Files
crawler-plugin/app/amazon/asin_status.py
铭坤 3ca569ed1e 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
2026-05-04 19:15:50 +08:00

563 lines
23 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import time
import traceback
from datetime import datetime
import requests
from amazon.amazon_base import AmamzonBase, kill_process,TaskBase
from amazon.tool import show_notification
from config import runing_task, runing_shop, DELETE_BRAND_API_BASE
class AmzonePStatus(AmamzonBase):
mark_name = "状态查询"
def search_asin(self, asin):
search_region = self.tab.ele('xpath://div[@id="searchBoxContainer"]//kat-input-group')
search_region.wait.displayed(raise_err=False)
time.sleep(0.6)
search_input = self.tab.ele("xpath://kat-input[contains(@class,'SearchBox-module__searchInput')]").sr(
'xpath://span[@class="container"]//input[@part="input"]')
search_input.input(asin, clear=True)
sku_ls = []
for _ in range(3):
search_btn = self.tab.ele("xpath://kat-icon[@name='search']")
search_btn.click()
load_ele = self.tab.ele("xpath://div[contains(@class,'Loader-module__loader')]")
# load_ele.wait.hidden(timeout=3, raise_err=False)
load_ele.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
return sku_ls
def search_asin_action(self, asin: str):
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)
sku_ls = self.search_asin(asin=asin)
print(f"{self.mark_name}{asin} 搜索到 {len(sku_ls)} 个SKU")
def clear_tab(self):
all_tab = self.browser.get_tabs()
close_tab = []
for tab in all_tab:
tab_id = tab if isinstance(tab, str) else tab.tab_id
if self.tab.tab_id == tab_id:
continue
close_tab.append(tab)
print("需要关闭的标签页", close_tab)
print("当前操作的tab_id", self.tab.tab_id)
self.browser.close_tabs(close_tab)
def run_page_action(self, appoint_asin: str = None):
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
try:
print(self.mark_name, "指定asin操作", appoint_asin)
self.search_asin_action(asin=appoint_asin)
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)
# 获取当前页码
try:
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
# 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}")
get_page_faild = 0
except Exception as e:
print("{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
sku_ls = self.tab.eles("xpath://div[@data-sku]", timeout=10)
print(f"{self.mark_name}】获取到 {len(sku_ls)}")
# for sku_ele in sku_ls[0:2]:
if len(sku_ls) == 0:
yield (appoint_asin,"查询不到")
break
for sku_ele in sku_ls:
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")
continue
# 状态
status_ele = sku_ele.eles('xpath:.//div[contains(@class,"Status-module__container")]//kat-label')
if len(status_ele) > 0:
statu = status_ele[0].attr("emphasis")
else:
statu = "未获取到状态"
already_asin.add(asin)
yield (asin,statu)
print(f"{self.mark_name}",(asin,statu))
# 判断是否存在需要翻页的情况
page_pamel = self.tab.eles('xpath://kat-pagination', timeout=5)
if len(page_pamel) == 0:
break
next_page_btn = page_pamel[0].sr('xpath:.//span[@part="pagination-nav-right"]')
class_str = next_page_btn.attr('class')
if "end" in class_str:
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()
except Exception as e:
print(f"{self.mark_name}】处理跟价操作异常", e)
traceback.print_exc()
retry_num += 1
self.tab.refresh()
self.tab.wait.doc_loaded(raise_err=False, timeout=120)
class 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
Args:
task_data: 任务数据
"""
try:
data = task_data.get("data", {})
task_id = data.get("taskId")
items = data.get("items", [])[0]
shop_name = items.get("shop_name")
queryAsins = items.get("queryAsins", [])
user_id = data.get("user_id")
stage_index = data.get("stage_index")
final_stage = bool(data.get("final_stage", True))
# 用于测试
limit = data.get("limit", None)
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")
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(queryAsins),
"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
self.log(f"开始处理店铺: {shop_name}")
show_notification(f"开始处理店铺: {shop_name}", "info")
try:
self.process_shop(items, queryAsins, task_id, user_id, stage_index,
final_stage, limit=limit)
# self.process_shop(shop_item, country_codes, task_id,risk_listing_filter)
# 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")
# 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 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
Args:
shop_item: 店铺信息
country_codes: 国家代码列表
task_id: 任务ID
risk_listing_filter: 风险商品筛选条件
"""
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
if task_id in runing_task:
runing_task[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"店铺 {shop_name} 已添加到执行列表,账号: {company_name},开始时间: {start_time}")
# 店铺打开重试最多3次
max_retries = 3
iskill = False
# 处理每个国家
for value in country_codes:
country_code = value.get("country")
all_asin = value.get("asins")
# 打开店铺
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")
for country_code in country_codes:
self.post_result(task_id, shop_name, country_code, "", "", is_done=True)
return
# 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", "ERROR")
driver.close_store()
break
try:
self.process_country(driver, country_code, task_id, shop_name,all_asin=all_asin )
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
# 更新已处理国家数
if task_id in runing_task:
runing_task[task_id]["processed_countries"] += 1
# 关闭店铺
driver.close_store()
self.log(f"{task_id}任务处理完成")
# 最后回传,标记完成
try:
# self.post_result(task_id, shop_name, country_code, "", "", is_done=True)
if final_stage:
self.post_result(task_id, shop_name, country_code, "", "", is_done=True)
else:
self.post_stage_finished(task_id, user_id, stage_index)
except Exception as e:
self.log(f"回传结果失败: {str(e)}", "ERROR")
# 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: AmzonePStatus, country_code: str, task_id: int, shop_name: str,
all_asin:list,limit: str = 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
"""
# 转换国家代码为中文名称
country_name = self.country_info.get(country_code, country_code)
info_mes = f"开始处理国家: {country_name} ({country_code})"
self.log(info_mes)
show_notification(info_mes, "info")
# 更新当前处理的国家
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:
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
for retry in range(max_retries):
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")
self.log(traceback.format_exc(), "ERROR")
if retry >= max_retries - 1:
if task_id in runing_task:
runing_task[task_id]["processed_countries"] += 1
self.log(f"切换页面失败重试退出", "ERROR")
return
# 处理所有需要审批的商品通过yield获取结果
# 指定 asin
for ap_asin in all_asin:
print(f"{driver.mark_name}】开始处理 ->",ap_asin)
for asin, status in driver.run_page_action(
appoint_asin=ap_asin
):
# 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ASIN", "WARNING")
break
self.log(f"ASIN {asin} 处理结果: {status}")
# 更新任务状态
if task_id in runing_task:
runing_task[task_id]["current_asin"] = asin
runing_task[task_id]["processed_asins"] += 1
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")
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")
if stage_index is None:
raise ValueError("stage_index is required for stage completion callback")
url = f"{DELETE_BRAND_API_BASE}/api/shop-match/tasks/{task_id}/stage-finished"
payload = {"stage_index": stage_index}
params = {"user_id": user_id}
max_retries = 3
for retry in range(max_retries):
try:
self.log(f"Attempting stage completion callback ({retry + 1}/{max_retries})")
response = requests.post(
url,
params=params,
json=payload,
headers={"Content-Type": "application/json"},
timeout=30,
verify=False,
)
self.log(f"Stage completion callback response: {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"Stage completion callback succeeded: task={task_id}, stage={stage_index}")
return
self.log(f"Stage completion callback failed, status={response.status_code}", "WARNING")
except Exception as e:
self.log(f"Stage completion callback exception: {str(e)}", "ERROR")
if retry < max_retries - 1:
time.sleep(2)
raise RuntimeError(f"Stage completion callback failed after retries: task={task_id}, stage={stage_index}")
def post_result(self, task_id: int, shop_name: str, country_code: str, asin: str, status: dict,
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/query-asin/tasks/{task_id}/result"
payload = {
"shops": [
{
"shopName": shop_name,
"countryResults": [
{
"country": country_code,
"items": [
{
"asin": asin,
"status": status
}
]
}
],
"shopDone": is_done,
"submissionId": f"{int(time.time())}"
}
]
}
if is_done:
payload["shops"][0]["success"] = is_done
max_retries = 3
for retry in range(max_retries):
try:
print("================【跟价】=====================")
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: {asin} - {status}")
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__':
# 使用示例
user_info = {
"company": "rongchuang123",
"username": "自动化_Robot",
"password": "#20zsg25"
}
shop_name = "魏振峰"
country = "德国"
kill_process('v6')
driver = AmzonePStatus(user_info)
browser = driver.open_shop(shop_name)
sw_suc = driver.SwitchingCountries(country)
driver.SwitchPage()
risk_listing_filter = "Active"
_shopMallName = "WEIZHENFENG168"
ap_asin = "B0F1N18XFW"
skip_asin = []
for _ in range(3):
try:
sku_ls = driver.search(filter_type=risk_listing_filter)
break
except Exception as e:
print(e)
driver.tab.refresh()
if len(sku_ls) > 0:
print("有数据,开始操作")
for asin, status in driver.run_page_action(
current_shop_name=_shopMallName,
appoint_asin=ap_asin, skip_asin=skip_asin
):
print(f"ASIN {asin} 的处理结果: {status}")
print("已完成操作")