Skip to content

A
amazon_reports
Commit fe4c52b5 authored by 邱阿朋's avatar 邱阿朋
Browse files
Options

多国家

parent 4a31fbe6
Hide whitespace changes
Inline Side-by-side
Showing with 98 additions and 43 deletions
coop.py
View file @ fe4c52b5
......@@ -10,7 +10,7 @@ from DrissionPage import ChromiumPage
from DrissionPage.errors import ElementNotFoundError
from lxml import etree
from helper import helper, excel, file
from helper import helper, excel, file, domain
page = ChromiumPage()
page.set.load_mode.eager()
......@@ -24,6 +24,12 @@ helper.make_dir(download_path)
page.set.download_path(download_path)
def page_get(url):
host = domain.switch_domain(country)
full_url = host + url
page.get(full_url, timeout=3)
def sku_relations():
relations_dict = {}
df = pd.read_excel('relations.xlsx')
......@@ -37,14 +43,14 @@ def sku_relations():
def export_list_read_data():
file_name = "ContraCogsInvoices.xls"
if not os.path.isfile(file_name):
# raise FileNotFoundError(f"{file_name},文件不存在")
page.get("https://vendorcentral.amazon.com/hz/vendor/members/coop?ref_=vc_xx_subNav")
# 全选
page.ele("#select-all").click()
# 点击选项卡
page.ele("#cc-invoice-actions-dropdown").click()
# 点击下载报表
page.ele("#cc-invoice-actions-dropdown_2").click.to_download().wait()
raise FileNotFoundError(f"{file_name},文件不存在")
# page_get("hz/vendor/members/coop?ref_=vc_xx_subNav")
# # 全选
# page.ele("#select-all").click()
# # 点击选项卡
# page.ele("#cc-invoice-actions-dropdown").click()
# # 点击下载报表
# page.ele("#cc-invoice-actions-dropdown_2").click.to_download().wait()
return pd.read_excel(file_name, engine='xlrd')
......@@ -52,7 +58,7 @@ def export_list_read_data():
def get_report_table_html(invoice_id):
while True:
try:
page.get(f"https://vendorcentral.amazon.com/hz/vendor/members/coop?searchText={invoice_id}")
page_get(f"hz/vendor/members/coop?searchText={invoice_id}")
# 点击选项卡
page.ele("#a-autoid-2-announce").click()
# 下载报表
......@@ -69,6 +75,7 @@ def get_report_table_html(invoice_id):
print("元素未找到,刷新网页")
page.refresh()
def export_item_read_data(invoice_id):
file_name = f"coop\\{invoice_id}.xlsx"
if os.path.isfile(file_name):
......@@ -87,7 +94,8 @@ def export_item_read_data(invoice_id):
# 提取 filename 参数
filename = query_params.get('fileName', ['未找到文件名'])[0]
report_file_tmp_dir = f"coop\\{invoice_id}\\{filename}\\"
page.download("https://vendorcentral.amazon.com" + link, report_file_tmp_dir, show_msg=True)
host = domain.switch_domain(country)
page.download(host + link, report_file_tmp_dir, show_msg=True)
report_file = report_file_tmp_dir + "BackupReport.xls"
file.wait_for_downloads(report_file)
......@@ -114,7 +122,6 @@ def export_item_read_data(invoice_id):
def main():
relation_data = sku_relations() # 获取 ASIN 与 SKU 的对应关系数据
coop_list = export_list_read_data() # 获取合作数据列表
coop_list = coop_list[:10]
print(f"共计:{len(coop_list)} 条数据")
i = 0
......@@ -199,6 +206,12 @@ def main():
if __name__ == '__main__':
try:
country = helper.get_input_with_default("国家", "usa")
if country is None:
raise Exception("请选择国家")
main()
except KeyboardInterrupt:
pass
except Exception as e:
print(e)
helper/domain.py 0 → 100644
View file @ fe4c52b5
# coding: utf-8
def switch_domain(country):
domain = "https://vendorcentral.amazon.com/"
if country == "jp":
domain = "https://vendorcentral.amazon.co.jp/"
if country == "uk":
domain = "https://vendorcentral.amazon.co.uk/"
if country == "fr":
domain = "https://vendorcentral.amazon.fr/"
if country == "ca":
domain = "https://vendorcentral.amazon.ca/"
if country == "mx":
domain = "https://vendorcentral.amazon.com.mx/"
return domain
invoices.py
View file @ fe4c52b5
......@@ -10,7 +10,7 @@ from DrissionPage import ChromiumPage
from DrissionPage.errors import ElementNotFoundError
from lxml import etree
from helper import helper, excel, file
from helper import helper, excel, file, domain
page = ChromiumPage()
page.set.load_mode.normal()
......@@ -26,6 +26,12 @@ page.set.download_path(download_path)
warnings.filterwarnings("ignore", category=UserWarning, module="openpyxl")
def page_get(url):
host = domain.switch_domain(country)
full_url = host + url
page.get(full_url, timeout=3)
def export_list_read_data():
new_file_name = 'new_Payments.xlsx'
if os.path.isfile(new_file_name):
......@@ -34,13 +40,13 @@ def export_list_read_data():
file_name = 'Payments.xlsx'
if not os.path.isfile(file_name):
# raise FileNotFoundError(f"{file_name},文件不存在")
raise FileNotFoundError(f"{file_name},文件不存在")
pass
page.get(f"https://vendorcentral.amazon.com/hz/vendor/members/remittance/home", timeout=3)
page.ele("#remittance-home-select-all", timeout=2).click()
page.ele("#remittance-home-export-link", timeout=2).click.to_download()
file.wait_for_downloads(file_name)
# page_get(f"hz/vendor/members/remittance/home")
# page.ele("#remittance-home-select-all", timeout=2).click()
# page.ele("#remittance-home-export-link", timeout=2).click.to_download()
# file.wait_for_downloads(file_name)
all_df = pd.read_excel(file_name, header=None)
......@@ -70,13 +76,13 @@ def export_list_read_data():
def export_details_read_data(invoice_number):
params = {
"invoiceNumber": invoice_number,
"payeeCode": "VECET",
"payeeCode": "E8PFB",
"activeTab": "lineItems",
}
# 将字典转换为 URL 查询参数
query_string = urllib.parse.urlencode(params)
full_url = f"https://vendorcentral.amazon.com/hz/vendor/members/inv-mgmt/invoice-details?" + query_string
page.get(full_url, timeout=3)
full_url = f"hz/vendor/members/inv-mgmt/invoice-details?" + query_string
page_get(full_url)
# 读取详情内容
file_name = f"invoices\\{invoice_number}.csv"
......@@ -108,7 +114,7 @@ def get_po_code(index, po_id) -> dict:
"po_id": po_id
}
page.get(f"https://vendorcentral.amazon.com/po/vendor/members/po-mgmt/order?poId={po_id}", timeout=3)
page_get(f"po/vendor/members/po-mgmt/order?poId={po_id}")
po_table = page.ele("#po-header", timeout=5).html
# 使用 lxml 解析 HTML
......@@ -122,7 +128,7 @@ def get_po_code(index, po_id) -> dict:
if match:
result["payment_terms"] = match.group(1)[:-1] # 去掉%
else:
result["payment_terms"] = None
result["payment_terms"] = 0
return result
......@@ -168,12 +174,12 @@ def price_extract_data(html_content):
def click_get_price_data():
try:
# 获取 Amounts 表格html
page_html = page.ele(".a-box-inner", timeout=5).html
page_html = page.ele(".a-box-inner", timeout=3).html
# 使用 lxml 解析 HTML
tree = etree.HTML(page_html)
# 使用 XPath 查找第三个 span class="a-color-base invoice-property-field"
# 提取第二个 class="a-column a-span4" 下的第三个 class="a-row invoice-property-field-row" 下的 span 的值
price_variance_amount = tree.xpath(
'//span[contains(text(),"Price variance amount (price claim)")]/../../div[@class="a-column a-span6 a-span-last"]/span/text()')
'(//div[@class="a-column a-span4"])[2]//div[@class="a-row invoice-property-field-row"][3]//div[@class="a-column a-span6 a-span-last"]/span/text()')
# 检查内容是否有效
if price_variance_amount and price_variance_amount[0].strip() != "-":
page.ele("#pd", timeout=5).click()
......@@ -221,8 +227,11 @@ def handle_data(detail_datum, vendor, deduction_points):
if detail_datum.get('Shortage quantity', -1) == 0:
is_finished = "是"
# 计算扣除后的金额
amount_after_deduction = amount - (amount * (deduction_points / 100))
amount_after_deduction = amount
if deduction_points > 0:
# 计算扣除后的金额
amount_after_deduction = amount - (amount * (deduction_points / 100))
# 复制原始行数据，避免直接修改
record = detail_datum.copy()
record["IsFinished"] = is_finished
......@@ -235,8 +244,8 @@ def handle_data(detail_datum, vendor, deduction_points):
def main():
list_data = export_list_read_data()
# list_data = list_data[62:]
print(f"共计：{len(list_data)} 订单")
all_normal_pay_data = []
all_price_pay_data = []
i = 0
......@@ -247,8 +256,7 @@ def main():
invoice_number = invoice_number[:8]
# 获取当前订单的Payee和优惠比例
vendor_payment_terms = get_po_code(i, invoice_number)
page.wait(2)
vendor_payment_terms = get_po_code(i, invoice_number)
print(vendor_payment_terms)
vendor = vendor_payment_terms['vendor']
......@@ -256,7 +264,6 @@ def main():
# 下载excel文件并读取数据
detail_data = export_details_read_data(invoice_number)
page.wait(2)
# 获取争议数据
all_price_data = click_get_price_data()
......@@ -297,6 +304,12 @@ def main():
if __name__ == '__main__':
try:
country = helper.get_input_with_default("国家", "usa")
if country is None:
raise Exception("请选择国家")
main()
except KeyboardInterrupt:
pass
except Exception as e:
print(e)
returns.py
View file @ fe4c52b5
......@@ -6,10 +6,9 @@ import pandas as pd
from DrissionPage import ChromiumPage
from DrissionPage.errors import ElementNotFoundError
from helper import helper, excel, file
from helper import helper, excel, file, domain
email = None
password = None
country = None
page = ChromiumPage()
page.set.load_mode.eager()
......@@ -23,6 +22,12 @@ helper.make_dir(download_path)
page.set.download_path(download_path)
def page_get(url):
host = domain.switch_domain(country)
full_url = host + url
page.get(full_url, timeout=3)
def sku_relations():
relations_dict = {}
# 读取ASIN和sku映射关系
......@@ -41,12 +46,12 @@ def sku_relations():
def export_list_read_data():
file_name = "Return_Summary.xls"
if not os.path.isfile(file_name):
# raise FileNotFoundError(f"{file_name},文件不存在")
raise FileNotFoundError(f"{file_name},文件不存在")
# 访问网页
page.get("https://vendorcentral.amazon.com/hz/vendor/members/returns?ref_=vc_xx_subNav", timeout=3)
# 导出退货单
page.ele("#file-download-button").click.to_download()
file.wait_for_downloads(file_name)
# page_get("hz/vendor/members/returns?ref_=vc_xx_subNav")
# # 导出退货单
# page.ele("#file-download-button").click.to_download()
# file.wait_for_downloads(file_name)
return pd.read_excel(file_name, engine='xlrd')
......@@ -57,7 +62,7 @@ def export_item_read_data(return_id):
while True:
try:
# 打开退回详情下载明细
page.get(f"https://vendorcentral.amazon.com/katalmonsapp/vendor/members/returns/{return_id}", timeout=3)
page_get(f"katalmonsapp/vendor/members/returns/{return_id}")
page.ele("#file-download-button").click.to_download(rename=file_name)
file.wait_for_downloads(file_name)
break
......@@ -72,10 +77,11 @@ def export_item_read_data(return_id):
def main():
# 读取sku映射关系
relations_dict = sku_relations()
# 下载并读取list数据
list_data = export_list_read_data()
print(f"共计：{len(list_data)} 订单")
new_list_data = []
i = 0
for _, data in list_data.iterrows():
......@@ -113,6 +119,12 @@ def main():
if __name__ == '__main__':
try:
country = helper.get_input_with_default("国家", "usa")
if country is None:
raise Exception("请选择国家")
main()
except KeyboardInterrupt:
pass
except Exception as e:
print(e)
\ No newline at end of file
print(e)
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment