Python语言自动化处理文件夹中的文件

0 功能

将文件夹中的PDF文件，转化成markdwon格式的链接语法，即[]()格式，输入自己的github存放地址以及文件夹路径即可。

1 代码

# _*_ coding=utf-8 _*_
'''

这个程序用来整理文件夹中的PDF文件，将其转化成Markdown格式的链接，即[]()的形式
'''
import os,re

def get_book_lists():
    root_dir = r"J:\电子书"
    dir_tree = os.walk(root_dir)
    sub_dir = dir_tree.__next__()[1]
    pdf_list = []
    for sub in sub_dir:
        for _sub in os.walk(root_dir + "\\" + str(sub)):
            _book_list = _sub[-1]
            if _sub[1] is not None:
                for book in _book_list:
                    if ".pdf" in book:
                        pdf_list.append(book)
    return pdf_list

def get_url_links(book_list):
    urls = []
    url = "https://jums.club/images/article/pdf"
    for book in book_list:
        book = re.sub(" |:|：|，|,|（|）|\(|\)","_",book)
        book = re.sub("《|》","",book)
        _url = "[{}]({}/{})    ".format(book[:-4], url, book)
        urls.append(_url)

    return urls

def show_markdown_format(book_list,urls,type_name):
    dict = {}
    for i in type_name:
        dict[i] = []
    # print(dict)
    dict["other"] = []
    used = []
    for each_url in urls:
        for each_name in type_name:
            if each_name in each_url:
                _ = dict[each_name]
                _.append(each_url)
                used.append(each_url)
    print(len(urls))
    print(len(used))
    for each in type_name:
        _list = dict[each]
        print(each + ":   ")
        for _url in _list:
            print("- {}".format(_url))
    print("other:    ")
    for i in urls:
        if i not in used:
            print("- {}".format(i))


def main():
    book_list = get_book_lists()
    urls = get_url_links(book_list)
    type_name = ["Python","SQL","TCP-IP详解","Kali_Linux无线网络渗透测试","HTTP","Shell","Linux"]
    show_markdown_format(book_list,urls,type_name)


if __name__ == '__main__':
    main()