python爬虫爬取淘宝商品信息（selenum+phontomjs）

本文实例为大家分享了python爬虫爬取淘宝商品的具体代码，供大家参考，具体内容如下

1、需求目标 ：

进去淘宝页面，搜索耐克关键词，抓取 商品的标题，链接，价格，城市，旺旺号，付款人数，进去第二层，抓取商品的销售量，款号等。

2、结果展示

3、源代码

# encoding: utf-8
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import time
import pandas as pd
time1=time.time()
from lxml import etree
from selenium import webdriver
#########自动模拟
driver=webdriver.PhantomJS(executable_path='D:/Python27/Scripts/phantomjs.exe')
import re

#################定义列表存储#############
title=[]
price=[]
city=[]
shop_name=[]
num=[]
link=[]
sale=[]
number=[]

#####输入关键词耐克(这里必须用unicode)
keyword="%E8%80%90%E5%85%8B"


for i in range(0,1):

  try:
    print "...............正在抓取第"+str(i)+"页..........................."

    url="https://s.taobao.com/search?q=%E8%80%90%E5%85%8B&imgfile=&js=1&stats_click=search_radio_all%3A1&initiative_id=staobaoz_20170710&ie=utf8&bcoffset=4&ntoffset=4&p4ppushleft=1%2C48&s="+str(i*44)
    driver.get(url)
    time.sleep(5)
    html=driver.page_source

    selector=etree.HTML(html)
    title1=selector.xpath('//div[@class="row row-2 title"]/a')
    for each in title1:
      print each.xpath('string(.)').strip()
      title.append(each.xpath('string(.)').strip())


    price1=selector.xpath('//div[@class="price g_price g_price-highlight"]/strong/text()')
    for each in price1:
      print each
      price.append(each)


    city1=selector.xpath('//div[@class="location"]/text()')
    for each in city1:
      print each
      city.append(each)


    num1=selector.xpath('//div[@class="deal-cnt"]/text()')
    for each in num1:
      print each
      num.append(each)


    shop_name1=selector.xpath('//div[@class="shop"]/a/span[2]/text()')
    for each in shop_name1:
      print each
      shop_name.append(each)


    link1=selector.xpath('//div[@class="row row-2 title"]/a/@href')
    for each in link1:
      kk="https://" + each


      link.append("https://" + each)
      if "https" in each:
        print each

        driver.get(each)
      else:
        print "https://" + each
        driver.get("https://" + each)
      time.sleep(3)
      html2=driver.page_source
      selector2=etree.HTML(html2)

      sale1=selector2.xpath('//*[@id="J_DetailMeta"]/div[1]/div[1]/div/ul/li[1]/div/span[2]/text()')
      for each in sale1:
        print each
        sale.append(each)

      sale2=selector2.xpath('//strong[@id="J_SellCounter"]/text()')
      for each in sale2:
        print each
        sale.append(each)

      if "tmall" in kk:
        number1 = re.findall('<ul id="J_AttrUL">(.*?)</ul>', html2, re.S)
        for each in number1:
          m = re.findall('>*号: (.*?)</li>', str(each).strip(), re.S)
          if len(m) > 0:
            for each1 in m:
              print each1
              number.append(each1)

          else:
            number.append("NULL")

      if "taobao" in kk:
        number2=re.findall('<ul class="attributes-list">(.*?)</ul>',html2,re.S)
        for each in number2:
          h=re.findall('>*号: (.*?)</li>', str(each).strip(), re.S)
          if len(m) > 0:
            for each2 in h:
              print each2
              number.append(each2)

          else:
            number.append("NULL")

      if "click" in kk:
        number.append("NULL")

  except:
    pass


print len(title),len(city),len(price),len(num),len(shop_name),len(link),len(sale),len(number)

# #
# ######数据框
data1=pd.DataFrame({"标题":title,"价格":price,"旺旺":shop_name,"城市":city,"付款人数":num,"链接":link,"销量":sale,"款号":number})
print data1
# 写出excel
writer = pd.ExcelWriter(r'C:\\taobao_spider2.xlsx', engine='xlsxwriter', options={'strings_to_urls': False})
data1.to_excel(writer, index=False)
writer.close()

time2 = time.time()
print u'ok,爬虫结束!'
print u'总共耗时：' + str(time2 - time1) + 's'
####关闭浏览器
driver.close()