93 lines
2.4 KiB
Python
93 lines
2.4 KiB
Python
import argparse
|
|
import re
|
|
|
|
def parse_args() -> argparse.Namespace:
|
|
parser = argparse.ArgumentParser(description="对UP主按首字母排序")
|
|
parser.add_argument(
|
|
"--input",
|
|
default="source/output/reports/up_analysis_full_auto.md",
|
|
help="输入报告路径",
|
|
)
|
|
parser.add_argument(
|
|
"--output",
|
|
help="输出报告路径（默认覆盖输入）",
|
|
)
|
|
return parser.parse_args()
|
|
|
|
def main():
|
|
args = parse_args()
|
|
input_file = args.input
|
|
output_file = args.output or input_file
|
|
|
|
with open(input_file, 'r', encoding='utf-8') as f:
|
|
content = f.read()
|
|
|
|
lines = content.split('\n')
|
|
|
|
header_lines = []
|
|
section_starts = []
|
|
for i, line in enumerate(lines):
|
|
if line.startswith('## '):
|
|
section_starts.append(i)
|
|
|
|
if len(section_starts) < 2:
|
|
print('No sections found')
|
|
return 1
|
|
|
|
header = '\n'.join(lines[:section_starts[0]])
|
|
sections_data = []
|
|
|
|
for idx in range(len(section_starts)):
|
|
start = section_starts[idx]
|
|
if idx + 1 < len(section_starts):
|
|
end = section_starts[idx + 1]
|
|
else:
|
|
end = len(lines)
|
|
|
|
section_lines = lines[start:end]
|
|
section_text = '\n'.join(section_lines)
|
|
sections_data.append(section_text)
|
|
|
|
sections_data = sections_data[1:]
|
|
|
|
parsed = []
|
|
for sec in sections_data:
|
|
match = re.match(r'^## (\d+)\. (.+) \(mid: (\d+)\)', sec)
|
|
if match:
|
|
num = int(match.group(1))
|
|
name = match.group(2)
|
|
mid = match.group(3)
|
|
parsed.append({
|
|
'num': num,
|
|
'name': name,
|
|
'mid': mid,
|
|
'content': sec
|
|
})
|
|
|
|
def sort_key(item):
|
|
name = item['name']
|
|
first_char = name[0].lower() if name else ''
|
|
if first_char.isdigit():
|
|
return '0' + first_char
|
|
elif first_char.isalpha():
|
|
return '1' + first_char
|
|
else:
|
|
return '2' + first_char
|
|
|
|
parsed.sort(key=sort_key)
|
|
|
|
new_content = header + '\n'
|
|
for i, sec in enumerate(parsed):
|
|
new_content += sec['content'] + '\n'
|
|
|
|
with open(output_file, 'w', encoding='utf-8') as f:
|
|
f.write(new_content)
|
|
|
|
print(f'Sorted {len(parsed)} sections')
|
|
print('First 10:')
|
|
for s in parsed[:10]:
|
|
print(f' {s["name"]}')
|
|
return 0
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main()) |