支付寶十年賬單上的數(shù)字有點(diǎn)嚇人，但它統(tǒng)計(jì)的項(xiàng)目太多，只是想看看到底單純?cè)谔詫毶现С隽硕嗌伲谑菍懥硕文_本，統(tǒng)計(jì)任意時(shí)間段淘寶訂單的消費(fèi)情況，看那結(jié)果其實(shí)在淘寶上我還是相當(dāng)節(jié)約的說。
腳本的主要工作是模擬了瀏覽器登錄，解析“已買到的寶貝”頁面以獲得指定的訂單及寶貝信息。

用方法見代碼或執(zhí)行命令加參數(shù)-h，另外需要BeautifulSoup4支持，BeautifulSoup的官方項(xiàng)目列表頁：https://www.crummy.com/software/BeautifulSoup/bs4/download/
首先來說一下代碼使用方法:

            
              python taobao.py -u USERNAME -p PASSWORD -s START-DATE -e END-DATE --verbose

            
          

所有參數(shù)均可選，如:

            
              python taobao.py -u jinnlynn

            
          

統(tǒng)計(jì)用戶jinnlynn所有訂單的情況

            
              python taobao.py -s 2014-12-12 -e 2014-12-12

            
          

統(tǒng)計(jì)用戶(用戶名在命令執(zhí)行時(shí)會(huì)要求輸入)在2014-12-12當(dāng)天的訂單情況

            
              python taobao.py --verbose

            
          

這樣就可以統(tǒng)計(jì)并輸出訂單明細(xì)。
好了，說了這么多我們就來看代碼吧：

            
              from __future__ import unicode_literals, print_function, absolute_import, division
import urllib
import urllib2
import urlparse
import cookielib
import re
import sys
import os
import json
import subprocess
import argparse
import platform
from getpass import getpass
from datetime import datetime
from pprint import pprint
try:
 from bs4 import BeautifulSoup
except ImportError:
 sys.exit('BeautifulSoup4 missing.')
__version__ = '1.0.0'
__author__ = 'JinnLynn'
__copyright__ = 'Copyright (c) 2014 JinnLynn'
__license__ = 'The MIT License'
HEADERS = {
 'x-requestted-with' : 'XMLHttpRequest',
 'Accept-Language' : 'zh-cn',
 'Accept-Encoding' : 'gzip, deflate',
 'ContentType' : 'application/x-www-form-urlencoded; chartset=UTF-8',
 'Cache-Control' : 'no-cache',
 'User-Agent' :'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.38 Safari/537.36',
 'Connection' : 'Keep-Alive'
}
DEFAULT_POST_DATA = {
 'TPL_username' : '', #用戶名
 'TPL_password' : '', #密碼
 'TPL_checkcode' : '',
 'need_check_code' : 'false',
 'callback' : '0', # 有值返回JSON
}
# 無效訂單狀態(tài)
INVALID_ORDER_STATES = [
 'CREATE_CLOSED_OF_TAOBAO', # 取消
 'TRADE_CLOSED', # 訂單關(guān)閉
]
LOGIN_URL = 'https://login.taobao.com/member/login.jhtml'
RAW_IMPUT_ENCODING = 'gbk' if platform.system() == 'Windows' else 'utf-8'
def _request(url, data, method='POST'):
 if data:
   data = urllib.urlencode(data)
 if method == 'GET':
   if data:
     url = '{}?{}'.format(url, data)
   data = None
 # print(url)
 # print(data)
 req = urllib2.Request(url, data, HEADERS)
 return urllib2.urlopen(req)
def stdout_cr(msg=''):
 sys.stdout.write('\r{:10}'.format(' '))
 sys.stdout.write('\r{}'.format(msg))
 sys.stdout.flush()
def get(url, data=None):
 return _request(url, data, method='GET')
def post(url, data=None):
 return _request(url, data, method='POST')
def login_post(data):
 login_data = DEFAULT_POST_DATA
 login_data.update(data)
 res = post(LOGIN_URL, login_data)
 return json.load(res, encoding='gbk')
def login(usr, pwd):
 data = {
   'TPL_username' : usr.encode('utf-8' if platform.system() == 'Windows' else 'GB18030'),
   'TPL_password' : pwd
 }
 # 1. 嘗試登錄
 ret = login_post(data)
 while not ret.get('state', False):
   code = ret.get('data', {}).get('code', 0)
   if code == 3425 or code == 1000:
     print('INFO: {}'.format(ret.get('message')))
     check_code = checkcode(ret.get('data', {}).get('ccurl'))
     data.update({'TPL_checkcode' : check_code, 'need_check_code' : 'true'})
     ret = login_post(data)
   else:
     sys.exit('ERROR. code: {}, message:{}'.format(code, ret.get('message', '')))
 token = ret.get('data', {}).get('token')
 print('LOGIN SUCCESS. token: {}'.format(token))
 # 2. 重定向
 # 2.1 st值
 res = get('https://passport.alipay.com/mini_apply_st.js', {
   'site' : '0',
   'token' : token,
   'callback' : 'stCallback4'})
 content = res.read()
 st = re.search(r'"st":"(\S*)"( |})', content).group(1)
 # 2.1 重定向
 get('http://login.taobao.com/member/vst.htm',
   {'st' : st, 'TPL_uesrname' : usr.encode('GB18030')})
def checkcode(url):
 filename, _ = urllib.urlretrieve(url)
 if not filename.endswith('.jpg'):
   old_fn = filename
   filename = '{}.jpg'.format(filename)
   os.rename(old_fn, filename)
 if platform.system() == 'Darwin':
   # mac 下直接preview打開
   subprocess.call(['open', filename])
 elif platform.system() == 'Windows':
   # windows 執(zhí)行文件用默認(rèn)程序打開
   subprocess.call(filename, shell=True)
 else:
   # 其它系統(tǒng) 輸出文件名
   print('打開該文件獲取驗(yàn)證碼: {}'.format(filename))
 return raw_input('輸入驗(yàn)證碼: '.encode(RAW_IMPUT_ENCODING))
def parse_bought_list(start_date=None, end_date=None):
 url = 'http://buyer.trade.taobao.com/trade/itemlist/list_bought_items.htm'
 #         運(yùn)費(fèi)險(xiǎn)      增值服務(wù)     分段支付（定金，尾款）
 extra_service = ['freight-info', 'service-info', 'stage-item']
 stdout_cr('working... {:.0%}'.format(0))
 # 1. 解析第一頁
 res = urllib2.urlopen(url)
 soup = BeautifulSoup(res.read().decode('gbk'))
 # 2. 獲取頁數(shù)相關(guān)
 page_jump = soup.find('span', id='J_JumpTo')
 jump_url = page_jump.attrs['data-url']
 url_parts = urlparse.urlparse(jump_url)
 query_data = dict(urlparse.parse_qsl(url_parts.query))
 total_pages = int(query_data['tPage'])
 # 解析
 orders = []
 cur_page = 1
 out_date = False
 errors = []
 while True:
   bought_items = soup.find_all('tbody', attrs={'data-orderid' : True})
   # pprint(len(bought_items))
   count = 0
   for item in bought_items:
     count += 1
     # pprint('{}.{}'.format(cur_page, count))
     try:
       info = {}
       # 訂單在頁面上的位置 頁數(shù).排序號(hào)
       info['pos'] = '{}.{}'.format(cur_page, count)
       info['orderid'] = item.attrs['data-orderid']
       info['status'] = item.attrs['data-status']
       # 店鋪
       node = item.select('tr.order-hd a.shopname')
       if not node:
         # 店鋪不存在，可能是贈(zèng)送彩票訂單，忽略
         # print('ignore')
         continue
       info['shop_name'] = node[0].attrs['title'].strip()
       info['shop_url'] = node[0].attrs['href']
       # 日期
       node = item.select('tr.order-hd span.dealtime')[0]
       info['date'] = datetime.strptime(node.attrs['title'], '%Y-%m-%d %H:%M')
       if end_date and info['date'].toordinal() > end_date.toordinal():
         continue
       if start_date and info['date'].toordinal() < start_date.toordinal():
         out_date = True
         break
       # 寶貝
       baobei = []
       node = item.find_all('tr', class_='order-bd')
       # pprint(len(node))
       for n in node:
         try:
           bb = {}
           if [True for ex in extra_service if ex in n.attrs['class']]:
             # 額外服務(wù)處理
             # print('額外服務(wù)處理')
             name_node = n.find('td', class_='baobei')
             # 寶貝地址
             bb['name'] = name_node.text.strip()
             bb['url'] = ''
             bb['spec'] = ''
             # 寶貝快照
             bb['snapshot'] = ''
             # 寶貝價(jià)格
             bb['price'] = 0.0
             # 寶貝數(shù)量
             bb['quantity'] = 1
             bb['is_goods'] = False
             try:
               bb['url'] = name_node.find('a').attrs['href']
               bb['price'] = float(n.find('td', class_='price').text)
             except:
               pass
           else:
             name_node = n.select('p.baobei-name a')
             # 寶貝地址
             bb['name'] = name_node[0].text.strip()
             bb['url'] = name_node[0].attrs['href']
             # 寶貝快照
             bb['snapshot'] = ''
             if len(name_node) > 1:
               bb['snapshot'] = name_node[1].attrs['href']
             # 寶貝規(guī)格
             bb['spec'] = n.select('.spec')[0].text.strip()
             # 寶貝價(jià)格
             bb['price'] = float(n.find('td', class_='price').attrs['title'])
             # 寶貝數(shù)量
             bb['quantity'] = int(n.find('td', class_='quantity').attrs['title'])
             bb['is_goods'] = True
           baobei.append(bb)
           # 嘗試獲取實(shí)付款
           # 實(shí)付款所在的節(jié)點(diǎn)可能跨越多個(gè)tr的td
           amount_node = n.select('td.amount em.real-price')
           if amount_node:
             info['amount'] = float(amount_node[0].text)
         except Exception as e:
           errors.append({
             'type' : 'baobei',
             'id' : '{}.{}'.format(cur_page, count),
             'node' : '{}'.format(n),
             'error' : '{}'.format(e)
           })
     except Exception as e:
       errors.append({
         'type' : 'order',
         'id' : '{}.{}'.format(cur_page, count),
         'node' : '{}'.format(item),
         'error' : '{}'.format(e)
       })
     info['baobei'] = baobei
     orders.append(info)
   stdout_cr('working... {:.0%}'.format(cur_page / total_pages))
   # 下一頁
   cur_page += 1
   if cur_page > total_pages or out_date:
     break
   query_data.update({'pageNum' : cur_page})
   page_url = '{}?{}'.format(url, urllib.urlencode(query_data))
   res = urllib2.urlopen(page_url)
   soup = BeautifulSoup(res.read().decode('gbk'))
 stdout_cr()
 if errors:
   print('INFO. 有錯(cuò)誤發(fā)生，統(tǒng)計(jì)結(jié)果可能不準(zhǔn)確。')
   # pprint(errors)
 return orders
def output(orders, start_date, end_date):
 amount = 0.0
 org_amount = 0
 baobei_count = 0
 order_count = 0
 invaild_order_count = 0
 for order in orders:
   if order['status'] in INVALID_ORDER_STATES:
     invaild_order_count += 1
     continue
   amount += order['amount']
   order_count += 1
   for baobei in order.get('baobei', []):
     if not baobei['is_goods']:
       continue
     org_amount += baobei['price'] * baobei['quantity']
     baobei_count += baobei['quantity']
 print('{:<9} {}'.format('累計(jì)消費(fèi):', amount))
 print('{:<9} {}/{}'.format('訂單/寶貝:', order_count, baobei_count))
 if invaild_order_count:
   print('{:<9} {} (退貨或取消等, 不在上述訂單之內(nèi))'.format('無效訂單:', invaild_order_count))
 print('{:<7} {}'.format('寶貝原始總價(jià):', org_amount))
 print('{:<7} {:.2f}'.format('寶貝平均單價(jià):', 0 if baobei_count == 0 else org_amount / baobei_count))
 print('{:<9} {} ({:.2%})'.format('節(jié)約了(?)：',
                  org_amount - amount,
                  0 if org_amount == 0 else (org_amount - amount) / org_amount))
 from_date = start_date if start_date else orders[-1]['date']
 to_date = end_date if end_date else datetime.now()
 print('{:<9} {:%Y-%m-%d} - {:%Y-%m-%d}'.format('統(tǒng)計(jì)區(qū)間:', from_date, to_date))
 if not start_date:
   print('{:<9} {:%Y-%m-%d %H:%M}'.format('敗家始于:', orders[-1]['date']))
def ouput_orders(orders):
 print('所有訂單:')
 if not orders:
   print(' --')
   return
 for order in orders:
   print(' {:-^20}'.format('-'))
   print(' * 訂單號(hào): {orderid} 實(shí)付款: {amount} 店鋪: {shop_name} 時(shí)間: {date:%Y-%m-%d %H:%M}'.format(**order))
   for bb in order['baobei']:
     if not bb['is_goods']:
       continue
     print('  - {name}'.format(**bb))
     if bb['spec']:
       print('   {spec}'.format(**bb))
     print('   {price} X {quantity}'.format(**bb))
def main():
 parser = argparse.ArgumentParser(
   prog='python {}'.format(__file__)
 )
 parser.add_argument('-u', '--username', help='淘寶用戶名')
 parser.add_argument('-p', '--password', help='淘寶密碼')
 parser.add_argument('-s', '--start', help='起始時(shí)間，可選, 格式如: 2014-11-11')
 parser.add_argument('-e', '--end', help='結(jié)束時(shí)間，可選, 格式如: 2014-11-11')
 parser.add_argument('--verbose', action='store_true', default=False, help='訂單詳細(xì)輸出')
 parser.add_argument('-v', '--version', action='version',
           version='v{}'.format(__version__), help='版本號(hào)')
 args = parser.parse_args()
 usr = args.username
 if not usr:
   usr = raw_input('輸入淘寶用戶名: '.encode(RAW_IMPUT_ENCODING))
 usr = usr.decode('utf-8') # 中文輸入問題
 pwd = args.password
 if not pwd:
   if platform.system() == 'Windows':
     # Windows下中文輸出有問題
     pwd = getpass()
   else:
     pwd = getpass('輸入淘寶密碼: '.encode('utf-8'))
 pwd = pwd.decode('utf-8')
 verbose = args.verbose
 start_date = None
 if args.start:
   try:
     start_date = datetime.strptime(args.start, '%Y-%m-%d')
   except Exception as e:
     sys.exit('ERROR. {}'.format(e))
 end_date = None
 if args.end:
   try:
     end_date = datetime.strptime(args.end, '%Y-%m-%d')
   except Exception as e:
     sys.exit('ERROR. {}'.format(e))
 if start_date and end_date and start_date > end_date:
   sys.exit('ERROR, 結(jié)束日期必須晚于或等于開始日期')
 cj_file = './{}.tmp'.format(usr)
 cj = cookielib.LWPCookieJar()
 try:
   cj.load(cj_file)
 except:
   pass
 opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj), urllib2.HTTPHandler)
 urllib2.install_opener(opener)
 login(usr, pwd)
 try:
   cj.save(cj_file)
 except:
   pass
 orders = parse_bought_list(start_date, end_date)
 output(orders, start_date, end_date)
 # 輸出訂單明細(xì)
 if verbose:
   ouput_orders(orders)
if __name__ == '__main__':
 main()