131 lines
4.1 KiB
Python
131 lines
4.1 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
使用阿里百炼API翻译题目内容
|
|
"""
|
|
import json
|
|
import os
|
|
import time
|
|
import urllib.request
|
|
import urllib.parse
|
|
import ssl
|
|
|
|
API_KEY = "sk-74905419d30541d18991396892bb27b0"
|
|
API_URL = "https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation"
|
|
|
|
def translate_text(text):
|
|
"""
|
|
使用阿里百炼API翻译文本
|
|
"""
|
|
if not text or not text.strip():
|
|
return text
|
|
|
|
prompt = f"""请将以下英文翻译成中文，保持专业术语的准确性，直接输出翻译结果，不要添加任何解释：
|
|
|
|
英文原文：
|
|
{text}
|
|
|
|
中文翻译："""
|
|
|
|
try:
|
|
headers = {
|
|
'Content-Type': 'application/json',
|
|
'Authorization': f'Bearer {API_KEY}'
|
|
}
|
|
|
|
data = {
|
|
"model": "qwen-turbo",
|
|
"input": {
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": prompt
|
|
}
|
|
]
|
|
},
|
|
"parameters": {
|
|
"temperature": 0.1,
|
|
"max_tokens": 2000
|
|
}
|
|
}
|
|
|
|
req = urllib.request.Request(
|
|
API_URL,
|
|
data=json.dumps(data).encode('utf-8'),
|
|
headers=headers,
|
|
method='POST'
|
|
)
|
|
|
|
ssl_context = ssl.create_default_context()
|
|
|
|
with urllib.request.urlopen(req, context=ssl_context, timeout=60) as response:
|
|
result = json.loads(response.read().decode('utf-8'))
|
|
|
|
if result and 'output' in result and 'text' in result['output']:
|
|
translated = result['output']['text'].strip()
|
|
if translated.startswith('中文翻译：'):
|
|
translated = translated[6:].strip()
|
|
return translated
|
|
else:
|
|
print(f"API响应格式错误: {result}")
|
|
return text
|
|
|
|
except Exception as e:
|
|
print(f"翻译错误: {e}")
|
|
return text
|
|
|
|
def translate_questions(input_file, output_file, start_index=0, batch_size=10):
|
|
"""
|
|
翻译题目，支持分批处理
|
|
"""
|
|
if os.path.exists(output_file):
|
|
with open(output_file, 'r', encoding='utf-8') as f:
|
|
questions = json.load(f)
|
|
else:
|
|
with open(input_file, 'r', encoding='utf-8') as f:
|
|
questions = json.load(f)
|
|
|
|
total = len(questions)
|
|
end_index = min(start_index + batch_size, total)
|
|
|
|
print(f"正在翻译第 {start_index + 1} 到 {end_index} 题，共 {total} 题")
|
|
|
|
for i in range(start_index, end_index):
|
|
q = questions[i]
|
|
print(f"翻译 Topic {q['topic']} - Question {q['question_num']} ({i+1}/{total})")
|
|
|
|
if 'stem_cn' not in q or not q['stem_cn'] or q['stem_cn'] == '待翻译...':
|
|
print(f" 翻译题干...")
|
|
q['stem_cn'] = translate_text(q['stem'])
|
|
time.sleep(0.5)
|
|
|
|
for j, opt in enumerate(q['options']):
|
|
if 'text_cn' not in opt or not opt['text_cn'] or opt['text_cn'] == '待翻译...':
|
|
print(f" 翻译选项 {opt['label']}...")
|
|
opt['text_cn'] = translate_text(opt['text'])
|
|
time.sleep(0.3)
|
|
|
|
with open(output_file, 'w', encoding='utf-8') as f:
|
|
json.dump(questions, f, ensure_ascii=False, indent=2)
|
|
|
|
print(f"\n翻译进度: {end_index}/{total}")
|
|
|
|
if end_index < total:
|
|
print(f"继续翻译请运行: python3 translate_aliyun.py --start {end_index}")
|
|
else:
|
|
print("所有题目翻译完成！")
|
|
|
|
return questions
|
|
|
|
if __name__ == '__main__':
|
|
import argparse
|
|
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--start', type=int, default=0, help='起始索引')
|
|
parser.add_argument('--batch', type=int, default=10, help='批量大小')
|
|
args = parser.parse_args()
|
|
|
|
input_file = '/Users/duguoyou/D365/exam_data/questions.json'
|
|
output_file = '/Users/duguoyou/D365/exam_data/questions_translated.json'
|
|
|
|
translate_questions(input_file, output_file, args.start, args.batch)
|