Python模拟登陆淘宝并统计淘宝消费情况的代码实例分享
程序员文章站
2022-05-03 19:12:54
...
支付宝十年账单上的数字有点吓人,但它统计的项目太多,只是想看看到底单纯在淘宝上支出了多少,于是写了段脚本,统计任意时间段淘宝订单的消费情况,看那结果其实在淘宝上我还是相当节约的说。
脚本的主要工作是模拟了浏览器登录,解析“已买到的宝贝”页面以获得指定的订单及宝贝信息。
脚本的主要工作是模拟了浏览器登录,解析“已买到的宝贝”页面以获得指定的订单及宝贝信息。
使用方法见代码或执行命令加参数-h,另外需要BeautifulSoup4支持,BeautifulSoup的官方项目列表页:https://www.crummy.com/software/BeautifulSoup/bs4/download/
首先来说一下代码使用方法:
python taobao.py -u USERNAME -p PASSWORD -s START-DATE -e END-DATE --verbose
所有参数均可选,如:
python taobao.py -u jinnlynn
统计用户jinnlynn所有订单的情况
python taobao.py -s 2014-12-12 -e 2014-12-12
统计用户(用户名在命令执行时会要求输入)在2014-12-12当天的订单情况
python taobao.py --verbose
这样就可以统计并输出订单明细。
好了,说了这么多我们就来看代码吧:
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' : '', #用户名 'TPL_password' : '', #密码 'TPL_checkcode' : '', 'need_check_code' : 'false', 'callback' : '0', # 有值返回JSON } # 无效订单状态 INVALID_ORDER_STATES = [ 'CREATE_CLOSED_OF_TAOBAO', # 取消 'TRADE_CLOSED', # 订单关闭 ] 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. 尝试登录 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打开 subprocess.call(['open', filename]) elif platform.system() == 'Windows': # windows 执行文件用默认程序打开 subprocess.call(filename, shell=True) else: # 其它系统 输出文件名 print('打开该文件获取验证码: {}'.format(filename)) return raw_input('输入验证码: '.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' # 运费险 增值服务 分段支付(定金,尾款) extra_service = ['freight-info', 'service-info', 'stage-item'] stdout_cr('working... {:.0%}'.format(0)) # 1. 解析第一页 res = urllib2.urlopen(url) soup = BeautifulSoup(res.read().decode('gbk')) # 2. 获取页数相关 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 = {} # 订单在页面上的位置 页数.排序号 info['pos'] = '{}.{}'.format(cur_page, count) info['orderid'] = item.attrs['data-orderid'] info['status'] = item.attrs['data-status'] # 店铺 node = item.select('tr.order-hd a.shopname') if not node: # 店铺不存在,可能是赠送彩票订单,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() 1: bb['snapshot'] = name_node[1].attrs['href'] # 宝贝规格 bb['spec'] = n.select('.spec')[0].text.strip() # 宝贝价格 bb['price'] = float(n.find('td', class_='price').attrs['title']) # 宝贝数量 bb['quantity'] = int(n.find('td', class_='quantity').attrs['title']) bb['is_goods'] = True baobei.append(bb) # 尝试获取实付款 # 实付款所在的节点可能跨越多个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)) # 下一页 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. 有错误发生,统计结果可能不准确。') # 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('{: end_date: sys.exit('ERROR, 结束日期必须晚于或等于开始日期') 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) # 输出订单明细 if verbose: ouput_orders(orders) if __name__ == '__main__': main()
声明:本文内容由网友自发贡献,版权归原作者所有,本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容,请联系admin@php.cn核实处理。
相关文章
相关视频
专题推荐
-
独孤九贱-php全栈开发教程
全栈 170W+
主讲:Peter-Zhu 轻松幽默、简短易学,非常适合PHP学习入门
-
玉女心经-web前端开发教程
入门 80W+
主讲:灭绝师太 由浅入深、明快简洁,非常适合前端学习入门
-
天龙八部-实战开发教程
实战 120W+
主讲:西门大官人 思路清晰、严谨规范,适合有一定web编程基础学习
网友评论
文明上网理性发言,请遵守 新闻评论服务协议
我要评论