admin/BIPAuto
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(logging): Add optional logging support throughout codebase

Browse Source 
Add centralized logging utility and optional logger parameters to all
core functions for better observability and debugging capabilities.

New modules:
- utils/logging.py: Centralized logger configuration with console
  and optional file handlers

Enhanced features:
- Added optional logger parameter to all extractor_core functions
- Added logger support to extractor, excel_converter, and auth modules
- Functions remain silent when logger=None (backward compatible)
- Improved environment variable validation in test files

Documentation:
- Added discrete_material_plan_extractor_core.md with complete API
  reference and usage patterns

Benefits:
- Consistent logging format across all components
- Optional debug output for troubleshooting
- No breaking changes - fully backward compatible
- Better error messages and validation

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Misaka_Company
2026-03-27 16:08:21 +08:00
parent c3bbc919a5
commit e7bbbbc194
10 changed files with 790 additions and 138 deletions
Download Patch File Download Diff File Expand all files Collapse all files

147
utils/discrete_material_plan/excel_converter.py
View File

@@ -1,139 +1,150 @@
"""
Excel 报表数据转换工具组件
将 Excel 报表数据转换为数据库记录形式
Excel Report Data Conversion Utility
Converts Excel report data to database record format
"""
import pandas as pd
import openpyxl
from typing import List, Dict, Optional
import os
import logging
from utils.logging import get_logger
class ExcelConverter:
"""Excel 报表数据转换器"""
"""Excel Report Data Converter"""
# 字段名称映射（解决字段名冲突）
FIELD_NAME_MAPPING = {"计划数量": "产品计划数量", "单位": "产品单位"}
# Field name mapping (resolves field name conflicts)
FIELD_NAME_MAPPING = {"计划数量": "Product planned quantity", "单位": "Product unit"}
def __init__(self, verbose: bool = True):
def __init__(self, verbose: bool = True, logger: Optional[logging.Logger] = None):
"""
初始化转换器
Initialize the converter
Args:
verbose: 是否打印详细日志
verbose: Whether to print detailed logs (default: True). Deprecated, use logger instead.
logger: Optional logging.Logger instance. If None and verbose=True, creates default logger.
"""
self.verbose = verbose
# Create default logger if needed
if logger is None and verbose:
self.logger = get_logger('bipauto.converter')
elif logger is None:
# Silent mode - create a logger but disable output
silent_logger = logging.getLogger('bipauto.converter.silent')
silent_logger.setLevel(logging.CRITICAL + 1) # Higher than critical, never logs
self.logger = silent_logger
else:
self.logger = logger
def _print(self, *args, **kwargs):
"""打印日志（如果 verbose=True）"""
if self.verbose:
print(*args, **kwargs)
def convert(self, input_file: str, output_file: str = None) -> pd.DataFrame:
def convert(self, input_file: str, output_file: Optional[str] = None) -> pd.DataFrame:
"""
转换 Excel 文件
Convert Excel file
Args:
input_file: 输入文件路径
output_file: 输出文件路径（可选，不指定则不保存）
input_file: Input file path
output_file: Output file path (optional, not saved if not specified)
Returns:
转换后的 DataFrame
Converted DataFrame
"""
# 处理输出文件名
# Handle output file
if output_file:
output_file = self._handle_output_file(output_file)
# 读取工作表
# Read worksheet
wb = openpyxl.load_workbook(input_file)
ws = wb.active
# 解析订单数据
# Parse order data
orders = self._parse_sheet(ws)
# 转换为 DataFrame
# Convert to DataFrame
df = self._convert_to_dataframe(orders)
if not df.empty:
# 保存文件
# Save file
if output_file:
df.to_excel(output_file, index=False)
# 打印汇总报告
self._print("=" * 60)
self._print("转换完成")
self._print("=" * 60)
self._print(f"订单数: {len(orders)}")
self._print(f"数据行数: {len(df)}")
self._print(f"输出文件: {output_file if output_file else 'N/A'}")
self._print("=" * 60)
# Print summary report (using logger)
self.logger.info("=" * 60)
self.logger.info("Conversion complete")
self.logger.info("=" * 60)
self.logger.info(f"Order count: {len(orders)}")
self.logger.info(f"Data row count: {len(df)}")
self.logger.info(f"Output file: {output_file if output_file else 'N/A'}")
self.logger.info("=" * 60)
return df
def _handle_output_file(self, output_file: str) -> str:
"""
处理输出文件，如果文件存在则尝试删除
Handle output file, attempt to delete if it exists
Args:
output_file: 输出文件路径
output_file: Output file path
Returns:
实际使用的输出文件路径
Actual output file path used
"""
if os.path.exists(output_file):
try:
os.remove(output_file)
except PermissionError:
self._print(f"警告: 无法删除 {output_file}，可能文件被其他程序打开")
# 修改文件名
self.logger.warning(
f"Warning: Could not delete {output_file}, file may be open by another program"
)
# Modify filename
base, ext = os.path.splitext(output_file)
output_file = f"{base}_new{ext}"
return output_file
def _parse_sheet(self, ws) -> List[Dict]:
"""
解析一个工作表，返回所有订单的数据
Parse a worksheet and return data for all orders
每个订单包含:
- order_info: 订单头信息（包括页脚）
- materials: 物料数据列表
Each order contains:
- order_info: Order header information (including footer)
- materials: List of material data
Args:
ws: openpyxl 工作表对象
ws: openpyxl worksheet object
Returns:
订单列表
Order list
"""
orders = []
all_rows = list(ws.iter_rows(values_only=True))
# 逐行扫描，按订单结构解析
# Scan row by row, parse by order structure
i = 0
while i < len(all_rows):
row = all_rows[i]
# 检查是否是订单标题行
# Check if this is the order title row
if row and "离散备料计划" in str(row[0]):
# 解析订单头信息（接下来的4行）
# Parse order header information (next 4 rows)
order_info = {}
for j in range(1, 5):
if i + j < len(all_rows) and all_rows[i + j]:
self._parse_header_row(all_rows[i + j], order_info)
# 跳过空行，找到表格标题行
# Skip empty rows, find table header row
table_row = i + 5
while table_row < len(all_rows) and (
not all_rows[table_row] or not all_rows[table_row][0]
):
table_row += 1
# 检查是否是表格标题行
# Check if this is the table header row
if (
table_row < len(all_rows)
and all_rows[table_row]
and all_rows[table_row][0] == "序号"
):
# 检查表头下一行是否为空，判断是否存在数据
# Check if the row below the header is empty to determine if data exists
next_row = table_row + 1
is_empty_row = (
next_row < len(all_rows)
@@ -145,7 +156,7 @@ class ExcelConverter:
)
if is_empty_row:
# 没有数据，查找页脚信息
# No data, find footer information
materials = []
footer_info = {}
data_row = next_row + 1
@@ -172,18 +183,18 @@ class ExcelConverter:
}
)
else:
# 有数据，开始提取物料
# Has data, start extracting materials
materials = []
footer_info = {} # 页脚信息
footer_info = {} # Footer information
data_row = table_row + 1
while data_row < len(all_rows) and all_rows[data_row]:
# 检查是否是页脚信息（制单人、打印人）
# Check if this is footer information (creator, printer)
if all_rows[data_row + 1][0] and "制单人" in str(
all_rows[data_row + 1][0]
):
# 解析页脚信息
# Parse footer information
self._parse_header_row(all_rows[data_row], footer_info)
# 检查下一行是否也是页脚信息
# Check if the next row is also footer information
if (
data_row + 1 < len(all_rows)
and all_rows[data_row + 1]
@@ -193,7 +204,7 @@ class ExcelConverter:
)
break
# 提取物料数据
# Extract material data
material_row = all_rows[data_row]
material = {
"序号": material_row[0],
@@ -227,45 +238,45 @@ class ExcelConverter:
def _parse_header_row(self, row: tuple, info: Dict):
"""
解析订单头信息的一行（字段名和值交错排列）
Parse a row of order header information (field names and values interleaved)
Args:
row: 行数据
info: 存储解析结果的字典
row: Row data
info: Dictionary to store parsing results
"""
i = 0
while i < len(row):
cell = row[i]
if cell and str(cell).strip() and "：" in str(cell):
# 找到字段名
field_name = str(cell).replace("：", "").strip()
# Find field name
field_name = str(cell).replace(":", "").strip()
# 应用字段名映射
# Apply field name mapping
if field_name in self.FIELD_NAME_MAPPING:
field_name = self.FIELD_NAME_MAPPING[field_name]
# 跳过空单元格，找到第一个非字段名的值
# Skip empty cells, find the first non-field-name value
j = i + 1
while j < len(row) and (
not row[j] or not str(row[j]).strip() or "：" in str(row[j])
not row[j] or not str(row[j]).strip() or ":" in str(row[j])
):
j += 1
if j < len(row) and row[j] and not "：" in str(row[j]):
if j < len(row) and row[j] and ":" not in str(row[j]):
info[field_name] = str(row[j]).strip()
# 跳过已处理的值，继续找下一个字段名
# Skip processed value, continue to find next field name
i = j + 1
else:
i += 1
def _convert_to_dataframe(self, orders: List[Dict]) -> pd.DataFrame:
"""
将订单数据转换为扁平化的 DataFrame
Convert order data to a flattened DataFrame
Args:
orders: 订单列表
orders: Order list
Returns:
扁平化的 DataFrame
Flattened DataFrame
"""
all_records = []

124
utils/discrete_material_plan/extractor.py
View File

@@ -9,7 +9,9 @@ Caller is responsible for browser/session lifecycle management.
import pandas as pd
from pathlib import Path
from typing import List, Optional, Tuple
from playwright.sync_api import Page, Frame
from playwright.sync_api import Page, Frame, FrameLocator
import logging
from utils.logging import get_logger
def chunk_order_ids(order_ids: List[str], batch_size: int) -> List[List[str]]:
@@ -51,11 +53,12 @@ def get_login_url(base_url: str) -> str:
def extract_batch(
work_frame: Frame,
work_frame: FrameLocator,
page: Page,
order_ids: List[str],
batch_index: int,
download_dir: str,
logger: Optional[logging.Logger] = None,
) -> str:
"""
Execute download workflow for a single batch of order IDs.
@@ -69,6 +72,7 @@ def extract_batch(
order_ids: List of order IDs for this batch
batch_index: Zero-based batch index for naming the output file
download_dir: Directory path to save the downloaded file
logger: Optional logger for debug output (silent if None)
Returns:
Full path to the downloaded Excel file
@@ -81,15 +85,17 @@ def extract_batch(
order_ids=order_ids,
batch_index=batch_index,
download_dir=download_dir,
logger=logger,
)
def extract_batches(
work_frame: Frame,
work_frame: FrameLocator,
page: Page,
order_ids: List[str],
download_dir: str,
batch_size: int = 10,
logger: Optional[logging.Logger] = None,
) -> List[str]:
"""
Download data for multiple batches of order IDs.
@@ -105,6 +111,7 @@ def extract_batches(
order_ids: List of order IDs to download
download_dir: Directory path to save downloaded files
batch_size: Maximum number of order IDs per batch
logger: Optional logger for debug output (silent if None)
Returns:
List of paths to downloaded Excel files
@@ -124,7 +131,7 @@ def extract_batches(
chunks = chunk_order_ids(order_ids, batch_size)
# Setup query interface once
setup_query_interface(work_frame)
setup_query_interface(work_frame, logger)
# Process each batch
for batch_index, batch in enumerate(chunks):
@@ -134,6 +141,7 @@ def extract_batches(
order_ids=batch,
batch_index=batch_index,
download_dir=download_dir,
logger=logger,
)
downloaded_files.append(file_path)
@@ -145,6 +153,7 @@ def post_process_downloads(
output_file: str,
verbose: bool = True,
cleanup_temp_files: bool = True,
logger: Optional[logging.Logger] = None,
) -> Tuple[str, pd.DataFrame]:
"""
Convert and merge downloaded Excel files into structured DataFrame.
@@ -154,8 +163,9 @@ def post_process_downloads(
Args:
downloaded_files: List of paths to downloaded Excel files
output_file: Path to save merged Excel result
verbose: Whether to print progress messages
verbose: Whether to print progress messages (deprecated, use logger instead)
cleanup_temp_files: Whether to delete temporary downloaded files after processing (default: True)
logger: Optional logger for progress output. If None and verbose=True, creates default logger.
Returns:
Tuple of (output_file_path, merged_dataframe)
@@ -170,13 +180,26 @@ def post_process_downloads(
"""
from .excel_converter import ExcelConverter
converter = ExcelConverter(verbose=verbose)
# Create default logger if needed
if logger is None and verbose:
logger = logging.getLogger('bipauto.extractor.post_process')
logger.setLevel(logging.INFO)
if not logger.handlers:
handler = logging.StreamHandler()
handler.setFormatter(logging.Formatter("[%(levelname)s] %(name)s: %(message)s"))
logger.addHandler(handler)
logger.propagate = False
elif logger is None:
# Silent mode
logger = logging.getLogger('bipauto.extractor.post_process.silent')
logger.setLevel(logging.CRITICAL + 1)
converter = ExcelConverter(verbose=verbose, logger=logger)
all_dfs = []
# Convert each file
for i, file_path in enumerate(downloaded_files):
if verbose:
print(f"Converting file {i + 1}/{len(downloaded_files)}: {file_path}")
logger.info(f"Converting file {i + 1}/{len(downloaded_files)}: {file_path}")
# Convert (do not save intermediate result)
df = converter.convert(input_file=file_path)
@@ -193,43 +216,55 @@ def post_process_downloads(
output_path.parent.mkdir(parents=True, exist_ok=True)
merged_df.to_excel(output_path, index=False)
if verbose:
print(f"Merged result saved to: {output_path}")
print(f"Total rows: {len(merged_df)}")
logger.info(f"Merged result saved to: {output_path}")
logger.info(f"Total rows: {len(merged_df)}")
# Cleanup temporary downloaded files
if cleanup_temp_files:
_cleanup_temp_files(downloaded_files, verbose)
_cleanup_temp_files(downloaded_files, logger=logger)
return str(output_path), merged_df
def _cleanup_temp_files(downloaded_files: List[str], verbose: bool = True) -> int:
def _cleanup_temp_files(downloaded_files: List[str], logger: Optional[logging.Logger] = None, verbose: bool = True) -> int:
"""
Remove temporary downloaded files.
Args:
downloaded_files: List of file paths to delete
verbose: Whether to print progress messages
logger: Optional logger for progress output. If None and verbose=True, creates default logger.
verbose: Whether to print progress messages (deprecated, use logger instead)
Returns:
Number of files successfully deleted
"""
# Create default logger if needed
if logger is None and verbose:
logger = logging.getLogger('bipauto.extractor.cleanup')
logger.setLevel(logging.INFO)
if not logger.handlers:
handler = logging.StreamHandler()
handler.setFormatter(logging.Formatter("[%(levelname)s] %(name)s: %(message)s"))
logger.addHandler(handler)
logger.propagate = False
elif logger is None:
# Silent mode
logger = logging.getLogger('bipauto.extractor.cleanup.silent')
logger.setLevel(logging.CRITICAL + 1)
deleted_count = 0
for file_path in downloaded_files:
try:
Path(file_path).unlink()
deleted_count += 1
if verbose:
print(f"Deleted temp file: {file_path}")
logger.debug(f"Deleted temp file: {file_path}")
except Exception as e:
if verbose:
print(f"Warning: Could not delete {file_path}: {e}")
logger.warning(f"Warning: Could not delete {file_path}: {e}")
return deleted_count
def extract_and_post_process(
work_frame: Frame,
work_frame: FrameLocator,
page: Page,
order_ids: List[str],
download_dir: str,
@@ -237,6 +272,7 @@ def extract_and_post_process(
batch_size: int = 10,
verbose: bool = True,
cleanup_temp_files: bool = True,
logger: Optional[logging.Logger] = None,
) -> Tuple[str, pd.DataFrame]:
"""
Complete extraction workflow: download batches + post-process to merged Excel.
@@ -251,8 +287,9 @@ def extract_and_post_process(
download_dir: Directory for temporary batch files
output_file: Path for final merged Excel output
batch_size: Maximum order IDs per batch
verbose: Whether to print progress messages
verbose: Whether to print progress messages (deprecated, use logger instead)
cleanup_temp_files: Whether to delete temporary downloaded files after processing (default: True)
logger: Optional logger for debug output. If None and verbose=True, creates default logger.
Returns:
Tuple of (output_file_path, merged_dataframe)
@@ -268,9 +305,22 @@ def extract_and_post_process(
>>> context.close()
>>> browser.close()
"""
# Create default logger if needed
if logger is None and verbose:
logger = logging.getLogger('bipauto.extractor')
logger.setLevel(logging.INFO)
if not logger.handlers:
handler = logging.StreamHandler()
handler.setFormatter(logging.Formatter("[%(levelname)s] %(name)s: %(message)s"))
logger.addHandler(handler)
logger.propagate = False
elif logger is None:
# Silent mode
logger = logging.getLogger('bipauto.extractor.silent')
logger.setLevel(logging.CRITICAL + 1)
# Step 1: Download all batches
if verbose:
print(f"Downloading {len(order_ids)} orders in batches of {batch_size}...")
logger.info(f"Downloading {len(order_ids)} orders in batches of {batch_size}...")
downloaded_files = extract_batches(
work_frame=work_frame,
@@ -278,10 +328,10 @@ def extract_and_post_process(
order_ids=order_ids,
download_dir=download_dir,
batch_size=batch_size,
logger=logger,
)
if verbose:
print(f"Downloaded {len(downloaded_files)} batch file(s)")
logger.info(f"Downloaded {len(downloaded_files)} batch file(s)")
# Step 2: Post-process (convert + merge)
output_path, merged_df = post_process_downloads(
@@ -289,6 +339,7 @@ def extract_and_post_process(
output_file=output_file,
verbose=verbose,
cleanup_temp_files=cleanup_temp_files,
logger=logger,
)
return output_path, merged_df
@@ -321,13 +372,14 @@ def read_order_ids_from_file(id_file: str, encoding: str = "utf-8") -> List[str]
def extract_from_file(
id_file: str,
work_frame: Frame,
work_frame: FrameLocator,
page: Page,
download_dir: str,
output_file: str,
batch_size: int = 10,
verbose: bool = True,
cleanup_temp_files: bool = True,
logger: Optional[logging.Logger] = None,
) -> Tuple[str, pd.DataFrame]:
"""
Extract data from order IDs in a file and post-process to merged Excel.
@@ -341,8 +393,9 @@ def extract_from_file(
download_dir: Directory for temporary batch files
output_file: Path for final merged Excel output
batch_size: Maximum order IDs per batch
verbose: Whether to print progress messages
verbose: Whether to print progress messages (deprecated, use logger instead)
cleanup_temp_files: Whether to delete temporary downloaded files after processing (default: True)
logger: Optional logger for debug output. If None and verbose=True, creates default logger.
Returns:
Tuple of (output_file_path, merged_dataframe)
@@ -358,8 +411,22 @@ def extract_from_file(
"""
order_ids = read_order_ids_from_file(id_file)
if verbose:
print(f"Loaded {len(order_ids)} order IDs from {id_file}")
# Create default logger if needed (for this function's own logging)
func_logger = logger
if func_logger is None and verbose:
func_logger = logging.getLogger('bipauto.extractor.file')
func_logger.setLevel(logging.INFO)
if not func_logger.handlers:
handler = logging.StreamHandler()
handler.setFormatter(logging.Formatter("[%(levelname)s] %(name)s: %(message)s"))
func_logger.addHandler(handler)
func_logger.propagate = False
elif func_logger is None:
# Silent mode
func_logger = logging.getLogger('bipauto.extractor.file.silent')
func_logger.setLevel(logging.CRITICAL + 1)
func_logger.info(f"Loaded {len(order_ids)} order IDs from {id_file}")
return extract_and_post_process(
work_frame=work_frame,
@@ -370,4 +437,5 @@ def extract_from_file(
batch_size=batch_size,
verbose=verbose,
cleanup_temp_files=cleanup_temp_files,
logger=logger,
)

49
utils/discrete_material_plan/extractor_core.py
View File

@@ -6,17 +6,19 @@ All functions are stateless and accept required parameters explicitly.
import re
import os
from typing import List
from playwright.sync_api import Page, Frame, TimeoutError
import logging
from typing import List, Optional
from playwright.sync_api import Page, Frame, FrameLocator, TimeoutError
def navigate_to_discrete_material_page(main_frame: Frame, page: Page) -> tuple[Frame, Page]:
def navigate_to_discrete_material_page(main_frame: FrameLocator, page: Page, logger: Optional[logging.Logger] = None) -> tuple[FrameLocator, Page]:
"""
Navigate to the discrete material plan maintenance page.
Args:
main_frame: The main forwardFrame iframe
main_frame: The main forwardFrame iframe (FrameLocator)
page: The Playwright page object
logger: Optional logger for debug output (silent if None)
Returns:
tuple: (work_frame, page1) - The work iframe and the new popup page
@@ -35,16 +37,20 @@ def navigate_to_discrete_material_page(main_frame: Frame, page: Page) -> tuple[F
inner_frame_locator = f_frame.locator("#mainiframe")
inner_frame_locator.wait_for(state="visible", timeout=15000)
work_frame = inner_frame_locator.content_frame
if logger:
logger.debug("Navigated to discrete material plan page")
return work_frame, page1
def setup_query_interface(work_frame: Frame) -> None:
def setup_query_interface(work_frame: FrameLocator, logger: Optional[logging.Logger] = None) -> None:
"""
Initialize the query interface by selecting order number query tab.
Args:
work_frame: The inner work iframe containing the query interface
logger: Optional logger for debug output (silent if None)
"""
# Open search panel
work_frame.locator(".search-name-wrapper > .iconfont").click()
@@ -59,15 +65,19 @@ def setup_query_interface(work_frame: Frame) -> None:
input_box = work_frame.locator("#rc_select_0")
input_box.fill("5000")
input_box.press("Enter")
if logger:
logger.debug("Query interface setup complete")
def fill_and_search_orders(work_frame: Frame, order_ids: List[str]) -> None:
def fill_and_search_orders(work_frame: FrameLocator, order_ids: List[str], logger: Optional[logging.Logger] = None) -> None:
"""
Fill order IDs into the search textbox and trigger search.
Args:
work_frame: The work iframe containing the search form
order_ids: List of order IDs to search for
logger: Optional logger for debug output (silent if None)
"""
textbox = work_frame.get_by_role("textbox", name="来源生产订单号")
@@ -84,15 +94,20 @@ def fill_and_search_orders(work_frame: Frame, order_ids: List[str]) -> None:
loading_locator.wait_for(state="visible", timeout=3000)
loading_locator.wait_for(state="hidden", timeout=0)
except TimeoutError:
pass
if logger:
logger.debug("Loading indicator timeout - continuing anyway")
if logger:
logger.debug(f"Searched for {len(order_ids)} order IDs")
def download_batch_data(
work_frame: Frame,
work_frame: FrameLocator,
page: Page,
order_ids: List[str],
batch_index: int,
download_dir: str
download_dir: str,
logger: Optional[logging.Logger] = None
) -> str:
"""
Execute the download workflow for a single batch of order IDs.
@@ -103,6 +118,7 @@ def download_batch_data(
order_ids: List of order IDs to download
batch_index: Zero-based batch index for naming the output file
download_dir: Directory path to save the downloaded file
logger: Optional logger for info output (silent if None)
Returns:
str: Full path to the downloaded file
@@ -130,22 +146,26 @@ def download_batch_data(
# Step 5: Trigger download and save file
download_filename = f"temp_batch_{batch_index + 1}.xlsx"
download_path = os.path.join(download_dir, download_filename)
with page.expect_download() as download_info:
work_frame.get_by_role("button", name="确定(Y)").click()
download = download_info.value
download.save_as(download_path)
if logger:
logger.info(f"Downloaded batch {batch_index + 1} to {download_path}")
return download_path
def execute_batch_download_workflow(
work_frame: Frame,
work_frame: FrameLocator,
page: Page,
order_ids: List[str],
batch_index: int,
download_dir: str
download_dir: str,
logger: Optional[logging.Logger] = None
) -> str:
"""
Complete workflow: fill orders, search, and download for a single batch.
@@ -156,9 +176,10 @@ def execute_batch_download_workflow(
order_ids: List of order IDs for this batch
batch_index: Zero-based batch index for naming the output file
download_dir: Directory path to save the downloaded file
logger: Optional logger for debug output (silent if None)
Returns:
str: Full path to the downloaded file
"""
fill_and_search_orders(work_frame, order_ids)
return download_batch_data(work_frame, page, order_ids, batch_index, download_dir)
fill_and_search_orders(work_frame, order_ids, logger)
return download_batch_data(work_frame, page, order_ids, batch_index, download_dir, logger)