同学之间常常要共享精彩电影的,一般电影的大小都是300多M,我有个128M的小MP3,总向同学借大U盘也不是那么回事,有时就得耐着性子用winrar分割压缩,传到自己电脑里再解压缩合并成一个电影文件。用的次数多了大家就都会知道winrar对音乐和电影这些多媒体格式的文件压缩率基本为0,也就是说,即使在那浪费时间浪费计算机资源(非常浪费CPU)最后的结果也只是完成了分割与合并文件的作用,大量的计算做的都是无用功。
用Pythong写了个简单的文件分割与合并的程序,这样自己的小容量MP3用起来就方便了,而且因为不需要压缩与解压缩的过程,可以大量节省我的耐心。
file.py
01 | import sys |
02 | from os.path import exists |
03 | fileCount = 0 |
04 | |
05 | def splitFile(fileName, partSize=1): |
06 | # 1024 * 1024 = 1048576 |
07 | length = partSize * 1048576 |
08 | f1 = open(fileName, "rb") |
09 | while True: |
10 | content = f1.read(length) |
11 | if content == "": |
12 | break |
13 | newFile = distFile(fileName) |
14 | f2 = open(newFile, "wb") |
15 | f2.write(content) |
16 | f2.close() |
17 | f1.close() |
18 | print 'split file complete!' |
19 | |
20 | |
21 | |
22 | def distFile(sourceFile): |
23 | global fileCount |
24 | fileCount = fileCount + 1 |
25 | extPos = sourceFile.rfind('.') |
26 | if extPos > 0: |
27 | return sourceFile + '.part' + str(fileCount) |
28 | else: # extPos == -1 |
29 | print 'File type? Can not split!' |
30 | sys.exit(1) |
31 | |
32 | def combine(filename): |
33 | count = 0 |
34 | extPos = filename.find('.part') |
35 | if extPos > 0: |
36 | file = filename[:extPos] |
37 | f1 = open(file, "wb") |
38 | while True: |
39 | count = count + 1 |
40 | partFile = file + '.part' + str(count) |
41 | if not exists(partFile): |
42 | break |
43 | else: |
44 | f2 = open(partFile, "rb") |
45 | content = f2.read() |
46 | f2.close() |
47 | f1.write(content) |
48 | f1.close() |
49 | print 'combine file complete!' |
50 | |
51 | else: |
52 | print 'File type? Can not combine!' |
53 | |
54 | def usage(): |
55 | print '''usage is "file.py s[c] filename" or "file.py s[c] filename size(M) /n 's' -- 'split', 'c' -- 'combine" ''' |
56 | |
57 | |
58 | if __name__ == "__main__": |
59 | if len(sys.argv) !=3 and len(sys.argv) !=4: |
60 | usage() |
61 | sys.exit(1) |
62 | if sys.argv[1] == 's': |
63 | if len(sys.argv) == 3: |
64 | splitFile(sys.argv[2]) |
65 | elif len(sys.argv) == 4 and int(sys.argv[3]) > 0: |
66 | splitFile(sys.argv[2], int(sys.argv[3])) |
67 | else: |
68 | usage() |
69 | sys.exit(1) |
70 | |
71 | elif sys.argv[1] =='c': |
72 | if len(sys.argv) == 3: |
73 | combine(sys.argv[2]) |
74 | else: |
75 | usage() |
76 | else: |
77 | usage() |
使用方法:
分割:file.py s 文件路径 每块的文件大小(不填默认为1M)
合并:file.py c 任意部分文件路径
因为用winrar解压缩时双击任何一个部分压缩文件都会成功解压该完成文件而不必只能点击part1,所以这个程序也写成给出任何一个部分文件名都可以合并处完整的文件,这样就可以方便的在命令行随便用鼠标拖入一个分割后的部分文件就可以了。估计winrar的.rar 格式文件里面是包含了压缩信息和共有多少个部分文件的,我的这种自己用的小程序就得人工判断分割成了几部分然后全部copy了。
再用py2exe转换成.exe文件装入U盘就可以了,以后到谁的机器上都可以用了。
转自: http://lulinbest.blog.sohu.com/62764871.html
用Python进行文件操作是比较简单的,在Python中file是内置类型之一,内置的函数open、file都可以创建file对象,创建好之后就可以对其进行读写等操作。
近几天看Python Programing 3rd ,觉得书很不错。
文件分割的原理很简单:以二进制形式打开文件流,按照指定的大小读取,然后写入新文件。
文件合并的原理正好相反。
下面的代码摘自PP3rd里面。
split_file.py
01 | #!/usr/bin/python |
02 | ########################################################################## |
03 | # split a file into a set of parts; join.py puts them back together; |
04 | # this is a customizable version of the standard unix split command-line |
05 | # utility; because it is written in Python, it also works on Windows and |
06 | # can be easily modified; because it exports a function, its logic can |
07 | # also be imported and reused in other applications; |
08 | ########################################################################## |
09 | |
10 | import sys, os |
11 | kilobytes = 1024 |
12 | megabytes = kilobytes * 1000 |
13 | chunksize = int(1.4 * megabytes) # default: roughly a floppy |
14 | |
15 | def split(fromfile, todir, chunksize=chunksize): |
16 | if not os.path.exists(todir): # caller handles errors |
17 | os.mkdir(todir) # make dir, read/write parts |
18 | else: |
19 | for fname in os.listdir(todir): # delete any existing files |
20 | os.remove(os.path.join(todir, fname)) |
21 | partnum = 0 |
22 | input = open(fromfile, 'rb') # use binary mode on Windows |
23 | while 1: # eof=empty string from read |
24 | chunk = input.read(chunksize) # get next part <= chunksize |
25 | if not chunk: break |
26 | partnum = partnum+1 |
27 | filename = os.path.join(todir, ('part%04d' % partnum)) |
28 | fileobj = open(filename, 'wb') |
29 | fileobj.write(chunk) |
30 | fileobj.close() # or simply open().write() |
31 | input.close() |
32 | assert partnum <= 9999 # join sort fails if 5 digits |
33 | return partnum |
34 | |
35 | if __name__ == '__main__': |
36 | if len(sys.argv) == 2 and sys.argv[1] == '-help': |
37 | print 'Use: split.py [file-to-split target-dir [chunksize]]' |
38 | else: |
39 | if len(sys.argv) < 3: |
40 | interactive = 1 |
41 | fromfile = raw_input('File to be split? ') # input if clicked |
42 | todir = raw_input('Directory to store part files? ') |
43 | else: |
44 | interactive = 0 |
45 | fromfile, todir = sys.argv[1:3] # args in cmdline |
46 | if len(sys.argv) == 4: chunksize = int(sys.argv[3]) |
47 | absfrom, absto = map(os.path.abspath, [fromfile, todir]) |
48 | print 'Splitting', absfrom, 'to', absto, 'by', chunksize |
49 | |
50 | try: |
51 | parts = split(fromfile, todir, chunksize) |
52 | except: |
53 | print 'Error during split:' |
54 | print sys.exc_info()[0], sys.exc_info()[1] |
55 | else: |
56 | print 'Split finished:', parts, 'parts are in', absto |
57 | if interactive: raw_input('Press Enter key') # pause if clicked |
join_file.py
01 | #!/usr/bin/python |
02 | ########################################################################## |
03 | # join all part files in a dir created by split.py, to recreate file. |
04 | # This is roughly like a 'cat fromdir/* > tofile' command on unix, but is |
05 | # more portable and configurable, and exports the join operation as a |
06 | # reusable function. Relies on sort order of file names: must be same |
07 | # length. Could extend split/join to popup Tkinter file selectors. |
08 | ########################################################################## |
09 | |
10 | import os, sys |
11 | readsize = 1024 |
12 | |
13 | def join(fromdir, tofile): |
14 | output = open(tofile, 'wb') |
15 | parts = os.listdir(fromdir) |
16 | parts.sort() |
17 | for filename in parts: |
18 | filepath = os.path.join(fromdir, filename) |
19 | fileobj = open(filepath, 'rb') |
20 | while 1: |
21 | filebytes = fileobj.read(readsize) |
22 | if not filebytes: break |
23 | output.write(filebytes) |
24 | fileobj.close() |
25 | output.close() |
26 | |
27 | if __name__ == '__main__': |
28 | if len(sys.argv) == 2 and sys.argv[1] == '-help': |
29 | print 'Use: join.py [from-dir-name to-file-name]' |
30 | else: |
31 | if len(sys.argv) != 3: |
32 | interactive = 1 |
33 | fromdir = raw_input('Directory containing part files? ') |
34 | tofile = raw_input('Name of file to be recreated? ') |
35 | else: |
36 | interactive = 0 |
37 | fromdir, tofile = sys.argv[1:] |
38 | absfrom, absto = map(os.path.abspath, [fromdir, tofile]) |
39 | print 'Joining', absfrom, 'to make', absto |
40 | |
41 | try: |
42 | join(fromdir, tofile) |
43 | except: |
44 | print 'Error joining files:' |
45 | print sys.exc_info()[0], sys.exc_info()[1] |
46 | else: |
47 | print 'Join complete: see', absto |
48 | if interactive: raw_input('Press Enter key') # pause if clicked |
以上代码在window下面测试成功,可以分割文件文件已经任何二进制文件。
转自: http://blog.csdn.net/foyuan/archive/2007/08/01/1720600.aspx
--End--
1842

被折叠的 条评论
为什么被折叠?



