xiaodu.py-20180830

# -*- coding: utf-8 -*-
"""
Created on Mon Aug 27 14:42:09 2018

@author: wenyun.wxw
"""

import requests
import re

#创建循环链接
urls = []
#替换页面数为i，取前100页评论
for i in list(range(1,99)):
    urls.append('https://rate.tmall.com/list_detail_rate.htm?itemId=566737021294&spuId=946907732&sellerId=3876960410&order=3&currentPage=%s' %i)

# 构建字段容器
#nickname = []
#saletype =[]
color = []
ratecontent = []
#ratedate = []

# 循环抓取数据
for url in urls:
    content = requests.get(url).text
    
# 借助正则表达式使用findall进行匹配查询
    #nickname.extend(re.findall('"displayUserNick":"(.*?)"',content))
    #saletype.extend(re.findall(re.compile('套餐类型:(.*?);'),content))
    color.extend(re.findall(re.compile('颜色分类:(.*?)","anony"'),content))
    ratecontent.extend(re.findall(re.compile('"rateContent":"(.*?)","fromMall"'),content))
    ratecontent.extend(re.findall(re.compile('"content":"(.*?)","fromMemory"'),content))#追评
    #ratedate.extend(re.findall(re.compile('"rateDate":"(.*?)","reply"'),content))

#去重
ratecontent_less=list(set(ratecontent))  

# 写入数据
file = open('小度在家评价-天猫.csv','w',encoding='gbk',errors='ignore')
#for i in list(range(len(nickname))):
#    file.write(','.join((nickname[i],ratedate[i],saletype[i],color[i],ratecontent[i]))+'\n')
for i in list(range(len(ratecontent))):
    file.write(','.join((color[i],ratecontent[i]))+'\n')
file.close()