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

feat: add progress callback mechanism for real-time updates in data extraction

Browse Source 
- Add ProgressInfo and ProgressCalculator classes for structured progress tracking
- Implement RealtimeOutput for immediate log display without buffering
- Add progress callback support to DiscreteMaterialPlanExtractor
- Use queue-based thread-safe communication for GUI progress updates
- Fix log output issue where all content appeared at once after completion

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
Misaka_Company
2026-02-05 14:06:30 +08:00
parent 71621dc8a0
commit 885d87dff8
4 changed files with 329 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files

212
utils/离散备料计划维护数据提取.py
View File

@@ -8,12 +8,13 @@ from playwright.sync_api import sync_playwright
from utils.excel_converter import ExcelConverter
from utils.auth import login, logout
from db.production_order_query import read_production_ids, query_production_order_numbers
from typing import Callable, Optional
class DiscreteMaterialPlanExtractor:
"""离散备料计划维护数据提取器"""
def __init__(self, username, password, headless=False, verbose=True):
def __init__(self, username, password, headless=False, verbose=True, progress_callback=None):
"""
初始化提取器
@@ -22,11 +23,13 @@ class DiscreteMaterialPlanExtractor:
password: 登录密码
headless: 是否无头模式运行
verbose: 是否打印详细日志
progress_callback: 进度回调函数，接收 ProgressInfo 对象
"""
self.username = username
self.password = password
self.headless = headless
self.verbose = verbose
self.progress_callback = progress_callback
self.converter = ExcelConverter(verbose=verbose)
def _print(self, *args, **kwargs):
@@ -34,12 +37,39 @@ class DiscreteMaterialPlanExtractor:
if self.verbose:
print(*args, **kwargs)
def get_production_order_numbers(self, production_id_file):
def _report_progress(self, stage: str, current: int, total: int, message: str, **detail):
"""
报告进度
Args:
stage: 阶段标识
current: 当前进度值
total: 总量
message: 显示消息
**detail: 额外详细信息
"""
if self.progress_callback:
try:
from gui.progress import ProgressInfo
progress_info = ProgressInfo(
stage=stage,
current=current,
total=total,
message=message,
detail=detail
)
self.progress_callback(progress_info)
except Exception:
# 如果进度回调失败，忽略错误，不影响主流程
pass
def get_production_order_numbers(self, production_id_file, report_progress=False):
"""
读取总排号文件并查询数据库获取生产订单号
Args:
production_id_file: ProductionID.txt 文件路径
report_progress: 是否报告进度
Returns:
生产订单号列表
@@ -52,6 +82,9 @@ class DiscreteMaterialPlanExtractor:
order_ids = query_production_order_numbers(production_ids)
self._print(f"查询到 {len(order_ids)} 个生产订单号")
if report_progress:
self._report_progress('query', 1, 1, f"查询到 {len(order_ids)} 个生产订单号", count=len(order_ids))
return order_ids
def group_order_ids(self, order_ids, group_size=100):
@@ -59,7 +92,7 @@ class DiscreteMaterialPlanExtractor:
for i in range(0, len(order_ids), group_size):
yield order_ids[i:i + group_size]
def download_batch(self, inner_frame, order_ids, batch_index, page1, debug_mode=False, debug_batch=None):
def download_batch(self, inner_frame, order_ids, batch_index, total_batches, page1, debug_mode=False, debug_batch=None):
"""下载一批订单号的数据"""
from playwright.sync_api import TimeoutError
import re
@@ -111,6 +144,15 @@ class DiscreteMaterialPlanExtractor:
download.save_as(download_path)
self._print(f"第 {batch_index + 1} 批下载完成: {download_path}")
# 报告进度
self._report_progress(
'download',
batch_index + 1,
total_batches,
f"第 {batch_index + 1}/{total_batches} 批下载完成",
batch_index=batch_index + 1
)
# 关闭输出对话框（如果有的话）
# try:
# inner_frame.get_by_role("button", name="取消").click()
@@ -142,6 +184,17 @@ class DiscreteMaterialPlanExtractor:
for i, file_path in enumerate(file_paths, 1):
self._print(f"转换第 {i} 个文件: {file_path}")
# 报告进度
self._report_progress(
'convert',
i,
len(file_paths),
f"转换第 {i}/{len(file_paths)} 个文件",
file_index=i,
file_path=file_path
)
df = self.converter.convert(file_path, output_file=None) # 只转换，不保存
all_dataframes.append(df)
self._print(f" 提取到 {len(df)} 条记录")
@@ -187,7 +240,7 @@ class DiscreteMaterialPlanExtractor:
def extract(self, production_id_file, data_dir="D:/python/playwrite/data",
output_file="D:/python/playwrite/data/离散备料计划维护_合并.xlsx",
debug_mode=False, debug_batch=None):
debug_mode=False, debug_batch=None, progress_callback=None):
"""
执行完整的数据提取流程
@@ -197,76 +250,113 @@ class DiscreteMaterialPlanExtractor:
output_file: 最终输出文件路径
debug_mode: 是否启用调试模式
debug_batch: 调试批次号
progress_callback: 进度回调函数（覆盖初始化时的回调）
Returns:
输出文件路径
"""
with sync_playwright() as playwright:
# 调用登录模块
browser, context, page, main_frame = login(
playwright=playwright,
username=self.username,
password=self.password,
headless=self.headless,
ignore_https_errors=True
)
# 保存原始回调
original_callback = self.progress_callback
# 使用传入的回调或初始化时的回调
self.progress_callback = progress_callback or self.progress_callback
self._print("=" * 80)
self._print("开始执行离散备料计划维护数据提取")
self._print("=" * 80)
# 登录成功后可以进行后续操作
# 点击打开"功能菜单"
main_frame.locator("i").first.click()
# 点击打开"离散备料计划维护"
with page.expect_popup() as page1_info:
main_frame.get_by_title("离散备料计划维护", exact=True).first.click()
page1 = page1_info.value
# 获取 nested iframe
main_frame = page1.locator("#forwardFrame").content_frame
inner_frame_locator = main_frame.locator("#mainiframe")
inner_frame_locator.wait_for(state="visible", timeout=15000)
inner_frame = inner_frame_locator.content_frame
# 设置查询界面
self.setup_query_interface(inner_frame)
# 读取总排号并查询生产订单号
order_ids = self.get_production_order_numbers(production_id_file)
# 按批次下载
downloaded_files = []
for batch_index, order_ids_batch in enumerate(self.group_order_ids(order_ids, 100)):
self._print(f"\n=== 开始处理第 {batch_index + 1} 批，共 {len(order_ids_batch)} 个订单号 ===")
downloaded_file = self.download_batch(
inner_frame, order_ids_batch, batch_index, page1,
debug_mode=debug_mode, debug_batch=debug_batch
try:
with sync_playwright() as playwright:
# 调用登录模块
browser, context, page, main_frame = login(
playwright=playwright,
username=self.username,
password=self.password,
headless=self.headless,
ignore_https_errors=True
)
downloaded_files.append(downloaded_file)
# 执行账号注销
self._print("\n开始执行账号注销...")
logout(main_frame, verbose=self.verbose)
# 登录完成
self._report_progress('login', 1, 1, "登录成功")
# 转换并合并文件
if downloaded_files:
self._print(f"\n=== 开始转换并合并 {len(downloaded_files)} 个文件 ===")
self.convert_and_merge_files(downloaded_files, output_file)
else:
self._print("\n没有下载到任何文件")
self._print("=" * 80)
self._print("开始执行离散备料计划维护数据提取")
self._print("=" * 80)
self._print(f"\n=== 全部完成 ===")
self._print(f"最终文件: {output_file}")
# 登录成功后可以进行后续操作
# 点击打开"功能菜单"
main_frame.locator("i").first.click()
# 点击打开"离散备料计划维护"
with page.expect_popup() as page1_info:
main_frame.get_by_title("离散备料计划维护", exact=True).first.click()
page1 = page1_info.value
# 获取 nested iframe
main_frame = page1.locator("#forwardFrame").content_frame
inner_frame_locator = main_frame.locator("#mainiframe")
inner_frame_locator.wait_for(state="visible", timeout=15000)
inner_frame = inner_frame_locator.content_frame
# 关闭浏览器
context.close()
browser.close()
# 设置查询界面
self.setup_query_interface(inner_frame)
return output_file
# 读取总排号并查询生产订单号
order_ids = self.get_production_order_numbers(production_id_file, report_progress=True)
# 按批次下载
downloaded_files = []
# 计算总批次数
total_batches = sum(1 for _ in self.group_order_ids(order_ids, 100))
for batch_index, order_ids_batch in enumerate(self.group_order_ids(order_ids, 100)):
self._print(f"\n=== 开始处理第 {batch_index + 1} 批，共 {len(order_ids_batch)} 个订单号 ===")
# 报告开始下载批次
self._report_progress(
'download',
batch_index,
total_batches,
f"正在下载第 {batch_index + 1}/{total_batches} 批...",
batch_index=batch_index + 1,
batch_size=len(order_ids_batch)
)
downloaded_file = self.download_batch(
inner_frame, order_ids_batch, batch_index, total_batches, page1,
debug_mode=debug_mode, debug_batch=debug_batch
)
downloaded_files.append(downloaded_file)
# 执行账号注销
self._print("\n开始执行账号注销...")
self._report_progress('logout', 1, 1, "正在注销账号...")
logout(main_frame, verbose=self.verbose)
# 转换并合并文件
if downloaded_files:
self._report_progress(
'convert',
0,
len(downloaded_files),
f"开始转换并合并 {len(downloaded_files)} 个文件",
file_count=len(downloaded_files)
)
self._print(f"\n=== 开始转换并合并 {len(downloaded_files)} 个文件 ===")
self.convert_and_merge_files(downloaded_files, output_file)
else:
self._print("\n没有下载到任何文件")
self._print(f"\n=== 全部完成 ===")
self._print(f"最终文件: {output_file}")
# 报告完成
self._report_progress('complete', 1, 1, "提取完成", output_file=output_file)
# 关闭浏览器
context.close()
browser.close()
return output_file
finally:
# 恢复原始回调
self.progress_callback = original_callback
def main():
"""测试函数"""