淘宝增加爬虫并分析

README.md

@@ -56,21 +56,31 @@
 
 ## show
 
-- bilibili自动登录测试正常，成功率98%
+### bilibili自动登录测试正常，成功率98%
 
 ![](./image/bilibili.jpg)
 
-- web微信
+### web微信
 
 
 ![Alt text](./image/weixin.jpg)
 
-- 图虫爬虫
+### 图虫爬虫
 
 ![](./image/Jietu20190306-232224.jpg)
 
 ![](./image/Jietu20190306-232303.jpg)
 
+### 淘宝 - 淘宝网
+- taobao.py 为模拟登录
+- 剩下的为爬虫
+
+```
+1. 爬取淘宝各子标签，按销量排名商品信息，按分类保存至MongoDB
+2. 通过pandas进行数据分析
+3. 将商品在各省分布、销量排行、地图分布等通过matplotlib绘图显示
+```
+
 ## tips of pull request 
 
 - 欢迎大家一起来 pull request 

taobao/scrapy.cfg

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = taobao.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = taobao

taobao/taobao/items.py

@@ -0,0 +1,21 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class TaobaoItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    goods_url=scrapy.Field()
+    title=scrapy.Field()
+    price=scrapy.Field()
+    sell_count =scrapy.Field()
+    goods_class=scrapy.Field()
+    seller=scrapy.Field()
+    area=scrapy.Field()
+

taobao/taobao/middlewares.py

@@ -0,0 +1,103 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class TaobaoSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(self, response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(self, response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(self, response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(self, start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)
+
+
+class TaobaoDownloaderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the downloader middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_request(self, request, spider):
+        # Called for each request that goes through the downloader
+        # middleware.
+
+        # Must either:
+        # - return None: continue processing this request
+        # - or return a Response object
+        # - or return a Request object
+        # - or raise IgnoreRequest: process_exception() methods of
+        #   installed downloader middleware will be called
+        return None
+
+    def process_response(self, request, response, spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        return response
+
+    def process_exception(self, request, exception, spider):
+        # Called when a download handler or a process_request()
+        # (from other downloader middleware) raises an exception.
+
+        # Must either:
+        # - return None: continue processing this exception
+        # - return a Response object: stops process_exception() chain
+        # - return a Request object: stops process_exception() chain
+        pass
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

taobao/taobao/pipelines.py

@@ -0,0 +1,32 @@
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+import pymongo
+
+class TaobaoPipeline(object):
+    def __init__(self,mongo_url,mongo_db):
+        self.mongo_url=mongo_url
+        self.mongo_db=mongo_db
+    @classmethod
+    def from_crawler(cls,crawler):
+        return cls(
+            mongo_url=crawler.settings.get("MONGO_URL"),
+            mongo_db=crawler.settings.get("MONGO_DB")
+        )
+
+    def open_spider(self, spider):
+        self.client = pymongo.MongoClient(self.mongo_url)
+        self.db = self.client[self.mongo_db]
+
+    def process_item(self, item, spider):
+        sheet = self.db[item['goods_class']]
+        if sheet.find_one({'goods_url':item['goods_url']}):
+            print('数据已存在')
+        else:
+            sheet.insert(dict(item))
+
+        return item
+

taobao/taobao/settings.py

@@ -0,0 +1,106 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for taobao 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 = 'taobao'
+
+SPIDER_MODULES = ['taobao.spiders']
+NEWSPIDER_MODULE = 'taobao.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'taobao (+http://www.yourdomain.com)'
+
+# 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 = {
+   # 'taobao.middlewares.TaobaoSpiderMiddleware': 543,
+    'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
+
+}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+DOWNLOADER_MIDDLEWARES = {
+   # 'taobao.middlewares.TaobaoDownloaderMiddleware': 543,
+   'scrapy_splash.SplashCookiesMiddleware': 723,
+   'scrapy_splash.SplashMiddleware': 725,
+   'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
+}
+
+# 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 = {
+   'taobao.pipelines.TaobaoPipeline': 300,
+}
+
+# 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_splash.SplashAwareFSCacheStorage'
+DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'
+
+# REDIRECT_ENABLED = False
+SPLASH_URL='http://localhost:8050'
+
+# REDIS_URL='redis://:zkyr1006@localhost:6379/1'
+MONGO_URL = 'mongodb://admin:zkyr1006@localhost:28018'
+MONGO_DB='taobao'
+
+# 遇到502，504，重复请求
+RETRY_HTTP_CODES = [502, 504]

taobao/taobao/spiders/__init__.py

@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

taobao/taobao/spiders/analysis.py

@@ -0,0 +1,216 @@
+#!/home/zkfr/.local/share/virtualenvs/xf-5EfV3Nly/bin/python
+#-*- coding:utf-8 -*-
+# @author : MaLei 
+# @datetime : 2018-10-06 12:50
+# @file : analysis.py
+# @software : PyCharm
+import numpy as np
+from pymongo import MongoClient
+from  matplotlib import pyplot as plt
+import re,json,jieba,pandas
+from collections import Counter
+from wordcloud import WordCloud
+import seaborn as sns
+# matprotlib显示中文
+from pylab import *
+mpl.rcParams['font.sans-serif'] = ['SimHei']
+
+# 从mongodb中获取数据
+def data_analysis(parameter):
+    client = MongoClient('mongodb://admin:zkyr1006@localhost:28018')
+    db = client.taobao
+    colls = [db.内搭, db.外套, db.牛仔裤, db.秋季套装]
+    data=[]
+    for coll in colls:
+        list_data=coll.aggregate([{'$group': {'_id': 0, parameter: {'$push': '$'+parameter}}}]).next()[parameter]
+        data+=list_data
+    return data
+    # print(provience)
+
+# 商品所属省份分布柱状图
+def provience():
+    data=[]
+    provs=data_analysis('area')
+    # print(provience)
+    for each in provs:
+        prov = (each.split())[0]
+        data.append(prov)
+    count={}
+    for i in data:
+        count[i]=data.count(i)
+    # print(count)
+    prov=list(count.keys())
+    nums=list(count.values())
+    return prov,nums
+
+def prov_plt():
+    prov, nums = provience()
+    plt.figure(figsize=(8, 4))
+    plt.xticks(rotation=0)
+    plt.bar(prov, nums, color='g')
+    plt.xlabel('省份')
+    plt.ylabel('数量')
+    plt.title('不同省份数量分布图')
+    plt.legend()
+    plt.show()
+
+# 词云及根据词云数据进行分析的柱状图
+def cloud_plt():
+    def cloud_data():
+        title=data_analysis('title')
+        titles=[]
+        # 对每个标题进行分词
+        for each in title:
+            title_cut=jieba.lcut(each)
+            titles.append(title_cut)
+
+        # 剔除不需要的词语
+        title_del=[]
+        for line in titles:
+            line_del=[]
+            for word in line:
+                if word not in ['2018','妈妈','❤','】','【',' ','Chinism','工作室','倔强']:
+                    line_del.append(word)
+            title_del.append(line_del)
+        # print(title_del)
+
+        # 元素去重,每个标题中不含重复元素
+        title_clean=[]
+        for each in title_del:
+            line_dist=[]
+            for word in each:
+                if word not in line_dist:
+                    line_dist.append(word)
+            title_clean.append(line_dist)
+
+        # 将所有词语转为一个list
+        allwords_dist=[]
+        for line in title_clean:
+            for word in line:
+                allwords_dist.append(word)
+        # 把列表转为数据框
+        allwords_dist=pandas.DataFrame({'allwords':allwords_dist})
+        # 对词语进行分类汇总
+        word_count=allwords_dist.allwords.value_counts().reset_index()
+        # 添加列名
+        word_count.columns=['word','count']
+        # print(allwords_dist)
+        return word_count,title_clean
+
+    def cloud_data_count():
+        # 获取商品销量数据
+        sell_count = data_analysis('sell_count')
+        word_count, title_clean = cloud_data()
+        ws_count = []
+        # 商品中包含统计的词时，将其销量加入list
+        for each in word_count.word:
+            i = 0
+            s_list = []
+            for t in title_clean:
+                if each in t:
+                    s_list.append(int(sell_count[i]))
+                    # print(s_list)
+                i += 1
+            # 统计一个关键词所包含商品的销量总数
+            ws_count.append(sum(s_list))
+        # 把列表转为数据框
+        ws_count = pandas.DataFrame({'ws_count': ws_count})
+        # 把word_count, ws_count合并为一个表
+        word_count = pandas.concat([word_count, ws_count], axis=1, ignore_index=True)
+        word_count.columns = ['word', 'count', 'ws_count']
+        # 升序排列
+        word_count.sort_values('ws_count', inplace=True, ascending=True)
+        # 取最大30行数据
+        df_ws = word_count.tail(30)
+        return df_ws
+
+    # 图云部分
+    word_count=cloud_data()[0]
+    # 设置字体，背景颜色，字体最大号，
+    w_c=WordCloud(font_path='/usr/local/lib/python3.6/dist-packages/matplotlib/mpl-data/fonts/ttf/simhei.ttf',
+                  background_color='white',
+                  max_font_size=60,
+                  margin=1)
+    # 取前400个词进行可视化
+    wc=w_c.fit_words({x[0]:x[1] for x in word_count.head(1000).values})
+    # 设置图优化
+    plt.imshow(wc,interpolation='bilinear')
+    # 去除边框
+    plt.axis('off')
+    plt.show()
+
+    # 统计分析柱状图部分
+    data = cloud_data_count()
+    index = np.arange(data.word.size)
+    # plt.figure(figsize=(6,12))
+    plt.barh(index, data.ws_count, align='center', alpha=0.8)
+    plt.yticks(index, data.word)
+    # 添加数据标签
+    for y, x in zip(index, data.ws_count):
+        plt.text(x, y, '%.0f' % x, ha='left', va='center')
+    plt.show()
+
+
+def impact_analysis():
+    sell_count=pandas.DataFrame({'sell_count': data_analysis('sell_count')})
+    price=[]
+    for i in data_analysis('price'):
+        p=i.split('-')
+        p_i=p[0].split('.')
+        price.append(p_i[0])
+    price=pandas.DataFrame({'price':price})
+    infos=pandas.concat([sell_count, price], axis=1, ignore_index=True)
+    infos.columns = ['sell_count', 'price'] #一定注意定义到columns
+    infos['sell_count']=infos.sell_count.astype('int')
+    infos['price']=infos.sell_count.astype('int')
+    infos['GMV']=infos['sell_count']*infos['price']
+    # print(infos.GMV.dtype)
+    sns.regplot(x='price',y='GMV',data=infos)
+    # sns.lmplot(x='price',y='GMV',data=infos,x_jitter=.05)
+    plt.show()
+
+def mean_sale():
+    prov,nums=provience()
+    sell_count = data_analysis('sell_count')
+    areas=[]
+    count=[]
+    for i in data_analysis('area'):
+        areas.append((i.split(' '))[0])
+    for each in prov:
+        counts=[]
+        for i in range(0,len(areas)):
+            if each==areas[i]:
+                counts.append(int(sell_count[i]))
+        count.append(sum(counts))
+    # print(count)
+    count=pandas.DataFrame({'count':count})
+    prov=pandas.DataFrame({'prov':prov})
+    nums=pandas.DataFrame({'nums':nums})
+    data = pandas.concat([nums,count], axis=1, ignore_index=True)
+    data.columns = ['nums','count']
+    data['nums']=data.nums.astype('int')
+    m_l=data['count']/data['nums']
+    mean_list=[]
+    for each in m_l:
+        each=str(each).split('.')
+        mean_list.append(each[0])
+    mean_list=pandas.DataFrame({'mean_list':mean_list},dtype=np.int)
+    infos = pandas.concat([prov,mean_list], axis=1, ignore_index=True)
+    infos.columns = ['prov','mean_list']
+    infos['mean_list']=infos.mean_list.astype('int')
+    infos.sort_values('mean_list',inplace=True,ascending=False)
+    infos=infos.reset_index()
+    index=np.arange(infos.mean_list.size)
+    print(infos)
+    plt.figure(figsize=(8,4))
+    plt.bar(index,infos.mean_list,color='purple')
+    plt.xticks(index,infos.prov,rotation=0)
+    plt.xlabel('省份')
+    plt.ylabel('平均销量')
+    plt.title('不同省份销量分布')
+    plt.show()
+
+mean_sale()
+
+# def hot_map():
+

taobao/taobao/spiders/taobao.py

@@ -0,0 +1,132 @@
+# -*- coding: utf-8 -*-
+import scrapy,numpy
+from scrapy import Selector
+from taobao.items import TaobaoItem
+from scrapy.spiders import CrawlSpider, Rule
+from bs4 import BeautifulSoup
+import requests,re
+from scrapy_splash import SplashRequest
+from urllib.parse import urlencode
+
+
+class comicspider(scrapy.Spider):
+    name = 'tb'
+    allowed_domains=['www.taobao.com']
+    start_urls=['https://www.taobao.com']
+
+    headers1 = {
+        'Connection': 'keep-alive',
+        'Host': 'www.taobao.com',
+        'Accept-Encoding':'gzip, deflate, br',
+        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:58.0) Gecko/20100101 Firefox/58.0'
+    }
+
+    def start_requests(self):
+        yield scrapy.Request(url=self.start_urls[0],callback=self.sub_nav,headers=self.headers1)
+
+    def sub_nav(self, response):
+        page=Selector(response)
+        # 女装、男装、内衣
+        # sub_navs1=page.xpath('//ul[@class="service-bd"]/li[position()<2]/a/text()').extract()
+        # print(sub_navs1)
+        sub_urls1=page.xpath('//ul[@class="service-bd"]/li[position()<2]/a/@href').extract()
+        # print(sub_urls1)
+        for sub_url in sub_urls1:
+            yield scrapy.Request(url=sub_url,callback=self.parse0,headers=self.headers1,dont_filter=True)
+
+    def parse0(self, response):
+        headers2 = {
+            'Connection': 'keep-alive',
+            'Host': 's.taobao.com',
+            'Accept-Encoding': 'gzip, deflate, br',
+            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:58.0) Gecko/20100101 Firefox/58.0'
+        }
+        page=Selector(response)
+        # 连衣裙、毛衫/内搭、秋外套……
+        sub_navs11=page.xpath('//dl[@class="theme-bd-level2"]/dt/div/a/text()').extract()
+        del sub_navs11[-1]
+        sub_urls11=page.xpath('//dl[@class="theme-bd-level2"]/dt/div/a/@href').extract()
+        del sub_urls11[-1]
+        for i in range(0,len(sub_urls11)):
+            page_urls=[]
+            page_urls.append(sub_urls11[i]+'&sort=sale-desc')
+            s=0
+            sub_nav=sub_navs11[i]
+            for j in range(1,20):
+            # for j in range(0, 1):
+                senddata = {
+                    'sort':'sale-desc',
+                    'bcoffset': '0',
+                    's': s
+                }
+                page_url=sub_urls11[i]+'&'+ urlencode(senddata)
+                page_urls.append(page_url)
+                s+=60
+            # print(page_urls)
+
+            for page_url in page_urls:
+                yield SplashRequest(page_url,self.parse1,args={'wait':0.5},splash_headers=headers2,dont_filter=True,meta={'sub_nav':sub_nav})
+                # yield scrapy.Request(page_url,callback=self.parse1,headers=headers2,dont_filter=True,meta={'sub_nav':sub_nav})
+
+    def parse1(self, response):
+        headers3 = {
+            'Connection': 'keep-alive',
+            'Host': 'item.taobao.com',
+            'Accept-Encoding': 'gzip, deflate, br',
+            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:58.0) Gecko/20100101 Firefox/58.0'
+        }
+        page=Selector(response)
+        goods_urls=page.xpath('//div[@class="grid g-clearfix"]/div[@class="items"]/div/div[3]/div[2]/a/@href').extract()
+        # goods_class=page.xpath('//div[@class="grid g-clearfix"]/div[@class="items"]/div[1]/div[3]/div[2]/a/span[@class="H"]/text()').extract()
+        goods_class=response.meta['sub_nav']
+        areas = page.xpath('//div[@class="row row-3 g-clearfix"]/div[@class="location"]/text()').extract()
+        sell_counts=page.xpath('//div[@class="deal-cnt"]/text()').extract()
+
+        # print(goods_urls)
+        for i in range(0,len(goods_urls)):
+            area=areas[i]
+            sell_count=sell_counts[i]
+            goods_url='http:'+goods_urls[i]
+            yield scrapy.Request(goods_url,self.parse2,headers=headers3,dont_filter=True,
+                                 meta={'goods_url':goods_url,
+                                       'goods_class':goods_class,
+                                       'area':area,
+                                       'sell_count':sell_count})
+
+    def parse2(self, response):
+        item=TaobaoItem()
+        page=Selector(response)
+        # print(response.text)
+        item['title']=page.xpath('//head/title/text()').extract()[0][:-4]
+        item['goods_url']=response.meta['goods_url']
+        item['goods_class']=response.meta['goods_class']
+        item['price']=page.xpath('//strong[@id="J_StrPrice"]/em[@class="tb-rmb-num"]/text()').extract()[0]
+        item['sell_count']=response.meta['sell_count'][:-3]
+        item['area']=response.meta['area']
+        # item['trade']=page.xpath('//div[@class="tb-sell-counter"]/a/strong/text()').extract()
+        seller= page.xpath('//div[@class="tb-shop-name"]/dl/dd/strong/a/@title').extract()
+        if len(seller)==1:
+            item['seller']=seller[0]
+        else:
+            seller=page.xpath('//span[@class="shop-name-title"]/@title').extract()
+            if len(seller)==1:
+                item['seller'] = seller[0]
+            else:
+                seller = page.xpath('//span[@class="shop-name-title"]/@title').extract()
+                if len(seller) == 1:
+                    item['seller'] = seller[0]
+                else:
+                    item['seller'] = '未知'
+
+        yield item
+
+
+
+
+
+
+
+

taobao/text.py

@@ -0,0 +1,48 @@
+# -*- coding: utf-8 -*-
+import requests
+
+# headers = {
+#     'Connection': 'keep-alive',
+#     'Host': 'item.taobao.com',
+#     'Accept-Encoding': 'gzip, deflate, br',
+#     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:58.0) Gecko/20100101 Firefox/58.0'
+# }
+# url='https://item.taobao.com/item.htm?spm=a219r.lm874.14.1.422f2140YG82hc&id=574990577169&ns=1&abbucket=20#detail'
+# # yield SplashRequest(page_url, self.parse1, args={'wait': 0.5}, splash_headers=self.headers, dont_filter=True)
+# page=requests.get(url,headers=headers)
+# print(page.text)
+import re
+# Start your middleware class
+class ProxyMiddleware(object):
+    # overwrite process request
+    def process_request(self, request, spider):
+        # Set the location of the proxy
+        request.meta['proxy'] =self.proxy_test()
+
+    def proxy_test(self):
+        # ....
+        def get_proxy():
+            return requests.get("http://192.168.1.137:8001/get/").text
+
+        def delete_proxy(proxy):
+            requests.get("http://192.168.1.137:8001/delete/?proxy={}".format(proxy))
+
+        proxy = "http://{}".format(get_proxy())
+        try:
+            requests.get('https://www.baidu.com', proxies={"proxy": proxy})
+            print(proxy,'代理可用')
+            # 使用代理访问
+            return proxy
+        except Exception:
+            # 出错1次, 删除代理池中代理
+            delete_proxy(proxy)
+            return None
+
+DOWNLOADER_MIDDLEWARES = {
+   # 'taobao.middlewares.TaobaoDownloaderMiddleware': 543,
+   'scrapy_splash.SplashCookiesMiddleware': 723,
+   'scrapy_splash.SplashMiddleware': 725,
+   'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
+   'taobao.middlewares.ProxyMiddleware': 100,
+}