mol2分子庫文件拆分成單個mol2文件

    利用Python將.mol2文件格式的分子庫拆分成單個.mol2格式的文件，以便從分子庫中眾多的化合物進行拆分，有利於逐個分析所提取的化合物。拆分主要的思想如下：

    1.用戶選擇分子庫文件所在的目錄以及選擇將拆分文件所存儲的目錄

    2.讀取分子庫文件所有內容

    3.依照一定的拆分規律，將分子庫文件逐個拆分並寫入新的文件

    主要依照以上思路即可實現將.mol2分子庫文件進行拆分，廢話不多說，直接看干貨：

import os
from tkinter import filedialog
# 拆分文件
def divide_file(read_fold, write_fold):
    all_files = []
    for files in os.walk(read_fold):
        all_files = files[2]
    for file in all_files:
        file_path = read_fold + '/' + file
        with open(file_path, 'r') as mol2_file:
            contents = mol2_file.readlines()
            contents.append('@<tripos>MOLECULE')
            write_file(contents, write_fold, file)

# 寫入文件
def write_file(article, write_fold, file_name):
    file_name = file_name[:-5]
    file_path = write_fold + '/' + file_name
    if not os.path.exists(file_path):
        os.makedirs(file_path)
        print(file_path, "創建成功")
    else:
        print(file_path, "目錄已存在")
    temp_article = []
    molecule_count = 0
    for line in article:
        if not line.startswith('@<tripos>MOLECULE'):
            temp_article.append(line)
        elif line.startswith('@<tripos>MOLECULE'):
            molecule_count = molecule_count + 1
            if molecule_count == 1:
                temp_article.append(line)
            elif molecule_count == 2:
                path = file_path + '/' + temp_article[1].rstrip("\n")+'.mol2'
                with open(path, 'w') as new_file:
                    for new_line in temp_article:
                        new_file.write(new_line)
                temp_article.clear()
                temp_article.append('@<tripos>MOLECULE')
                molecule_count = 1

if __name__ == '__main__':
    # 讀取獲得的文件夾路徑
    read_fold = filedialog.askdirectory()
    # 讀取寫入文件夾的路徑
    write_fold = filedialog.askdirectory()
    divide_file(read_fold, write_fold)