Python抓取淘宝手机销量排行榜

#!/usr/bin/env python
# encoding: utf-8
"""
@version: v1.0
@author: W_H_J
@license: Apache Licence
@contact: 415900617@qq.com
@site:
@software: PyCharm
@file: taoBaoSpider.py
@time: 2017/12/25 15:07
@describe:淘宝部分页面分析

"""
import pandas
import re
import requests
import sys
reload(sys)
sys.setdefaultencoding("utf-8")
for ii in range(1,10):  # 翻页
    mn = 44 * (ii-1)url = 'https://s.taobao.com/search?q=%E6%89%8B%E6%9C%BA&imgfile=&commend=all&ssid=s5-e&search_type=item&sourceId=tb.index&spm=a21bo.2017.201856-taobao-item.1&ie=utf8&initiative_id=tbindexz_20170306'
    header = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36',
              'cookie':'thw=cn; t=be73ea5ec1ffbeb254d0a3535dd00415; cna=HqWrEpIZeG4CAbYSAEIb6bav; hng=CN%7Czh-CN%7CCNY%7C156; miid=596160490770762658; lgc=%5Cu5815%5Cu843D%5Cu4E4B%5Cu6CEAa; tracknick=%5Cu5815%5Cu843D%5Cu4E4B%5Cu6CEAa; tg=0; uc2=wuf=https%3A%2F%2Ftrade.tmall.com%2Fdetail%2ForderDetail.htm%3Fbiz_order_id%3D104827474284154168%26forward_action%3D; x=e%3D1%26p%3D*%26s%3D0%26c%3D0%26f%3D0%26g%3D0%26t%3D0%26__ll%3D-1%26_ato%3D0; uc3=sg2=VWxidJMT8gLCYBc%2BxP5FJdYe9%2FXfUvq2%2Byf0cFWq90Q%3D&nk2=1RSXayUHM0Sl&id2=UUpkvTJ9k5HsSA%3D%3D&vt3=F8dBzLbVzPYkPml1NZk%3D&lg2=W5iHLLyFOGW7aA%3D%3D; uss=VvioJOfdaT365u5YugXSKrRnG47jUQQG9UQvstfUu5fjcHD0zxGQLEmn; _cc_=VFC%2FuZ9ajQ%3D%3D; mt=ci=67_1; tk_trace=oTRxOWSBNwn9dPy4KVJVbutfzK5InlkjwbWpxHegXyGxPdWTLVRjn23RuZzZtB1ZgD6Khe0jl%2BAoo68rryovRBE2Yp933GccTPwH%2FTbWVnqEfudSt0ozZPG%2BkA1iKeVv2L5C1tkul3c1pEAfoOzBoBsNsJySQJwqIKz2kX83uPP5e4iE9t1ZpHdHZkk218jfUuTKISIEGrGMtBctY%2B2vMCmzCRVhIqleLIl%2BRRQHs4ekW3wNcZhDfwkkQzp9RF7kjYiNbNLTbo2mRCr3Wf97aW%2FfC72uuEf9Tcc6cNT9QCiB0y7NxqzS4M5NvMkxl5KoKbA%2BorLqu5Y9jpCfT31RlA%3D%3D; cookie2=1c16eb46ef00c015dd101f731c258d77; _tb_token_=8de4c4560b63; v=0; alitrackid=www.taobao.com; lastalitrackid=www.taobao.com; swfstore=107855; JSESSIONID=ED726367865542B7BA84D801D1C72812; isg=AhcXOlKpAS4SKIXa0x_6AhsZpovNTcSrwSKOp2lEKOZNmDfacSx7DtWyjg59; uc1=cookie14=UoTdf1DFLRnICg%3D%3D',
              'accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
              'path':'/search?q=%E6%89%8B%E6%9C%BA&imgfile=&commend=all&ssid=s5-e&search_type=item&sourceId=tb.index&spm=a21bo.2017.201856-taobao-item.1&ie=utf8&initiative_id=tbindexz_20170306'}html = requests.request('GET', url, headers=header)# print html.text
    # ren = re.compile('"title":"(.*?)","pic_url":"(.*?)","price":"(.*?)","importantKey":"(.*?)","month_sales":"(.*?)"')
    ren = re.compile('"title":"(.*?)","pic_url":"(.*?)","price":"(.*?)","trace":"(.*?)","month_sales":"(.*?)"')data = re.findall(ren, html.text)# print data
    data2 = pandas.DataFrame(data)print data2data2.to_csv(r'taobao.csv', header=False, index=False, mode='a+',encoding='utf-8')

销量信息可视化

#!/usr/bin/env python
# encoding: utf-8
"""
@version: v1.0
@author: W_H_J
@license: Apache Licence
@contact: 415900617@qq.com
@site:
@software: PyCharm
@file: taobaoPlot.py
@time: 2017/12/25 16:12
@describe:淘宝信息分析

"""
import pandas
import matplotlib as mpl
import matplotlib.pyplot as pltmpl.rcParams["font.sans-serif"] = ['SimHei'] #配置字体
# 绘图格式
plt.rcParams["axes.labelsize"] = 16
plt.rcParams["xtick.labelsize"] = 10
# print plt.rcParams.keys()
plt.rcParams["ytick.labelsize"] = 10
plt.rcParams["legend.fontsize"] = 10  # 图例字体大小
plt.rcParams["figure.figsize"] = [15,12]
# plt.rcParams['patch.facecolor'] = 'red'
def1 =pandas.read_csv('taobao.csv')
# print def1
TBdata =pandas.DataFrame(list(zip(def1['A'], def1['E'])))
# 可视化
DD = TBdata.groupby([0]).sum()
DD[1].plot(color='r')
DD[1].plot(kind='bar', rot=90)
DD[1].plot(rot=90)plt.show()

Python抓取淘宝手机销量排行榜相关推荐

python爬取淘宝手机信息并下载到excel文件中
#coding=GBK import requests import re from xlwt import Workbook import xlrd import time def key_name ...
Python爬取淘宝商品价格销量信息
用到了requests库和re库 import requests import re lis = [] # https://s.taobao.com/search?q=荣耀v20&imgfil ...
Python 抓取淘宝联盟优惠券
要获取淘宝联盟的数据第一步当然是分析淘宝联盟的 html 啦. 话不多少说,我们开始吧. 首先我们进入淘宝客的主站 https://pub.alimama.com/ 随便点一个进入商品推广页面,如女装 ...
python 抓取淘宝价格信息
接着上一回. 这段程序实现从淘宝主页开始,输入搜索信息(搜索'手表'),确定搜索后,爬取结果前20页所有的价格信息和地区信息(其他信息也可以获取,暂时只获取了这两个),最后用matplotlib绘制了 ...
python抓取淘宝关键字信息
懒得写字,不要说,就是干. # coding=utf-8 import urllib.request import re from urllib.request import urlopen, url ...
python爬淘宝商品销量信息_python爬取淘宝商品销量信息
python爬取淘宝商品销量的程序,运行程序,输入想要爬取的商品关键词,在代码中的'###'可以进一步约束商品的属性,比如某某作者的书籍,可以在###处输入作者名字,以及时期等等.最后可以得到所要商品 ...
用Python爬取淘宝1000多商品，只想为老父亲做点事
本文来自我们小密圈的一位非常铁杆的粉丝,这位粉丝看我的文章大概有2年多了,非常朴实的一位铁杆,希望大家耐心看完这篇文章! 北靠黄河南靠山,我家住在老潼关. 对,就是那个鸡鸣啼三省(秦晋豫)的陕西东大门 ...
Python爬虫实战八之利用Selenium抓取淘宝匿名旺旺
其实本文的初衷是为了获取淘宝的非匿名旺旺,在淘宝详情页的最下方有相关评论,含有非匿名旺旺号,快一年了淘宝都没有修复这个. 很多人学习python,不知道从何学起. 很多人学习python,掌握了基本语 ...
Python爬虫实战（4）：抓取淘宝MM照片
Python爬虫入门(1):综述 Python爬虫入门(2):爬虫基础了解 Python爬虫入门(3):Urllib库的基本使用 Python爬虫入门(4):Urllib库的高级用法 Python爬虫 ...

Python抓取淘宝手机销量排行榜

Python抓取淘宝手机销量排行榜相关推荐

最新文章

热门文章