Python如何查找字符串中距离基准词最近的ticker及对应周边文本

import re

def get_identifier(ticker: str, base_word: str, content: str, extra_char_num: int = 0) -> str:
    # 匹配所有基准词位置，如需区分大小写可删除re.IGNORECASE参数
    base_match_list = list(re.finditer(re.escape(base_word), content, re.IGNORECASE))
    if not base_match_list:
        return ""
    # 存在多个基准词时默认取第一个，可按需调整遍历逻辑
    target_base = base_match_list[0]
    base_start_idx, base_end_idx = target_base.span()

    # 匹配所有ticker位置
    ticker_match_list = list(re.finditer(re.escape(ticker), content, re.IGNORECASE))
    if not ticker_match_list:
        return ""
    
    # 计算距离筛选最近的ticker
    nearest_ticker = min(ticker_match_list, key=lambda match: abs(match.start() - base_start_idx))
    ticker_start_idx = nearest_ticker.start()

    # 计算提取范围，extra_char_num为基准词前后额外提取的字符长度
    extract_start = max(0, ticker_start_idx - extra_char_num)
    extract_end = min(len(content), base_end_idx + extra_char_num)

    return content[extract_start:extract_end].strip()

ticker = 'TRBCX'
base_word = 'goal'
content = 'TRBCX fund is up 2% today. TRBCX investment goal is to beat the S&P 500. TRBCX is managed by investment manager John Smith'

# 提取最近ticker到基准词之间的内容
identifier = get_identifier(ticker, base_word, content)
print(identifier)
# 输出：TRBCX investment goal

# 前后额外各取10个字符，获取周边完整文本
identifier = get_identifier(ticker, base_word, content, extra_char_num=10)
print(identifier)
# 输出：today. TRBCX investment goal is to beat

• 如需按词数而非字符数扩展提取范围，可先将文本按空格分词后再计算起止索引，逻辑一致
• 存在多个基准词时，可遍历base_match_list批量生成对应的identifier
• 默认不区分大小写匹配ticker和基准词，如有严格匹配需求删除re.IGNORECASE参数即可

内容的提问来源于stack exchange，提问作者MellyJ13