递归地遍历文件大小

Question

您好，我创建了一个小程序来获取脚本所在目录中所有文件的MD5 hash。

我的问题是当我生成文件的get_size() 时，我的filelist.md5.txt 中只有一行，而get_size() 似乎正在输出整个目录的总和而不是每个单独的文件大小。 如何在此脚本中输出单个文件的大小？

我在filelist.md5.txt 文件中得到这个输出：

#
#  GENERATE_FILELIST
#  (filename)    (filesize)    (md5)    (major_version)    (minor_version)
#

Test_2.txt                                   190         dea9fe052f1abf71bac7421c732b0475      ----           ----

但是我想得到这个输出：

#
#  GENERATE_FILELIST
#  (filename)    (filesize)    (md5)    (major_version)    (minor_version)
#

MD5.bat                                      filesize              b9a7c825517002e0da8e980c2c2c2cef      ----           ----
MD5.py                                       filesize              b61124e8bef473d377f59aa0964174ce      ----           ----
MD5test.bat                                  filesize              f29d68f9721c57d648164cae79dac71b      ----           ----
MD5test.py                                   filesize              a7a3c45ebe1aca82f57591c7fccd6cfc      ----           ----
MD5v1.bat                                    filesize              e5e7407117845a2413fe667fe7a2f681      ----           ----
MD5v1.py                                     filesize              55ab90b5a623548825a0b40406fcdde2      ----           ----
MD5v2.bat                                    filesize              e9e31aaa62f6f37572cf89a03860cb96      ----           ----
MD5v3.bat                                    filesize              559c0e9ed05fc9b4884c83bc3e04f8fd      ----           ----
MD5v3.py                                     filesize              d20a8841f3c37d28fd3b74847731e212      ----           ----
Test_2.txt                                   filesize              dea9fe052f1abf71bac7421c732b0475      ----           ----

到目前为止的代码：

import glob
import hashlib
import sys
import os


filenames = glob.glob('*.*')

# truncate the file to zero length before opening
f1 = open(os.path.expanduser(sys.path[0]) + '\\filelist.md5.txt', 'w')

#'a' will append the file, rather than write over whatever else you put in it like 'w' 
with open('filelist.md5.txt', 'a') as f:
        print >> f,''
        print >> f,'#'
        print >> f,'#  GENERATE_FILELIST'
        print >> f,'#  (filename)    (filesize)    (md5)    (major_version)    (minor_version)'
        print >> f,'#'
        print >> f,''
f.close()

# print to console
for filename in filenames:
    with open(filename, 'rb') as inputfile:
        data = inputfile.read()
        print '. -- ',filename, ' ---------- ', hashlib.md5(data).hexdigest()

# get the size of each file
def get_size(start_path = '.'):
    total_size = 0
    for dirpath, dirnames, filenames in os.walk(start_path):
        for fn in filenames:
            fp = os.path.join(dirpath, fn)
            total_size += os.path.getsize(fp)
            return total_size

    #'a' will append the file, rather than write over whatever else you put in it like 'w'
with open('filelist.md5.txt', 'a') as f:

        print >> f,'{:44}'.format(filename), get_size(),'       ', hashlib.md5(data).hexdigest(),'    ','----','         ','----'

f.close()

Answer 1

您的get_size() 被写入返回整个目录的大小，这不是您要查找的内容。

dir=r'specify\path\here'
with open('filelist.md5.txt', 'w') as fx:
    for f in os.listdir(dir):
        path = os.path.join(dir, f)
        if os.path.isfile(path):
            # specify anything else you want to write inside fx.write()
            fx.write(f + "\t\t" + str(os.path.getsize(path)) + "\n")

上面的代码用制表符分隔文件名和大小，并在单独的行中。

你在做with open('filelist.md5.txt', 'a') as f:时不必显式关闭

Answer 2

试试这个（对于 larg_file、none_ascci_format_files_names、whitout glob 模块和 error_handling 效果更好）：

import hashlib, os, hashlib, sys

your_target_folder = "."  # put your folder or just this "."


def get_size(filename):
    st = os.stat(filename)
    return str(st.st_size)


def get_minor_version(filename):
    # Your Code ...
    return "minor_version"


def get_major_version(filename):
    # Your Code ...
    return "major_version"


def get_md5(fname):
    hash_md5 = hashlib.md5()
    with open(fname, "rb") as f:
        for chunk in iter(lambda: f.read(2 ** 20), b""):
            hash_md5.update(chunk)
    return hash_md5.hexdigest()


# this function works for none ascii files names ( like chinese format )!!
def sys_out(out_data):
    try:
        print(out_data)
    except UnicodeEncodeError:
        if sys.version_info >= (3,):
            print(out_data.encode('utf8').decode(sys.stdout.encoding))
        else:
            print(out_data.encode('utf8'))


def make_beautiful_terminal_output(get_list):

    col_width = max(len(word) for word in get_list) + 3  # padding

    buffer_last = []
    for row in get_list:
        buffer_last.append("".join(word.ljust(col_width) for word in get_list))

    return buffer_last[0]


def print_header():

    header_tag = "(filename)                         (filesize)                         (md5)                             (major_version)                    (minor_version)\n"

    with open("filelist.md5.txt", "a") as my_header:
        my_header.write(header_tag)

    print(header_tag)


print_header()

for dirpath, _, filenames in os.walk(your_target_folder):

    for items in filenames:
        file_full_path = os.path.abspath(os.path.join(dirpath, items))

        try:

            my_last_data = [items, get_size(file_full_path), get_md5(file_full_path), get_major_version(file_full_path), get_minor_version(file_full_path)]

            terminal_output = make_beautiful_terminal_output(my_last_data)

            sys_out(terminal_output)

            re_buffer = terminal_output + "\n"
            with open("filelist.md5.txt", "a", encoding='utf-8') as my_save_file:
                my_save_file.write(re_buffer)

        except:
            sys_out("Error On " + str(file_full_path))