根据关键字查找文件工具

LiCan857

不知道这种工具之前有没有人写过。
用python写了个根据关键字找文件的工具，做成了GUI界面。
对于只记得文件部分内容，但找不到文件在哪里的很有帮助。

[Python] 纯文本查看 复制代码

?

001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050 051 052 053 054 055 056 057 058 059 060 061 062 063 064 065 066 067 068 069 070 071 072 073 074 075 076 077 078 079 080 081 082 083 084 085 086 087 088 089 090 091 092 093 094 095 096 097 098 099 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176

import tkinter as tk from tkinter import filedialog, messagebox import threading import pandas as pd import os import sys     # 自定义控制台输出到GUI class RedirectText:     def __init__(self, text_widget):         self.text_widget = text_widget       def write(self, string):         self.text_widget.insert(tk.END, string)         self.text_widget.see(tk.END)  # 自动滚动到最后一行       def flush(self):         pass     def find_key(directory, keyword, process_button, check_var, check_btn):     found_files = False     num = 0     for root, dirs, files in os.walk(directory):         for filename in files:             if check_var.get():                 if filename.endswith('.xls'):                     file_path = os.path.join(root, filename)                     index_excel = find_key_in_excel(file_path, keyword, 'xls')                     for i in range(len(index_excel)):                         num = num + 1                         print(f"[{num}] " + file_path + f": " + str(index_excel[i]))                         found_files = True                         print("******************************************\n")                 if filename.endswith('.xlsx'):                     file_path = os.path.join(root, filename)                     index_excel = find_key_in_excel(file_path, keyword, 'xlsx')                     for i in range(len(index_excel)):                         num = num + 1                         print(f"[{num}] " + file_path + f": " + str(index_excel[i]))                         found_files = True                         print("******************************************\n")             if filename.endswith(('.py', '.txt', 'json', 'md', '.c', '.cpp', '.h', '.java', '.js', '.html', '.css',                                   '.xml', '.sql', '.bat', '.ps1', '.sh', '.yaml', '.yml', '.conf', '.ini', '.license')):                 file_path = os.path.join(root, filename)                 try:                     with open(file_path, 'r', encoding='utf-8', errors='ignore') as file:                         content_lines = file.readlines()                         for line_number, line in enumerate(content_lines, start=1):                             if keyword in line:                                 num = num + 1                                 print(f"[{num}] " + file_path + f": " + line.strip(), f"({line_number})")                                 found_files = True                                 print("******************************************\n")                 except IOError as e:                     print(f"文件读取错误 {file_path}: {e}")                     process_button.config(state='normal')                     check_btn.config(state='normal')     if not found_files:         print(f"在'{directory}'下没有找到关键字为'{keyword}'的文件...")     process_button.config(state='normal')     check_btn.config(state='normal')     def find_key_in_excel(file_path, key, typ):     try:         if typ == 'xlsx':             sheets = pd.read_excel(file_path, sheet_name=None, engine='openpyxl',                                    header=None)  # 设置header=None以不将第一行视为表头         else:             sheets = pd.read_excel(file_path, sheet_name=None, engine='xlrd', header=None)  # 设置header=None以不将第一行视为表头     except Exception as e:         print(f"文件读取错误 {file_path}: {e}")         return       index_list = []     # 遍历DataFrame的所有单元格     try:         for sheet_name, sheet in sheets.items():             for i in range(sheet.shape[0]):  # 行数                 for j in range(sheet.shape[1]):  # 列数                     if key in str(sheet.iat[i, j]):  # 比较单元格中的值是否等于key                         row_num = i + 1  # Excel的行号是从1开始的                         col_num = j + 1  # Excel的列号也是从1开始的                         index_list.append([sheet_name, row_num, col_num])         return index_list     except IOError as e:         print(f"文件读取错误 {file_path}: {e}")         return     def select_directory(entry_widget):     directory = filedialog.askdirectory()     if directory:         entry_widget.delete(0, tk.END)         entry_widget.insert(0, directory)     # 软件详情 def show_info():     info_text = ("Author: 灿\n"                  "编译时间版本: 2024-08-12/ V-0.01\n"                  "说明:读取指定目录下的文件,查找文件中包含的指定关键词,并输出到控制台。\n"                  "支持文件类型:.py, .txt, json, md, .c, .cpp, .h, .java, .js, .html, .css, .xml, .sql, .bat, .ps1, .sh, .yaml, .yml, .conf, .ini, .license, .xls, .xlsx")     messagebox.showinfo("软件信息", info_text)     def update_gui(button):     """在主线程中更新 GUI"""     button.config(state='normal')  # 任务完成后重新启用按钮     def start_task(process_button, path_entry, keyword_entry, check_var, check_btn):     """启动一个新线程来执行耗时任务，并禁用按钮"""     process_button.config(state='disabled')  # 在开始任务前禁用按钮     check_btn.config(state='disabled')     thread = threading.Thread(target=lambda: find_key(path_entry.get(), keyword_entry.get(), process_button, check_var, check_btn))     thread.start()     def create_gui():     root = tk.Tk()     root.title("文件查找工具")     root.geometry("600x500")     root.resizable(width=False, height=False)  # 不可改变窗口大小       # 设置窗口图标     # root.iconbitmap('../fish.ico')       # 路径选择部分     label = tk.Label(root, text="请选择文件夹路径:")     label.place(x=10, y=10, width=120, height=30)       # 路径     path_entry = tk.Entry(root, width=40)     path_entry.place(x=140, y=10, width=350, height=30)       browse_button = tk.Button(root, text="浏览", command=lambda: select_directory(path_entry))     browse_button.place(x=500, y=10, width=50, height=30)       label = tk.Label(root, text="关键字:")     label.place(x=10, y=50, width=120, height=30)       # 关键字输入框     keyword_entry = tk.Entry(root, width=40)     keyword_entry.place(x=140, y=50, width=200, height=30)       check_var = tk.IntVar()     check_btn = tk.Checkbutton(root, text="是否检索excel(勾选将会增加检索时间)", variable=check_var)     check_btn.place(x=350, y=50, width=240, height=30)       process_button = tk.Button(root, text="开始查找",                                command=lambda: start_task(process_button, path_entry, keyword_entry, check_var, check_btn))     process_button.place(x=250, y=90, width=80, height=30)       # 信息按钮     info_button = tk.Button(root, text="软件信息", command=show_info)     info_button.place(x=250, y=130, width=80, height=30)       # 控制台输出区域     console_frame = tk.Frame(root)     console_frame.place(x=10, y=170, width=580, height=320)       text_console = tk.Text(console_frame, wrap='word', height=20)     text_console.place(x=10, y=0, width=580, height=320)       # 将 sys.stdout 重定向到 text_console     redirect_text = RedirectText(text_console)     sys.stdout = redirect_text       root.mainloop()     if __name__ == '__main__':     create_gui()

hly2233

如果是当工具，推荐直接用everything

开创者

不太好用，估计文件多了，出结果后直接卡死了

LiCan857

开创者 发表于 2024-8-14 10:23
不太好用，估计文件多了，出结果后直接卡死了

尽量选择大概的文件夹，不要直接选根目录

52soft

我来测试一下

Pwaerm

window自带这样的功能呀

谢谢楼主分享，可以作为学习资料

chenyong2020

不知道具体使用情况咋样，但愿好用。

mytomsummer

进步空间很广阔!

long88888888

建议还是直接用主流成熟的软件，毕竟现在这种很多很稳定。