京东抢购

Python爬虫，自动登录京东网站，查询商品库存，价格，显示购物车详情等。
可以指定抢购商品，自动购买下单，然后手动去京东付款就行。

chang log

  • 2017-03-30 实现二维码扫码登陆

  • 2017-06-27 Golang版JD_AutoBuy

运行环境

Python 2.7

第三方库

  • Requests: 简单好用，功能强大的Http请求库

  • beautifulsoup4: HTML文档格式化及便签选择器

环境配置

pip install requests
pip install beautifulsoup4

ps：推荐一下我建的python零基础系统学习交流扣扣qun：前面是934，中间109，后面是170，群里有免费的视频教程，开发工具、电子书籍分享。专业的老师答疑！学习python web、python爬虫、数据分析、大数据，人工智能等技术有不懂的可以加入一起交流学习，一起进步！

项目源码分享


# -*- coding: utf-8 -*-

"""
JD online shopping helper tool
-----------------------------------------------------
only support to login by QR code, 
username / password is not working now.
"""


import bs4
import requests, requests.utils, pickle
import requests.packages.urllib3
requests.packages.urllib3.disable_warnings()

import os
import time
import json
import random


import argparse
#from selenium import webdriver


import sys
reload(sys)
sys.setdefaultencoding('utf-8')

# get function name
FuncName = lambda n=0: sys._getframe(n + 1).f_code.co_name


def tags_val(tag, key='', index=0):
    '''
    return html tag list attribute @key @index
    if @key is empty, return tag content
    '''
    if len(tag) == 0 or len(tag) <= index:
        return ''
    elif key:
        txt = tag[index].get(key)
        return txt.strip(' \t\r\n') if txt else ''
    else:
        txt = tag[index].text
        return txt.strip(' \t\r\n') if txt else ''


def tag_val(tag, key=''):
    '''
    return html tag attribute @key
    if @key is empty, return tag content
    '''
    if tag is None: 
        return ''
    elif key:
        txt = tag.get(key)
        return txt.strip(' \t\r\n') if txt else ''
    else:
        txt = tag.text
        return txt.strip(' \t\r\n') if txt else ''


class JDWrapper(object):
    '''
    This class used to simulate login JD
    '''
    
    def __init__(self, usr_name=None, usr_pwd=None):
        # cookie info
        self.trackid = ''
        self.uuid = ''
        self.eid = ''
        self.fp = ''

        self.usr_name = usr_name
        self.usr_pwd = usr_pwd

        self.interval = 0

        # init url related
        self.home = 'https://passport.jd.com/new/login.aspx'
        self.login = 'https://passport.jd.com/uc/loginService'
        self.imag = 'https://authcode.jd.com/verify/image'
        self.auth = 'https://passport.jd.com/uc/showAuthCode'
        
        self.sess = requests.Session()

        self.headers = {
            'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36',
            'ContentType': 'text/html; charset=utf-8',
            'Accept-Encoding':'gzip, deflate, sdch',
            'Accept-Language':'zh-CN,zh;q=0.8',
            'Connection' : 'keep-alive',
        }
        
        self.cookies = {

        }

        '''
        try:
            self.browser = webdriver.PhantomJS('phantomjs.exe')
        except Exception, e:
            print 'Phantomjs initialize failed :', e
            exit(1)
        '''
        
    @staticmethod
    def print_json(resp_text):
        '''
        format the response content
        '''
        if resp_text[0] == '(':
            resp_text = resp_text[1:-1]
        
        for k,v in json.loads(resp_text).items():
            print u'%s : %s' % (k, v)

    @staticmethod
    def response_status(resp):
        if resp.status_code != requests.codes.OK:
            print 'Status: %u, Url: %s' % (resp.status_code, resp.url)
            return False
        return True

    def _need_auth_code(self, usr_name):
        # check if need auth code
        # 
        auth_dat = {
            'loginName': usr_name,
        }
        payload = {
            'r' : random.random(),
            'version' : 2015
        }
        
        resp = self.sess.post(self.auth, data=auth_dat, params=payload)
        if self.response_status(resp) : 
            js = json.loads(resp.text[1:-1])
            return js['verifycode']

        print u'获取是否需要验证码失败'
        return False

    def _get_auth_code(self, uuid):
        # image save path
        image_file = os.path.join(os.getcwd(), 'authcode.jfif')
            
        payload = {
            'a' : 1,
            'acid' : uuid,
            'uid' : uuid,
            'yys' : str(int(time.time() * 1000)),
        }
            
        # get auth code
        r = self.sess.get(self.imag, params=payload)
        if not self.response_status(r):
            print u'获取验证码失败'
            return False

        with open (image_file, 'wb') as f:
            for chunk in r.iter_content(chunk_size=1024):
                f.write(chunk)
                        
            f.close()
        
        os.system('start ' + image_file)
        return str(raw_input('Auth Code: '))

    def _login_once(self, login_data):
        # url parameter
        payload = {
            'r': random.random(),
            'uuid' : login_data['uuid'],
            'version' : 2015,
        }
        
        resp = self.sess.post(self.login, data=login_data, params=payload)
        if self.response_status(resp):
            js = json.loads(resp.text[1:-1])
            #self.print_json(resp.text)