关键字检测匹配
ahocorasick
ahocorasick python
发布日期:   2020-02-18
作者:   四两波千斤
文章字数:   341
阅读时长:   1 分

关键字检测匹配

import ahocorasick
def check_keyword(text, keywords):
    """检查文本中是否包含关键词"""
    A = ahocorasick.Automaton()
    for i, keyword in enumerate(keywords):
        A.add_word(keyword, (i, keyword))
    A.make_automaton()
    matched_keywords = []
    for end_index, (insert_order, keyword) in A.iter(text):
        if text[end_index-len(keyword)+1:end_index+1] == keyword:
            matched_keywords.append(keyword)
    if matched_keywords:
        matched_keywords.sort(key=lambda x: len(x), reverse=True)
        return True, matched_keywords[0]  # 返回最长的匹配关键词
    return False, None
text = "你好有没有x350型号的车"
keywords = [ "x350","x35","x3500","x3"]
found, keyword = check_keyword(text, keywords)
print(found, keyword)
赏