| import json | |
| def extract_tcb_ids_without_standalone_hash(json_file_path, output_file_path): | |
| with open(json_file_path, 'r', encoding='utf-8') as f: | |
| data = json.load(f) | |
| def has_standalone_hash(query): | |
| tokens = query.strip().split() | |
| return '#' in tokens | |
| tcb_ids = [ | |
| item['tcb_id'] | |
| for item in data | |
| if not has_standalone_hash(item.get('query_en', '')) and 'tcb_id' in item | |
| ] | |
| with open(output_file_path, 'w', encoding='utf-8') as f: | |
| json.dump(tcb_ids, f, indent=2, ensure_ascii=False) | |
| # 示例调用 | |
| extract_tcb_ids_without_standalone_hash('EN_section-6修正(1).json', 'filtered_tcb_ids_6.json') | |
Xet Storage Details
- Size:
- 693 Bytes
- Xet hash:
- 5e6aad17a6f6d466962a3f7dd624db14e0610f8c2cf67c8f819abb2c756b476e
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.