🚀 作者 ：“码上有前”
🚀 文章简介 ：Python
🚀 欢迎小伙伴们 点赞👍、收藏⭐、留言💬

抽取关键词

import os
import json
import pandas as pd


# 指定文件夹路径和关键词列名
folder_path = './Cosmetic_data/Brand_Classification/brand&details_analysis'
categories_path = './Cosmetic_data/Makeup_Classification/pcommit&details_analysis'
keyword_column = '关键词'  # 替换为实际的关键词列名

def extract_keywords(folder_path, keyword_column):
    # 存储关键词的列表
    keyword_list = []

    # 获取文件夹下所有的 csv 文件
    csv_files = [file for file in os.listdir(folder_path) if file.endswith('.csv')]

    # 遍历每个 csv 文件
    for csv_file in csv_files:
        file_path = os.path.join(folder_path, csv_file)

        # 读取 csv 文件
        df = pd.read_csv(file_path)

        # 检查关键词列是否存在
        if keyword_column in df.columns:
            # 获取关键词列的值并去除换行符和制表符
            keywords = df[keyword_column].astype(str).str.replace(r'\n|\t', '', regex=True).tolist()

            # 将关键词添加到列表中
            keyword_list.extend(keywords)

    # 去除空字符串
    keyword_list = [keyword for keyword in keyword_list if keyword]
    
    return keyword_list

# 提取关键词
# result_keywords = extract_keywords(folder_path, keyword_column)
# 打印结果
# print("提取的关键词列表:")
# print(result_keywords)

def extract_keywords_from_json(categories_path, keyword_key):
    keyword_list = []

    json_files = [file for file in os.listdir(categories_path) if file.endswith('.json')]

    for json_file in json_files:
        file_path = os.path.join(categories_path, json_file)

        with open(file_path, 'r',encoding="utf-8") as f:
            data = json.load(f)
        
        for item in data:
            if keyword_key in item:
                keywords = item[keyword_key]
                if isinstance(keywords, str):
                    # 替换关键词中的换行符和制表符
                    keywords = keywords.replace('\n', '').replace('\t', '')
                    keyword_list.append(keywords)
                elif isinstance(keywords, list):
                    for keyword in keywords:
                        # 替换关键词中的换行符和制表符
                        keyword = keyword.replace('\n', '').replace('\t', '')
                        keyword_list.append(keyword)

    keyword_list = [keyword.strip() for keyword in keyword_list if keyword.strip()]
    return keyword_list
categories_keywords = extract_keywords_from_json(categories_path, keyword_column)