大型React JS项目批量词汇搜索需求：求可用工具或修复Python代码

修复后的单词汇搜索代码 #

原代码可能因编码异常、文件类型覆盖不全导致运行失败，以下是修复后的版本：

import os

def search_text_in_directory(directory, text_to_search):
    total_occurrences = 0
    # 扩展支持React项目常见的文件类型
    target_extensions = (".js", ".jsx", ".ts", ".tsx")
    
    for root, dirs, files in os.walk(directory):
        # 跳过node_modules目录，避免无效搜索
        if 'node_modules' in dirs:
            dirs.remove('node_modules')
        for file in files:
            if file.endswith(target_extensions):
                file_path = os.path.join(root, file)
                # 加入编码错误处理，防止程序中断
                try:
                    with open(file_path, 'r', encoding='utf-8') as f:
                        content = f.read()
                        occurrences = content.count(text_to_search)
                        total_occurrences += occurrences
                        if occurrences > 0:
                            print(f"'{text_to_search}' 在 '{file_path}' 中出现 {occurrences} 次")
                except UnicodeDecodeError:
                    print(f"跳过文件 {file_path}：编码格式不兼容")
    
    return total_occurrences

directory_to_search = r"C:\Users\hmmer\newsapi-app"
text_to_search = "news-image"
total = search_text_in_directory(directory_to_search, text_to_search)
print(f"'{text_to_search}' 总出现次数: {total}")

批量处理2400个词汇的方案 #

将所有词汇存入keywords.txt（每行一个词汇），通过脚本批量统计并导出结果：

import os
import csv

def search_text_in_directory(directory, text_to_search):
    total_occurrences = 0
    target_extensions = (".js", ".jsx", ".ts", ".tsx")
    
    for root, dirs, files in os.walk(directory):
        if 'node_modules' in dirs:
            dirs.remove('node_modules')
        for file in files:
            if file.endswith(target_extensions):
                file_path = os.path.join(root, file)
                try:
                    with open(file_path, 'r', encoding='utf-8') as f:
                        content = f.read()
                        total_occurrences += content.count(text_to_search)
                except UnicodeDecodeError:
                    continue
    
    return total_occurrences

def batch_search_keywords(directory, keywords_file, output_file):
    # 读取所有关键词
    with open(keywords_file, 'r', encoding='utf-8') as f:
        keywords = [line.strip() for line in f if line.strip()]
    
    # 批量统计
    results = []
    for idx, keyword in enumerate(keywords, 1):
        count = search_text_in_directory(directory, keyword)
        results.append({"关键词": keyword, "出现次数": count})
        print(f"[{idx}/{len(keywords)}] 完成统计: {keyword} - {count}次")
    
    # 导出结果到CSV
    with open(output_file, 'w', encoding='utf-8', newline='') as csvfile:
        fieldnames = ["关键词", "出现次数"]
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
        writer.writeheader()
        writer.writerows(results)
    
    print(f"统计结果已保存到 {output_file}")

# 配置路径
directory_to_search = r"C:\Users\hmmer\newsapi-app"
keywords_file = "keywords.txt"  # 你的关键词文件路径
output_file = "keyword_counts.csv"

batch_search_keywords(directory_to_search, keywords_file, output_file)

使用步骤 #

1. 将2400个词汇按每行一个的格式写入keywords.txt
2. 修改directory_to_search为你的React项目根目录
3. 运行脚本，最终统计结果会保存到keyword_counts.csv中

内容的提问来源于stack exchange，提问作者aikostr