淘宝爬取个人资料、微博绑定、收货地址、支付宝绑定设置、安全设置等信息

#coding=utf-8
import time,random,requests,json,re

from selenium import webdriver
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities

from lxml import etree
from area import dict_area

class Taobao(object):

    def __init__(self,name,password,browser,use_cookie):
        self.name=name
        self.password=password
        self.login_url=‘https://login.taobao.com/member/login.jhtml?redirectURL=https%3A%2F%2Fwww.taobao.com%2F‘
        self.order_url=‘https://buyertrade.taobao.com/trade/itemlist/asyncBought.htm?action=itemlist/BoughtQueryAction&event_submit_do_query=1&_input_charset=utf8‘
        self.num=0
        self.cost=0
        self.browser=browser
        self.use_cookiex=use_cookie

        if self.use_cookiex==0:
            dcap = dict(DesiredCapabilities.PHANTOMJS)
            dcap["phantomjs.page.settings.userAgent"] = (‘Mozilla/5.0(WindowsNT6.1;WOW64) AppleWebKit/537.36(KHTML, likeGecko) Chrome/59.0.3071.115Safari/537.36x-requested-with:XMLHttpRequest‘)#(random.choice(agents))
            dcap["phantomjs.page.settings.loadImages"] = True
            if self.browser==0:
                self.driver = webdriver.PhantomJS(executable_path=‘C:\\Python27\\phantomjs.exe‘,desired_capabilities=dcap)
            if self.browser==1:
                self.driver=webdriver.Chrome()
            if self.browser==2:
                self.driver=webdriver.Firefox()

            self.login()
            print self.cookies


    def login(self):

        self.driver.get(self.login_url)
        self.driver.find_element_by_id(‘J_Quick2Static‘).click()

        WebDriverWait(self.driver, 30, 0.5).until(EC.presence_of_element_located((By.ID, ‘TPL_username_1‘)))
        self.driver.find_element_by_id(‘TPL_username_1‘).send_keys(self.name)
        self.driver.save_screenshot(‘1.jpg‘)
        self.driver.find_element_by_id(‘TPL_password_1‘).send_keys(self.password)
        self.driver.save_screenshot(‘2.jpg‘)
        self.driver.find_element_by_id(‘J_SubmitStatic‘).click()
        time.sleep(5)
        self.driver.save_screenshot(‘3.jpg‘)
        self.cookies={}
        for dictx in self.driver.get_cookies():
            self.cookies[dictx[‘name‘]]=dictx[‘value‘]

        #driver.quit()





    def get_orders(self,p,flag):
        if flag==0:
            print ‘\n订单列表‘,‘#‘*100
            pass
            #print self.cookies
        datax={‘pageNum‘:p+1,
                ‘pageSize‘:15,
               ‘prePageNo‘:p,
               }
        header = {‘origin‘: ‘https://buyertrade.taobao.com‘,
                ‘referer‘:‘https://buyertrade.taobao.com/trade/itemlist/list_bought_items.htm‘,
                ‘user-agent‘:‘Mozilla/5.0(WindowsNT6.1;WOW64) AppleWebKit/537.36(KHTML, likeGecko) Chrome/59.0.3071.115Safari/537.36x-requested-with:XMLHttpRequest‘,
                  #‘cookie‘:‘miid=387872062667523128; thw=cn;xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx.....‘,
                  }
        resp=requests.post(self.order_url,data=datax,cookies=self.cookies,headers=header)
        #resp=requests.post(self.order_url,data=datax,headers=header)
        #print resp.content.decode(‘gbk‘)
        orders_dictx = json.loads(resp.content.decode(‘gbk‘))
        pages=orders_dictx[‘page‘][‘totalPage‘]
        for order in orders_dictx[‘mainOrders‘]:
            self.num+=1

            self.cost+=float(order[‘payInfo‘][‘actualFee‘])
            print self.num,‘ ‘,order[‘subOrders‘][0][‘itemInfo‘][‘title‘],‘    价格是： ‘,order[‘payInfo‘][‘actualFee‘],‘元 交易状态是：‘,order[‘statusInfo‘][‘text‘],self.cost

        if flag==0:
            for p in range(1,pages+1):
                self.get_orders(p,1)


    def get_userinfo(self):
        url=‘https://i.taobao.com/user/baseInfoSet.htm‘

        # self.driver.get(url)
        # time.sleep(3)
        # contentx2=self.driver.page_source
        contentx=requests.get(url,cookies=self.cookies).content.decode(‘gbk‘)
        selector=etree.HTML(contentx)
        self.userinfo_page_content=contentx
        print ‘\n个人资料‘,‘#‘*100
        print ‘用户名：‘,selector.xpath(‘//input[@id="J_uniqueName-mask"]/@value‘)[0]
        print ‘性别：‘,re.findall(u‘name="_fm.b._0.g" value="0"  checked="checked" />(.*?)</label>‘,contentx)[0]
        print ‘真实姓名：‘,selector.xpath(‘//input[@id="J_realname-mask"]/@value‘)[0]
        yearx=int(selector.xpath(‘//select[@id="J_Year"]//option[@selected="selected"]/text()‘)[0])
        print ‘生日：年‘,yearx
        monthx=int(selector.xpath(‘//select[@id="J_Month"]//option[@selected="selected"]/text()‘)[0])
        print ‘生日：月‘,monthx
        dayx=int(selector.xpath(‘//select[@id="J_Date"]//option[@selected="selected"]/text()‘)[0])
        print ‘生日：日‘,dayx

        divisionCode=selector.xpath(‘//input[@id="divisionCode"]/@value‘)[0]
        print ‘divisionCode：‘,divisionCode
        if divisionCode[0:2]!=‘00‘:
            print ‘省份：‘, dict_area[‘%s0000‘%divisionCode[0:2]][0]                             #re.findall(u‘<option value="%s0000">(.*?)</option>‘%divisionCode[0:2],contentx)[0]
        else:
            print ‘省份：‘,‘无省份‘
        if divisionCode[2:4]!=‘00‘:
            print ‘城市：‘, dict_area[‘%s00‘%divisionCode[0:4]][0]
        else:
            print ‘城市：‘,‘无城市‘
        if divisionCode[4:6]!=‘00‘:
            print ‘区县：‘, dict_area[‘%s‘%divisionCode][0]
        else:
            print ‘区县：‘,‘无区县‘

        def chinese_zodiac(year):
            return u‘猴鸡狗猪鼠牛虎兔龙蛇马羊‘[year%12]

        def zodiac(month, day):
            n = (u‘摩羯座‘,u‘水瓶座‘,u‘双鱼座‘,u‘白羊座‘,u‘金牛座‘,u‘双子座‘,
                 u‘巨蟹座‘,u‘狮子座‘,u‘处女座‘,u‘天秤座‘,u‘天蝎座‘,u‘射手座‘)
            d = ((1,20),(2,19),(3,21),(4,21),(5,21),(6,22),(7,23),(8,23),(9,23),(10,23),(11,23),(12,23))
            return n[len(filter(lambda y:y<=(month,day), d))%12]

        print ‘星座：‘,zodiac(monthx,dayx)

        liveDivisionCode=selector.xpath(‘//input[@id="liveDivisionCode"]/@value‘)[0]
        print ‘liveDivisionCode：‘,liveDivisionCode
        if liveDivisionCode[0:2]!=‘00‘:
            print ‘家乡省份：‘, dict_area[‘%s0000‘%liveDivisionCode[0:2]][0]                             #re.findall(u‘<option value="%s0000">(.*?)</option>‘%divisionCode[0:2],contentx)[0]
        else:
            print ‘家乡省份：‘,‘无省份‘
        if liveDivisionCode[2:4]!=‘00‘:
            print ‘家乡城市：‘, dict_area[‘%s00‘%liveDivisionCode[0:4]][0]
        else:
            print ‘家乡城市：‘,‘无城市‘
        if liveDivisionCode[4:6]!=‘00‘:
            print ‘家乡区县：‘, dict_area[‘%s‘%liveDivisionCode][0]
        else:
            print ‘家乡区县：‘,‘无区县‘


    def get_weibo(self):
        url=‘http://member1.taobao.com/member/fresh/weibo_bind_management.htm‘
        contentx=requests.get(url,cookies=self.cookies).content.decode(‘gbk‘)
        #print contentx
        print ‘\n微博信息‘,‘#‘*100
        print ‘微博账号：‘,re.findall(u‘<li><span class="label">帐号：</span>(.*?)</li>‘,contentx)[0]
        print ‘微博名称：‘,re.findall(u‘<li><span class="label">会员名：</span>([\s\S]*?)</li>‘,contentx)[0]

    def get_deliver_address(self):
        url=‘http://member1.taobao.com/member/fresh/deliver_address.htm‘
        contentx=requests.get(url,cookies=self.cookies).content.decode(‘gbk‘)
        print ‘\n收货地址列表‘,‘#‘*100
        selector=etree.HTML(contentx)
        all_addres=selector.xpath(‘//tr[contains(@class,"thead-tbl-address")]‘)
        for addres in all_addres:
            print ‘收货人：‘,addres.xpath(‘.//td[1]/text()‘)[0]
            print ‘所在地区：‘,addres.xpath(‘.//td[2]/text()‘)[0]
            print ‘详细地址：‘,addres.xpath(‘.//td[3]/text()‘)[0]
            print ‘邮编：‘,addres.xpath(‘.//td[4]/text()‘)[0]
            print ‘手机：‘,re.findall(‘(\d+)‘,addres.xpath(‘.//td[5]/text()‘)[0])[0]
            print ‘*************‘*3

    def get_zhifubao(self):
        url=‘http://member1.taobao.com/member/fresh/account_management.htm‘
        contentx=requests.get(url,cookies=self.cookies).content.decode(‘gbk‘)
        selector=etree.HTML(contentx)
        print ‘\n支付宝信息‘,‘#‘*100
        print ‘绑定的支付宝账号：‘,selector.xpath(‘//h3[@class="ui-tipbox-title"]/span/text()‘)[0]
        print ‘支付宝邮箱：‘,re.findall(u‘<th>邮箱</th>[\s\S]*?<td>\s*?(\S*?)\s*?</td>‘,contentx)[0]
        print ‘支付宝手机：‘,re.findall(u‘<th>绑定手机</th>[\s\S]*?<td>\s*?(\S*?)\s*?</td>‘,contentx)[0]
        print ‘支付宝账户类型：‘,re.findall(u‘<th>账户类型</th>[\s\S]*?<td>\s*?(\S*?)\s*?</td>‘,contentx)[0]
        print ‘支付宝实名认证：‘,re.sub(‘&nbsp;‘,‘  ‘,re.findall(u‘<th>实名认证</th>[\s\S]*?<td>\s*?(\S*?)\s*?</td>‘,contentx)[0])

    def get_renzheng(self):
        url=‘http://member1.taobao.com/member/fresh/certify_info.htm‘
        contentx=requests.get(url,cookies=self.cookies).content.decode(‘gbk‘)
        selector=etree.HTML(contentx)

        #print ‘\n身份认证‘,‘#‘*100
        self.renzhen_info={
        u‘认证渠道‘:re.findall(u‘<div class="explain-info"><span>认证渠道：</span> <div class="left">(.*?)</div></div>‘,contentx)[0],
        u‘认证通过时间‘:re.findall(u‘<div class="explain-info"><span>认证通过时间：</span> <div class="left">(.*?)</div></div>‘,contentx)[0],
        u‘认证姓名‘:re.findall(u‘<div class="explain-info">\s*?<span>姓名：</span>\s*?<div class="left">(.*?)</div>‘,contentx)[0],
        u‘认证身份证号‘:re.findall(u‘<div class="explain-info">\s*?<span>18位身份证号：</span>\s*?<div class="left">(.*?)</div>‘,contentx)[0],
         u‘认证身份证有效期‘:re.findall(u‘<div class="explain-info">\s*?<span>身份证有效期：</span>\s*?<div class="left">(.*?)</div>‘,contentx)[0],
        }






if __name__=="__main__":
    pass
    use_cookie=1
    tb=Taobao(‘12345@qq.com‘,‘123456‘,1,use_cookie)
    if use_cookie==1:
        tb.cookies={u‘_umdata‘: u‘xxxxxxxxxxxxxxxxB175EE499FED3B3DB41256484B8FBF58099DD458D29468A7AFECD43AD3E795C914C1B678C6F1F0D0C087770B1F894F15899‘, u‘_cc_‘: u‘xxxx3xSw%3D%3D‘, u‘skt‘: u‘751ffb46795bad03‘, u‘_tb_token_‘: u‘xxxxxx3ae5‘, u‘cookie17‘: u‘VvlwxxxxuReh‘, u‘uss‘: u‘VWooAnygozL9eeP1O0VHsDIgLwkjUFL3Pm%2BgaeJYZMGg9XDPDG4OXKk3BFM%3D‘, u‘cna‘: u‘Ol/4ESakOQYCAdoRzmJ1JWwE‘, u‘tg‘: u‘0‘, u‘tracknick‘: u‘ydxxx‘, u‘cookie1‘: u‘UtQxxxrIiRm6r2E%2FHolRxkGbXug%2FaJO2tWYm4Kxs7s%3D‘, u‘cookie2‘: u‘1baa9a096afba9112378bfd5d9bd08b8‘, u‘uc3‘: u‘sg2=BYTq6utDySfPSlYSUQkhG733K%2B4teufAzgD%2B%2BwEcUgA%3D&nk2=Ggxxxx&id2=VvlwnNFwuReh&vt3=F8dBzWOeW1bwMAMnSM4%3D&lg2=VT5L2FSpMGV7TQ%3D%3D‘, u‘uc1‘: u‘cookie16=URm48syIJ1yk0MX2J7mAAEhTuw%3D%3D&cookie21=U%2BGCWk%2F7pY%2FF&cookie15=VT5L2FSpMGV7TQ%3D%3D&existShop=false&pas=0&cookie14=UoTcDzxxxxQ%3D%3D&tag=8&lng=zh_CN‘, u‘lgc‘: u‘ydfxxxx‘, u‘_nk_‘: u‘ydfxxxx‘, u‘_l_g_‘: u‘Ug%3D%3D‘, u‘existShop‘: u‘MTUwMDYwNjc4OA%3D%3D‘, u‘_lastvisited‘: u‘Ol%2F4ESakOQYCAdoRzmJ1JWwE%2C%2COl4ESakOQYCAdoRzmJ1JWwEn0hVL8JYZ%2Cj5dajk9u%2Cj5dajk9u%2C1%2C8c84e1b0%2COl%2F4ESakOQYCAdoRzmJ1JWwE%2Cj5dajk9v‘, u‘thw‘: u‘cn‘, u‘isg‘: u‘AuvrvnMzNkMYEmqXPMgCBf9weg_fAfqtmvNARV1oxyqB_Ate5dCP0onWIAto‘, u‘mt‘: u‘ci=11_1‘, u‘unb‘: u‘57xxx4‘, u‘t‘: u‘099e66xxxxx256ef‘, u‘v‘: u‘0‘, u‘sg‘: u‘942‘, u‘_med‘: u‘dw:1920&dh:1080&pw:1920&ph:1080&ist:0‘}      ###这是slenium转换出来的，或者用header的cookie字符串用正则转字典，反正不是手写的。

    tb.get_orders(0,0)
    tb.get_userinfo()
    #print tb.userinfo_page_content
    tb.get_weibo()
    tb.get_deliver_address()
    tb.get_zhifubao()
    tb.get_renzheng()
    print ‘\n身份认证‘,‘#‘*100
    print tb.renzhen_info
    print json.dumps(tb.renzhen_info,ensure_ascii=False)