python--杂识--4--多格式文件合并

# merge.py
import os
import docx
import sys

file_type = ['.json', '.py', '.txt', '.docx', '.doc', '.md', '.html', '.css', '.js', '.data', '.java']


def get_all_path(rootDir, ):
    path_list = []
    all_list = os.listdir(rootDir)  # 列出文件夹下所有的目录与文件
    for i in all_list:
        com_path = os.path.join(rootDir, i)
        # print(com_path)
        if os.path.isfile(com_path):
            global file_type
            if '.' + i.split('.')[-1] in file_type:
                path_list.append(com_path)

        if os.path.isdir(com_path):
            path_list.extend(get_all_path(com_path))
            get_all_path(com_path)
    # print(path_list)
    return path_list


def readFile(path, fw):
    if "." + path.split("\\")[-1].split(".")[-1] != ".docx":
        f = open(path, "r", encoding='utf8')
        for line in f:
            line = line.rstrip()
            if line:
                line = line + "\n"
                fw.write(line)
                # para = doc_new.add_paragraph(line)
                # para_format = para.paragraph_format
                # para_format.space_fore =
                # print(line)
    else:
        f = docx.Document(path)
        for para in f.paragraphs:
            para = para.text.rstrip()
            if para:
                # doc_new.add_paragraph(para)
                para = para + '\n'
                fw.write(para)
                # print(para)


def docx_new(rootDir, newFile):
    doc_new = docx.Document()

    for path in get_all_path(rootDir):
        readFile(path, doc_new)
        # print("++UnicodeDecodeError++" * 5)
        # print(path)
        # print("++UnicodeDecodeError++" * 5)
    doc_new.save(newFile)


def txt_new(rootDir, newFile):
    with open(newFile, 'a', encoding='utf8') as fw:
        for path in get_all_path(rootDir):
            print(path)
            readFile(path, fw)


if __name__ == "__main__":
    rootDir = sys.argv[1]
    # rootDir = r"C:\Users\Administrator\Desktop\wordCloud软著\test"
    newFile = sys.argv[2]
    # newFile = r"C:\Users\Administrator\Desktop\wordCloud软著\test.txt"
    txt_new(rootDir, newFile)
# 进入到merge.py所在目录
(python3.6.6) E:\PycharmProject\多格式文件合并>python merge.py 所合并的多个文件所在绝对路径 新文件所在绝对路径
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值