Repository navigation
Expand file tree
/
Copy pathmain.py
More file actions
45 lines (35 loc) · 1.45 KB
/
Copy pathmain.py
File metadata and controls
45 lines (35 loc) · 1.45 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
import os
import pandas as pd
from core.xlsx_handler import process_xlsx
from core.xls_handler import process_xls
from core.postprocess import (
process_processed_files,
remove_empty_columns,
deduplicate_column_names
)
from core.collapsed_column import generate_collapsed_column
def main():
input_dir = os.path.join(os.getcwd(), '待处理')
base_output_dir = os.path.join(os.getcwd(), '已处理')
os.makedirs(base_output_dir, exist_ok=True)
for fname in os.listdir(input_dir):
if not fname.lower().endswith(('.xlsx', '.xls')):
continue
fullpath = os.path.join(input_dir, fname)
base_name = os.path.splitext(fname)[0]
output_dir = os.path.join(base_output_dir, base_name)
os.makedirs(output_dir, exist_ok=True)
tables = process_xlsx(fullpath) if fname.lower().endswith('.xlsx') else process_xls(fullpath)
count = 1
for sheet_name, tbl in tables:
out_path = os.path.join(output_dir, f"{base_name}_分表{count:03d}.xlsx")
df = pd.DataFrame(tbl)
with pd.ExcelWriter(out_path, engine='openpyxl') as writer:
df.to_excel(writer, sheet_name=f'_分表{count}', index=False, header=False)
count += 1
process_processed_files(output_dir)
remove_empty_columns(output_dir)
deduplicate_column_names(output_dir)
generate_collapsed_column(output_dir)
if __name__ == '__main__':
main()