new file: amazon/amazon_base.py
modified: amazon/approve.py modified: amazon/asin_status.py new file: amazon/chrome_base.py modified: amazon/del_brand.py modified: amazon/detail_spider.py new file: "amazon/detail_spider_\345\244\207\344\273\275.py" modified: amazon/main.py modified: amazon/match_action.py modified: amazon/price_match.py new file: amazon/similar_asin.py modified: app.py new file: assets/appearance-patent-Br1dtmol.css new file: assets/appearance-patent-D1DgeYhe.css new file: assets/delete-brand-BfMLVSQU.css new file: assets/patrol-delete-BAzbYtgc.css new file: assets/price-track-Hozgt_em.css new file: assets/product-risk-CbX7bwZi.css new file: assets/query-asin-B4RsOiza.css new file: assets/shop-match-B2HWAgBY.css modified: main.py
This commit is contained in:
铭坤
847
app/amazon/amazon_base.py
Normal file
847
app/amazon/amazon_base.py
Normal file
@@ -0,0 +1,847 @@
|
||||
import traceback
|
||||
import winreg
|
||||
import subprocess
|
||||
import time
|
||||
import uuid
|
||||
import requests
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
from datetime import datetime
|
||||
|
||||
from DrissionPage import Chromium,ChromiumOptions
|
||||
from DrissionPage.common import By
|
||||
from DrissionPage._pages.chromium_tab import ChromiumTab
|
||||
from typing import Literal,Dict,Any,TypeVar,Type
|
||||
|
||||
|
||||
from amazon.tool import get_shop_info,show_notification
|
||||
from config import runing_shop
|
||||
|
||||
# 定义类型变量，用于泛型类型注解
|
||||
T = TypeVar('T', bound='AmamzonBase')
|
||||
|
||||
|
||||
def kill_process(version: Literal["v5", "v6"]):
|
||||
"""杀紫鸟客户端进程（独立函数版本）"""
|
||||
driver = ZiniaoDriver({})
|
||||
driver.kill_process(version)
|
||||
|
||||
|
||||
class ZiniaoDriver:
|
||||
"""紫鸟浏览器自动化驱动类"""
|
||||
|
||||
def __init__(self, user_info: dict, socket_port: int = 19890):
|
||||
"""
|
||||
初始化紫鸟浏览器驱动
|
||||
|
||||
Args:
|
||||
user_info: 用户信息字典，包含 company, username, password
|
||||
socket_port: 客户端通信端口，默认 19890
|
||||
"""
|
||||
self.user_info = user_info
|
||||
self.socket_port = socket_port
|
||||
self.client_path = None
|
||||
self.browser = None
|
||||
self.tab: ChromiumTab = None
|
||||
self.store_id = None
|
||||
|
||||
self.url = None #用于记录当前链接，实现断点续传
|
||||
|
||||
|
||||
|
||||
def get_zinaio_exe(self, protocol_name: str = "superbrowser"):
|
||||
"""
|
||||
获取紫鸟安装目录
|
||||
|
||||
Args:
|
||||
protocol_name: 协议名称，默认 "superbrowser"
|
||||
|
||||
Returns:
|
||||
exe_path: 紫鸟浏览器可执行文件路径
|
||||
"""
|
||||
try:
|
||||
key_path = rf"SOFTWARE\Classes\{protocol_name}\shell\open\command"
|
||||
key = winreg.OpenKey(winreg.HKEY_CURRENT_USER, key_path)
|
||||
command, _ = winreg.QueryValueEx(key, "")
|
||||
winreg.CloseKey(key)
|
||||
if isinstance(command, str):
|
||||
sub = "ziniao.exe"
|
||||
exe_path = command[0: command.find(sub) + len(sub) + 1]
|
||||
else:
|
||||
exe_path = command[0]
|
||||
return exe_path
|
||||
except FileNotFoundError:
|
||||
try:
|
||||
key = winreg.OpenKey(winreg.HKEY_LOCAL_MACHINE, key_path)
|
||||
command, _ = winreg.QueryValueEx(key, "")
|
||||
winreg.CloseKey(key)
|
||||
if isinstance(command, str):
|
||||
sub = "ziniao.exe"
|
||||
exe_path = command[0: command.find(sub) + len(sub) + 1]
|
||||
else:
|
||||
exe_path = command[0]
|
||||
return exe_path
|
||||
except FileNotFoundError:
|
||||
return None
|
||||
|
||||
def update_core(self):
|
||||
"""
|
||||
下载所有内核，打开店铺前调用，需客户端版本5.285.7以上
|
||||
因为http有超时时间，所以这个action适合循环调用，直到返回成功
|
||||
"""
|
||||
data = {
|
||||
"action": "updateCore",
|
||||
"requestId": str(uuid.uuid4()),
|
||||
}
|
||||
data.update(self.user_info)
|
||||
while True:
|
||||
url = f'http://127.0.0.1:{self.socket_port}'
|
||||
response = requests.post(url, json.dumps(data).encode('utf-8'), timeout=120)
|
||||
result = response.json()
|
||||
print(result)
|
||||
if result is None:
|
||||
print("等待客户端启动...")
|
||||
time.sleep(2)
|
||||
continue
|
||||
if result.get("statusCode") is None or result.get("statusCode") == -10003:
|
||||
print("当前版本不支持此接口，请升级客户端")
|
||||
return
|
||||
elif result.get("statusCode") == 0:
|
||||
print("更新内核完成")
|
||||
return
|
||||
else:
|
||||
print(f"等待更新内核: {json.dumps(result)}")
|
||||
time.sleep(2)
|
||||
|
||||
def kill_process(self, version: Literal["v5", "v6"]):
|
||||
"""
|
||||
杀紫鸟客户端进程
|
||||
|
||||
Args:
|
||||
version: 客户端版本
|
||||
"""
|
||||
if version == "v5":
|
||||
process_name = 'SuperBrowser.exe'
|
||||
os.system('taskkill /f /t /im ' + "starter.exe")
|
||||
else:
|
||||
process_name = 'ziniao.exe'
|
||||
os.system('taskkill /f /t /im ' + process_name)
|
||||
time.sleep(3)
|
||||
|
||||
def get_browser_list(self) -> list:
|
||||
"""
|
||||
获取浏览器列表
|
||||
|
||||
Returns:
|
||||
list: 浏览器列表
|
||||
"""
|
||||
request_id = str(uuid.uuid4())
|
||||
data = {
|
||||
"action": "getBrowserList",
|
||||
"requestId": request_id
|
||||
}
|
||||
data.update(self.user_info)
|
||||
|
||||
url = f'http://127.0.0.1:{self.socket_port}'
|
||||
response = requests.post(url, json.dumps(data).encode('utf-8'), timeout=120)
|
||||
r = response.json()
|
||||
if str(r.get("statusCode")) == "0":
|
||||
print(r)
|
||||
return r.get("browserList")
|
||||
elif str(r.get("statusCode")) == "-10003":
|
||||
print(f"【get_browser_list】登录失败 {json.dumps(r, ensure_ascii=False)}")
|
||||
# exit()
|
||||
else:
|
||||
print(f"【get_browser_list】失败 {json.dumps(r, ensure_ascii=False)} ")
|
||||
# exit()
|
||||
|
||||
def open_store(self, store_info, isWebDriverReadOnlyMode=0, isprivacy=0,
|
||||
isHeadless=0, cookieTypeSave=0, jsInfo=""):
|
||||
"""
|
||||
打开店铺
|
||||
|
||||
Args:
|
||||
store_info: 店铺信息（browserId 或 browserOauth）
|
||||
isWebDriverReadOnlyMode: 是否只读模式，默认 0
|
||||
isprivacy: 隐私模式，默认 0
|
||||
isHeadless: 无头模式，默认 0
|
||||
cookieTypeSave: cookie保存类型，默认 0
|
||||
jsInfo: 注入的JS信息，默认 ""
|
||||
|
||||
Returns:
|
||||
dict: 返回结果
|
||||
"""
|
||||
request_id = str(uuid.uuid4())
|
||||
data = {
|
||||
"action": "startBrowser",
|
||||
"isWaitPluginUpdate": 0,
|
||||
"isHeadless": isHeadless,
|
||||
"requestId": request_id,
|
||||
"isWebDriverReadOnlyMode": isWebDriverReadOnlyMode,
|
||||
"cookieTypeLoad": 0,
|
||||
"cookieTypeSave": cookieTypeSave,
|
||||
"runMode": "1",
|
||||
"isLoadUserPlugin": True,
|
||||
"pluginIdType": 1,
|
||||
"privacyMode": isprivacy
|
||||
}
|
||||
data.update(self.user_info)
|
||||
|
||||
if store_info.isdigit():
|
||||
data["browserId"] = store_info
|
||||
else:
|
||||
data["browserOauth"] = store_info
|
||||
|
||||
if len(str(jsInfo)) > 2:
|
||||
data["injectJsInfo"] = json.dumps(jsInfo)
|
||||
|
||||
url = f'http://127.0.0.1:{self.socket_port}'
|
||||
response = requests.post(url, json.dumps(data).encode('utf-8'), timeout=120)
|
||||
r = response.json()
|
||||
if str(r.get("statusCode")) == "0":
|
||||
return r
|
||||
elif str(r.get("statusCode")) == "-10003":
|
||||
raise RuntimeError(f"【open_store】登录失败 {json.dumps(r, ensure_ascii=False)}")
|
||||
# exit()
|
||||
else:
|
||||
raise RuntimeError(f"【open_store】失败 {json.dumps(r, ensure_ascii=False)} ")
|
||||
# exit()
|
||||
|
||||
def get_browser(self, port) -> Chromium:
|
||||
"""
|
||||
获取浏览器实例
|
||||
|
||||
Args:
|
||||
port: 调试端口
|
||||
|
||||
Returns:
|
||||
Chromium: DrissionPage浏览器实例
|
||||
"""
|
||||
co = ChromiumOptions()
|
||||
# 设置不加载图片、静音
|
||||
co.set_local_port(port)
|
||||
co.no_imgs(True).mute(True)
|
||||
browser = Chromium(co)
|
||||
return browser
|
||||
|
||||
def start_client(self):
|
||||
"""启动紫鸟客户端"""
|
||||
|
||||
# 检查端口是否已经启动
|
||||
try:
|
||||
url = f'http://127.0.0.1:{self.socket_port}'
|
||||
response = requests.get(url, timeout=2)
|
||||
print(f"端口 {self.socket_port} 已经启动，跳过启动客户端操作")
|
||||
return
|
||||
except (requests.exceptions.ConnectionError, requests.exceptions.Timeout):
|
||||
# 端口未启动，继续执行启动操作
|
||||
print(f"端口 {self.socket_port} 未启动，开始启动客户端")
|
||||
|
||||
self.kill_process('v6')
|
||||
time.sleep(5)
|
||||
self.client_path = self.get_zinaio_exe("superbrowserv6").strip('"')
|
||||
print(self.client_path)
|
||||
cmd = [self.client_path, '--run_type=web_driver', '--ipc_type=http',
|
||||
'--port=' + str(self.socket_port)]
|
||||
print(" ".join(cmd))
|
||||
|
||||
# 最大重试次数
|
||||
max_retries = 3
|
||||
|
||||
for retry_count in range(max_retries):
|
||||
print(f"第 {retry_count + 1} 次尝试启动客户端...")
|
||||
|
||||
# 启动进程
|
||||
subprocess.Popen(cmd)
|
||||
|
||||
# 循环检测10秒，每0.5秒检测一次
|
||||
start_check_time = time.time()
|
||||
client_started = False
|
||||
|
||||
while time.time() - start_check_time < 10:
|
||||
try:
|
||||
response = requests.get(url, timeout=2)
|
||||
print(f"客户端启动成功！(第 {retry_count + 1} 次尝试)")
|
||||
client_started = True
|
||||
break
|
||||
except (requests.exceptions.ConnectionError, requests.exceptions.Timeout):
|
||||
# 端口还未启动，继续等待
|
||||
time.sleep(0.5)
|
||||
|
||||
if client_started:
|
||||
time.sleep(5) # 等待客户端完全启动
|
||||
# 更新内核
|
||||
self.update_core()
|
||||
return
|
||||
else:
|
||||
print(f"第 {retry_count + 1} 次尝试启动失败，10秒内未检测到客户端启动")
|
||||
|
||||
# 超过最大重试次数，抛出异常
|
||||
raise RuntimeError(f"客户端启动失败：重试 {max_retries} 次后仍未成功启动")
|
||||
|
||||
def open_shop(self, shop_name: str):
|
||||
"""
|
||||
打开指定店铺
|
||||
|
||||
Args:
|
||||
shop_name: 店铺名称
|
||||
|
||||
Returns:
|
||||
Chromium or str: 成功返回浏览器实例，失败返回错误信息
|
||||
"""
|
||||
print("=============打开指定店铺================")
|
||||
# 启动客户端
|
||||
self.start_client()
|
||||
|
||||
# 获取店铺列表
|
||||
shop_ls = self.get_browser_list()
|
||||
self.store_id = None
|
||||
print(shop_ls)
|
||||
for shop in shop_ls:
|
||||
if shop.get("browserName") == shop_name:
|
||||
self.store_id = shop.get('browserOauth')
|
||||
break
|
||||
|
||||
if not self.store_id:
|
||||
print("店铺不存在")
|
||||
return "店铺不存在"
|
||||
|
||||
# 打开店铺
|
||||
ret_json = self.open_store(self.store_id)
|
||||
print(ret_json)
|
||||
self.store_id = ret_json.get("browserOauth")
|
||||
if self.store_id is None:
|
||||
self.store_id = ret_json.get("browserId")
|
||||
|
||||
# 获取drissionpage浏览器会话
|
||||
self.browser = self.get_browser(ret_json.get('debuggingPort'))
|
||||
|
||||
ip_check_url = ret_json.get("ipDetectionPage")
|
||||
if not ip_check_url:
|
||||
print("ip检测页地址为空，请升级紫鸟浏览器到最新版")
|
||||
print(f"=====关闭店铺：{shop_name}=====")
|
||||
self.close_store(self.store_id)
|
||||
# exit()
|
||||
raise RuntimeError("没有IP检测地址，为了店铺安全不打开店铺")
|
||||
ip_usable = self.open_ip_check(self.browser, ip_check_url)
|
||||
if ip_usable:
|
||||
print("ip检测通过，打开店铺平台主页")
|
||||
self.open_launcher_page(ret_json.get("launcherPage"), self.browser)
|
||||
else:
|
||||
print("IP检测不通过")
|
||||
raise RuntimeError("IP检测不通过，可能是因为网络环境变化导致的，为了店铺安全不打开店铺")
|
||||
return self.browser
|
||||
|
||||
def close_store(self, browser_oauth=None):
|
||||
"""
|
||||
关闭店铺
|
||||
|
||||
Args:
|
||||
browser_oauth: 店铺OAuth标识，如果不提供则使用当前打开的店铺
|
||||
|
||||
Returns:
|
||||
dict: 返回结果
|
||||
"""
|
||||
if browser_oauth is None:
|
||||
browser_oauth = self.store_id
|
||||
|
||||
request_id = str(uuid.uuid4())
|
||||
data = {
|
||||
"action": "stopBrowser",
|
||||
"requestId": request_id,
|
||||
"duplicate": 0,
|
||||
"browserOauth": browser_oauth
|
||||
}
|
||||
data.update(self.user_info)
|
||||
|
||||
url = f'http://127.0.0.1:{self.socket_port}'
|
||||
response = requests.post(url, json.dumps(data).encode('utf-8'), timeout=120)
|
||||
r = response.json()
|
||||
if str(r.get("statusCode")) == "0":
|
||||
return r
|
||||
elif str(r.get("statusCode")) == "-10003":
|
||||
raise RuntimeError(f"【close_store】登录失败 {json.dumps(r, ensure_ascii=False)}")
|
||||
# exit()
|
||||
else:
|
||||
raise RuntimeError(f"【close_store】失败： {json.dumps(r, ensure_ascii=False)} ")
|
||||
# exit()
|
||||
|
||||
def open_launcher_page(self, launcher_page: str, browser: Chromium = None):
|
||||
"""
|
||||
打开启动页面
|
||||
|
||||
Args:
|
||||
launcher_page: 要打开的页面URL
|
||||
browser: 浏览器实例，如果不提供则使用当前浏览器实例
|
||||
"""
|
||||
if browser is None:
|
||||
browser = self.browser
|
||||
|
||||
tab = browser.new_tab(url=launcher_page)
|
||||
self.tab = tab
|
||||
return tab
|
||||
|
||||
def open_ip_check(self, browser: Chromium, ip_check_url: str):
|
||||
"""
|
||||
打开ip检测页检测ip是否正常
|
||||
:param browser: drissionpage浏览器会话
|
||||
:param ip_check_url ip检测页地址
|
||||
:return 检测结果
|
||||
"""
|
||||
try:
|
||||
tab = browser.latest_tab
|
||||
tab.get(ip_check_url)
|
||||
success_button = tab.ele((By.XPATH, '//button[contains(@class, "styles_btn--success")]'),
|
||||
timeout=60) # 等待查找元素60秒
|
||||
if success_button:
|
||||
print("ip检测成功")
|
||||
return True
|
||||
else:
|
||||
print("ip检测超时")
|
||||
return False
|
||||
except Exception as e:
|
||||
print("ip检测异常:" + traceback.format_exc())
|
||||
return False
|
||||
|
||||
|
||||
class AmamzonBase(ZiniaoDriver):
|
||||
"""亚马逊操作基类，包含一些通用方法"""
|
||||
mark_name = "操作基类"
|
||||
|
||||
def log(self, message: str, level: str = "INFO"):
|
||||
"""日志输出
|
||||
Args:
|
||||
message: 日志消息
|
||||
level: 日志级别
|
||||
"""
|
||||
try:
|
||||
timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
if level == "ERROR":
|
||||
show_notification(message, "error")
|
||||
print(f"[{timestamp}] [{self.mark_name}] [{level}] {message}")
|
||||
except Exception as e:
|
||||
print(f"输出出错,{e}")
|
||||
|
||||
|
||||
def SwitchingCountries(self, country_name: str):
|
||||
"""
|
||||
切换国家
|
||||
操作：
|
||||
1、//div[@class="dropdown-account-switcher-header-label"]/span[last()] 获取此元素文本，判断当前国家，如果与目标国家相同则不操作，否则执行下一步
|
||||
2、点击 //div[@class="dropdown-account-switcher-header-label"] 打开下拉框
|
||||
3、点击 //div[@class="dropdown-account-switcher-list-item"] 第一个展开国家列表
|
||||
4、点击 //div[@class="dropdown-account-switcher-list-item dropdown-account-switcher-list-item-indented" and @title="国家名"] 切换到目标国家
|
||||
5、等待页面加载完成，判断国家是否切换成功，成功则返回True，否则返回False
|
||||
|
||||
Args:
|
||||
country_name: 目标国家名称
|
||||
|
||||
Returns:
|
||||
bool: 切换成功返回True，失败返回False
|
||||
"""
|
||||
try:
|
||||
print("=============切换国家================")
|
||||
if self.browser is None:
|
||||
print("浏览器实例不存在，请先打开店铺")
|
||||
return False
|
||||
|
||||
# 获取当前标签页
|
||||
tab = self.tab
|
||||
tab.wait.doc_loaded(timeout=120, raise_err=False)
|
||||
|
||||
# 步骤1：获取当前国家名称
|
||||
self.log(f"正在检查当前国家...")
|
||||
current_country_ele = tab.ele('xpath://div[@class="dropdown-account-switcher-header-label"]/span[last()]',
|
||||
timeout=20)
|
||||
if current_country_ele:
|
||||
current_country = current_country_ele.text.strip()
|
||||
self.log(f"当前国家：{current_country}")
|
||||
|
||||
# 判断是否与目标国家相同
|
||||
if current_country == country_name:
|
||||
self.log(f"当前已经是目标国家 {country_name}，无需切换")
|
||||
return True
|
||||
else:
|
||||
self.log("无法获取当前国家信息")
|
||||
return False
|
||||
|
||||
# 步骤2：点击打开下拉框
|
||||
self.log(f"正在打开国家切换下拉框...")
|
||||
dropdown_header = tab.ele('xpath://div[@class="dropdown-account-switcher-header-label"]', timeout=10)
|
||||
if not dropdown_header:
|
||||
self.log("找不到国家切换下拉框")
|
||||
return False
|
||||
dropdown_header.click()
|
||||
time.sleep(1) # 等待下拉框展开
|
||||
|
||||
# 步骤3：点击第一个展开国家列表
|
||||
self.log(f"正在展开国家列表...")
|
||||
first_item = tab.ele('xpath://div[@class="dropdown-account-switcher-list-item"]', timeout=10)
|
||||
if not first_item:
|
||||
self.log("找不到国家列表项")
|
||||
return False
|
||||
first_item.click()
|
||||
time.sleep(1) # 等待国家列表展开
|
||||
|
||||
# 步骤4：点击目标国家
|
||||
self.log(f"正在切换到国家：{country_name}")
|
||||
target_country_xpath = f'//div[@class="dropdown-account-switcher-list-item dropdown-account-switcher-list-item-indented" and @title="{country_name}"]'
|
||||
target_country = tab.ele(f'xpath:{target_country_xpath}', timeout=10)
|
||||
if not target_country:
|
||||
self.log(f"找不到目标国家：{country_name}")
|
||||
return False
|
||||
target_country.click()
|
||||
|
||||
# 步骤5：等待页面加载完成并验证切换结果
|
||||
self.log(f"等待页面加载...")
|
||||
# time.sleep(3) # 等待页面加载
|
||||
self.tab.wait.doc_loaded()
|
||||
|
||||
# 再次检查当前国家
|
||||
new_country_ele = tab.ele('xpath://div[@class="dropdown-account-switcher-header-label"]/span[last()]',
|
||||
timeout=10)
|
||||
if new_country_ele:
|
||||
new_country = new_country_ele.text.strip()
|
||||
if new_country == country_name:
|
||||
self.log(f"国家切换成功：{new_country}")
|
||||
return True
|
||||
else:
|
||||
self.log(f"国家切换失败，当前国家：{new_country}，目标国家：{country_name}")
|
||||
return False
|
||||
else:
|
||||
self.log("无法验证切换结果")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
self.log(f"切换国家时发生异常：{traceback.format_exc()}")
|
||||
return False
|
||||
|
||||
def need_login(self):
|
||||
"""
|
||||
判断是否需要登录，部分国家可能需要登录后才能切换国家
|
||||
处理流程：
|
||||
|
||||
"""
|
||||
time.sleep(3) # 等待页面可能的登录元素加载,避免跳转等等
|
||||
self.tab.wait.doc_loaded(timeout=30, raise_err=False)
|
||||
need_login_ele = self.tab.eles('xpath://h1[@class="a-spacing-small"]|//span[contains(text(),"登录")]', timeout=5)
|
||||
if len(need_login_ele) > 0:
|
||||
self.log("检测到需要登录元素")
|
||||
return True
|
||||
return False
|
||||
|
||||
def login(self, password, username=""):
|
||||
try:
|
||||
self.tab.wait.doc_loaded(timeout=30, raise_err=False)
|
||||
for _ in range(4):
|
||||
switch_account = self.tab.eles(
|
||||
'xpath://div[@data-test-id="switchableAccounts"]//div[@class="a-fixed-left-grid"]', timeout=5)
|
||||
if len(switch_account) > 0:
|
||||
switch_account[0].click()
|
||||
time.sleep(1)
|
||||
self.tab.wait.doc_loaded(timeout=30, raise_err=False)
|
||||
|
||||
pwd_input = self.tab.eles('xpath://input[@type="password"]', timeout=5)
|
||||
if len(pwd_input) > 0:
|
||||
pwd_input[0].input(password, clear=True)
|
||||
submit_btn = self.tab.eles('xpath://input[@id="signInSubmit"]', timeout=5)
|
||||
if len(submit_btn) > 0:
|
||||
submit_btn[0].click()
|
||||
self.tab.wait.doc_loaded(timeout=30, raise_err=False)
|
||||
|
||||
send_code = self.tab.eles('xpath://span[@id="auth-send-code" and contains(string(.),"发送一次性密码")]',
|
||||
timeout=5)
|
||||
self.log(f"发送一次性密码:{len(send_code)}")
|
||||
if len(send_code) > 0:
|
||||
self.log("检测到 发送一次性密码")
|
||||
send_code[0].click()
|
||||
time.sleep(1)
|
||||
self.tab.wait.doc_loaded(timeout=30, raise_err=False)
|
||||
else:
|
||||
for j in range(5):
|
||||
opt_code_input = self.tab.eles('xpath://input[@name="otpCode"]', timeout=30)
|
||||
self.log(f"验证码输入框:{len(opt_code_input)}")
|
||||
if len(opt_code_input) > 0:
|
||||
opt_code_input[0].wait.displayed(timeout=10, raise_err=False)
|
||||
for _ in range(30):
|
||||
if opt_code_input[0].value is not None and opt_code_input[0].value.strip() != "":
|
||||
print("检测到验证码输入完成")
|
||||
submit_btn = self.tab.eles('xpath://input[@id="auth-signin-button"]', timeout=10)
|
||||
if len(submit_btn) > 0:
|
||||
submit_btn[0].click()
|
||||
self.tab.wait.doc_loaded(timeout=20, raise_err=False)
|
||||
# return True
|
||||
error_mes = self.tab.eles('xpath://div[@id="auth-error-message-box"]',
|
||||
timeout=10)
|
||||
if len(error_mes) > 0:
|
||||
self.log("验证码输入错误")
|
||||
self.log(f"验证码输入错误提示:{error_mes[0].text}")
|
||||
self.tab.refresh()
|
||||
else:
|
||||
self.log("登入成功")
|
||||
return True
|
||||
|
||||
time.sleep(1)
|
||||
|
||||
else:
|
||||
break
|
||||
|
||||
submit_btn = self.tab.eles('xpath://input[@id="auth-signin-button"]', timeout=10)
|
||||
if len(submit_btn) > 0:
|
||||
submit_btn[0].click()
|
||||
except Exception as e:
|
||||
self.log(f"登录过程中发生异常:{traceback.format_exc()}")
|
||||
return False
|
||||
|
||||
def SwitchPage(self):
|
||||
"""
|
||||
切换至 管理所有库存页面
|
||||
1、等待 //navigation-favorites-bar[@class="hydrated"] 出现
|
||||
"""
|
||||
navigation = self.tab.ele('xpath://navigation-favorites-bar[@class="hydrated"]')
|
||||
navigation.wait.displayed(raise_err=False)
|
||||
page_btn = navigation.sr('xpath://internal-fav-bar-links[@data-internal="navigation"]').sr(
|
||||
'xpath://a[@data-page-id="ezdpc-gui-inventory-mons"]')
|
||||
page_btn.wait.displayed(raise_err=False)
|
||||
page_btn.click(timeout=5)
|
||||
|
||||
self.tab.wait.doc_loaded()
|
||||
# 等待搜索框出现
|
||||
search_region = self.tab.ele('xpath://div[@id="searchBoxContainer"]//kat-input-group')
|
||||
search_region.wait.displayed(raise_err=False, timeout=60)
|
||||
|
||||
def search(self,filter_type="ApprovalRequired"):
|
||||
sku_ls = []
|
||||
|
||||
load_ele = self.tab.eles("xpath://div[contains(@class,'Loader-module__loader')]",timeout=5)
|
||||
if len(load_ele) > 0:
|
||||
load_ele[0].wait.deleted(timeout=3, raise_err=False)
|
||||
time.sleep(0.5)
|
||||
|
||||
drop_down = self.tab.ele('xpath://div[contains(@class,"VolusListingStatusDropDown-module__verticalContainer")]//kat-dropdown')
|
||||
drop_down.wait.displayed(raise_err=False)
|
||||
drop_down.wait.enabled(raise_err=False)
|
||||
time.sleep(0.6)
|
||||
drop_down.click()
|
||||
# //kat-option[@value="SearchSuppressed"]
|
||||
xp = f'xpath://kat-option[@value="{filter_type}"]'
|
||||
self.log(f"正在寻找筛选条件 {filter_type}，xpath: {xp}")
|
||||
approval_required = self.tab.eles(xp,timeout=5)
|
||||
if len(approval_required) == 0:
|
||||
self.log(f"没有需要{filter_type}选项】没有需要{filter_type}的商品了")
|
||||
return sku_ls # "没有需要审批的商品了"
|
||||
else:
|
||||
approval_required = approval_required[0]
|
||||
approval_required.wait.displayed(raise_err=False)
|
||||
approval_required.click()
|
||||
|
||||
approval_required_text = approval_required.text
|
||||
self.log(f"已选择筛选条件: {approval_required_text}")
|
||||
|
||||
count = re.findall(r'\d+', approval_required_text)
|
||||
if count:
|
||||
count = int(count[0])
|
||||
self.log(f"待审批的商品数量: {count}")
|
||||
if count <= 0:
|
||||
self.log(f"没有需要{filter_type}的商品了")
|
||||
return sku_ls #"没有需要审批的商品了"
|
||||
for _ in range(3):
|
||||
# 等待加载完成
|
||||
load_ele = self.tab.eles("xpath://div[contains(@class,'Loader-module__loader')]")
|
||||
if len(load_ele) > 0:
|
||||
load_ele[0].wait.deleted(timeout=3, raise_err=False)
|
||||
time.sleep(0.5)
|
||||
|
||||
sku_ls = self.tab.eles("xpath://div[@data-sku]",timeout=3)
|
||||
if len(sku_ls) > 0:
|
||||
break
|
||||
approval_required.click()
|
||||
return sku_ls
|
||||
|
||||
|
||||
class TaskBase:
|
||||
task_name = "任务基类"
|
||||
|
||||
country_info = {
|
||||
"DE": "德国",
|
||||
"FR": "法国",
|
||||
"ES": "西班牙",
|
||||
"IT": "意大利",
|
||||
"UK": "英国"
|
||||
}
|
||||
|
||||
def __init__(self, user_info: dict = None):
|
||||
"""初始化审批任务处理器
|
||||
|
||||
Args:
|
||||
user_info: 用户信息字典，包含 company, username, password
|
||||
"""
|
||||
self.user_info = user_info or {}
|
||||
self.running = True
|
||||
|
||||
|
||||
def log(self, message: str, level: str = "INFO"):
|
||||
"""日志输出
|
||||
Args:
|
||||
message: 日志消息
|
||||
level: 日志级别
|
||||
"""
|
||||
try:
|
||||
timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
if level == "ERROR":
|
||||
show_notification(message, "error")
|
||||
print(f"[{timestamp}] [{self.task_name}] [{level}] {message}")
|
||||
except Exception as e:
|
||||
print(f"输出出错,{e}")
|
||||
|
||||
def process_task(self, task_data: dict):
|
||||
pass
|
||||
|
||||
|
||||
def open_shop(self, cls: Type[T], max_retries: int, company_name: str, shop_name: str, iskill: bool = False) -> T:
|
||||
error_info = ""
|
||||
driver = None
|
||||
for retry in range(max_retries):
|
||||
try:
|
||||
self.log(f"尝试打开店铺 {shop_name} (第 {retry + 1}/{max_retries} 次)")
|
||||
|
||||
if iskill:
|
||||
self.log("重试前先杀掉浏览器进程...")
|
||||
kill_process("v6")
|
||||
kill_process("v5")
|
||||
time.sleep(2)
|
||||
|
||||
# 组装用户信息并创建驱动
|
||||
user_info = {
|
||||
**self.user_info,
|
||||
"company": company_name
|
||||
}
|
||||
driver = cls(user_info)
|
||||
browser = driver.open_shop(shop_name)
|
||||
|
||||
if browser and browser != "店铺不存在":
|
||||
self.log(f"成功打开店铺 {shop_name}")
|
||||
else:
|
||||
self.log(f"打开店铺失败: {browser}", "WARNING")
|
||||
driver = None
|
||||
continue
|
||||
|
||||
# 判断是否需要登录
|
||||
need_login = driver.need_login()
|
||||
print("【是否需要登录】：", need_login)
|
||||
if need_login:
|
||||
self.log(f"店铺 {shop_name} 需要登录，正在登录...")
|
||||
# 获取店铺凭证
|
||||
response = get_shop_info(shop_name)
|
||||
print("【获取店铺凭证返回】：", response.text)
|
||||
shop_data = response.json()
|
||||
if not shop_data:
|
||||
mes = f"获取店铺凭证失败，响应数据: {shop_data.get('message', '未知错误')}"
|
||||
self.log(mes, "ERROR")
|
||||
show_notification(mes, "ERROR")
|
||||
continue
|
||||
|
||||
password = shop_data["data"]["password"]
|
||||
|
||||
login_success = driver.login(password)
|
||||
if login_success:
|
||||
self.log(f"店铺 {shop_name} 登录成功，正在重新打开店铺...")
|
||||
browser = driver.open_shop(shop_name)
|
||||
if browser and browser != "店铺不存在":
|
||||
self.log(f"成功打开店铺 {shop_name} 登录后")
|
||||
break
|
||||
else:
|
||||
self.log(f"登录后打开店铺失败: {browser}", "WARNING")
|
||||
driver = None
|
||||
else:
|
||||
self.log(f"店铺 {shop_name} 登录失败", "WARNING")
|
||||
driver = None
|
||||
else:
|
||||
break
|
||||
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"打开店铺异常: {traceback.format_exc()}", "INFO")
|
||||
driver = None
|
||||
error_info = str(e)
|
||||
time.sleep(10)
|
||||
|
||||
# 如果还有重试机会，等待后继续
|
||||
if retry < max_retries - 1:
|
||||
time.sleep(3)
|
||||
|
||||
# 检查是否成功打开
|
||||
if not driver or not browser or browser == "店铺不存在":
|
||||
error_msg = f"店铺 {shop_name} 打开失败，已重试 {max_retries} 次，跳过该店铺,{error_info}"
|
||||
self.log(error_msg, "ERROR")
|
||||
# 从执行列表中移除
|
||||
if shop_name in runing_shop:
|
||||
del runing_shop[shop_name]
|
||||
return driver
|
||||
return driver
|
||||
|
||||
|
||||
def process_shop(self, shop_data: Dict[str, Any], task_id: int):
|
||||
pass
|
||||
|
||||
def action_init(self, driver, country_name, shop_name, risk_listing_filter=None):
|
||||
"""切换到指定国际 -> 页面 -》 筛选好"""
|
||||
max_retries = 5
|
||||
switch_success = False
|
||||
switch_success_pg = False
|
||||
search_success = False
|
||||
sku_ls = []
|
||||
for retry in range(max_retries):
|
||||
try:
|
||||
self.log(f"尝试切换到国家 {country_name} (第 {retry + 1}/{max_retries} 次)")
|
||||
if retry > 2:
|
||||
# 刷新不行就重新打开店铺
|
||||
self.log("重试前重新打开店铺...")
|
||||
try:
|
||||
driver.close_store()
|
||||
time.sleep(3)
|
||||
driver.open_shop(shop_name)
|
||||
except Exception as e:
|
||||
self.log(f"关闭重新打开店铺: {str(e)}", "WARNING")
|
||||
# 如果不是第一次尝试，先刷新页面
|
||||
if retry > 0:
|
||||
self.log("重试前刷新页面...")
|
||||
try:
|
||||
driver.tab.refresh()
|
||||
time.sleep(3)
|
||||
except Exception as e:
|
||||
self.log(f"刷新页面失败: {str(e)}", "WARNING")
|
||||
|
||||
switch_success = driver.SwitchingCountries(country_name)
|
||||
if switch_success:
|
||||
self.log(f"成功切换到国家 {country_name}")
|
||||
|
||||
# 切换到库存管理页面
|
||||
driver.SwitchPage()
|
||||
self.log(f"已切换到库存管理页面")
|
||||
time.sleep(3)
|
||||
switch_success_pg = True
|
||||
|
||||
if risk_listing_filter is None:
|
||||
self.log(f"risk_listing_filter 为空，不筛选, {risk_listing_filter}")
|
||||
search_success = True
|
||||
break
|
||||
|
||||
sku_ls = driver.search(filter_type=risk_listing_filter)
|
||||
search_success = True
|
||||
self.log(f"国家 {country_name} 搜索出 {len(sku_ls)} 商品，开始处理...")
|
||||
break
|
||||
else:
|
||||
self.log(f"切换到国家 {country_name} 失败", "WARNING")
|
||||
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"切换国家 {country_name} 异常: {str(e)}", "ERROR")
|
||||
self.log(traceback.format_exc(), "ERROR")
|
||||
|
||||
# 如果还有重试机会，等待后继续
|
||||
if retry < max_retries - 1:
|
||||
time.sleep(2)
|
||||
|
||||
return switch_success, switch_success_pg, search_success, sku_ls
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,42 +1,17 @@
|
||||
import json
|
||||
import sys
|
||||
import os
|
||||
import io
|
||||
# sys.stdout.reconfigure(encoding='utf-8')
|
||||
|
||||
import time
|
||||
import re
|
||||
import traceback
|
||||
from datetime import datetime
|
||||
from DrissionPage import Chromium, ChromiumOptions
|
||||
import requests
|
||||
|
||||
from amazon.del_brand import AmamzonBase, kill_process
|
||||
from amazon.tool import show_notification, get_shop_info, remove_special_characters, split_currency_values
|
||||
from amazon.amazon_base import AmamzonBase, kill_process,TaskBase
|
||||
from amazon.tool import show_notification
|
||||
|
||||
from config import runing_task, runing_shop, base_dir, DELETE_BRAND_API_BASE
|
||||
from config import runing_task, runing_shop, DELETE_BRAND_API_BASE
|
||||
|
||||
|
||||
class AmzonePStatus(AmamzonBase):
|
||||
mark_name = "状态查询"
|
||||
|
||||
def SwitchPage(self):
|
||||
"""
|
||||
切换至 管理所有库存页面
|
||||
1、等待 //navigation-favorites-bar[@class="hydrated"] 出现
|
||||
"""
|
||||
navigation = self.tab.ele('xpath://navigation-favorites-bar[@class="hydrated"]')
|
||||
navigation.wait.displayed(raise_err=False)
|
||||
page_btn = navigation.sr('xpath://internal-fav-bar-links[@data-internal="navigation"]').sr(
|
||||
'xpath://a[@data-page-id="ezdpc-gui-inventory-mons"]')
|
||||
page_btn.wait.displayed(raise_err=False)
|
||||
page_btn.click(timeout=5)
|
||||
|
||||
self.tab.wait.doc_loaded()
|
||||
# 等待搜索框出现
|
||||
search_region = self.tab.ele('xpath://div[@id="searchBoxContainer"]//kat-input-group')
|
||||
search_region.wait.displayed(raise_err=False, timeout=60)
|
||||
|
||||
def search_asin(self, asin):
|
||||
search_region = self.tab.ele('xpath://div[@id="searchBoxContainer"]//kat-input-group')
|
||||
search_region.wait.displayed(raise_err=False)
|
||||
@@ -81,14 +56,8 @@ class AmzonePStatus(AmamzonBase):
|
||||
self.browser.close_tabs(close_tab)
|
||||
|
||||
def run_page_action(self, appoint_asin: str = None):
|
||||
"""
|
||||
|
||||
miniprice_info :
|
||||
{
|
||||
"B0DSJGJBWV" : "19.81" # asin : 最低价
|
||||
}
|
||||
"""
|
||||
print(f"【{self.mark_name}】，开始执行")
|
||||
self.log(f"==================={self.mark_name}=======================")
|
||||
self.log("开始执行...")
|
||||
num = 0
|
||||
retry_num = 0
|
||||
already_asin = set()
|
||||
@@ -174,29 +143,8 @@ class AmzonePStatus(AmamzonBase):
|
||||
self.tab.wait.doc_loaded(raise_err=False, timeout=120)
|
||||
|
||||
|
||||
class StatusTask:
|
||||
country_info = {
|
||||
"DE": "德国",
|
||||
"FR": "法国",
|
||||
"ES": "西班牙",
|
||||
"IT": "意大利",
|
||||
"UK": "英国"
|
||||
}
|
||||
|
||||
def __init__(self, user_info: dict = None):
|
||||
"""初始化审批任务处理器
|
||||
|
||||
Args:
|
||||
user_info: 用户信息字典，包含 company, username, password
|
||||
"""
|
||||
self.user_info = user_info or {}
|
||||
self.running = True
|
||||
|
||||
def log(self, message: str, level: str = "INFO"):
|
||||
timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
if level == "ERROR":
|
||||
show_notification(message, "error")
|
||||
print(f"[{timestamp}] [PriceTask] [{level}] {message}")
|
||||
class StatusTask(TaskBase):
|
||||
task_name = "状态查询-TASK"
|
||||
|
||||
def process_task(self, task_data: dict):
|
||||
"""处理审批任务主入口
|
||||
@@ -218,21 +166,12 @@ class StatusTask:
|
||||
# 用于测试
|
||||
limit = data.get("limit", None)
|
||||
|
||||
if not task_id:
|
||||
self.log("任务ID为空，跳过", "WARNING")
|
||||
return
|
||||
|
||||
# if not items:
|
||||
# self.log("店铺列表为空，跳过", "WARNING")
|
||||
# return
|
||||
|
||||
if not queryAsins:
|
||||
self.log("queryAsins 列表为空，跳过", "WARNING")
|
||||
if not task_id or not queryAsins:
|
||||
self.log("任务ID / queryAsins列表 为空，跳过", "WARNING")
|
||||
return
|
||||
|
||||
self.log(f"开始处理审批任务 {task_id}，共 1 个店铺，{len(queryAsins)} 个国家")
|
||||
|
||||
from config import runing_task
|
||||
runing_task[task_id] = {
|
||||
"status": "running",
|
||||
"start_time": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
|
||||
@@ -265,7 +204,6 @@ class StatusTask:
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["processed_shops"] += 1
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"处理店铺 {shop_name} 失败: {str(e)}", "ERROR")
|
||||
self.log(traceback.format_exc(), "ERROR")
|
||||
|
||||
@@ -279,96 +217,12 @@ class StatusTask:
|
||||
self.log(f"任务 {task_id} 处理完成！")
|
||||
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"任务处理失败: {traceback.format_exc()}", "ERROR")
|
||||
if task_id:
|
||||
from config import runing_task
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["status"] = "failed"
|
||||
runing_task[task_id]["error"] = str(e)
|
||||
|
||||
def open_shop(self, max_retries, company_name, shop_name, iskill=False):
|
||||
error_info = ""
|
||||
driver = None
|
||||
for retry in range(max_retries):
|
||||
try:
|
||||
self.log(f"尝试打开店铺 {shop_name} (第 {retry + 1}/{max_retries} 次)")
|
||||
|
||||
if iskill:
|
||||
self.log("重试前先杀掉浏览器进程...")
|
||||
kill_process("v6")
|
||||
kill_process("v5")
|
||||
time.sleep(2)
|
||||
|
||||
# 组装用户信息并创建驱动
|
||||
user_info = {
|
||||
**self.user_info,
|
||||
"company": company_name
|
||||
}
|
||||
driver = AmzonePStatus(user_info)
|
||||
browser = driver.open_shop(shop_name)
|
||||
|
||||
if browser and browser != "店铺不存在":
|
||||
self.log(f"成功打开店铺 {shop_name}")
|
||||
else:
|
||||
self.log(f"打开店铺失败: {browser}", "WARNING")
|
||||
driver = None
|
||||
continue
|
||||
|
||||
# 判断是否需要登录
|
||||
need_login = driver.need_login()
|
||||
print("【是否需要登录】：", need_login)
|
||||
if need_login:
|
||||
self.log(f"店铺 {shop_name} 需要登录，正在登录...")
|
||||
# 获取店铺凭证
|
||||
response = get_shop_info(shop_name)
|
||||
print("【获取店铺凭证返回】：", response.text)
|
||||
shop_data = response.json()
|
||||
if not shop_data:
|
||||
mes = f"获取店铺凭证失败，响应数据: {shop_data.get('message', '未知错误')}"
|
||||
self.log(mes, "ERROR")
|
||||
show_notification(mes, "ERROR")
|
||||
continue
|
||||
|
||||
password = shop_data["data"]["password"]
|
||||
|
||||
login_success = driver.login(password)
|
||||
if login_success:
|
||||
self.log(f"店铺 {shop_name} 登录成功，正在重新打开店铺...")
|
||||
browser = driver.open_shop(shop_name)
|
||||
if browser and browser != "店铺不存在":
|
||||
self.log(f"成功打开店铺 {shop_name} 登录后")
|
||||
break
|
||||
else:
|
||||
self.log(f"登录后打开店铺失败: {browser}", "WARNING")
|
||||
driver = None
|
||||
else:
|
||||
self.log(f"店铺 {shop_name} 登录失败", "WARNING")
|
||||
driver = None
|
||||
else:
|
||||
break
|
||||
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"打开店铺异常: {traceback.format_exc()}", "INFO")
|
||||
driver = None
|
||||
error_info = str(e)
|
||||
time.sleep(10)
|
||||
|
||||
# 如果还有重试机会，等待后继续
|
||||
if retry < max_retries - 1:
|
||||
time.sleep(3)
|
||||
|
||||
# 检查是否成功打开
|
||||
if not driver or not browser or browser == "店铺不存在":
|
||||
error_msg = f"店铺 {shop_name} 打开失败，已重试 {max_retries} 次，跳过该店铺,{error_info}"
|
||||
self.log(error_msg, "ERROR")
|
||||
# 从执行列表中移除
|
||||
if shop_name in runing_shop:
|
||||
del runing_shop[shop_name]
|
||||
return driver
|
||||
return driver
|
||||
|
||||
def process_shop(self, shop_item: dict, country_codes: list, task_id: int,
|
||||
user_id=None, stage_index=None, final_stage: bool = True, limit: str = None):
|
||||
"""处理单个店铺
|
||||
@@ -382,7 +236,6 @@ class StatusTask:
|
||||
shop_name = shop_item.get("shopName", "未知店铺")
|
||||
company_name = shop_item.get("companyName", "")
|
||||
|
||||
|
||||
if not company_name:
|
||||
self.log(f"店铺 {shop_name} 的公司名称为空，跳过", "WARNING")
|
||||
return
|
||||
@@ -403,7 +256,7 @@ class StatusTask:
|
||||
country_code = value.get("country")
|
||||
all_asin = value.get("asins")
|
||||
# 打开店铺
|
||||
driver = self.open_shop(max_retries=max_retries, company_name=company_name,
|
||||
driver = self.open_shop(cls=AmzonePStatus,max_retries=max_retries, company_name=company_name,
|
||||
shop_name=shop_name, iskill=iskill)
|
||||
if driver is None:
|
||||
self.log(f"任务 {task_id} 启动店铺失败，结束任务", "ERROR")
|
||||
@@ -419,7 +272,6 @@ class StatusTask:
|
||||
try:
|
||||
self.process_country(driver, country_code, task_id, shop_name,all_asin=all_asin )
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"处理国家 {country_code} 失败: {str(e)}", "ERROR")
|
||||
self.log(traceback.format_exc(), "ERROR")
|
||||
if "与页面的连接已断开" in str(e):
|
||||
@@ -450,8 +302,7 @@ class StatusTask:
|
||||
self.log(f"店铺 {shop_name} 已从执行列表中移除")
|
||||
|
||||
def process_country(self, driver: AmzonePStatus, country_code: str, task_id: int, shop_name: str,
|
||||
all_asin:list,
|
||||
limit: str = None):
|
||||
all_asin:list,limit: str = None):
|
||||
"""处理单个国家的审批任务
|
||||
|
||||
Args:
|
||||
@@ -505,7 +356,6 @@ class StatusTask:
|
||||
self.log(f"切换到国家 {country_name} 失败", "WARNING")
|
||||
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"切换国家 {country_name} 异常: {str(e)}", "ERROR")
|
||||
self.log(traceback.format_exc(), "ERROR")
|
||||
|
||||
@@ -527,7 +377,6 @@ class StatusTask:
|
||||
driver.SwitchPage()
|
||||
self.log(f"已切换到库存管理页面")
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"切换页面失败: {str(e)}", "ERROR")
|
||||
self.log(traceback.format_exc(), "ERROR")
|
||||
|
||||
@@ -677,6 +526,7 @@ class StatusTask:
|
||||
raise RuntimeError("已达到最大重试次数，结果回传最终失败")
|
||||
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
# 使用示例
|
||||
user_info = {
|
||||
|
||||
189
app/amazon/chrome_base.py
Normal file
189
app/amazon/chrome_base.py
Normal file
@@ -0,0 +1,189 @@
|
||||
import json
|
||||
import sys
|
||||
import os
|
||||
import io
|
||||
|
||||
import time
|
||||
import traceback
|
||||
from datetime import datetime
|
||||
from DrissionPage import Chromium, ChromiumOptions
|
||||
from collections import defaultdict
|
||||
|
||||
from config import base_dir
|
||||
from amazon.tool import get_shop_info,show_notification
|
||||
|
||||
|
||||
|
||||
class ChromeAmzoneBase:
|
||||
mark_name = "谷歌浏览器基类"
|
||||
|
||||
country_info = {
|
||||
"英国": {
|
||||
"url": "https://www.amazon.co.uk/dp/B0CJ8SNXXV",
|
||||
"zip_code": "SW1A 1AA",
|
||||
"mark": "SW1A 1"
|
||||
},
|
||||
"德国": {
|
||||
"url": "https://www.amazon.de/dp/B0CC8CW9G2?th=1",
|
||||
"zip_code": "10115"
|
||||
},
|
||||
"法国": {
|
||||
"url": "https://www.amazon.fr/dp/B0FRG1MJ8H?th=1",
|
||||
"zip_code": "75001"
|
||||
},
|
||||
"西班牙": {
|
||||
"url": "https://www.amazon.es/dp/B08ZXVNYNN",
|
||||
"zip_code": "28001"
|
||||
},
|
||||
"意大利": {
|
||||
"url": "https://www.amazon.it/dp/B0D1P17T2Q",
|
||||
"zip_code": "20121"
|
||||
}
|
||||
}
|
||||
|
||||
def __init__(self):
|
||||
"""
|
||||
杀死当前谷歌浏览器进程，并使用 drissionpage 启动谷歌浏览器，使用系统安装的浏览器默认用户文件夹
|
||||
"""
|
||||
print("正在关闭现有的chromium浏览器进程...")
|
||||
os.system('taskkill /f /t /im chrome.exe')
|
||||
time.sleep(2)
|
||||
|
||||
print("正在启动chromium浏览器...")
|
||||
# 配置浏览器选项
|
||||
co = ChromiumOptions()
|
||||
user_data_path = os.path.join(base_dir, "user_data", "chrome_data")
|
||||
if not os.path.exists(user_data_path):
|
||||
os.makedirs(user_data_path, exist_ok=True)
|
||||
co.set_user_data_path(user_data_path)
|
||||
co.set_local_port(port=19897)
|
||||
self.browser = Chromium(co)
|
||||
self.tab = self.browser.latest_tab
|
||||
print("Chrome浏览器启动成功")
|
||||
|
||||
def log(self, message: str, level: str = "INFO"):
|
||||
"""日志输出
|
||||
Args:
|
||||
message: 日志消息
|
||||
level: 日志级别
|
||||
"""
|
||||
try:
|
||||
timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
if level == "ERROR":
|
||||
show_notification(message, "error")
|
||||
print(f"[{timestamp}] [{self.mark_name}] [{level}] {message}")
|
||||
except Exception as e:
|
||||
print(f"输出出错,{e}")
|
||||
|
||||
def close_init_popup(self):
|
||||
"""
|
||||
关闭所有的初始化弹窗
|
||||
"""
|
||||
self.tab.wait.doc_loaded(timeout=60, raise_err=True)
|
||||
footbar = self.tab.eles('xpath://footer[@class="el-dialog__footer"]', timeout=5)
|
||||
if len(footbar) > 0:
|
||||
do_not_remind = footbar[0].eles('xpath:.//input[@class="el-checkbox__original"]')
|
||||
if len(do_not_remind) > 0:
|
||||
do_not_remind[0].check()
|
||||
resume_immediately = footbar[0].eles('xpath:.//button')
|
||||
if len(resume_immediately) > 0:
|
||||
resume_immediately[0].click()
|
||||
|
||||
self.tab.wait.doc_loaded(timeout=60, raise_err=True)
|
||||
accept_btn = self.tab.eles('xpath://input[@id="sp-cc-accept"]', timeout=5)
|
||||
if len(accept_btn) > 0:
|
||||
accept_btn[0].click()
|
||||
|
||||
def _set_zip_code(self, zip_code, mark=None):
|
||||
"""
|
||||
设置邮编
|
||||
|
||||
Args:
|
||||
zip_code: 目标邮编
|
||||
"""
|
||||
try:
|
||||
# 检查当前邮编
|
||||
zip_display = self.tab.ele('xpath://div[@id="glow-ingress-block"]', timeout=10)
|
||||
|
||||
if zip_display:
|
||||
current_text = zip_display.text
|
||||
# print(f"当前地址信息: {current_text}")
|
||||
# 先检查标识
|
||||
if mark is not None and mark in current_text:
|
||||
print(f"邮编检测到标识: {mark}，无需修改")
|
||||
return True
|
||||
# 检查是否已经包含目标邮编
|
||||
if zip_code in current_text:
|
||||
print(f"邮编已经设置为: {zip_code}，无需修改")
|
||||
return True
|
||||
|
||||
# 需要设置邮编
|
||||
print(f"正在设置邮编为: {zip_code}")
|
||||
|
||||
# 点击地址选择按钮
|
||||
location_link = self.tab.ele('xpath://a[@id="nav-global-location-popover-link"]', timeout=10)
|
||||
if not location_link:
|
||||
print("找不到地址设置按钮")
|
||||
return False
|
||||
|
||||
location_link.click()
|
||||
time.sleep(1)
|
||||
|
||||
# 等待邮编输入框出现
|
||||
zip_input = self.tab.ele('xpath://input[@id="GLUXZipUpdateInput"]', timeout=10)
|
||||
if not zip_input:
|
||||
print("找不到邮编输入框")
|
||||
return False
|
||||
|
||||
# 输入邮编
|
||||
zip_input.input(zip_code, clear=True)
|
||||
time.sleep(0.5)
|
||||
|
||||
# 点击提交按钮
|
||||
submit_btn = self.tab.ele('xpath://input[@aria-labelledby="GLUXZipUpdate-announce"]', timeout=10)
|
||||
if not submit_btn:
|
||||
print("找不到提交按钮")
|
||||
return False
|
||||
|
||||
submit_btn.click()
|
||||
|
||||
continue_btn = self.tab.eles('xpath://div[@class="a-popover-footer"]//input[@id="GLUXConfirmClose"]',
|
||||
timeout=10)
|
||||
if len(continue_btn) > 0:
|
||||
continue_btn[0].click()
|
||||
|
||||
# 等待提交按钮消失（表示请求已发送）
|
||||
print("等待邮编更新...")
|
||||
time.sleep(2)
|
||||
|
||||
# 等待页面加载完成
|
||||
self.tab.wait.doc_loaded(timeout=30, raise_err=False)
|
||||
time.sleep(2)
|
||||
|
||||
# 验证邮编是否设置成功
|
||||
zip_display_after = self.tab.ele('xpath://div[@id="glow-ingress-block"]', timeout=10)
|
||||
if zip_display_after:
|
||||
updated_text = zip_display_after.text
|
||||
# print(f"更新后的地址信息: {updated_text}")
|
||||
|
||||
if zip_code in updated_text:
|
||||
print(f"邮编设置成功: {zip_code}")
|
||||
return True
|
||||
else:
|
||||
# print(f"邮编设置可能失败，当前显示: {updated_text}")
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
print(f"设置邮编时出错: {traceback.format_exc()}")
|
||||
return False
|
||||
|
||||
def close(self):
|
||||
"""关闭浏览器"""
|
||||
try:
|
||||
if self.browser:
|
||||
self.browser.quit()
|
||||
print("浏览器已关闭")
|
||||
except Exception as e:
|
||||
print(f"关闭浏览器时出错: {str(e)}")
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,88 +1,23 @@
|
||||
import json
|
||||
import sys
|
||||
import os
|
||||
import io
|
||||
# sys.stdout.reconfigure(encoding='utf-8')
|
||||
|
||||
import time
|
||||
import re
|
||||
import traceback
|
||||
from datetime import datetime
|
||||
from DrissionPage import Chromium, ChromiumOptions
|
||||
from collections import defaultdict
|
||||
import requests
|
||||
|
||||
from amazon.del_brand import AmamzonBase, kill_process
|
||||
from amazon.tool import show_notification,get_shop_info,remove_special_characters,split_currency_values
|
||||
from amazon.amazon_base import TaskBase
|
||||
from amazon.chrome_base import ChromeAmzoneBase
|
||||
|
||||
|
||||
from config import runing_task, runing_shop,base_dir,DELETE_BRAND_API_BASE
|
||||
|
||||
|
||||
class ChromeAmzone:
|
||||
class ChromeAmzone(ChromeAmzoneBase):
|
||||
mark_name = "亚马逊详情采集"
|
||||
country_info = {
|
||||
"英国": {
|
||||
"url": "https://www.amazon.co.uk/dp/B0CJ8SNXXV",
|
||||
"zip_code": "SW1A 1AA",
|
||||
"mark": "SW1A 1"
|
||||
},
|
||||
"德国": {
|
||||
"url": "https://www.amazon.de/dp/B0CC8CW9G2?th=1",
|
||||
"zip_code": "10115"
|
||||
},
|
||||
"法国": {
|
||||
"url": "https://www.amazon.fr/dp/B0FRG1MJ8H?th=1",
|
||||
"zip_code": "75001"
|
||||
},
|
||||
"西班牙": {
|
||||
"url": "https://www.amazon.es/dp/B08ZXVNYNN",
|
||||
"zip_code": "28001"
|
||||
},
|
||||
"意大利": {
|
||||
"url": "https://www.amazon.it/dp/B0D1P17T2Q",
|
||||
"zip_code": "20121"
|
||||
}
|
||||
}
|
||||
|
||||
def __init__(self):
|
||||
"""
|
||||
杀死当前谷歌浏览器进程，并使用 drissionpage 启动谷歌浏览器，使用系统安装的浏览器默认用户文件夹
|
||||
"""
|
||||
# 杀死现有的Chrome进程
|
||||
print("正在关闭现有的chromium浏览器进程...")
|
||||
os.system('taskkill /f /t /im chrome.exe')
|
||||
time.sleep(2)
|
||||
|
||||
print("正在启动chromium浏览器...")
|
||||
# 配置浏览器选项
|
||||
co = ChromiumOptions()
|
||||
user_data_path = os.path.join(base_dir, "user_data", "chrome_data")
|
||||
if not os.path.exists(user_data_path):
|
||||
os.makedirs(user_data_path, exist_ok=True)
|
||||
co.set_user_data_path(user_data_path)
|
||||
co.set_local_port(port=19897)
|
||||
self.browser = Chromium(co)
|
||||
self.tab = self.browser.latest_tab
|
||||
print("Chrome浏览器启动成功")
|
||||
|
||||
def close_init_popup(self):
|
||||
"""
|
||||
关闭所有的初始化弹窗
|
||||
"""
|
||||
self.tab.wait.doc_loaded(timeout=60, raise_err=True)
|
||||
footbar = self.tab.eles('xpath://footer[@class="el-dialog__footer"]', timeout=5)
|
||||
if len(footbar) > 0:
|
||||
do_not_remind = footbar[0].eles('xpath:.//input[@class="el-checkbox__original"]')
|
||||
if len(do_not_remind) > 0:
|
||||
do_not_remind[0].check()
|
||||
resume_immediately = footbar[0].eles('xpath:.//button')
|
||||
if len(resume_immediately) > 0:
|
||||
resume_immediately[0].click()
|
||||
|
||||
self.tab.wait.doc_loaded(timeout=60, raise_err=True)
|
||||
accept_btn = self.tab.eles('xpath://input[@id="sp-cc-accept"]', timeout=5)
|
||||
if len(accept_btn) > 0:
|
||||
accept_btn[0].click()
|
||||
|
||||
def run(self, country, asin):
|
||||
"""
|
||||
@@ -99,7 +34,7 @@ class ChromeAmzone:
|
||||
# 验证国家是否支持
|
||||
if country not in self.country_info:
|
||||
error_msg = f"不支持的国家: {country}，支持的国家有: {list(self.country_info.keys())}"
|
||||
print(error_msg)
|
||||
self.log(error_msg)
|
||||
show_notification(error_msg, "error")
|
||||
return None
|
||||
|
||||
@@ -114,7 +49,7 @@ class ChromeAmzone:
|
||||
domain = base_url.split("/dp/")[0]
|
||||
# 拼接新的URL
|
||||
product_url = f"{domain}/dp/{asin}"
|
||||
print(f"正在访问: {product_url}")
|
||||
self.log(f"正在访问: {product_url}")
|
||||
|
||||
# 打开链接
|
||||
self.tab.get(product_url)
|
||||
@@ -123,13 +58,13 @@ class ChromeAmzone:
|
||||
|
||||
self.close_init_popup()
|
||||
# 2. 切换国家/设置邮编
|
||||
print(f"正在检查并设置邮编: {zip_code},标识： {mark}")
|
||||
self.log(f"正在检查并设置邮编: {zip_code},标识： {mark}")
|
||||
self._set_zip_code(zip_code, mark)
|
||||
|
||||
# self.tab.wait.doc_loaded(timeout=5, raise_err=False)
|
||||
|
||||
# 3. 抓取数据
|
||||
print("正在抓取商品数据...")
|
||||
self.log("正在抓取商品数据...")
|
||||
data = self._scrape_data()
|
||||
|
||||
# 添加基本信息
|
||||
@@ -138,100 +73,15 @@ class ChromeAmzone:
|
||||
data['url'] = product_url
|
||||
data['timestamp'] = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
|
||||
|
||||
print(f"数据抓取完成: {json.dumps(data)}")
|
||||
self.log(f"数据抓取完成: {json.dumps(data)}")
|
||||
return data
|
||||
|
||||
except Exception as e:
|
||||
error_msg = f"运行出错: {traceback.format_exc()}"
|
||||
print(error_msg)
|
||||
self.log(error_msg)
|
||||
show_notification(f"采集失败: {str(e)}", "error")
|
||||
return {}
|
||||
|
||||
def _set_zip_code(self, zip_code, mark=None):
|
||||
"""
|
||||
设置邮编
|
||||
|
||||
Args:
|
||||
zip_code: 目标邮编
|
||||
"""
|
||||
try:
|
||||
# 检查当前邮编
|
||||
zip_display = self.tab.ele('xpath://div[@id="glow-ingress-block"]', timeout=10)
|
||||
|
||||
if zip_display:
|
||||
current_text = zip_display.text
|
||||
# print(f"当前地址信息: {current_text}")
|
||||
# 先检查标识
|
||||
if mark is not None and mark in current_text:
|
||||
print(f"邮编检测到标识: {mark}，无需修改")
|
||||
return True
|
||||
# 检查是否已经包含目标邮编
|
||||
if zip_code in current_text:
|
||||
print(f"邮编已经设置为: {zip_code}，无需修改")
|
||||
return True
|
||||
|
||||
# 需要设置邮编
|
||||
print(f"正在设置邮编为: {zip_code}")
|
||||
|
||||
# 点击地址选择按钮
|
||||
location_link = self.tab.ele('xpath://a[@id="nav-global-location-popover-link"]', timeout=10)
|
||||
if not location_link:
|
||||
print("找不到地址设置按钮")
|
||||
return False
|
||||
|
||||
location_link.click()
|
||||
time.sleep(1)
|
||||
|
||||
# 等待邮编输入框出现
|
||||
zip_input = self.tab.ele('xpath://input[@id="GLUXZipUpdateInput"]', timeout=10)
|
||||
if not zip_input:
|
||||
print("找不到邮编输入框")
|
||||
return False
|
||||
|
||||
# 输入邮编
|
||||
zip_input.input(zip_code, clear=True)
|
||||
time.sleep(0.5)
|
||||
|
||||
# 点击提交按钮
|
||||
submit_btn = self.tab.ele('xpath://input[@aria-labelledby="GLUXZipUpdate-announce"]', timeout=10)
|
||||
if not submit_btn:
|
||||
print("找不到提交按钮")
|
||||
return False
|
||||
|
||||
submit_btn.click()
|
||||
|
||||
continue_btn = self.tab.eles('xpath://div[@class="a-popover-footer"]//input[@id="GLUXConfirmClose"]',
|
||||
timeout=10)
|
||||
if len(continue_btn) > 0:
|
||||
continue_btn[0].click()
|
||||
|
||||
# 等待提交按钮消失（表示请求已发送）
|
||||
print("等待邮编更新...")
|
||||
time.sleep(2)
|
||||
|
||||
# 等待页面加载完成
|
||||
self.tab.wait.doc_loaded(timeout=30, raise_err=False)
|
||||
time.sleep(2)
|
||||
|
||||
# 验证邮编是否设置成功
|
||||
zip_display_after = self.tab.ele('xpath://div[@id="glow-ingress-block"]', timeout=10)
|
||||
if zip_display_after:
|
||||
updated_text = zip_display_after.text
|
||||
# print(f"更新后的地址信息: {updated_text}")
|
||||
|
||||
if zip_code in updated_text:
|
||||
print(f"邮编设置成功: {zip_code}")
|
||||
return True
|
||||
else:
|
||||
# print(f"邮编设置可能失败，当前显示: {updated_text}")
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
print(f"设置邮编时出错: {traceback.format_exc()}")
|
||||
return False
|
||||
|
||||
def _scrape_data(self):
|
||||
"""
|
||||
抓取商品数据
|
||||
@@ -256,36 +106,13 @@ class ChromeAmzone:
|
||||
return data
|
||||
|
||||
except Exception as e:
|
||||
print(f"抓取数据时出错: {traceback.format_exc()}")
|
||||
self.log(f"抓取数据时出错: {traceback.format_exc()}")
|
||||
return data
|
||||
|
||||
def close(self):
|
||||
"""关闭浏览器"""
|
||||
try:
|
||||
if self.browser:
|
||||
self.browser.quit()
|
||||
print("浏览器已关闭")
|
||||
except Exception as e:
|
||||
print(f"关闭浏览器时出错: {str(e)}")
|
||||
|
||||
|
||||
class SpiderTask:
|
||||
mark_name = "亚马逊采集"
|
||||
|
||||
def __init__(self, user_info: dict = None):
|
||||
"""初始化审批任务处理器
|
||||
|
||||
Args:
|
||||
user_info: 用户信息字典，包含 company, username, password
|
||||
"""
|
||||
self.user_info = user_info or {}
|
||||
self.running = True
|
||||
|
||||
def log(self, message: str, level: str = "INFO"):
|
||||
timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
if level == "ERROR":
|
||||
show_notification(message, "error")
|
||||
print(f"[{timestamp}] [PriceTask] [{level}] {message}")
|
||||
class SpiderTask(TaskBase):
|
||||
task_name = "亚马逊采集"
|
||||
|
||||
@staticmethod
|
||||
def group_by_id_prefix(data):
|
||||
@@ -357,7 +184,6 @@ class SpiderTask:
|
||||
self.log("appearance-patent groups/rows is empty, skip", "WARNING")
|
||||
return
|
||||
|
||||
from config import runing_task
|
||||
runing_task[task_id] = {
|
||||
"status": "running",
|
||||
"start_time": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
|
||||
@@ -396,7 +222,6 @@ class SpiderTask:
|
||||
}
|
||||
asin = value.get("asin")
|
||||
country = value.get("country")
|
||||
return_data = None
|
||||
for _ in range(max_retry):
|
||||
try:
|
||||
return_data = chrome.run(country, asin) or {}
|
||||
@@ -457,7 +282,6 @@ class SpiderTask:
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["processed_shops"] += 1
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"处理店铺 {task_id} 失败: {str(e)}", "ERROR")
|
||||
self.log(traceback.format_exc(), "ERROR")
|
||||
|
||||
@@ -471,10 +295,8 @@ class SpiderTask:
|
||||
self.log(f"任务 {task_id} 处理完成！")
|
||||
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"任务处理失败: {traceback.format_exc()}", "ERROR")
|
||||
if task_id:
|
||||
from config import runing_task
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["status"] = "failed"
|
||||
runing_task[task_id]["error"] = str(e)
|
||||
@@ -488,7 +310,7 @@ class SpiderTask:
|
||||
url = f"{DELETE_BRAND_API_BASE}/api/appearance-patent/tasks/{task_id}/result"
|
||||
|
||||
payload ={
|
||||
"submissionId": f"{int(time.time())}",
|
||||
"submissionId": f"{task_id}",
|
||||
"chunkIndex": chunkIndex,
|
||||
"chunkTotal": chunkTotal,
|
||||
"error": error,
|
||||
|
||||
8384
app/amazon/detail_spider_备份.py
Normal file
8384
app/amazon/detail_spider_备份.py
Normal file
File diff suppressed because it is too large
Load Diff
@@ -1,4 +1,3 @@
|
||||
import time
|
||||
import traceback
|
||||
import requests
|
||||
import threading
|
||||
@@ -6,7 +5,7 @@ from datetime import datetime
|
||||
from typing import Dict, Any, List
|
||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||
from config import JSON_TASK_QUEUE, runing_task, runing_shop, DELETE_BRAND_API_BASE, ZN_COMPANY, ZN_USERNAME, ZN_PASSWORD
|
||||
from amazon.del_brand import AmazoneDriver, kill_process
|
||||
from amazon.del_brand import AmazoneDriver, DelbramdTask
|
||||
from amazon.approve import ApproveTask
|
||||
from amazon.match_action import MatchTak
|
||||
from amazon.price_match import PriceTask
|
||||
@@ -14,8 +13,7 @@ from amazon.asin_status import StatusTask
|
||||
from amazon.patrol_delete import PatrolDeleteTask
|
||||
from amazon.detail_spider import SpiderTask
|
||||
|
||||
|
||||
from amazon.tool import get_shop_info,show_notification
|
||||
from amazon.amazon_base import kill_process
|
||||
|
||||
|
||||
class TaskMonitor:
|
||||
@@ -60,6 +58,7 @@ class TaskMonitor:
|
||||
futures = [] # 保存所有提交的任务Future对象
|
||||
|
||||
task_type_info = {
|
||||
"delete-brand-run" : "删除品牌",
|
||||
"product-risk-resolve-run" : "产品风险审批",
|
||||
"shop-match-run" : "匹配价格",
|
||||
"price-track-run" : "跟价",
|
||||
@@ -70,20 +69,13 @@ class TaskMonitor:
|
||||
try:
|
||||
while self.running:
|
||||
try:
|
||||
# 使用较长超时时间等待任务，减少空等待异常
|
||||
# 超时后继续循环检查self.running状态，避免卡死
|
||||
task_data = JSON_TASK_QUEUE.get(block=True, timeout=30)
|
||||
|
||||
# 检查任务类型
|
||||
task_type = task_data.get("type", "")
|
||||
|
||||
if task_type == "delete-brand-run":
|
||||
# 提交删除品牌任务到线程池
|
||||
self.log(f"接收到【删除品牌】任务，提交到线程池处理...")
|
||||
future = self.executor.submit(self._process_task_wrapper, task_data)
|
||||
futures.append(future)
|
||||
|
||||
elif task_type in task_type_info:
|
||||
if task_type in task_type_info:
|
||||
# 提交产品风险审批任务到线程池
|
||||
self.log(f"接收到任务，提交到线程池处理...")
|
||||
future = self.executor.submit(self._process_approve_task_wrapper, task_data, task_type_info[task_type])
|
||||
@@ -116,9 +108,9 @@ class TaskMonitor:
|
||||
task_data: 任务数据
|
||||
"""
|
||||
try:
|
||||
self.log(f"线程 {id(task_data)} 开始处理删除品牌任务...")
|
||||
self.log(f"线程 {id(task_data)} 开始处理任务...")
|
||||
self.process_task(task_data)
|
||||
self.log(f"线程 {id(task_data)} 删除品牌任务处理完成")
|
||||
self.log(f"线程 {id(task_data)} 任务处理完成")
|
||||
except Exception as e:
|
||||
self.log(f"线程 {id(task_data)} 删除品牌任务处理异常: {traceback.format_exc()}", "ERROR")
|
||||
|
||||
@@ -140,6 +132,7 @@ class TaskMonitor:
|
||||
"""
|
||||
try:
|
||||
TASK_INFO = {
|
||||
"删除品牌": DelbramdTask ,
|
||||
"产品风险审批" : ApproveTask,
|
||||
"匹配价格" : MatchTak,
|
||||
"跟价" : PriceTask,
|
||||
@@ -152,539 +145,9 @@ class TaskMonitor:
|
||||
TASK_CLS = TASK_INFO[TASK_TYPE] # 根据任务类型选择处理类，默认为ApproveTask
|
||||
approve_task = TASK_CLS(user_info=self.user_info)
|
||||
approve_task.process_task(task_data)
|
||||
self.log(f"线程 {id(task_data)} 产品风险审批任务处理完成")
|
||||
self.log(f"线程 {id(task_data)} {TASK_TYPE} 任务处理完成")
|
||||
except Exception as e:
|
||||
self.log(f"线程 {id(task_data)} 产品风险审批任务处理异常: {traceback.format_exc()}", "ERROR")
|
||||
|
||||
def process_task(self, task_data: Dict[str, Any]):
|
||||
"""处理单个任务
|
||||
|
||||
Args:
|
||||
task_data: 任务数据
|
||||
"""
|
||||
try:
|
||||
data = task_data.get("data", {})
|
||||
task_id = data.get("taskId")
|
||||
items = data.get("items", [])
|
||||
|
||||
if not task_id:
|
||||
self.log("任务ID为空，跳过", "WARNING")
|
||||
return
|
||||
|
||||
# 初始化任务状态
|
||||
self.update_task_status(
|
||||
task_id,
|
||||
status="running",
|
||||
start_time=datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
|
||||
total_shops=len(items),
|
||||
processed_shops=0,
|
||||
total_asins=sum(shop.get("totalRows", 0) for shop in items),
|
||||
processed_asins=0,
|
||||
success_count=0,
|
||||
failed_count=0,
|
||||
stop_requested=False # 暂停请求标志
|
||||
)
|
||||
|
||||
self.log(f"开始处理任务 {task_id}，共 {len(items)} 个店铺")
|
||||
|
||||
# 遍历处理每个店铺
|
||||
for idx, shop_data in enumerate(items, 1):
|
||||
shop_name = shop_data.get("shopName", "未知店铺")
|
||||
self.log(f"[{idx}/{len(items)}] 开始处理店铺: {shop_name}")
|
||||
|
||||
try:
|
||||
self.process_shop(shop_data, task_id)
|
||||
# 更新已处理店铺数
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["processed_shops"] += 1
|
||||
except Exception as e:
|
||||
self.log(f"处理店铺 {shop_name} 失败: {str(e)}", "ERROR")
|
||||
self.log(traceback.format_exc(), "ERROR")
|
||||
|
||||
# 检查任务最终状态
|
||||
if task_id in runing_task and runing_task[task_id].get("stop_requested", False):
|
||||
self.update_task_status(task_id, status="stopped")
|
||||
self.log(f"任务 {task_id} 已被暂停！")
|
||||
else:
|
||||
self.update_task_status(task_id, status="completed")
|
||||
self.log(f"任务 {task_id} 处理完成！")
|
||||
|
||||
except Exception as e:
|
||||
self.log(f"任务处理失败: {traceback.format_exc()}", "ERROR")
|
||||
if task_id:
|
||||
self.update_task_status(task_id, status="failed", error=str(e))
|
||||
|
||||
def process_shop(self, shop_data: Dict[str, Any], task_id: int):
|
||||
"""处理单个店铺（包含重试逻辑）
|
||||
|
||||
Args:
|
||||
shop_data: 店铺数据
|
||||
task_id: 任务ID
|
||||
"""
|
||||
shop_name = shop_data.get("shopName", "未知店铺")
|
||||
result_id = shop_data.get("resultId")
|
||||
countries = shop_data.get("countries", [])
|
||||
company_name = shop_data.get("companyName", "未知公司")
|
||||
|
||||
if not countries:
|
||||
self.log(f"店铺 {shop_name} 没有国家数据，跳过", "WARNING")
|
||||
return
|
||||
|
||||
# 更新当前处理的店铺
|
||||
self.update_task_status(task_id, current_shop=shop_name)
|
||||
|
||||
# 将店铺添加到正在执行中的店铺列表
|
||||
start_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
runing_shop[shop_name] = start_time
|
||||
self.log(f"账号：{company_name},店铺 {shop_name} 已添加到执行列表，开始时间: {start_time}")
|
||||
|
||||
# 店铺打开重试最多3次
|
||||
driver = None
|
||||
browser = None
|
||||
max_retries = 3
|
||||
|
||||
for retry in range(max_retries):
|
||||
try:
|
||||
self.log(f"尝试打开店铺 {shop_name} (第 {retry + 1}/{max_retries} 次)")
|
||||
|
||||
# 如果不是第一次尝试，先杀进程
|
||||
# if retry > 0:
|
||||
# self.log("重试前先杀掉浏览器进程...")
|
||||
# kill_process("v6")
|
||||
# kill_process("v5")
|
||||
# time.sleep(2)
|
||||
|
||||
# 创建驱动并打开店铺
|
||||
user_info = {
|
||||
**self.user_info,
|
||||
"company": company_name
|
||||
}
|
||||
driver = AmazoneDriver(user_info)
|
||||
browser = driver.open_shop(shop_name)
|
||||
|
||||
if browser and browser != "店铺不存在":
|
||||
self.log(f"成功打开店铺 {shop_name}")
|
||||
break
|
||||
else:
|
||||
self.log(f"打开店铺失败: {browser}", "WARNING")
|
||||
driver = None
|
||||
|
||||
# 判断是否需要登录
|
||||
driver.tab.wait.doc_loaded(timeout=30, raise_err=False) # 等待页面加载，避免过早判断登录状态
|
||||
need_login = driver.need_login()
|
||||
print("【是否需要登录】：",need_login)
|
||||
if need_login:
|
||||
self.log(f"店铺 {shop_name} 需要登录，正在登录...")
|
||||
# 获取店铺凭证
|
||||
response = get_shop_info(shop_name)
|
||||
print("【获取店铺凭证返回】：",response.text)
|
||||
shop_data = response.json()
|
||||
if not shop_data:
|
||||
mes = f"获取店铺凭证失败，响应数据: {shop_data.get('message', '未知错误')}"
|
||||
self.log(mes, "ERROR")
|
||||
show_notification(mes, "ERROR")
|
||||
continue
|
||||
|
||||
password = shop_data["data"]["password"]
|
||||
|
||||
login_success = driver.login(password)
|
||||
if login_success:
|
||||
self.log(f"店铺 {shop_name} 登录成功，正在重新打开店铺...")
|
||||
browser = driver.open_shop(shop_name)
|
||||
if browser and browser != "店铺不存在":
|
||||
self.log(f"成功打开店铺 {shop_name} 登录后")
|
||||
break
|
||||
else:
|
||||
self.log(f"登录后打开店铺失败: {browser}", "WARNING")
|
||||
driver = None
|
||||
else:
|
||||
self.log(f"店铺 {shop_name} 登录失败", "WARNING")
|
||||
driver = None
|
||||
|
||||
|
||||
except Exception as e:
|
||||
self.log(f"打开店铺异常: {str(e)}", "ERROR")
|
||||
driver = None
|
||||
|
||||
# 如果还有重试机会，等待后继续
|
||||
if retry < max_retries - 1:
|
||||
time.sleep(3)
|
||||
|
||||
# 检查是否成功打开
|
||||
if not driver or not browser or browser == "店铺不存在":
|
||||
self.log(f"店铺 {shop_name} 打开失败，已重试 {max_retries} 次，跳过该店铺", "ERROR")
|
||||
return
|
||||
|
||||
try:
|
||||
# 处理每个国家
|
||||
chunk_index =1
|
||||
for country_data in countries:
|
||||
# 检查是否收到暂停请求
|
||||
if task_id in runing_task and runing_task[task_id].get("stop_requested", False):
|
||||
self.log(f"检测到任务 {task_id} 的暂停请求，停止处理国家", "WARNING")
|
||||
break # 跳出循环，进入finally关闭店铺
|
||||
|
||||
try:
|
||||
chunk_index = self.process_country(driver, country_data, task_id, result_id, shop_data,chunk_index)
|
||||
except Exception as e:
|
||||
country_name = country_data.get("country", "未知")
|
||||
self.log(f"处理国家 {country_name} 失败: {str(e)}", "ERROR")
|
||||
self.log(traceback.format_exc(), "ERROR")
|
||||
|
||||
finally:
|
||||
# 关闭店铺
|
||||
try:
|
||||
if driver:
|
||||
self.log(f"关闭店铺 {shop_name}")
|
||||
driver.close_store()
|
||||
time.sleep(2)
|
||||
except Exception as e:
|
||||
self.log(f"关闭店铺失败: {str(e)}", "WARNING")
|
||||
|
||||
# 从正在执行中的店铺列表中移除
|
||||
if shop_name in runing_shop:
|
||||
del runing_shop[shop_name]
|
||||
self.log(f"店铺 {shop_name} 已从执行列表中移除")
|
||||
|
||||
def process_country(self, driver: AmazoneDriver, country_data: Dict[str, Any],
|
||||
task_id: int, result_id: int, shop_data: Dict[str, Any],chunk_index:int):
|
||||
"""处理单个国家的所有ASIN
|
||||
|
||||
Args:
|
||||
driver: 亚马逊驱动实例
|
||||
country_data: 国家数据
|
||||
task_id: 任务ID
|
||||
result_id: 结果ID
|
||||
shop_data: 店铺数据
|
||||
"""
|
||||
country = country_data.get("country", "未知")
|
||||
items = country_data.get("items", [])
|
||||
|
||||
self.log(f"开始处理国家: {country}，共 {len(items)} 个ASIN")
|
||||
self.update_task_status(task_id, current_country=country)
|
||||
|
||||
# 切换国家，最多重试3次
|
||||
max_retries = 3
|
||||
switch_success = False
|
||||
|
||||
for retry in range(max_retries):
|
||||
try:
|
||||
self.log(f"尝试切换到国家 {country} (第 {retry + 1}/{max_retries} 次)")
|
||||
|
||||
# 如果不是第一次尝试，先刷新页面
|
||||
if retry > 0:
|
||||
self.log("重试前刷新页面...")
|
||||
try:
|
||||
driver.tab.refresh()
|
||||
time.sleep(3)
|
||||
except Exception as e:
|
||||
self.log(f"刷新页面失败: {str(e)}", "WARNING")
|
||||
|
||||
switch_success = driver.SwitchingCountries(country)
|
||||
if switch_success:
|
||||
self.log(f"成功切换到国家 {country}")
|
||||
break
|
||||
else:
|
||||
self.log(f"切换到国家 {country} 失败", "WARNING")
|
||||
|
||||
except Exception as e:
|
||||
self.log(f"切换国家 {country} 异常: {str(e)}", "ERROR")
|
||||
|
||||
# 如果还有重试机会，等待后继续
|
||||
if retry < max_retries - 1:
|
||||
time.sleep(2)
|
||||
|
||||
# 如果切换失败，回传该国家所有ASIN为失败状态
|
||||
if not switch_success:
|
||||
self.log(f"切换到国家 {country} 失败，已重试 {max_retries} 次，将所有ASIN标记为失败", "ERROR")
|
||||
chunk_index = self._report_all_asins_failed(country, items, task_id, shop_data,chunk_index)
|
||||
return chunk_index
|
||||
|
||||
# 切换到库存管理页面
|
||||
try:
|
||||
driver.SwitchPage()
|
||||
self.log(f"已切换到库存管理页面")
|
||||
except Exception as e:
|
||||
self.log(f"切换页面失败: {str(e)}", "ERROR")
|
||||
# 切换页面失败也回传所有ASIN为失败
|
||||
chunk_index = self._report_all_asins_failed(country, items, task_id, shop_data,chunk_index)
|
||||
return chunk_index
|
||||
|
||||
# 处理每个ASIN
|
||||
file_key = shop_data.get("fileKey", "")
|
||||
source_filename = shop_data.get("sourceFilename", "")
|
||||
total_rows = shop_data.get("totalRows", 0)
|
||||
|
||||
for idx, asin_item in enumerate(items, 1):
|
||||
# 检查是否收到暂停请求
|
||||
if task_id in runing_task and runing_task[task_id].get("stop_requested", False):
|
||||
self.log(f"检测到任务 {task_id} 的暂停请求，停止处理", "WARNING")
|
||||
return # 返回到上层，会触发店铺关闭
|
||||
|
||||
try:
|
||||
self.log(f"[{idx}/{len(items)}] 处理ASIN: {asin_item.get('asin', '')}")
|
||||
self.process_asin(driver, asin_item, country, task_id, result_id,
|
||||
file_key, source_filename, total_rows,chunk_index)
|
||||
except Exception as e:
|
||||
asin = asin_item.get("asin", "未知")
|
||||
self.log(f"处理ASIN {asin} 失败: {str(e)}", "ERROR")
|
||||
# 继续处理下一个ASIN
|
||||
chunk_index += 1
|
||||
return chunk_index
|
||||
|
||||
|
||||
def process_asin(self, driver: AmazoneDriver, asin_item: Dict[str, Any],
|
||||
country: str, task_id: int, result_id: int, file_key: str,
|
||||
source_filename: str, total_rows: int,chunk_index:int):
|
||||
"""处理单个ASIN并回传结果
|
||||
|
||||
Args:
|
||||
driver: 亚马逊驱动实例
|
||||
asin_item: ASIN数据项
|
||||
country: 国家名称
|
||||
task_id: 任务ID
|
||||
result_id: 结果ID
|
||||
file_key: 文件KEY
|
||||
source_filename: 源文件名
|
||||
total_rows: 总行数
|
||||
chunk_index: 当前处理索引
|
||||
"""
|
||||
asin = asin_item.get("asin", "")
|
||||
row_index = asin_item.get("rowIndex", 0)
|
||||
|
||||
# 更新当前处理的ASIN
|
||||
self.update_task_status(task_id, current_asin=asin)
|
||||
|
||||
status = "失败"
|
||||
max_retries = 3 # 最多重试3次
|
||||
|
||||
for retry in range(max_retries):
|
||||
try:
|
||||
self.log(f"处理ASIN {asin} (第 {retry + 1}/{max_retries} 次)")
|
||||
|
||||
# 如果不是第一次尝试，先刷新页面
|
||||
if retry > 0:
|
||||
self.log("重试前刷新页面...")
|
||||
try:
|
||||
driver.tab.refresh()
|
||||
time.sleep(3)
|
||||
except Exception as e:
|
||||
self.log(f"刷新页面失败: {str(e)}", "WARNING")
|
||||
|
||||
# 搜索ASIN
|
||||
sku_ls = driver.search(asin=asin)
|
||||
self.log(f"搜索到 {len(sku_ls)} 个SKU")
|
||||
|
||||
if len(sku_ls) == 0:
|
||||
status = "查询不到"
|
||||
self.log(f"ASIN {asin} 未找到商品", "WARNING")
|
||||
break # 查询不到商品，无需重试
|
||||
else:
|
||||
# 删除所有找到的SKU，如果任何一个失败则重新开始整个流程
|
||||
success_count = 0
|
||||
all_success = True # 标记是否所有SKU都删除成功
|
||||
total_sku_count = len(sku_ls)
|
||||
|
||||
for sku in sku_ls:
|
||||
try:
|
||||
suc = driver.del_action(sku)
|
||||
if suc:
|
||||
success_count += 1
|
||||
self.log(f"SKU 删除成功 ({success_count}/{total_sku_count})")
|
||||
else:
|
||||
self.log(f"SKU 删除失败", "WARNING")
|
||||
all_success = False
|
||||
break # 任何一个失败，退出循环，准备重试整个流程
|
||||
except Exception as e:
|
||||
self.log(f"删除SKU异常: {str(e)}", "ERROR")
|
||||
all_success = False
|
||||
break # 发生异常，退出循环，准备重试整个流程
|
||||
|
||||
# 判断删除结果
|
||||
if all_success and success_count == total_sku_count:
|
||||
status = "成功"
|
||||
self.log(f"ASIN {asin} 所有SKU删除成功 ({success_count}/{total_sku_count})")
|
||||
# 更新成功计数
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["success_count"] += 1
|
||||
break # 全部成功，跳出重试循环
|
||||
else:
|
||||
# 有失败的SKU
|
||||
if retry < max_retries - 1:
|
||||
self.log(f"有SKU删除失败，准备重试整个流程... ({retry + 1}/{max_retries})")
|
||||
time.sleep(2)
|
||||
continue # 继续下一次重试
|
||||
else:
|
||||
# 所有重试都用完了
|
||||
if success_count > 0:
|
||||
status = "部分成功"
|
||||
self.log(f"ASIN {asin} 部分SKU删除成功 ({success_count}/{total_sku_count})", "WARNING")
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["success_count"] += 1
|
||||
else:
|
||||
status = "失败"
|
||||
self.log(f"ASIN {asin} 所有SKU删除失败", "ERROR")
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["failed_count"] += 1
|
||||
|
||||
except Exception as e:
|
||||
status = "删除异常"
|
||||
self.log(f"处理ASIN {asin} 异常: {str(e)}", "ERROR")
|
||||
|
||||
# 如果还有重试机会，继续重试
|
||||
if retry < max_retries - 1:
|
||||
self.log(f"发生异常，准备重试... ({retry + 1}/{max_retries})")
|
||||
time.sleep(2)
|
||||
else:
|
||||
# 所有重试都失败了，更新失败计数
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["failed_count"] += 1
|
||||
|
||||
# 更新已处理ASIN计数
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["processed_asins"] += 1
|
||||
|
||||
# 回传结果到API
|
||||
try:
|
||||
payload = {
|
||||
"submissionId": "",
|
||||
"files": [{
|
||||
"fileKey": file_key,
|
||||
"sourceFilename": source_filename,
|
||||
"chunkIndex": chunk_index,
|
||||
"chunkTotal": total_rows,
|
||||
"processedRows": chunk_index,
|
||||
"totalRows": total_rows,
|
||||
"currentCountry": country,
|
||||
"currentAsin": asin,
|
||||
"countries": [{
|
||||
"country": country,
|
||||
"items": [{
|
||||
"asin": asin,
|
||||
"status": status
|
||||
}]
|
||||
}]
|
||||
}]
|
||||
}
|
||||
|
||||
self.post_result(task_id, payload)
|
||||
self.log(f"ASIN {asin} 结果已回传，状态: {status}")
|
||||
|
||||
except Exception as e:
|
||||
self.log(f"回传结果失败: {str(e)}", "ERROR")
|
||||
|
||||
def _report_all_asins_failed(self, country: str, items: List[Dict[str, Any]],
|
||||
task_id: int, shop_data: Dict[str, Any],chunk_index:int):
|
||||
"""将国家下所有ASIN标记为失败并回传
|
||||
|
||||
Args:
|
||||
country: 国家名称
|
||||
items: ASIN列表
|
||||
task_id: 任务ID
|
||||
shop_data: 店铺数据
|
||||
"""
|
||||
self.log(f"开始回传国家 {country} 下的 {len(items)} 个ASIN失败状态")
|
||||
|
||||
file_key = shop_data.get("fileKey", "")
|
||||
source_filename = shop_data.get("sourceFilename", "")
|
||||
total_rows = shop_data.get("totalRows", 0)
|
||||
|
||||
for asin_item in items:
|
||||
asin = asin_item.get("asin", "")
|
||||
|
||||
try:
|
||||
# 更新失败计数
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["failed_count"] += 1
|
||||
runing_task[task_id]["processed_asins"] += 1
|
||||
|
||||
# 回传失败状态
|
||||
payload = {
|
||||
"submissionId": "",
|
||||
"files": [{
|
||||
"fileKey": file_key,
|
||||
"sourceFilename": source_filename,
|
||||
"chunkIndex": chunk_index,
|
||||
"chunkTotal": total_rows,
|
||||
"processedRows": chunk_index,
|
||||
"totalRows": total_rows,
|
||||
"currentCountry": country,
|
||||
"currentAsin": asin,
|
||||
"countries": [{
|
||||
"country": country,
|
||||
"items": [{
|
||||
"asin": asin,
|
||||
"status": "失败"
|
||||
}]
|
||||
}]
|
||||
}]
|
||||
}
|
||||
|
||||
self.post_result(task_id, payload)
|
||||
chunk_index += 1
|
||||
self.log(f"ASIN {asin} 失败状态已回传")
|
||||
|
||||
except Exception as e:
|
||||
self.log(f"回传ASIN {asin} 失败状态时出错: {str(e)}", "ERROR")
|
||||
|
||||
return chunk_index
|
||||
|
||||
def post_result(self, task_id: int, payload: Dict[str, Any]):
|
||||
"""回传结果到API（带重试机制）
|
||||
|
||||
Args:
|
||||
task_id: 任务ID
|
||||
payload: 结果数据
|
||||
"""
|
||||
url = f"{DELETE_BRAND_API_BASE}/api/delete-brand/tasks/{task_id}/result"
|
||||
max_retries = 3 # 最多重试3次
|
||||
|
||||
for retry in range(max_retries):
|
||||
try:
|
||||
self.log(f"尝试回传结果 (第 {retry + 1}/{max_retries} 次)")
|
||||
|
||||
response = requests.post(
|
||||
url,
|
||||
json=payload,
|
||||
headers={"Content-Type": "application/json"},
|
||||
timeout=30,
|
||||
verify=False # 忽略SSL证书验证
|
||||
)
|
||||
print("【结果提交】：",payload)
|
||||
print("【结果提交返回】：",response.text)
|
||||
|
||||
if response.status_code == 200:
|
||||
self.log(f"结果回传成功: {url}")
|
||||
return # 成功后直接返回，不再重试
|
||||
else:
|
||||
self.log(f"结果回传失败，状态码: {response.status_code}", "WARNING")
|
||||
# 如果还有重试机会，继续重试
|
||||
if retry < max_retries - 1:
|
||||
self.log(f"准备重试... ({retry + 1}/{max_retries})")
|
||||
time.sleep(2) # 等待2秒后重试
|
||||
else:
|
||||
self.log(f"已达到最大重试次数，结果回传最终失败", "ERROR")
|
||||
|
||||
except Exception as e:
|
||||
self.log(f"调用API异常: {str(e)}", "ERROR")
|
||||
# 如果还有重试机会，继续重试
|
||||
if retry < max_retries - 1:
|
||||
self.log(f"发生异常，准备重试... ({retry + 1}/{max_retries})")
|
||||
time.sleep(2) # 等待2秒后重试
|
||||
else:
|
||||
self.log(f"已达到最大重试次数，结果回传最终失败", "ERROR")
|
||||
|
||||
def update_task_status(self, task_id: int, **kwargs):
|
||||
"""更新任务状态
|
||||
|
||||
Args:
|
||||
task_id: 任务ID
|
||||
**kwargs: 要更新的字段
|
||||
"""
|
||||
if task_id not in runing_task:
|
||||
runing_task[task_id] = {}
|
||||
|
||||
runing_task[task_id].update(kwargs)
|
||||
self.log(f"线程 {id(task_data)} {TASK_TYPE} 任务处理异常: {traceback.format_exc()}", "ERROR")
|
||||
|
||||
def stop(self):
|
||||
"""停止监控"""
|
||||
|
||||
@@ -1,82 +1,24 @@
|
||||
import time
|
||||
import re
|
||||
import traceback
|
||||
from DrissionPage._pages.chromium_tab import ChromiumTab
|
||||
|
||||
from config import runing_task, runing_shop
|
||||
from config import runing_task, runing_shop,DELETE_BRAND_API_BASE
|
||||
from datetime import datetime
|
||||
from amazon.del_brand import AmamzonBase, kill_process
|
||||
|
||||
from amazon.tool import show_notification,get_shop_info
|
||||
from amazon.amazon_base import AmamzonBase, kill_process,TaskBase
|
||||
from amazon.tool import show_notification
|
||||
import requests
|
||||
|
||||
|
||||
class AmzoneMatchAction(AmamzonBase):
|
||||
mark_name = "匹配价格"
|
||||
|
||||
def SwitchPage(self):
|
||||
"""
|
||||
切换至 管理所有库存页面
|
||||
1、等待 //navigation-favorites-bar[@class="hydrated"] 出现
|
||||
"""
|
||||
navigation = self.tab.ele('xpath://navigation-favorites-bar[@class="hydrated"]')
|
||||
navigation.wait.displayed(raise_err=False)
|
||||
page_btn = navigation.sr('xpath://internal-fav-bar-links[@data-internal="navigation"]').sr(
|
||||
'xpath://a[@data-page-id="ezdpc-gui-inventory-mons"]')
|
||||
page_btn.wait.displayed(raise_err=False)
|
||||
page_btn.click(timeout=5)
|
||||
def __init__(self, user_info: dict, socket_port: int = 19890):
|
||||
super().__init__(user_info,socket_port)
|
||||
self.already_asin = set()
|
||||
|
||||
self.tab.wait.doc_loaded()
|
||||
# 等待搜索框出现
|
||||
search_region = self.tab.ele('xpath://div[@id="searchBoxContainer"]//kat-input-group')
|
||||
search_region.wait.displayed(raise_err=False)
|
||||
|
||||
def search(self,filter_type="ApprovalRequired"):
|
||||
sku_ls = []
|
||||
|
||||
load_ele = self.tab.eles("xpath://div[contains(@class,'Loader-module__loader')]",timeout=5)
|
||||
if len(load_ele) > 0:
|
||||
load_ele[0].wait.deleted(timeout=3, raise_err=False)
|
||||
time.sleep(0.5)
|
||||
|
||||
drop_down = self.tab.ele('xpath://div[contains(@class,"VolusListingStatusDropDown-module__verticalContainer")]//kat-dropdown')
|
||||
drop_down.wait.displayed(raise_err=False)
|
||||
drop_down.wait.enabled(raise_err=False)
|
||||
time.sleep(0.6)
|
||||
drop_down.click()
|
||||
# //kat-option[@value="SearchSuppressed"]
|
||||
xp = f'xpath://kat-option[@value="{filter_type}"]'
|
||||
print(f"【{self.mark_name}】正在寻找筛选条件 {filter_type}，xpath: {xp}")
|
||||
approval_required = self.tab.eles(xp,timeout=5)
|
||||
if len(approval_required) == 0:
|
||||
print(f"【{self.mark_name}】没有需要{filter_type}选项】没有需要{filter_type}的商品了")
|
||||
return sku_ls # "没有需要审批的商品了"
|
||||
else:
|
||||
approval_required = approval_required[0]
|
||||
approval_required.wait.displayed(raise_err=False)
|
||||
approval_required.click()
|
||||
|
||||
approval_required_text = approval_required.text
|
||||
print(f"【{self.mark_name}】已选择筛选条件: {approval_required_text}")
|
||||
|
||||
count = re.findall(r'\d+', approval_required_text)
|
||||
if count:
|
||||
count = int(count[0])
|
||||
print(f"【{self.mark_name}】待审批的商品数量: {count}")
|
||||
if count <= 0:
|
||||
print(f"【{self.mark_name}】没有需要{filter_type}的商品了")
|
||||
return sku_ls #"没有需要审批的商品了"
|
||||
for _ in range(3):
|
||||
# 等待加载完成
|
||||
load_ele = self.tab.eles("xpath://div[contains(@class,'Loader-module__loader')]")
|
||||
if len(load_ele) > 0:
|
||||
load_ele[0].wait.deleted(timeout=3, raise_err=False)
|
||||
time.sleep(0.5)
|
||||
|
||||
sku_ls = self.tab.eles("xpath://div[@data-sku]",timeout=3)
|
||||
if len(sku_ls) > 0:
|
||||
break
|
||||
approval_required.click()
|
||||
return sku_ls
|
||||
def reset_already_asin(self):
|
||||
self.already_asin = set()
|
||||
self.log("already_asin 已重置")
|
||||
|
||||
def wait_loaded(self):
|
||||
# 等待加载完成
|
||||
@@ -89,10 +31,10 @@ class AmzoneMatchAction(AmamzonBase):
|
||||
print(f"【{self.mark_name}】等待加载中消失出错", e)
|
||||
|
||||
def run_page_action(self):
|
||||
print(f"【{self.mark_name}】开始执行")
|
||||
self.log(f"==================={self.mark_name}=======================")
|
||||
self.log("开始执行...")
|
||||
num = 0
|
||||
retry_num = 0
|
||||
already_asin = set()
|
||||
get_page_faild = 0
|
||||
|
||||
while retry_num < 3: # 最多重试3次
|
||||
@@ -110,39 +52,50 @@ class AmzoneMatchAction(AmamzonBase):
|
||||
page_pamel = self.tab.eles('xpath://kat-pagination',timeout=5)
|
||||
if len(page_pamel) > 0:
|
||||
current_page = page_pamel[0].sr('xpath:.//ul[@class="pages"]//li[@aria-current="true"]').text
|
||||
|
||||
# 测试
|
||||
# if current_page > 1:
|
||||
# break
|
||||
# 总页数
|
||||
total_page = page_pamel[0].sr.eles('xpath:.//ul[@class="pages"]//span[@class="page__inner"][last()]')
|
||||
if len(total_page) > 0:
|
||||
total_page = total_page[-1].text
|
||||
else:
|
||||
total_page = 0
|
||||
print(f"【{self.mark_name}】当前页码: {current_page} / 总页数: {total_page}")
|
||||
self.log(f"【{self.mark_name}】当前页码: {current_page} / 总页数: {total_page}")
|
||||
get_page_faild = 0
|
||||
except Exception as e:
|
||||
print(f"【{self.mark_name}】获取页码失败", e)
|
||||
self.log(f"【{self.mark_name}】获取页码失败", e)
|
||||
get_page_faild+= 1
|
||||
if get_page_faild > 2:
|
||||
show_notification(f"【{self.mark_name}】获取页码失败超3次停止任务！")
|
||||
break
|
||||
|
||||
# 保存当前URL，用于失败重试时访问
|
||||
try:
|
||||
self.url = self.tab.url
|
||||
self.log(f"获取当前的链接:{self.url}")
|
||||
except Exception as e:
|
||||
self.url = None
|
||||
self.log(f"获取当前的链接失败:{e}")
|
||||
|
||||
|
||||
sku_ls = self.tab.eles("xpath://div[@data-sku]",timeout=10)
|
||||
print(f"【{self.mark_name}】获取到 {len(sku_ls)}")
|
||||
self.log(f"【{self.mark_name}】获取到 {len(sku_ls)}")
|
||||
# for sku_ele in sku_ls[0:2]:
|
||||
for sku_ele in sku_ls:
|
||||
# solve_problem = sku_ele.eles('xpath:.//kat-link[@label="解决商品信息问题"]')
|
||||
|
||||
asin = sku_ele.ele('xpath:.//div[contains(@class,"JanusSplitBox-module__container")]//div[contains(@class,"JanusSplitBox-module__panel--") and contains(string(.),"ASIN")]/..//div[last()]',timeout=3).text
|
||||
print(f"【{self.mark_name}】ASIN {asin} 找到....")
|
||||
if asin in already_asin:
|
||||
print(f"【{self.mark_name}】{asin} 已经处理过了，跳过")
|
||||
self.log(f"【{self.mark_name}】ASIN {asin} 找到....")
|
||||
if asin in self.already_asin:
|
||||
self.log(f"【{self.mark_name}】{asin} 已经处理过了，跳过")
|
||||
continue
|
||||
|
||||
price_match = sku_ele.eles('xpath:.//div[@data-test-id="FeaturedOfferPrice"]//a[text()="匹配"]',timeout=2)
|
||||
if len(price_match) == 0:
|
||||
print(f"【{self.mark_name}】{asin},没有推荐价格匹配按钮")
|
||||
self.log(f"【{self.mark_name}】{asin},没有推荐价格匹配按钮")
|
||||
yield (asin,"无需处理")
|
||||
already_asin.add(asin)
|
||||
self.already_asin.add(asin)
|
||||
continue
|
||||
try:
|
||||
price_match[0].click()
|
||||
@@ -154,11 +107,11 @@ class AmzoneMatchAction(AmamzonBase):
|
||||
save_all_btn.wait.deleted(timeout=10, raise_err=False)
|
||||
|
||||
yield (asin,"处理完成")
|
||||
already_asin.add(asin)
|
||||
self.already_asin.add(asin)
|
||||
except Exception as e:
|
||||
print(f"{asin} 处理失败", e)
|
||||
yield (asin,"处理失败")
|
||||
already_asin.add(asin)
|
||||
self.already_asin.add(asin)
|
||||
continue
|
||||
|
||||
|
||||
@@ -172,56 +125,21 @@ class AmzoneMatchAction(AmamzonBase):
|
||||
break
|
||||
next_page_btn.click()
|
||||
num += 1
|
||||
print(f"【{self.mark_name}】【程序计算】正在翻页，已翻 {num} 页...")
|
||||
|
||||
already_asin = set()
|
||||
self.log(f"【{self.mark_name}】【程序计算】正在翻页，已翻 {num} 页...")
|
||||
|
||||
except Exception as e:
|
||||
print(f"【{self.mark_name}】处理匹配操作异常", e)
|
||||
self.log(f"【{self.mark_name}】处理匹配操作异常", e)
|
||||
traceback.print_exc()
|
||||
retry_num += 1
|
||||
self.tab.refresh()
|
||||
self.tab.wait.doc_loaded(raise_err=False,timeout=120)
|
||||
|
||||
|
||||
|
||||
class MatchTak:
|
||||
|
||||
country_info = {
|
||||
"DE": "德国",
|
||||
"FR": "法国",
|
||||
"ES": "西班牙",
|
||||
"IT": "意大利",
|
||||
"UK": "英国"
|
||||
}
|
||||
|
||||
|
||||
def __init__(self, user_info: dict = None):
|
||||
"""初始化审批任务处理器
|
||||
|
||||
Args:
|
||||
user_info: 用户信息字典，包含 company, username, password
|
||||
"""
|
||||
self.user_info = user_info or {}
|
||||
self.running = True
|
||||
|
||||
def log(self, message: str, level: str = "INFO"):
|
||||
"""日志输出
|
||||
|
||||
Args:
|
||||
message: 日志消息
|
||||
level: 日志级别
|
||||
"""
|
||||
from datetime import datetime
|
||||
timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
if level == "ERROR":
|
||||
show_notification(message, "error")
|
||||
print(f"[{timestamp}] [MatchTak] [{level}] {message}")
|
||||
|
||||
class MatchTak(TaskBase):
|
||||
task_name = "匹配价格-TASK"
|
||||
|
||||
def process_task(self, task_data: dict):
|
||||
"""处理审批任务主入口
|
||||
|
||||
Args:
|
||||
task_data: 任务数据
|
||||
"""
|
||||
@@ -238,21 +156,12 @@ class MatchTak:
|
||||
# 用于测试
|
||||
limit = data.get("limit",None)
|
||||
|
||||
if not task_id:
|
||||
self.log("任务ID为空，跳过", "WARNING")
|
||||
return
|
||||
|
||||
if not items:
|
||||
self.log("店铺列表为空，跳过", "WARNING")
|
||||
return
|
||||
|
||||
if not country_codes:
|
||||
self.log("国家列表为空，跳过", "WARNING")
|
||||
if not task_id or not items or not country_codes:
|
||||
self.log(f"任务ID为空{task_id}/店铺列表为空{items}/国家列表为空{country_codes}，跳过", "WARNING")
|
||||
return
|
||||
|
||||
self.log(f"开始处理审批任务 {task_id}，共 {len(items)} 个店铺，{len(country_codes)} 个国家")
|
||||
|
||||
from config import runing_task
|
||||
runing_task[task_id] = {
|
||||
"status": "running",
|
||||
"start_time": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
|
||||
@@ -287,7 +196,6 @@ class MatchTak:
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["processed_shops"] += 1
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"处理店铺 {shop_name} 失败: {str(e)}", "ERROR")
|
||||
self.log(traceback.format_exc(), "ERROR")
|
||||
|
||||
@@ -301,97 +209,12 @@ class MatchTak:
|
||||
self.log(f"任务 {task_id} 处理完成！")
|
||||
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"任务处理失败: {traceback.format_exc()}", "ERROR")
|
||||
if task_id:
|
||||
from config import runing_task
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["status"] = "failed"
|
||||
runing_task[task_id]["error"] = str(e)
|
||||
|
||||
def open_shop(self,max_retries,company_name,shop_name,iskill=False):
|
||||
error_info = ""
|
||||
driver = None
|
||||
for retry in range(max_retries):
|
||||
try:
|
||||
self.log(f"尝试打开店铺 {shop_name} (第 {retry + 1}/{max_retries} 次)")
|
||||
|
||||
if iskill:
|
||||
self.log("重试前先杀掉浏览器进程...")
|
||||
kill_process("v6")
|
||||
kill_process("v5")
|
||||
time.sleep(2)
|
||||
|
||||
# 组装用户信息并创建驱动
|
||||
user_info = {
|
||||
**self.user_info,
|
||||
"company": company_name
|
||||
}
|
||||
driver = AmzoneMatchAction(user_info)
|
||||
browser = driver.open_shop(shop_name)
|
||||
|
||||
if browser and browser != "店铺不存在":
|
||||
self.log(f"成功打开店铺 {shop_name}")
|
||||
else:
|
||||
self.log(f"打开店铺失败: {browser}", "WARNING")
|
||||
driver = None
|
||||
continue
|
||||
|
||||
# 判断是否需要登录
|
||||
need_login = driver.need_login()
|
||||
print("【是否需要登录】：", need_login)
|
||||
if need_login:
|
||||
self.log(f"店铺 {shop_name} 需要登录，正在登录...")
|
||||
# 获取店铺凭证
|
||||
response = get_shop_info(shop_name)
|
||||
print("【获取店铺凭证返回】：", response.text)
|
||||
shop_data = response.json()
|
||||
if not shop_data:
|
||||
mes = f"获取店铺凭证失败，响应数据: {shop_data.get('message', '未知错误')}"
|
||||
self.log(mes, "ERROR")
|
||||
show_notification(mes, "ERROR")
|
||||
continue
|
||||
|
||||
password = shop_data["data"]["password"]
|
||||
|
||||
login_success = driver.login(password)
|
||||
if login_success:
|
||||
self.log(f"店铺 {shop_name} 登录成功，正在重新打开店铺...")
|
||||
browser = driver.open_shop(shop_name)
|
||||
if browser and browser != "店铺不存在":
|
||||
self.log(f"成功打开店铺 {shop_name} 登录后")
|
||||
break
|
||||
else:
|
||||
self.log(f"登录后打开店铺失败: {browser}", "WARNING")
|
||||
driver = None
|
||||
else:
|
||||
self.log(f"店铺 {shop_name} 登录失败", "WARNING")
|
||||
driver = None
|
||||
else:
|
||||
break
|
||||
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"打开店铺异常: {traceback.format_exc()}", "INFO")
|
||||
driver = None
|
||||
error_info = str(e)
|
||||
time.sleep(10)
|
||||
|
||||
# 如果还有重试机会，等待后继续
|
||||
if retry < max_retries - 1:
|
||||
time.sleep(3)
|
||||
|
||||
# 检查是否成功打开
|
||||
if not driver or not browser or browser == "店铺不存在":
|
||||
error_msg = f"店铺 {shop_name} 打开失败，已重试 {max_retries} 次，跳过该店铺,{error_info}"
|
||||
self.log(error_msg, "ERROR")
|
||||
# 从执行列表中移除
|
||||
if shop_name in runing_shop:
|
||||
del runing_shop[shop_name]
|
||||
return driver
|
||||
return driver
|
||||
|
||||
# def process_shop(self, shop_item: dict, country_codes: list, task_id: int, risk_listing_filter: str):
|
||||
def process_shop(self, shop_item: dict, country_codes: list, task_id: int, risk_listing_filter: str,
|
||||
user_id=None, stage_index=None, final_stage: bool = True,limit:str=None):
|
||||
"""处理单个店铺
|
||||
@@ -409,7 +232,6 @@ class MatchTak:
|
||||
self.log(f"店铺 {shop_name} 的公司名称为空，跳过", "WARNING")
|
||||
return
|
||||
|
||||
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["current_shop"] = shop_name
|
||||
|
||||
@@ -431,7 +253,7 @@ class MatchTak:
|
||||
break
|
||||
|
||||
# 打开店铺
|
||||
driver = self.open_shop(max_retries=max_retries, company_name=company_name,
|
||||
driver = self.open_shop(cls=AmzoneMatchAction,max_retries=max_retries, company_name=company_name,
|
||||
shop_name=shop_name, iskill=iskill)
|
||||
if driver is None:
|
||||
self.log(f"任务 {task_id} 启动店铺失败，结束任务", "ERROR")
|
||||
@@ -439,18 +261,25 @@ class MatchTak:
|
||||
self.post_result(task_id, shop_name, country_code, "", "", is_done=True)
|
||||
return
|
||||
|
||||
try:
|
||||
self.process_country(driver, country_code, task_id, shop_name,risk_listing_filter,limit)
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"处理国家 {country_code} 失败: {str(e)}", "ERROR")
|
||||
self.log(traceback.format_exc(), "ERROR")
|
||||
if "与页面的连接已断开" in str(e):
|
||||
iskill = True
|
||||
current_url = None
|
||||
for _ in range(max_retries):
|
||||
try:
|
||||
self.process_country(driver, country_code, task_id, shop_name,risk_listing_filter,limit,
|
||||
target_url=current_url)
|
||||
driver.reset_already_asin()
|
||||
driver.close_store()
|
||||
break
|
||||
except Exception as e:
|
||||
self.log(f"处理国家 {country_code} 失败: {str(e)}", "ERROR")
|
||||
self.log(traceback.format_exc(), "ERROR")
|
||||
if "与页面的连接已断开" in str(e):
|
||||
iskill = True
|
||||
current_url = driver.url
|
||||
|
||||
# 更新已处理国家数
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["processed_countries"] += 1
|
||||
|
||||
self.log(f"{task_id}任务处理完成")
|
||||
# 最后回传，标记完成
|
||||
try:
|
||||
@@ -468,81 +297,9 @@ class MatchTak:
|
||||
del runing_shop[shop_name]
|
||||
self.log(f"店铺 {shop_name} 已从执行列表中移除")
|
||||
|
||||
def action_init(self,driver,country_name,shop_name,risk_listing_filter):
|
||||
"""切换到指定国际 -> 页面 -》 筛选好"""
|
||||
max_retries = 5
|
||||
switch_success = False
|
||||
switch_success_pg = False
|
||||
search_success = False
|
||||
sku_ls = []
|
||||
for retry in range(max_retries):
|
||||
try:
|
||||
self.log(f"尝试切换到国家 {country_name} (第 {retry + 1}/{max_retries} 次)")
|
||||
if retry > 2:
|
||||
# 刷新不行就重新打开店铺
|
||||
self.log("重试前重新打开店铺...")
|
||||
try:
|
||||
driver.close_store()
|
||||
time.sleep(3)
|
||||
driver.open_shop(shop_name)
|
||||
except Exception as e:
|
||||
self.log(f"关闭重新打开店铺: {str(e)}", "WARNING")
|
||||
# 如果不是第一次尝试，先刷新页面
|
||||
if retry > 0:
|
||||
self.log("重试前刷新页面...")
|
||||
try:
|
||||
driver.tab.refresh()
|
||||
time.sleep(3)
|
||||
except Exception as e:
|
||||
self.log(f"刷新页面失败: {str(e)}", "WARNING")
|
||||
|
||||
switch_success = driver.SwitchingCountries(country_name)
|
||||
if switch_success:
|
||||
self.log(f"成功切换到国家 {country_name}")
|
||||
|
||||
# 切换到库存管理页面
|
||||
driver.SwitchPage()
|
||||
self.log(f"已切换到库存管理页面")
|
||||
time.sleep(3)
|
||||
switch_success_pg = True
|
||||
|
||||
sku_ls = driver.search(filter_type=risk_listing_filter)
|
||||
search_success = True
|
||||
self.log(f"国家 {country_name} 搜索出 {len(sku_ls)} 商品，开始处理...")
|
||||
break
|
||||
else:
|
||||
self.log(f"切换到国家 {country_name} 失败", "WARNING")
|
||||
|
||||
except Exception as e:
|
||||
import traceback
|
||||
self.log(f"切换国家 {country_name} 异常: {str(e)}", "ERROR")
|
||||
self.log(traceback.format_exc(), "ERROR")
|
||||
|
||||
# 如果还有重试机会，等待后继续
|
||||
if retry < max_retries - 1:
|
||||
time.sleep(2)
|
||||
|
||||
# 如果切换失败，直接返回
|
||||
# if not switch_success or not switch_success_pg or not search_success:
|
||||
# error_message = f"切换到国家({switch_success})/库存页面({switch_success_pg})/搜索筛选到指定选项({search_success}) {country_name} 失败，已重试 {max_retries} 次，跳过该国家"
|
||||
# self.log(error_message, "ERROR")
|
||||
# if task_id in runing_task:
|
||||
# runing_task[task_id]["processed_countries"] += 1
|
||||
return switch_success,switch_success_pg,search_success,sku_ls
|
||||
|
||||
|
||||
|
||||
def process_country(self, driver: AmzoneMatchAction, country_code: str, task_id: int, shop_name: str, risk_listing_filter: str,limit:str=None):
|
||||
def process_country(self, driver, country_code, task_id, shop_name, risk_listing_filter,limit=None,target_url=None):
|
||||
"""处理单个国家的审批任务
|
||||
|
||||
Args:
|
||||
driver: AmzoneApprove驱动实例
|
||||
country_code: 国家代码（如 UK, DE, FR 等）
|
||||
task_id: 任务ID
|
||||
shop_name: 店铺名称
|
||||
risk_listing_filter: 风险商品筛选条件
|
||||
"""
|
||||
from config import runing_task
|
||||
|
||||
# 转换国家代码为中文名称
|
||||
country_name = self.country_info.get(country_code, country_code)
|
||||
@@ -554,91 +311,7 @@ class MatchTak:
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["current_country"] = country_name
|
||||
|
||||
# 切换国家，最多重试3次
|
||||
# max_retries = 3
|
||||
# switch_success = False
|
||||
#
|
||||
# for retry in range(max_retries):
|
||||
# try:
|
||||
# self.log(f"尝试切换到国家 {country_name} (第 {retry + 1}/{max_retries} 次)")
|
||||
# if retry > 1:
|
||||
# # 刷新不行就重新打开店铺
|
||||
# self.log("重试前重新打开店铺...")
|
||||
# try:
|
||||
# driver.close_store()
|
||||
# time.sleep(3)
|
||||
# driver.open_shop(shop_name)
|
||||
# except Exception as e:
|
||||
# self.log(f"关闭重新打开店铺: {str(e)}", "WARNING")
|
||||
#
|
||||
# # 如果不是第一次尝试，先刷新页面
|
||||
# if retry > 0:
|
||||
# self.log("重试前刷新页面...")
|
||||
# try:
|
||||
# driver.tab.refresh()
|
||||
# time.sleep(3)
|
||||
# except Exception as e:
|
||||
# self.log(f"刷新页面失败: {str(e)}", "WARNING")
|
||||
#
|
||||
# switch_success = driver.SwitchingCountries(country_name)
|
||||
# if switch_success:
|
||||
# self.log(f"成功切换到国家 {country_name}")
|
||||
# break
|
||||
# else:
|
||||
# self.log(f"切换到国家 {country_name} 失败", "WARNING")
|
||||
#
|
||||
# except Exception as e:
|
||||
# import traceback
|
||||
# self.log(f"切换国家 {country_name} 异常: {str(e)}", "ERROR")
|
||||
# self.log(traceback.format_exc(), "ERROR")
|
||||
#
|
||||
# # 如果还有重试机会，等待后继续
|
||||
# if retry < max_retries - 1:
|
||||
# time.sleep(2)
|
||||
#
|
||||
# # 如果切换失败，直接返回
|
||||
# if not switch_success:
|
||||
# error_message = f"切换到国家 {country_name} 失败，已重试 {max_retries} 次，跳过该国家"
|
||||
# self.log(error_message, "ERROR")
|
||||
# if task_id in runing_task:
|
||||
# runing_task[task_id]["processed_countries"] += 1
|
||||
# return
|
||||
#
|
||||
# # 切换到库存管理页面
|
||||
# try:
|
||||
# driver.SwitchPage()
|
||||
# self.log(f"已切换到库存管理页面")
|
||||
# except Exception as e:
|
||||
# import traceback
|
||||
# self.log(f"切换页面失败: {str(e)}", "ERROR")
|
||||
# self.log(traceback.format_exc(), "ERROR")
|
||||
# if task_id in runing_task:
|
||||
# runing_task[task_id]["processed_countries"] += 1
|
||||
# return
|
||||
#
|
||||
# # 搜索需要审批的商品，最多重试3次
|
||||
# sku_ls = []
|
||||
# for retry in range(max_retries):
|
||||
# try:
|
||||
# self.log(f"尝试搜索匹配操作商品 (第 {retry + 1}/{max_retries} 次)")
|
||||
# sku_ls = driver.search(filter_type=risk_listing_filter)
|
||||
# break
|
||||
# except Exception as e:
|
||||
# self.log(f"搜索商品异常: {str(e)}", "ERROR")
|
||||
# if retry < max_retries - 1:
|
||||
# try:
|
||||
# driver.tab.refresh()
|
||||
# time.sleep(3)
|
||||
# except Exception as refresh_error:
|
||||
# self.log(f"刷新页面失败: {str(refresh_error)}", "WARNING")
|
||||
#
|
||||
# # 如果没有需要审批的商品，直接返回
|
||||
# if len(sku_ls) == 0:
|
||||
# self.log(f"国家 {country_name} 没有搜索出的商品")
|
||||
# if task_id in runing_task:
|
||||
# runing_task[task_id]["processed_countries"] += 1
|
||||
# return
|
||||
#
|
||||
|
||||
max_retries = 5
|
||||
switch_success, switch_success_pg, search_success, sku_ls = self.action_init(driver, country_name, shop_name,
|
||||
risk_listing_filter)
|
||||
@@ -659,6 +332,12 @@ class MatchTak:
|
||||
|
||||
self.log(f"国家 {country_name} 搜索出 {len(sku_ls)} 商品，开始处理...")
|
||||
|
||||
if target_url is not None: # 从失败的链接继续
|
||||
self.log(f"开始访问:{target_url}")
|
||||
driver.tab.get(url=target_url)
|
||||
driver.tab.wait.doc_loaded(timeout=60, raise_err=False)
|
||||
|
||||
result = []
|
||||
# 处理所有需要审批的商品（通过yield获取结果）
|
||||
for asin, status in driver.run_page_action():
|
||||
# 检查是否收到暂停请求
|
||||
@@ -675,19 +354,22 @@ class MatchTak:
|
||||
|
||||
runing_task[task_id]["failed_count"] += 1
|
||||
|
||||
# 回传结果到API
|
||||
try:
|
||||
self.post_result(task_id, shop_name, country_code, asin, status)
|
||||
except Exception as e:
|
||||
self.log(f"回传结果失败: {str(e)}", "ERROR")
|
||||
result.append({
|
||||
"asin": asin,
|
||||
"status": status,
|
||||
"done": False
|
||||
})
|
||||
|
||||
if len(result) > 20:
|
||||
self.post_result_batch(task_id, shop_name, country_code,result)
|
||||
result = []
|
||||
|
||||
if len(result) > 0:
|
||||
self.post_result_batch(task_id, shop_name, country_code, result)
|
||||
|
||||
self.log(f"国家 {country_name} 处理完成")
|
||||
|
||||
def post_stage_finished(self, task_id: int, user_id, stage_index):
|
||||
import requests
|
||||
from config import DELETE_BRAND_API_BASE
|
||||
|
||||
if user_id in (None, "", 0):
|
||||
raise ValueError("user_id is required for stage completion callback")
|
||||
@@ -733,8 +415,6 @@ class MatchTak:
|
||||
asin: ASIN
|
||||
status: 处理状态
|
||||
"""
|
||||
import requests
|
||||
from config import DELETE_BRAND_API_BASE
|
||||
|
||||
url = f"{DELETE_BRAND_API_BASE}/api/shop-match/tasks/{task_id}/result"
|
||||
|
||||
@@ -790,6 +470,65 @@ class MatchTak:
|
||||
self.log(f"已达到最大重试次数，结果回传最终失败", "ERROR")
|
||||
raise RuntimeError("已达到最大重试次数，结果回传最终失败")
|
||||
|
||||
def post_result_batch(self, task_id: int, shop_name: str, country_code: str, country_data:list,
|
||||
is_done: bool = False):
|
||||
"""回传处理结果到API
|
||||
|
||||
Args:
|
||||
task_id: 任务ID
|
||||
shop_name: 店铺名称
|
||||
country_code: 国家代码
|
||||
asin: ASIN
|
||||
status: 处理状态
|
||||
"""
|
||||
|
||||
url = f"{DELETE_BRAND_API_BASE}/api/shop-match/tasks/{task_id}/result"
|
||||
|
||||
payload = {
|
||||
"shops": [
|
||||
{
|
||||
"error": "",
|
||||
"countries": {
|
||||
country_code: country_data
|
||||
},
|
||||
"shopName": shop_name
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
max_retries = 3
|
||||
for retry in range(max_retries):
|
||||
try:
|
||||
print("================【匹配】=====================")
|
||||
self.log(f"尝试回传结果 (第 {retry + 1}/{max_retries} 次)")
|
||||
self.log(f"回传URL: {url}")
|
||||
self.log(f"回传数据: {payload}")
|
||||
response = requests.post(
|
||||
url,
|
||||
json=payload,
|
||||
headers={"Content-Type": "application/json"},
|
||||
timeout=30,
|
||||
verify=False
|
||||
)
|
||||
self.log(f"回传结果: {response.text}")
|
||||
data = response.json() if response.text else {}
|
||||
if response.status_code == 200 and isinstance(data, dict) and data.get("success"):
|
||||
self.log(f"结果回传成功")
|
||||
return
|
||||
else:
|
||||
self.log(f"结果回传失败，状态码: {response.status_code}", "WARNING")
|
||||
print("=====================================")
|
||||
|
||||
except Exception as e:
|
||||
self.log(f"调用API异常: {str(e)}", "ERROR")
|
||||
print("=====================================")
|
||||
|
||||
# 如果还有重试机会，等待后继续
|
||||
if retry < max_retries - 1:
|
||||
time.sleep(2)
|
||||
|
||||
self.log(f"已达到最大重试次数，结果回传最终失败", "ERROR")
|
||||
raise RuntimeError("已达到最大重试次数，结果回传最终失败")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
File diff suppressed because one or more lines are too long
505
app/amazon/similar_asin.py
Normal file
505
app/amazon/similar_asin.py
Normal file
@@ -0,0 +1,505 @@
|
||||
import json
|
||||
from pathlib import Path
|
||||
import base64
|
||||
import time
|
||||
import re
|
||||
import traceback
|
||||
from datetime import datetime
|
||||
from collections import defaultdict
|
||||
import requests
|
||||
from urllib.parse import quote
|
||||
|
||||
from curl_cffi import requests as requests_frp
|
||||
|
||||
|
||||
|
||||
from amazon.tool import show_notification,get_shop_info,remove_special_characters,split_currency_values
|
||||
from amazon.amazon_base import TaskBase
|
||||
|
||||
from amazon.chrome_base import ChromeAmzoneBase
|
||||
|
||||
from config import runing_task, runing_shop,base_dir,DELETE_BRAND_API_BASE
|
||||
|
||||
|
||||
class ChromeAmzone(ChromeAmzoneBase):
|
||||
mark_name = "亚马逊相似ASIN"
|
||||
|
||||
def wait_load_complete(self):
|
||||
try:
|
||||
for _ in range(3):
|
||||
content_area = self.tab.eles('xpath://div[@class="ap-sbi-aside__main"]', timeout=20)
|
||||
if len(content_area) > 0:
|
||||
pass
|
||||
|
||||
except Exception as e:
|
||||
self.log(f"等待加载完成失败,{e},等待5秒")
|
||||
time.sleep(5)
|
||||
|
||||
def encode_custom(self,input_):
|
||||
if not input_ or not isinstance(input_, str):
|
||||
return ""
|
||||
|
||||
transformed = ""
|
||||
|
||||
# 第一个字符：字符编码 + 字符串长度
|
||||
transformed += chr((ord(input_[0]) + len(input_)) & 0xFFFF)
|
||||
|
||||
# 后续字符：当前字符编码 + 前一个字符编码
|
||||
for i in range(1, len(input_)):
|
||||
current_code = ord(input_[i])
|
||||
prev_code = ord(input_[i - 1])
|
||||
transformed += chr((current_code + prev_code) & 0xFFFF)
|
||||
|
||||
# 对应 JavaScript 的 encodeURIComponent
|
||||
encoded = quote(transformed, safe="-_.!~*'()")
|
||||
|
||||
# 对应 replace(/[!'()*]/g, ...)
|
||||
for ch in ["!", "'", "(", ")", "*"]:
|
||||
encoded = encoded.replace(ch, "%" + format(ord(ch), "x"))
|
||||
return encoded
|
||||
|
||||
def image_to_base64(self,image_source: str) -> str:
|
||||
"""
|
||||
将图片链接（URL 或本地文件路径）转换为 Base64 编码的字符串。
|
||||
"""
|
||||
if image_source.startswith(('http://', 'https://')):
|
||||
response = requests.get(image_source, timeout=10)
|
||||
response.raise_for_status() # 非 2xx 状态码将抛出异常
|
||||
image_data = response.content
|
||||
else:
|
||||
path = Path(image_source)
|
||||
if not path.is_file():
|
||||
raise ValueError(f"本地文件不存在: {image_source}")
|
||||
with open(path, 'rb') as f:
|
||||
image_data = f.read()
|
||||
base64_str = base64.b64encode(image_data).decode('utf-8')
|
||||
return base64_str
|
||||
|
||||
def get_aliprice_data(self,page=1,title="",domain="",category="",imageBase64=""):
|
||||
"""
|
||||
"fishkeeper Quick Aquarium Siphon Pump Gravel Cleaner - 256GPH Adjustable Powerful Fish Tank Vacuum Gravel Cleaning Kit for Aquarium Water Changer, Sand Cleaner, Dirt Removal : Amazon.co.uk: Pet Supplies"
|
||||
标题 :
|
||||
|
||||
"""
|
||||
headers = {
|
||||
"accept": "application/json, text/plain, */*",
|
||||
"accept-language": "zh-CN,zh;q=0.9,en;q=0.8",
|
||||
"browser": "chrome",
|
||||
"cache-control": "no-cache",
|
||||
"channel": "chrome_offline",
|
||||
"content-type": "application/json;charset=UTF-8",
|
||||
"ext-id": "10100",
|
||||
"ext_id": "10100",
|
||||
"origin": "chrome-extension://ephkdklmdkaakeleplfpahjphaokcllh",
|
||||
"platform": "1688",
|
||||
"pragma": "no-cache",
|
||||
"priority": "u=1, i",
|
||||
"sec-fetch-dest": "empty",
|
||||
"sec-fetch-mode": "cors",
|
||||
"sec-fetch-site": "none",
|
||||
"sec-fetch-storage-access": "active",
|
||||
"version": "3.7.4",
|
||||
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/147.0.0.0 Safari/537.36"
|
||||
}
|
||||
cookie = {
|
||||
"e-info": "[{\"e-name\":\"1688\",\"adid\":\"100\",\"version\":\"3.7.4\",\"ext_id\":\"10100\"}]",
|
||||
"language": "chinese",
|
||||
"province_code": "Guangdong",
|
||||
"_ct": "czg",
|
||||
"_e_ct": "czg",
|
||||
"is_reto": "1",
|
||||
"crossborder": "1",
|
||||
"agent": "0",
|
||||
"first_view": "1",
|
||||
"currency": "USD",
|
||||
"is_coo": "1",
|
||||
"plugin": "chrome",
|
||||
"plugin_ext": "100,129",
|
||||
"m-info": "[{\"platform\":\"1688\",\"version\":\"3.7.4\",\"browser\":\"chrome\",\"m\":\"uni\",\"t\":1777902599578}]"
|
||||
}
|
||||
url = "https://api.aliprice.com/index.php/chrome/items/imageAnalysis"
|
||||
itemTitle = f"{title} : {domain}: {category}"
|
||||
|
||||
params = {"page": page, "size": 20, "website": "1688_lite2", "language": "zh-CN", "currency": "USD", "from": "",
|
||||
"itemTitle": itemTitle, "domain": domain }
|
||||
params['sign'] = self.encode_custom(json.dumps(params, ensure_ascii=False))
|
||||
data = {
|
||||
"imageBase64" : imageBase64
|
||||
}
|
||||
response = requests.post(url, headers=headers, params=params, json=data, impersonate="chrome101",
|
||||
cookies=cookie)
|
||||
response.encoding = "utf-8"
|
||||
data = response.json()
|
||||
return data
|
||||
|
||||
def _scrape_data(self):
|
||||
"""
|
||||
抓取商品数据
|
||||
|
||||
Returns:
|
||||
dict: 抓取到的数据
|
||||
"""
|
||||
data = {
|
||||
'image_url': "",
|
||||
'title': "",
|
||||
'category' : '',
|
||||
'success' : True
|
||||
}
|
||||
|
||||
try:
|
||||
# 等待页面加载
|
||||
# time.sleep(3)
|
||||
title_ele = self.tab.ele('xpath://h1[@id="title"]',timeout=30)
|
||||
title = title_ele.text
|
||||
data["title"] = title
|
||||
imge_ele = self.tab.ele('xpath://div[@id="imgTagWrapperId"]//img',timeout=20)
|
||||
image_url = imge_ele.attr("src")
|
||||
data["image_url"] = image_url
|
||||
category = self.tab.eles('xpath://div[@id="wayfinding-breadcrumbs_feature_div"]//span[@class="a-list-item"]//a[@class="a-link-normal a-color-tertiary"]',timeout=20)
|
||||
if len(category) > 0:
|
||||
data["category"] = category[0].text
|
||||
return data
|
||||
|
||||
except Exception as e:
|
||||
print(f"抓取数据时出错: {traceback.format_exc()}")
|
||||
data["success"] = False
|
||||
return data
|
||||
|
||||
def run(self, country, asin,total_page=2):
|
||||
"""
|
||||
运行亚马逊详情采集任务
|
||||
Args:
|
||||
country: 国家名称（如：英国、德国、法国、西班牙、意大利）
|
||||
asin: 亚马逊商品ASIN码
|
||||
Returns:
|
||||
dict: 包含采集到的数据
|
||||
"""
|
||||
try:
|
||||
# 验证国家是否支持
|
||||
if country not in self.country_info:
|
||||
error_msg = f"不支持的国家: {country}，支持的国家有: {list(self.country_info.keys())}"
|
||||
print(error_msg)
|
||||
show_notification(error_msg, "error")
|
||||
return None
|
||||
|
||||
# 获取国家配置
|
||||
country_config = self.country_info[country]
|
||||
zip_code = country_config["zip_code"]
|
||||
mark = country_config.get("mark")
|
||||
|
||||
# 1. 根据国家和ASIN拼接链接
|
||||
base_url = country_config["url"]
|
||||
# 提取域名部分
|
||||
domain = base_url.split("/dp/")[0]
|
||||
# 拼接新的URL
|
||||
product_url = f"{domain}/dp/{asin}"
|
||||
print(f"正在访问: {product_url}")
|
||||
|
||||
# 打开链接
|
||||
self.tab.get(product_url)
|
||||
time.sleep(3) # 等待页面初步加载
|
||||
self.tab.wait.doc_loaded(timeout=30, raise_err=False)
|
||||
|
||||
self.close_init_popup()
|
||||
# 2. 切换国家/设置邮编
|
||||
print(f"正在检查并设置邮编: {zip_code},标识： {mark}")
|
||||
self._set_zip_code(zip_code, mark)
|
||||
|
||||
# self.tab.wait.doc_loaded(timeout=5, raise_err=False)
|
||||
|
||||
# 3. 抓取数据
|
||||
print("正在抓取商品数据...")
|
||||
data = self._scrape_data()
|
||||
|
||||
# 判断是否采集标题出错
|
||||
new_size = "220,220"
|
||||
pattern = r"\._(?:[A-Z]+)?(\d+)_\."
|
||||
replacement = f"._{new_size}_.jpg"
|
||||
# 使用正则替换
|
||||
image_new_url = re.sub(pattern, lambda m: replacement, data["image_url"])
|
||||
|
||||
iamge_base64 = self.image_to_base64(image_new_url)
|
||||
|
||||
similar_data = []
|
||||
# 4、请求获取插件的数据
|
||||
for page_num in range(total_page):
|
||||
resp_data = self.get_aliprice_data(
|
||||
page=page_num,
|
||||
title = data["title"],
|
||||
domain=domain,
|
||||
category=data["category"],
|
||||
imageBase64 = iamge_base64
|
||||
)
|
||||
self.log(f"Aliprice 扩展数据获取:{resp_data}")
|
||||
if len(resp_data.get("data",[])) > 0:
|
||||
for i in resp_data.get("data"):
|
||||
similar_data.append(i)
|
||||
|
||||
data["similar_data"] = similar_data
|
||||
|
||||
# 添加基本信息
|
||||
data['country'] = country
|
||||
data['asin'] = asin
|
||||
data['url'] = product_url
|
||||
data['timestamp'] = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
|
||||
|
||||
print(f"数据抓取完成: {json.dumps(data)}")
|
||||
return data
|
||||
|
||||
except Exception as e:
|
||||
error_msg = f"运行出错: {traceback.format_exc()}"
|
||||
print(error_msg)
|
||||
show_notification(f"采集失败: {str(e)}", "error")
|
||||
return {}
|
||||
|
||||
|
||||
class SimilarAsinTask(TaskBase):
|
||||
mark_name = "相似ASIN采集"
|
||||
|
||||
@staticmethod
|
||||
def group_by_id_prefix(data):
|
||||
"""
|
||||
根据每条数据的 id 字段进行分组：
|
||||
- 如果 id 为 "2_1"，则取 "_" 前面的 "2" 作为分组 key
|
||||
- 如果 id 为 "1"，则分组 key 就是 "1"
|
||||
- 相同 key 的数据归为同一组
|
||||
|
||||
:param data: 原始列表数据
|
||||
:return: 二维列表，按 id 前缀分组
|
||||
"""
|
||||
grouped = defaultdict(list)
|
||||
|
||||
for item in data:
|
||||
item_id = str(item.get("id", ""))
|
||||
group_key = item_id.split("_")[0]
|
||||
grouped[group_key].append(item)
|
||||
|
||||
return list(grouped.values())
|
||||
|
||||
@staticmethod
|
||||
def normalize_groups(data):
|
||||
groups = data.get("groups")
|
||||
if isinstance(groups, list) and len(groups) > 0:
|
||||
return groups
|
||||
|
||||
rows = data.get("rows") or data.get("items") or []
|
||||
if not isinstance(rows, list) or len(rows) == 0:
|
||||
return []
|
||||
|
||||
normalized = []
|
||||
for items in SimilarAsinTask.group_by_id_prefix(rows):
|
||||
first = items[0] if items else {}
|
||||
item_id = str(first.get("id") or first.get("displayId") or "")
|
||||
base_id = item_id.split("_")[0] if item_id else ""
|
||||
normalized.append({
|
||||
"sourceFileKey": first.get("sourceFileKey", ""),
|
||||
"sourceFilename": first.get("sourceFilename", ""),
|
||||
"groupKey": first.get("groupKey") or base_id,
|
||||
"baseId": first.get("baseId") or base_id,
|
||||
"displayId": first.get("displayId") or item_id,
|
||||
"items": items,
|
||||
})
|
||||
return normalized
|
||||
|
||||
def process_task(self, task_data: dict):
|
||||
"""处理审批任务主入口
|
||||
|
||||
Args:
|
||||
task_data: 任务数据
|
||||
"""
|
||||
try:
|
||||
data = task_data.get("data", {})
|
||||
task_id = data.get("taskId")
|
||||
groups = self.normalize_groups(data)
|
||||
|
||||
if not task_id:
|
||||
self.log("任务ID为空，跳过", "WARNING")
|
||||
return
|
||||
|
||||
|
||||
self.log(f"开始处理爬取任务 {task_id}，{len(groups)} 个任务")
|
||||
|
||||
if not groups:
|
||||
self.log("appearance-patent groups/rows is empty, skip", "WARNING")
|
||||
return
|
||||
|
||||
runing_task[task_id] = {
|
||||
"status": "running",
|
||||
"start_time": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
|
||||
"total_shops": 1,
|
||||
"processed_shops": 0,
|
||||
"total_countries": len(groups) ,
|
||||
"processed_countries": 0,
|
||||
"total_asins": 0,
|
||||
"processed_asins": 0,
|
||||
"success_count": 0,
|
||||
"failed_count": 0,
|
||||
"stop_requested": False
|
||||
}
|
||||
|
||||
# 检查是否收到暂停请求
|
||||
if task_id in runing_task and runing_task[task_id].get("stop_requested", False):
|
||||
self.log(f"检测到任务 {task_id} 的暂停请求，停止处理", "WARNING")
|
||||
runing_task[task_id]["status"] = "stopped"
|
||||
return
|
||||
max_retry = 3
|
||||
show_notification(f"开始爬取数据", "info")
|
||||
chrome = ChromeAmzone()
|
||||
try:
|
||||
# 数据整理
|
||||
# new_items = self.group_by_id_prefix(items)
|
||||
result = []
|
||||
for gp_index,gp in enumerate(groups):
|
||||
items = gp.get("items", [])
|
||||
return_data = {}
|
||||
|
||||
for index,value in enumerate(items):
|
||||
|
||||
return_data = {
|
||||
'image_url': "",
|
||||
'title': ""
|
||||
}
|
||||
asin = value.get("asin")
|
||||
country = value.get("country")
|
||||
return_data = None
|
||||
for _ in range(max_retry):
|
||||
try:
|
||||
return_data = chrome.run(country, asin) or {}
|
||||
self.log(f"抓取结果->{return_data}")
|
||||
break
|
||||
except Exception as e:
|
||||
if "与页面的连接已断开" in str(e):
|
||||
chrome = ChromeAmzone()
|
||||
if not isinstance(return_data, dict):
|
||||
return_data = {}
|
||||
if return_data.get("image_url"):
|
||||
break
|
||||
|
||||
group_item = [
|
||||
{
|
||||
"sourceFileKey": i.get("sourceFileKey"),
|
||||
"sourceFilename": i.get("sourceFilename"),
|
||||
"rowToken": i.get("rowToken"),
|
||||
"groupKey": i.get("groupKey"),
|
||||
"id": i.get("id"),
|
||||
"asin": i.get("asin"),
|
||||
"country": i.get("country"),
|
||||
"url": return_data.get("image_url"),
|
||||
"title": return_data.get("title"),
|
||||
}
|
||||
for i in items
|
||||
]
|
||||
# task_id: int, chunkIndex:int,chunkTotal: int, country_code: str, asin: str, status: dict,error:str="",
|
||||
# item_data:dict={},
|
||||
res = {
|
||||
"sourceFileKey": gp.get("sourceFileKey"),
|
||||
"sourceFilename": gp.get("sourceFilename"),
|
||||
"groupKey": gp.get("groupKey"),
|
||||
"baseId": gp.get("baseId"),
|
||||
"displayId": gp.get("displayId"),
|
||||
"items": group_item
|
||||
}
|
||||
print("================")
|
||||
result.append(res)
|
||||
print("================")
|
||||
is_done = gp_index == len(groups)-1
|
||||
if len(result) > 20 or is_done:
|
||||
self.post_result(task_id=task_id,chunkIndex=gp_index+1,chunkTotal=len(groups),
|
||||
asin=asin,item_data=result,is_done=is_done)
|
||||
result = []
|
||||
|
||||
|
||||
if len(result) > 0:
|
||||
is_done = True
|
||||
self.post_result(task_id=task_id, chunkIndex=len(groups), chunkTotal=len(groups),
|
||||
asin=asin, item_data=result, is_done=is_done)
|
||||
|
||||
try:
|
||||
chrome.close()
|
||||
except Exception as e:
|
||||
print("退出浏览器出错",e)
|
||||
# 更新已处理店铺数
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["processed_shops"] += 1
|
||||
except Exception as e:
|
||||
self.log(f"处理店铺 {task_id} 失败: {str(e)}", "ERROR")
|
||||
self.log(traceback.format_exc(), "ERROR")
|
||||
|
||||
# 更新任务状态
|
||||
if task_id in runing_task:
|
||||
if runing_task[task_id].get("stop_requested", False):
|
||||
runing_task[task_id]["status"] = "stopped"
|
||||
self.log(f"任务 {task_id} 已被暂停！")
|
||||
else:
|
||||
runing_task[task_id]["status"] = "completed"
|
||||
self.log(f"任务 {task_id} 处理完成！")
|
||||
|
||||
except Exception as e:
|
||||
self.log(f"任务处理失败: {traceback.format_exc()}", "ERROR")
|
||||
if task_id:
|
||||
if task_id in runing_task:
|
||||
runing_task[task_id]["status"] = "failed"
|
||||
runing_task[task_id]["error"] = str(e)
|
||||
|
||||
def post_result(self, task_id: int, chunkIndex:int,chunkTotal: int, asin: str, error:str="",
|
||||
item_data:dict={},
|
||||
is_done: bool = False):
|
||||
"""回传处理结果到API
|
||||
"""
|
||||
|
||||
url = f"{DELETE_BRAND_API_BASE}/api/appearance-patent/tasks/{task_id}/result"
|
||||
|
||||
payload ={
|
||||
"submissionId": f"{int(time.time())}",
|
||||
"chunkIndex": chunkIndex,
|
||||
"chunkTotal": chunkTotal,
|
||||
"error": error,
|
||||
"groups": item_data,
|
||||
"done": is_done
|
||||
}
|
||||
|
||||
max_retries = 3
|
||||
for retry in range(max_retries):
|
||||
try:
|
||||
request_timeout = 300 if is_done else 30
|
||||
print("================【详情采集】=====================")
|
||||
self.log(f"尝试回传结果 (第 {retry + 1}/{max_retries} 次)")
|
||||
self.log(f"回传URL: {url}")
|
||||
self.log(f"回传数据: {payload}")
|
||||
response = requests.post(
|
||||
url,
|
||||
json=payload,
|
||||
headers={"Content-Type": "application/json"},
|
||||
timeout=request_timeout,
|
||||
verify=False
|
||||
)
|
||||
self.log(f"回传结果: {response.text}")
|
||||
data = response.json() if response.text else {}
|
||||
if response.status_code == 200 and isinstance(data, dict) and data.get("success"):
|
||||
self.log(f"结果回传成功: {asin} - {item_data}")
|
||||
return
|
||||
else:
|
||||
self.log(f"结果回传失败，状态码: {response.status_code}", "WARNING")
|
||||
print("=====================================")
|
||||
|
||||
except Exception as e:
|
||||
self.log(f"调用API异常: {str(e)}", "ERROR")
|
||||
print("=====================================")
|
||||
|
||||
# 如果还有重试机会，等待后继续
|
||||
if retry < max_retries - 1:
|
||||
time.sleep(2)
|
||||
|
||||
self.log(f"已达到最大重试次数，结果回传最终失败", "ERROR")
|
||||
raise RuntimeError("已达到最大重试次数，结果回传最终失败")
|
||||
|
||||
if __name__ == '__main__':
|
||||
spide = ChromeAmzone()
|
||||
|
||||
resp = spide.run(
|
||||
country="英国", asin="B0F79LCB3X", total_page=2
|
||||
)
|
||||
print(resp)
|
||||
|
||||
|
||||
|
||||
53
app/app.py
53
app/app.py
@@ -4,7 +4,9 @@
|
||||
"""
|
||||
import os
|
||||
import secrets
|
||||
from datetime import timedelta
|
||||
import logging
|
||||
from datetime import timedelta, datetime
|
||||
from logging.handlers import RotatingFileHandler
|
||||
|
||||
from flask import Flask
|
||||
from flask_cors import CORS
|
||||
@@ -16,6 +18,52 @@ from blueprints.admin import admin_bp
|
||||
from blueprints.image import image_bp
|
||||
from blueprints.brand import brand_bp
|
||||
from blueprints.communication import communication_bp
|
||||
|
||||
from config import cache_path, debug
|
||||
|
||||
|
||||
def setup_flask_logging(app):
|
||||
"""配置Flask访问日志，输出到独立的日志文件"""
|
||||
|
||||
api_cache_path = os.path.join(cache_path, "api_logs")
|
||||
os.makedirs(api_cache_path, exist_ok=True)
|
||||
|
||||
# 只在非debug模式下配置文件日志
|
||||
if not debug:
|
||||
# 获取当前日期作为日志文件名的一部分
|
||||
today = datetime.now().strftime("%Y_%m_%d")
|
||||
log_file = os.path.join(api_cache_path, f'api_{today}.log')
|
||||
|
||||
# 创建文件处理器，使用RotatingFileHandler避免日志文件过大
|
||||
file_handler = RotatingFileHandler(
|
||||
log_file,
|
||||
maxBytes=10 * 1024 * 1024, # 10MB
|
||||
backupCount=5,
|
||||
encoding='utf-8'
|
||||
)
|
||||
|
||||
# 设置日志格式
|
||||
formatter = logging.Formatter(
|
||||
'[%(asctime)s] %(levelname)s in %(module)s: %(message)s',
|
||||
datefmt='%Y-%m-%d %H:%M:%S'
|
||||
)
|
||||
file_handler.setFormatter(formatter)
|
||||
file_handler.setLevel(logging.INFO)
|
||||
|
||||
# 配置Flask应用日志
|
||||
app.logger.addHandler(file_handler)
|
||||
app.logger.setLevel(logging.INFO)
|
||||
|
||||
# 配置Werkzeug日志（HTTP访问日志）
|
||||
werkzeug_logger = logging.getLogger('werkzeug')
|
||||
werkzeug_logger.addHandler(file_handler)
|
||||
werkzeug_logger.setLevel(logging.INFO)
|
||||
|
||||
print(f"API 日志已配置，输出到: {log_file}")
|
||||
else:
|
||||
print("Debug模式下，API 日志输出到控制台")
|
||||
|
||||
|
||||
def create_app():
|
||||
app = Flask(__name__, template_folder=BASE_DIR, static_folder=BASE_DIR)
|
||||
frontend_origin = os.environ.get('FRONTEND_ORIGIN', '*')
|
||||
@@ -40,6 +88,9 @@ def create_app():
|
||||
app.register_blueprint(brand_bp)
|
||||
app.register_blueprint(communication_bp)
|
||||
|
||||
# 配置Flask访问日志
|
||||
setup_flask_logging(app)
|
||||
|
||||
return app
|
||||
|
||||
|
||||
|
||||
1
app/assets/appearance-patent-Br1dtmol.css
Normal file
1
app/assets/appearance-patent-Br1dtmol.css
Normal file
@@ -0,0 +1 @@
|
||||
.module-page[data-v-6542ed18]{min-height:100vh;background:#1a1a1a}.main-content[data-v-6542ed18]{display:flex;height:calc(100vh - 56px);min-height:calc(100vh - 56px)}.left-panel[data-v-6542ed18]{width:400px;background:#1e1e1e;padding:20px;overflow-y:auto;border-right:1px solid #2a2a2a}.right-panel[data-v-6542ed18]{flex:1;min-width:0;background:#1a1a1a;display:flex;flex-direction:column}.section-title[data-v-6542ed18],.subsection-title[data-v-6542ed18]{font-size:13px;color:#bbb;margin-bottom:10px}.upload-zone[data-v-6542ed18]{border:1px dashed #3a3a3a;border-radius:10px;padding:18px;background:#252525;margin-bottom:18px}.hint[data-v-6542ed18],.loading-msg[data-v-6542ed18],.files[data-v-6542ed18],.muted[data-v-6542ed18]{color:#888;font-size:12px;line-height:1.5}.link[data-v-6542ed18]{color:#6ea8fe;text-decoration:none}.link[data-v-6542ed18]:hover{color:#9fc5ff}.btns[data-v-6542ed18],.run-row[data-v-6542ed18]{display:flex;gap:10px;flex-wrap:wrap}.opt-btn[data-v-6542ed18],.btn-run[data-v-6542ed18],.btn-delete[data-v-6542ed18],.download[data-v-6542ed18]{border:none;cursor:pointer;border-radius:7px}.opt-btn[data-v-6542ed18]{padding:8px 14px;color:#ccc;background:#2a2a2a;border:1px solid #3a3a3a}.btn-run[data-v-6542ed18]{padding:10px 18px;color:#fff;background:#3498db;font-weight:600}.btn-queue[data-v-6542ed18]{background:#27ae60}.btn-run[data-v-6542ed18]:disabled{opacity:.55;cursor:not-allowed}.selected-files[data-v-6542ed18]{margin-top:14px;color:#999;font-size:12px;word-break:break-all}.selected-files span[data-v-6542ed18]{display:block;margin:4px 0}.prompt-card[data-v-6542ed18]{margin-bottom:18px}.prompt-input[data-v-6542ed18]{width:100%;box-sizing:border-box;resize:vertical;min-height:180px;padding:10px 12px;border:1px solid #333;border-radius:8px;background:#202020;color:#d8d8d8;font-size:12px;line-height:1.6;outline:none}.prompt-input[data-v-6542ed18]:focus{border-color:#3498db}.prompt-default-label[data-v-6542ed18]{margin-top:10px;color:#8d8d8d;font-size:12px}.prompt-preview[data-v-6542ed18]{margin-top:10px;padding:12px;border:1px solid #2a2a2a;border-radius:8px;background:#202020;color:#9ea7b3;font-size:12px;line-height:1.6;white-space:pre-wrap}.parse-card[data-v-6542ed18],.queue-payload[data-v-6542ed18]{margin-top:14px;padding:12px;border:1px solid #2a2a2a;border-radius:8px;background:#202020;color:#b8c1cc;font-size:12px}.queue-payload[data-v-6542ed18]{max-height:220px;overflow:auto;color:#8fd3ff;white-space:pre-wrap}.panel-header[data-v-6542ed18]{padding:16px 20px;border-bottom:1px solid #2a2a2a;font-size:15px;font-weight:600;color:#ddd}.task-list-wrap[data-v-6542ed18]{flex:1;padding:16px 20px;overflow:auto}.clean-result-summary[data-v-6542ed18]{display:grid;grid-template-columns:repeat(4,minmax(0,1fr));gap:12px;margin-bottom:16px}.summary-card[data-v-6542ed18]{padding:14px 16px;border:1px solid #2a2a2a;border-radius:8px;background:#1e1e1e}.summary-card strong[data-v-6542ed18]{display:block;margin-top:8px;color:#eaf4ff;font-size:22px}.summary-label[data-v-6542ed18]{color:#8d8d8d;font-size:12px}.result-list-wrap[data-v-6542ed18]{border:1px solid #2a2a2a;border-radius:8px;background:#1e1e1e;min-height:180px;margin:0 0 16px}.result-list-header[data-v-6542ed18]{display:flex;justify-content:space-between;padding:12px 16px;border-bottom:1px solid #2a2a2a;color:#ddd;font-size:14px}.empty-tasks[data-v-6542ed18]{color:#666;font-size:13px;padding:18px;text-align:center}.result-table[data-v-6542ed18]{--el-table-bg-color: #222;--el-table-tr-bg-color: #222;--el-table-header-bg-color: #2a2a2a;--el-table-text-color: #ccc;--el-table-border-color: #333}.task-list[data-v-6542ed18]{list-style:none;margin:0;padding:12px}.task-item[data-v-6542ed18]{display:flex;align-items:flex-start;justify-content:space-between;gap:12px;padding:12px 14px;border:1px solid #2a2a2a;border-radius:8px;margin-bottom:8px;background:#222}.left[data-v-6542ed18]{flex:1;min-width:0}.id[data-v-6542ed18]{color:#e0e0e0;font-size:13px;font-weight:600}.task-right[data-v-6542ed18]{display:flex;gap:8px;align-items:center;flex-wrap:wrap}.status[data-v-6542ed18]{padding:4px 10px;border-radius:6px;font-size:12px}.status.success[data-v-6542ed18]{background:#2ecc712e;color:#2ecc71}.status.failed[data-v-6542ed18]{background:#e74c3c2e;color:#ff6b6b}.status.running[data-v-6542ed18]{background:#3498db2e;color:#3498db}.result-hint[data-v-6542ed18]{margin-top:6px;color:#e0b96d}.download[data-v-6542ed18]{padding:6px 10px;color:#d6ecff;background:#3498db2e}.btn-delete[data-v-6542ed18]{padding:6px 10px;color:#ff8f8f;background:#e74c3c1f}@media(max-width:1100px){.main-content[data-v-6542ed18]{flex-direction:column;height:auto}.left-panel[data-v-6542ed18]{width:100%;border-right:none;border-bottom:1px solid #2a2a2a}.clean-result-summary[data-v-6542ed18]{grid-template-columns:repeat(2,minmax(0,1fr))}}
|
||||
1
app/assets/appearance-patent-D1DgeYhe.css
Normal file
1
app/assets/appearance-patent-D1DgeYhe.css
Normal file
@@ -0,0 +1 @@
|
||||
.module-page[data-v-89575b53]{min-height:100vh;background:#1a1a1a}.main-content[data-v-89575b53]{display:flex;height:calc(100vh - 56px);min-height:calc(100vh - 56px)}.left-panel[data-v-89575b53]{width:400px;background:#1e1e1e;padding:20px;overflow-y:auto;border-right:1px solid #2a2a2a}.right-panel[data-v-89575b53]{flex:1;min-width:0;background:#1a1a1a;display:flex;flex-direction:column}.section-title[data-v-89575b53],.subsection-title[data-v-89575b53]{font-size:13px;color:#bbb;margin-bottom:10px}.upload-zone[data-v-89575b53]{border:1px dashed #3a3a3a;border-radius:10px;padding:18px;background:#252525;margin-bottom:18px}.hint[data-v-89575b53],.loading-msg[data-v-89575b53],.files[data-v-89575b53],.muted[data-v-89575b53]{color:#888;font-size:12px;line-height:1.5}.link[data-v-89575b53]{color:#6ea8fe;text-decoration:none}.link[data-v-89575b53]:hover{color:#9fc5ff}.btns[data-v-89575b53],.run-row[data-v-89575b53]{display:flex;gap:10px;flex-wrap:wrap}.opt-btn[data-v-89575b53],.btn-run[data-v-89575b53],.btn-delete[data-v-89575b53],.download[data-v-89575b53]{border:none;cursor:pointer;border-radius:7px}.opt-btn[data-v-89575b53]{padding:8px 14px;color:#ccc;background:#2a2a2a;border:1px solid #3a3a3a}.btn-run[data-v-89575b53]{padding:10px 18px;color:#fff;background:#3498db;font-weight:600}.btn-queue[data-v-89575b53]{background:#27ae60}.btn-run[data-v-89575b53]:disabled{opacity:.55;cursor:not-allowed}.selected-files[data-v-89575b53]{margin-top:14px;color:#999;font-size:12px;word-break:break-all}.selected-files span[data-v-89575b53]{display:block;margin:4px 0}.prompt-card[data-v-89575b53]{margin-bottom:18px}.prompt-input[data-v-89575b53]{width:100%;box-sizing:border-box;resize:vertical;min-height:180px;padding:10px 12px;border:1px solid #333;border-radius:8px;background:#202020;color:#d8d8d8;font-size:12px;line-height:1.6;outline:none}.prompt-input[data-v-89575b53]:focus{border-color:#3498db}.prompt-default-label[data-v-89575b53]{margin-top:10px;color:#8d8d8d;font-size:12px}.prompt-preview[data-v-89575b53]{margin-top:10px;padding:12px;border:1px solid #2a2a2a;border-radius:8px;background:#202020;color:#9ea7b3;font-size:12px;line-height:1.6;white-space:pre-wrap}.parse-card[data-v-89575b53],.queue-payload[data-v-89575b53]{margin-top:14px;padding:12px;border:1px solid #2a2a2a;border-radius:8px;background:#202020;color:#b8c1cc;font-size:12px}.queue-payload[data-v-89575b53]{max-height:220px;overflow:auto;color:#8fd3ff;white-space:pre-wrap}.panel-header[data-v-89575b53]{padding:16px 20px;border-bottom:1px solid #2a2a2a;font-size:15px;font-weight:600;color:#ddd}.task-list-wrap[data-v-89575b53]{flex:1;padding:16px 20px;overflow:auto}.clean-result-summary[data-v-89575b53]{display:grid;grid-template-columns:repeat(4,minmax(0,1fr));gap:12px;margin-bottom:16px}.summary-card[data-v-89575b53]{padding:14px 16px;border:1px solid #2a2a2a;border-radius:8px;background:#1e1e1e}.summary-card strong[data-v-89575b53]{display:block;margin-top:8px;color:#eaf4ff;font-size:22px}.summary-label[data-v-89575b53]{color:#8d8d8d;font-size:12px}.result-list-wrap[data-v-89575b53]{border:1px solid #2a2a2a;border-radius:8px;background:#1e1e1e;min-height:180px;margin:0 0 16px}.result-list-header[data-v-89575b53]{display:flex;justify-content:space-between;padding:12px 16px;border-bottom:1px solid #2a2a2a;color:#ddd;font-size:14px}.empty-tasks[data-v-89575b53]{color:#666;font-size:13px;padding:18px;text-align:center}.result-table[data-v-89575b53]{--el-table-bg-color: #222;--el-table-tr-bg-color: #222;--el-table-header-bg-color: #2a2a2a;--el-table-text-color: #ccc;--el-table-border-color: #333}.task-list[data-v-89575b53]{list-style:none;margin:0;padding:12px}.task-item[data-v-89575b53]{display:flex;align-items:flex-start;justify-content:space-between;gap:12px;padding:12px 14px;border:1px solid #2a2a2a;border-radius:8px;margin-bottom:8px;background:#222}.left[data-v-89575b53]{flex:1;min-width:0}.id[data-v-89575b53]{color:#e0e0e0;font-size:13px;font-weight:600}.task-right[data-v-89575b53]{display:flex;gap:8px;align-items:center;flex-wrap:wrap}.status[data-v-89575b53]{padding:4px 10px;border-radius:6px;font-size:12px}.status.success[data-v-89575b53]{background:#2ecc712e;color:#2ecc71}.status.failed[data-v-89575b53]{background:#e74c3c2e;color:#ff6b6b}.status.running[data-v-89575b53]{background:#3498db2e;color:#3498db}.result-hint[data-v-89575b53]{margin-top:6px;color:#e0b96d}.download[data-v-89575b53]{padding:6px 10px;color:#d6ecff;background:#3498db2e}.btn-delete[data-v-89575b53]{padding:6px 10px;color:#ff8f8f;background:#e74c3c1f}@media(max-width:1100px){.main-content[data-v-89575b53]{flex-direction:column;height:auto}.left-panel[data-v-89575b53]{width:100%;border-right:none;border-bottom:1px solid #2a2a2a}.clean-result-summary[data-v-89575b53]{grid-template-columns:repeat(2,minmax(0,1fr))}}
|
||||
1
app/assets/delete-brand-BfMLVSQU.css
Normal file
1
app/assets/delete-brand-BfMLVSQU.css
Normal file
File diff suppressed because one or more lines are too long
1
app/assets/patrol-delete-BAzbYtgc.css
Normal file
1
app/assets/patrol-delete-BAzbYtgc.css
Normal file
File diff suppressed because one or more lines are too long
1
app/assets/price-track-Hozgt_em.css
Normal file
1
app/assets/price-track-Hozgt_em.css
Normal file
File diff suppressed because one or more lines are too long
1
app/assets/product-risk-CbX7bwZi.css
Normal file
1
app/assets/product-risk-CbX7bwZi.css
Normal file
File diff suppressed because one or more lines are too long
1
app/assets/query-asin-B4RsOiza.css
Normal file
1
app/assets/query-asin-B4RsOiza.css
Normal file
File diff suppressed because one or more lines are too long
1
app/assets/shop-match-B2HWAgBY.css
Normal file
1
app/assets/shop-match-B2HWAgBY.css
Normal file
File diff suppressed because one or more lines are too long
12
app/main.py
12
app/main.py
@@ -1,6 +1,3 @@
|
||||
"""
|
||||
基于 pywebview 实现的跨平台 UI，需先登录方可使用
|
||||
"""
|
||||
from config import cache_path,debug,version,JAVA_API_BASE,JSON_TASK_QUEUE,runing_task,runing_shop
|
||||
import datetime
|
||||
import json
|
||||
@@ -21,7 +18,8 @@ import requests
|
||||
import subprocess
|
||||
|
||||
from amazon.del_brand import kill_process
|
||||
|
||||
from app import run_app
|
||||
from generate_api import generate
|
||||
|
||||
|
||||
with open("version.txt","w",encoding="utf-8") as file:
|
||||
@@ -31,7 +29,6 @@ print(f"""
|
||||
========================================================
|
||||
版本： {version}
|
||||
========================================================
|
||||
|
||||
""")
|
||||
|
||||
|
||||
@@ -43,7 +40,6 @@ PORT = 5123
|
||||
|
||||
def generate_images(params):
|
||||
"""供前端调用的生成图片接口"""
|
||||
from generate_api import generate
|
||||
return generate(params)
|
||||
|
||||
|
||||
@@ -68,6 +64,7 @@ class WindowAPI:
|
||||
time.sleep(0.5)
|
||||
os._exit(0)
|
||||
|
||||
print("===============程序退出================")
|
||||
# 先销毁窗口，让用户看到立即响应
|
||||
try:
|
||||
self._window.destroy()
|
||||
@@ -368,7 +365,6 @@ class WindowAPI:
|
||||
|
||||
|
||||
def start_flask():
|
||||
from app import run_app
|
||||
run_app(host='127.0.0.1', port=PORT)
|
||||
|
||||
|
||||
@@ -396,10 +392,10 @@ def on_window_closing():
|
||||
time.sleep(0.5)
|
||||
os._exit(0)
|
||||
|
||||
print("=================程序退出=====================")
|
||||
# 立即在后台线程执行清理，不阻塞窗口关闭
|
||||
cleanup_thread = threading.Thread(target=cleanup_and_exit, daemon=True)
|
||||
cleanup_thread.start()
|
||||
|
||||
# 立即返回，让窗口快速关闭，用户不会感觉卡顿
|
||||
return True
|
||||
|
||||
|
||||
Reference in New Issue
Block a user