1. from FileUtil import *
    2. from OtherUtil import *
    3. from RequestUtil import *
    4. from selenium import webdriver
    7. class JdHelper:
    8.     def __init__(self, need_type, filter_list, is_reverse_filter, user_name, user_pwd):
    9.         self.not_apply_list = []  # 忽略种草官商品
    10.         self.user_name = user_name
    11.         self.user_pwd = user_pwd
    12.         self.cookie_file = "cookie.txt"
    13.         self.not_apply_file = "notApply.txt"
    14.         self.wait_apply_list = []  # 待申请列表
    15.         self.session = requests.session()
    16.         self.headers = {
    17.             "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.85 Safari/537.36",
    18.             "Referer": "https://try.jd.com/activity/getActivityList?page=1&cids=737",
    19.         }
    20.         self.count = 0
    22.         self.base_url_list = {
    23.             "家用电器": "https://try.jd.com/activity/getActivityList?activityState=0&cids=737",
    24.             "手机数码": "https://try.jd.com/activity/getActivityList?activityState=0&cids=652,9987",
    25.             "电脑办公": "https://try.jd.com/activity/getActivityList?activityState=0&cids=670",
    26.             "家居家装": "https://try.jd.com/activity/getActivityList?activityState=0&cids=1620,6728,9847,9855,6196,15248,14065",
    27.             "美妆护肤": "https://try.jd.com/activity/getActivityList?activityState=0&cids=1316",
    28.             "服饰鞋包": "https://try.jd.com/activity/getActivityList?activityState=0&cids=1315,1672,1318,11729",
    29.             "母婴玩具": "https://try.jd.com/activity/getActivityList?activityState=0&cids=1319,6233",
    30.             "生鲜美食": "https://try.jd.com/activity/getActivityList?activityState=0&cids=12218",
    31.             "图书音像": "https://try.jd.com/activity/getActivityList?activityState=0&cids=1713,4051,4052,4053,7191,7192,5272",
    32.             "钟表奢品": "https://try.jd.com/activity/getActivityList?activityState=0&cids=5025,6144",
    33.             "个人护理": "https://try.jd.com/activity/getActivityList?activityState=0&cids=16750",
    34.             "家庭清洁": "https://try.jd.com/activity/getActivityList?activityState=0&cids=15901",
    35.             "食品饮料": "https://try.jd.com/activity/getActivityList?activityState=0&cids=1320,12259",
    36.             "更多惊喜": "https://try.jd.com/activity/getActivityList?activityState=0&cids=4938,13314,6994,9192,12473,6196,5272,12379,13678,15083,15126,15980"
    37.         }
    39.         self.not_apply()
    40.         if not self.check_login():
    41.             LoginHelper().login(self.user_name, self.user_pwd)
    42.             self.check_login()
    43.         self.sum()
    45.         # 是否反转过滤 True:商品名必须包含在filter_list  False:商品名不能包含在filter_list
    46.         self.is_reverse_filter = is_reverse_filter
    47.         self.filter_list = filter_list
    48.         self.need_type = need_type
    49.         if self.is_reverse_filter:
    50.             print("入选词汇:", self.filter_list)
    51.         else:
    52.             print("过滤词汇:", self.filter_list)
    54.     @retry(stop_max_attempt_number=20)
    55.     def get_resp(self, url):
    56.         return self.session.get(url, headers=self.headers, timeout=3)
    58.     # 查询是否已申请
    59.     def getApplyStateByActivityIds(self, activityIds):
    60.         url = "https://try.jd.com/user/getApplyStateByActivityIds?activityIds=" + activityIds
    61.         resp = self.get_resp(url)
    62.         for item in resp.json():
    63.             obj = self.find_obj(item["activityId"])
    64.             if obj:
    65.                 self.wait_apply_list.remove(obj)
    67.     # 过滤list
    68.     def find_obj(self, id):
    69.         for data in self.wait_apply_list:
    70.             if str(id) == str(data["activity_id"]):
    71.                 return data
    73.     # 申请
    74.     def apply(self):
    75.         can_stop = False
    76.         for wait_apply in self.wait_apply_list:
    77.             print("\n正在申请,", wait_apply["activity_id"], wait_apply["name"])
    78.             # 获取店铺id
    79.             activity_id = wait_apply["activity_id"]
    80.             item_url = "https://try.jd.com/{}.html".format(activity_id)
    81.             shop_id = re.findall('id="_shopId" value="(.*?)"', self.get_resp(item_url).text)[0]
    82.             time.sleep(1)
    84.             # 关注
    85.             follow_url = "https://try.jd.com/migrate/follow?_s=pc&venderId={}".format(shop_id)
    86.             resp = self.get_resp(follow_url)
    87.             print(resp.json())
    88.             time.sleep(2)
    90.             # 申请
    91.             url = "https://try.jd.com/migrate/apply?activityId={}&source=0".format(activity_id)
    92.             resp = self.get_resp(url)
    93.             resp_data = resp.json()
    94.             print(resp_data)
    95.             if resp_data["success"]:
    96.                 self.count += 1
    97.                 print("当天已申请次数:", self.count)
    99.             elif '种草官' in resp_data["message"]:
    100.                 with open("notApply.txt", encoding="utf-8", mode="a+") as f:
    101.                     f.write(activity_id + "\n")
    103.             elif '超过' in resp_data["message"] or '已超' in resp_data["message"]:
    104.                 self.cancel_follow_item()
    105.                 self.cancel_follow_shop()
    106.                 can_stop = True
    107.                 break
    109.             time.sleep(3)
    110.         return can_stop
    112.     # 获取页面大小
    113.     def get_page_size(self, url):
    114.         resp = self.get_resp(url)
    115.         return int(re.findall('"pages":(\d+)', resp.text)[0])
    117.     # 检查登录状态
    118.     def check_login(self):
    119.         self.set_cookie()
    120.         url = "https://passport.jd.com/user/petName/getUserInfoForMiniJd.action"
    121.         resp = self.get_resp(url)
    122.         if 'null' in resp.text:
    123.             print("cookie失效, 返回信息:", resp.text)
    124.             return False
    125.         else:
    126.             print("登录成功, 当前用户名:", resp.json()["nickName"])
    127.             return True
    129.     # 读取并设置cookie
    130.     def set_cookie(self):
    131.         if os.path.exists(self.cookie_file):
    132.             with open(self.cookie_file, encoding="utf-8", mode="r") as f:
    133.                 self.headers["Cookie"] = f.read().strip()
    135.     # 统计今日已申请次数
    136.     def sum(self):
    137.         page = 1
    138.         run = True
    140.         today = time.strftime("%Y-%m-%d")
    142.         while run:
    143.             url = "https://try.jd.com/user/myTrial?page={}".format(page)
    144.             resp = self.get_resp(url)
    145.             parser = etree.HTML(resp.text)
    146.             day_list = parser.xpath('//span[@class="time"]/em/text()')
    147.             for day in day_list:
    148.                 if today in day:
    149.                     self.count += 1
    150.                 else:
    151.                     run = False
    152.             page += 1
    153.         print("今日已申请次数:", self.count)
    155.     # 过滤器
    156.     def in_filter_list(self, name):
    157.         has_find = True
    158.         for filter in self.filter_list:
    159.             if filter in name:
    160.                 has_find = False
    161.         if self.is_reverse_filter:
    162.             has_find = not has_find
    163.         return has_find
    165.     # 过滤种草官级别
    166.     def not_apply(self):
    167.         if os.path.exists(self.not_apply_file):
    168.             with open(self.not_apply_file, encoding="utf-8", mode="r") as f:
    169.                 for line in f.readlines():
    170.                     self.not_apply_list.append(line.strip())
    172.     # 取关商品
    173.     def cancel_follow_item(self):
    174.         can_run = True
    175.         while can_run:
    176.             page_url = "https://t.jd.com/home/follow?index=1"
    177.             resp = self.get_resp(page_url)
    178.             parser = etree.HTML(resp.text)
    180.             item_id_list = ""
    181.             for item in parser.xpath('//*[@id="main"]/div/div[2]/div[2]/div[1]/div'):
    182.                 if not item.xpath("./@id"):
    183.                     print("当前没有需要取关的商品")
    184.                     can_run = False
    185.                     break
    186.                 item_id_list += item.xpath("./@id")[0].replace('goods_', '') + ","
    187.             item_id_list = item_id_list[0:-1]
    189.             url = "https://api.m.jd.com/api?functionId=batchCancelFavorite&body={%22skus%22:%22" + item_id_list + "%22}&appid=follow_for_concert&soaKey=2e2i4fRvyfAek5MfHNCe;fMeBpvzbQimFgonJp9YpBqyMcz1VvO4sWcyIBRb8VdOTNQDVo7&client=pc&t=1627133437064&jsonp=result&_=1627133437064"
    190.             resp = self.get_resp(url)
    191.             print(resp.text)
    193.     # 取关店铺
    194.     def cancel_follow_shop(self):
    195.         can_run = True
    196.         while can_run:
    197.             page_url = "https://t.jd.com/follow/vender/list.do"
    198.             resp = self.get_resp(page_url)
    199.             re_list = re.findall('id="vender_(.*?)"', resp.text)
    201.             if not re_list:
    202.                 print("当前没有需要取关的店铺")
    203.                 break
    205.             shop_id_list = ""
    206.             for item in re_list:
    207.                 shop_id_list += item + ","
    208.             shop_id_list = shop_id_list[0:-1]
    210.             url = "https://t.jd.com/follow/vender/batchUnfollow.do"
    211.             resp = self.session.post(url, data={"venderIds": shop_id_list}, headers=self.headers)
    212.             print(resp.text)
    214.     def run(self):
    215.         can_stop = False
    216.         for need in self.need_type:
    217.             base_url = self.base_url_list[need]
    218.             page_size = self.get_page_size(base_url)
    219.             print("当前类型:{} 总页数:{}".format(need, page_size))
    221.             if can_stop:
    222.                 break
    224.             for i in range(1, page_size + 1):
    225.                 self.wait_apply_list = []
    226.                 url = base_url + "&page={}".format(i)
    227.                 print("\n获取第{}页 总页数:{} {}".format(i, page_size, url))
    228.                 resp = self.get_resp(url)
    229.                 parser = etree.HTML(resp.text)
    231.                 activityIds = []  # 查询是否已申请
    233.                 item_list = parser.xpath('//*[@id="goods-list"]/div[2]/div/ul/li')
    234.                 for item in item_list:
    235.                     wait_apply = {}
    236.                     activity_id = item.xpath("./@activity_id")[0]
    238.                     activityIds.append(activity_id)
    239.                     wait_apply["activity_id"] = activity_id
    240.                     wait_apply["name"] = item.xpath(".//div[@class='p-name']/text()")[0].strip()
    242.                     if activity_id in self.not_apply_list:
    243.                         print("该申请需种草官要求,跳过", wait_apply["name"])
    244.                         continue
    246.                     if self.in_filter_list(wait_apply["name"]):
    247.                         print("加入待申请:", wait_apply["name"])
    248.                         self.wait_apply_list.append(wait_apply)
    249.                     else:
    250.                         print("该商品已被过滤:", wait_apply["name"])
    251.                         continue
    253.                 self.getApplyStateByActivityIds(",".join(activityIds))
    255.                 can_stop = self.apply()
    256.                 if can_stop:
    257.                     break
    260. # 模拟登录
    261. class LoginHelper:
    263.     def login(self, user_name, user_pwd):
    264.         chrome_options = webdriver.ChromeOptions()
    265.         chrome_options.add_argument('log-level=2')
    267.         try:
    268.             driver = webdriver.Chrome(options=chrome_options)
    269.         except:
    270.             driver = webdriver.Chrome(options=chrome_options, executable_path="C:/chromedriver.exe")
    272.         driver.get('https://passport.jd.com/new/login.aspx')
    274.         driver.find_element_by_css_selector(
    275.             '#content > div.login-wrap > div.w > div > div.login-tab.login-tab-r > a').click()
    276.         driver.implicitly_wait(2)
    278.         input_username = driver.find_element_by_name('loginname')
    279.         input_username.send_keys(user_name)
    281.         input_password = driver.find_element_by_name('nloginpwd')
    282.         input_password.send_keys(user_pwd)
    284.         button_logOK = driver.find_elements_by_id('loginsubmit')
    285.         button_logOK = button_logOK[0]
    286.         button_logOK.click()
    288.         while True:
    289.             try:
    290.                 if driver.find_element_by_css_selector('#ttbar-login > div.dt.cw-icon > a'):
    291.                     break
    292.             except:
    293.                 print_exc()
    294.                 time.sleep(1)
    296.         print('登陆成功！')
    298.         cookie_dict_list = driver.get_cookies()
    299.         self.save_cookie(cookie_dict_list)
    301.         driver.quit()
    303.     def save_cookie(self, cookie_dict_list):
    304.         cookies_str = ""
    305.         for cookie_dict in cookie_dict_list:
    306.             name = cookie_dict["name"]
    307.             value = cookie_dict["value"]
    308.             cookies_str += name + "=" + value + "; "
    309.         cookies_str = cookies_str[0:-2]
    310.         with open("cookie.txt", encoding="utf-8", mode="w") as f:
    311.             f.write(cookies_str)
    314. if __name__ == '__main__':
    315.     user_name = "手机账号"
    316.     user_pwd = "密码"
    318.     need_type = [
    319.         "家用电器",
    320.         "手机数码",
    321.         "电脑办公",
    322.         "家居家装",
    323.         "美妆护肤",
    324.         "服饰鞋包",
    325.         "母婴玩具",
    326.         "生鲜美食",
    327.         "图书音像",
    328.         "钟表奢品",
    329.         "个人护理",
    330.         "家庭清洁",
    331.         "食品饮料",
    332.     ]
    333.     filter_list = [
    334.         '电话卡', '流量卡', '电信', '进销存', '贴纸', '书签', '便利贴', '笔', '纸',
    335.         '文具', '儿童', '贴画', '除螨', '口罩', '财务', '软件', '马丁靴', '耳罩', '鞋垫', '长虹', '钥匙'
    336.         , '系统', '钢化膜', '特雷索', '流量', '卡槽', '手机壳', '手套', '帽子', '指甲', '领带',
    337.         '牙刷', '刀', '袜子', '口红', '数据线', '充电器', '茶', '卸妆', '洗脸', '面巾', '毛巾',
    338.         '伸缩带', '剂', '灯', '香水', '车贴', '地漏', '雨刷', '胶', '门窗'
    339.     ]
    340.     jdHelper = JdHelper(need_type, filter_list, False, user_name, user_pwd)
    341.     jdHelper.run()