正则表达式-将一段话隔开为两个list，此中一个为标签list，一个为文本list - ToB企服应用市场:ToB评测及商务社交产业平台

import re
def extract_labels_and_contents(text):
# 构建正则表达式模式
pattern = re.compile(r'(\[FAC\]|\[ADV\]|\[SUP\]|\[RES\]|\[ANA\]|\[EXP\])(.*?)(?=\[FAC\]|\[ADV\]|\[SUP\]|\[RES\]|\[ANA\]|\[EXP\]|\Z)', re.DOTALL)
# 查找所有匹配的标签和内容
matches = pattern.findall(text)
# 将标签和中间内容分别存储在两个列表中
found_labels = []
contents = []
for match in matches:
found_labels.append(match[0])
contents.append(match[1].strip())
# print("Found Labels:", found_labels)
# print("Contents:", contents)
combined_list = [{"text": text, "speaker": "sys", "strategy": label} for label, text in zip(found_labels, contents)]
return combined_list
# 示例文本
text = """
[SUP]您好，给您一个温暖的抱抱。[ANA]您这样是对的。
"""
# 调用函数并打印结果
result = extract_labels_and_contents(text)
print(result)

复制代码