脚本怎样诗词关键字检索

本文目录导读：

1. 基础Python脚本（使用列表）
2. 使用JSON文件的完整检索系统
3. 命令行版本
4. 使用SQLite数据库的高级版本
5. PHP版本（Web接口）
6. 使用建议

基础Python脚本（使用列表）

# 简单的诗词数据库
poems = [
    {"title": "静夜思", "author": "李白", "content": "床前明月光，疑是地上霜，举头望明月，低头思故乡。"},
    {"title": "春晓", "author": "孟浩然", "content": "春眠不觉晓，处处闻啼鸟，夜来风雨声，花落知多少。"},
    {"title": "登鹳雀楼", "author": "王之涣", "content": "白日依山尽，黄河入海流，欲穷千里目，更上一层楼。"}
]
def search_poems(keyword):
    results = []
    for poem in poems:
        if keyword in poem["title"] or keyword in poem["content"] or keyword in poem["author"]:
            results.append(poem)
    return results
# 使用示例
keyword = "月"
results = search_poems(keyword)
for r in results:
    print(f"{r['title']} - {r['author']}")
    print(r['content'])
    print("---")

使用JSON文件的完整检索系统

import json
import re
class PoemSearch:
    def __init__(self, json_file="poems.json"):
        self.poems = self.load_poems(json_file)
    def load_poems(self, file_path):
        with open(file_path, 'r', encoding='utf-8') as f:
            return json.load(f)
    def search_by_keyword(self, keyword, fields=None):
        """
        关键词检索
        :param keyword: 搜索关键词
        :param fields: 搜索范围，如 ["title", "content", "author"]
        """
        if fields is None:
            fields = ["title", "content", "author", "dynasty"]
        results = []
        keyword_lower = keyword.lower()
        for poem in self.poems:
            for field in fields:
                if field in poem and isinstance(poem[field], str):
                    if keyword_lower in poem[field].lower():
                        results.append(poem)
                        break
        return results
    def search_by_regex(self, pattern, fields=None):
        """
        正则表达式检索
        """
        if fields is None:
            fields = ["title", "content"]
        results = []
        for poem in self.poems:
            for field in fields:
                if field in poem:
                    if re.search(pattern, poem[field]):
                        results.append(poem)
                        break
        return results
    def fuzzy_search(self, keyword, threshold=0.6):
        """
        模糊检索（使用Levenshtein距离）
        """
        from fuzzywuzzy import fuzz
        results = []
        for poem in self.poems:
            score = 0
            # 计算标题和内容的相似度
            title_score = fuzz.partial_ratio(keyword, poem.get("title", ""))
            content_score = fuzz.partial_ratio(keyword, poem.get("content", ""))
            score = max(title_score, content_score) / 100
            if score >= threshold:
                poem["similarity"] = score
                results.append(poem)
        # 按相似度排序
        results.sort(key=lambda x: x["similarity"], reverse=True)
        return results
# 使用示例
search = PoemSearch()
# 普通搜索
results = search.search_by_keyword("明月")
# 正则搜索 - 搜索以"月"结尾的诗句
results = search.search_by_regex(r'月$')
# 模糊搜索
results = search.fuzzy_search("明朋光")

命令行版本

#!/usr/bin/env python3
# poem_search.py
import json
import sys
from colorama import init, Fore, Style
init(autoreset=True)  # 初始化colorama
class PoemCLI:
    def __init__(self):
        self.poems = self.load_default_data()
    def load_default_data(self):
        # 这里可以加载JSON文件
        return [
            {
                "title": "静夜思",
                "author": "李白",
                "dynasty": "唐",
                "content": "床前明月光，疑是地上霜，举头望明月，低头思故乡。"
            },
            # ... 更多诗词
        ]
    def search_and_display(self, keyword):
        results = []
        for poem in self.poems:
            if (keyword in poem["title"] or 
                keyword in poem["content"] or 
                keyword in poem["author"]):
                results.append(poem)
        if not results:
            print(f"{Fore.RED}未找到包含'{keyword}'的诗词")
            return
        print(f"{Fore.GREEN}找到 {len(results)} 首诗词：\n")
        for i, poem in enumerate(results, 1):
            print(f"{Fore.YELLOW}{i}. {poem['title']}")
            print(f"   {Fore.CYAN}作者：{poem['author']} | 朝代：{poem['dynasty']}")
            print(f"   {Fore.WHITE}{poem['content']}")
            # 高亮关键字
            highlighted = poem['content'].replace(
                keyword, 
                f"{Fore.RED}{keyword}{Style.RESET_ALL}"
            )
            print(f"   {highlighted}")
            print()
def main():
    if len(sys.argv) < 2:
        print("使用方法：python poem_search.py <关键词>")
        sys.exit(1)
    keyword = sys.argv[1]
    cli = PoemCLI()
    cli.search_and_display(keyword)
if __name__ == "__main__":
    main()

使用SQLite数据库的高级版本

import sqlite3
import jieba
class AdvancedPoemSearch:
    def __init__(self, db_path="poems.db"):
        self.conn = sqlite3.connect(db_path)
        self.create_tables()
    def create_tables(self):
        cursor = self.conn.cursor()
        cursor.execute('''
            CREATE TABLE IF NOT EXISTS poems (
                id INTEGER PRIMARY KEY,
                title TEXT,
                author TEXT,
                dynasty TEXT,
                content TEXT
            )
        ''')
        cursor.execute('''
            CREATE INDEX IF NOT EXISTS idx_content 
            ON poems(content)
        ''')
        self.conn.commit()
    def fulltext_search(self, keyword):
        """全文搜索"""
        cursor = self.conn.cursor()
        cursor.execute('''
            SELECT * FROM poems 
            WHERE content LIKE ? OR title LIKE ? OR author LIKE ?
        ''', (f'%{keyword}%', f'%{keyword}%', f'%{keyword}%'))
        return cursor.fetchall()
    def keyword_analysis(self, text):
        """中文分词和关键词提取"""
        words = jieba.lcut(text)
        # 去除停用词
        stop_words = set(['的', '了', '是', '在', '我', '有', '和', '就', '不', '人'])
        keywords = [w for w in words if w not in stop_words and len(w) > 1]
        return keywords
    def advanced_search(self, keywords):
        """多关键词组合搜索"""
        results = []
        keywords_list = keywords.split()
        for poem in self.get_all_poems():
            score = 0
            for kw in keywords_list:
                if kw in poem['content']:
                    score += 1
                if kw in poem['title']:
                    score += 2  # 标题匹配权重更高
            if score > 0:
                poem['score'] = score
                results.append(poem)
        # 按相关性排序
        results.sort(key=lambda x: x['score'], reverse=True)
        return results
# 使用示例
searcher = AdvancedPoemSearch()
results = searcher.fulltext_search("明月")
results = searcher.advanced_search("明月 思乡")  # 多关键词搜索

PHP版本（Web接口）

<?php
// poem_search.php
class PoemSearch {
    private $poems = [];
    public function __construct() {
        $this->loadPoems();
    }
    private function loadPoems() {
        // 从文件加载诗词数据
        $json = file_get_contents('poems.json');
        $this->poems = json_decode($json, true);
    }
    public function search($keyword, $fields = ['title', 'content', 'author']) {
        $results = [];
        foreach ($this->poems as $poem) {
            foreach ($fields as $field) {
                if (isset($poem[$field]) && 
                    mb_stripos($poem[$field], $keyword) !== false) {
                    $results[] = $poem;
                    break;
                }
            }
        }
        return $results;
    }
    public function ajaxResponse($keyword) {
        header('Content-Type: application/json; charset=utf-8');
        $results = $this->search($keyword);
        echo json_encode([
            'status' => 'success',
            'count' => count($results),
            'data' => $results
        ]);
    }
}
// HTML前端界面
?>
<!DOCTYPE html>
<html>
<head>诗词检索</title>
    <style>
        .search-box { margin: 20px; }
        .result-item { 
            border: 1px solid #ddd; 
            margin: 10px 0; 
            padding: 10px; 
        }
        .highlight { 
            background-color: yellow; 
            font-weight: bold; 
        }
    </style>
</head>
<body>
    <div class="search-box">
        <input type="text" id="keyword" placeholder="输入关键词">
        <button onclick="searchPoems()">搜索</button>
    </div>
    <div id="results"></div>
    <script>
        function searchPoems() {
            const keyword = document.getElementById('keyword').value;
            fetch(`poem_search.php?keyword=${encodeURIComponent(keyword)}`)
                .then(response => response.json())
                .then(data => {
                    displayResults(data);
                });
        }
        function displayResults(data) {
            const container = document.getElementById('results');
            container.innerHTML = `<h3>找到 ${data.count} 首诗词</h3>`;
            data.data.forEach(poem => {
                const div = document.createElement('div');
                div.className = 'result-item';
                div.innerHTML = `
                    <h4>${poem.title}</h4>
                    <p>作者：${poem.author} | 朝代：${poem.dynasty}</p>
                    <p>${highlightKeyword(poem.content, keyword)}</p>
                `;
                container.appendChild(div);
            });
        }
        function highlightKeyword(text, keyword) {
            const regex = new RegExp(keyword, 'gi');
            return text.replace(regex, `<span class="highlight">$&</span>`);
        }
    </script>
</body>
</html>

使用建议

1. 小规模数据：使用Python列表或JSON文件
2. 大规模数据：使用数据库（SQLite、MySQL）
3. 需要高性能：使用Elasticsearch或Whoosh
4. Web应用：使用PHP/Node.js配合前端框架
5. 需要考虑：
   • 中文分词（jieba）
   • 同义词扩展
   • 拼音搜索
   • 模糊匹配

这些脚本可以根据你的具体需求进行调整和扩展,需要我详细解释某个特定部分吗？