.meta['meta_1']
# print("meta_1",meta_1)
item = PosproductredisItem()
# 获取销售标题
sales_title = response.xpath('//div[@id="tabs-1"]/p[8]/span[@class="field"]/text()').extract()
# 获取销售情况(有空格)
sale_list = response.xpath('//div[@id="tabs-1"]/p[6]/span/text()').extract()
# 获取销售区域
sales_area = response.xpath('//div[@id="tabs-6"]/table/tbody[@id="review_list"]/tr/td[2]/text()').extract()
# 获取规格
product_size = response.xpath('//div[@id="tabs"]/div[@id="tabs-5"]/table/tbody/tr/td[1]/text()').extract()
# 获取起订量
product_quantity = response.xpath('//div[@id="tabs"]/div[@id="tabs-5"]/table/tbody/tr/td[8]/text()').extract()
# 获取规格对应的skuid号码》》》javascript:show('688')
skuid_list = response.xpath('//div[@id="tabs"]/div[@id="tabs-5"]/table/tbody/tr/td[9]/a/@href').extract()
# 对skuid_list结果进行正则匹配出数字
pattent = re.compile("\d+")
# items = []
# 有规格必然有起订量，这两个是一一对应，并且是必填项不可能为空，只要是在线的产品都会有规格和起订量
for i in range(len(product_size)):
# items = []
item['product_size'] = product_size[i]
item['product_quantity'] = product_quantity[i]
# 如果是多个销售区域，那么用分号隔开
if len(sales_area)>1:
item['sales_area'] = "；".join(sales_area)
elif len(sales_area) == 1:
area_list ="北京市,天津市,河北省,山西省,内蒙古,辽宁省,吉林省,黑龙江省,上海市,江苏省,浙江省,安徽省,福建省,江西省,山东省,河南省,湖北省,湖南省,广东省,广西,海南省,重庆市,四川省,贵州省,云南省,西藏,陕西省,甘肃省,青海省,宁夏,新疆"
area_list2 = "北京市,天津市,河北省,山西省,内蒙古,辽宁省,吉林省,黑龙江省,上海市,江苏省,浙江省,安徽省,福建省,江西省,山东省,河南省,湖北省,湖南省,广东省,广西,海南省,重庆市,四川省,贵州省,云南省,西藏,陕西省,甘肃省,青海省,宁夏,新疆省"
full_area_list = "北京市,天津市,河北省,山西省,内蒙古,辽宁省,吉林省,黑龙江省,上海市,江苏省,浙江省,安徽省,福建省,江西省,山东省,河南省,湖北省,湖南省,广东省,广西,海南省,重庆市,四川省,贵州省,云南省,西藏,陕西省,甘肃省,青海省,宁夏,新疆,台湾省,香港,澳门"
if sales_area[0] == area_list or sales_area[0] == area_list2:
item['sales_area'] = "全国（不含港澳台）"
elif sales_area[0] == full_area_list:
item['sales_area'] = "全国"
else:
item['sales_area'] = sales_area[0]
else:
item['sales_area'] = "无区域"
item['sales_title'] = sales_title[0].strip()
item['sale_list'] = sale_list[0].strip()
item['number_list'] = meta_1['number_list']
item['id_list'] = meta_1['id_list']
item['qiye_list'] = meta_1['qiye_list']
item['product_list'] = meta_1['product_list']
item['product_name_list'] = meta_1['product_name_list']
# items.append(item)
# 提取javascript:show('688')里面skuid号码
skuid_number = pattent.search(skuid_list[i]).group()
# 可以把skuid保存下来，这里无用就不保存了
# item['skuid'] = skuid_number
skuid_url = "https://pos.XXXX.com/item/showitemprice.html?sku.id="+ skuid_number
yield scrapy.Request(url=skuid_url,meta={'meta_2':item},callback=self.parse_skuid)
def parse_skuid(self,response):
# 提取每次response的meta数据
meta_2 = response.meta['meta_2']
item = PosproductredisItem()
# 零售价,将重复的价格筛选掉，用set去掉重复项,并转换为列表
retail_price_list = response.xpath('//div[@id="tabs-1"]/table[@id="item"]/tbody/tr/td[2]/text()').extract()
retail_price = list(set(retail_price_list))
for i in range(len(retail_price)):
if retail_price[i] == "0.0":
retail_price[i] = '零售价待定'
elif retail_price[i] == "0.00":
retail_price[i] = '零售价数据0.00有误'
# 如果是多个价格，用分号隔开
if len(retail_price)>1:
item['retail_price'] = "；".join(retail_price)
elif len(retail_price) ==1:
item['retail_price'] = retail_price[0]
# 获取零售促销价,将重复的促销价筛选掉，用set去掉重复项,并转换为列表
promotion_price_list = response.xpath('//div[@id="tabs-1"]/table[@id="item"]/tbody/tr/td[3]/text()').extract()
promotion_price = list(set(promotion_price_list))
for i in range(len(promotion_price)):
if promotion_price[i] == "0.0":
promotion_price[i] = '无促销价'
elif promotion_price[i] == "0.00":
promotion_price[i] = '促销价数据0.00有误'
# 如果是多个促销价格，用分号隔开
if len(promotion_price)>1:
item['promotion_price'] = "；".join(promotion_price)
elif len(promotion_price) ==1:
item['promotion_price'] = promotion_price[0]
item['number_list'] = meta_2['number_list']
# item['skuid'] = meta_2['skuid']
item['id_list'] = meta_2['id_list']
item['qiye_list'] = meta_2['qiye_list']
item['product_list'] = meta_2['product_list']
item['product_name_list'] = meta_2['product_name_list']
item['sales_title'] = meta_2['sales_title']
item['sale_list'] = meta_2['sale_list']
item['product_size'] = meta_2['product_size']
item['product_quantity'] = meta_2['product_quantity']
item['sales_area'] = meta_2['sales_area']
yield item
5.处理pipelines管道文件保存数据，可将结果保存到文件中（pipelines.py）
# -*- coding: utf-8 -*-
import json
from openpyxl import Workbook
import time
# 转码操作
class MyEncoder(json.JSONEncoder):
def default(self, o):
if isinstance(o, bytes):
return str(o, encoding='utf-8')
return json.JSONEncoder.default(self, o)
class PosproductredisPipeline(object):
def __init__(self):
self.wb = Workbook()
self.ws = self.wb.active
# 创建表头
self.ws.append(['序号', 'ID', '商家名称', '产品分类',
'产品名称', '销售标题','销售情况', '零售价',
'促销价', '规格', '起订量', '销售区域'
])
def process_item(self, item, spider):
text = [item['number_list'], item['id_list'], item['qiye_list'], item['product_list'],
item['product_name_list'], item['sales_title'], item['sale_list'], item['retail_price'],
item['promotion_price'], item['product_size'], item['product_quantity'], item['sales_area']]
self.ws.append(text)
return item
def close_spider(self, spider):
# 给保存的文件名字加上个当天的日期年月日
file_end_name = time.strftime("%Y-%m-%d", time.localtime())
self.wb.save("pos_product_redis"+file_end_name+'.xlsx')
print("数据处理完成，谢谢使用！")6.配置settings文件（settings.py）
# 使用scrapy-redis里的去重组件，不再使用scrapy默认的去重
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
# 使用了scrapy-redis里的调度器组件，不再使用scrapy默认的调度器
SCHEDULER = "scrapy_redis.scheduler.Scheduler"
# 允许暂停，redis请求记录不丢失
SCHEDULER_PERSIST = True
# 不写默认存储到本地数据库
# REDIS_HOST = "192.168.0.109"
# REDIS_PORT = 6379
# 默认的scrapy-redis请求队列形式
SCHEDULER_QUEUE_CLASS = "scrapy_redis.queue.SpiderPriorityQueue"
# 队列形式，先进先出,选这个会报错：Unhandled error in Deferred
# SCHEDULER_QUEUE_CLASS = "scrapy_redis.queue.SpiderQueue"
# 栈形式，先进后出
#SCHEDULER_QUEUE_CLASS = "scrapy_redis.queue.SpiderStack"
# Configure item pipelines去掉下面注释，打开管道文件,添加RedisPipeline
ITEM_PIPELINES = {
'PosProductRedis.pipelines.PosproductredisPipeline': 300,
'scrapy_redis.pipelines.RedisPipeline': 400,
}
# Obey robots.txt rules，具体含义参照：https://blog.csdn.net/z564359805/article/details/80691677
ROBOTSTXT_OBEY = False
# Override the default request headers:添加User-Agent信息
DEFAULT_REQUEST_HEADERS = {
'User-Agent': 'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0);',
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Language': 'en',
}
# 还可以将日志存到本地文件中（可选添加设置）
LOG_FILE = "posproductredis.log"
LOG_LEVEL = "DEBUG"
# 包含print全部放在日志中
LOG_STDOUT = True
7.参照以下链接打开redis数据库：
https://blog.csdn.net/z564359805/article/details/808081558.以上设置完毕，进行爬取：进入到spiders文件夹下执行项目命令，启动Spider：
scrapy runspider posproductredis.py9.在Master端(核心服务器)的redis-cli输入push指令，参考格式：
输入：lpush PosproductredisSpider:start_urls https://pos.XXXX.com/item/itemonlist.html?d-49489-p=1