Python-File Processing

Source: Internet
Author: User
#!/usr/bin/env python# -*- coding:utf-8 -*-import sys, os, zipfile, tempfile, tarfile, fnmatch;def read_file(fileName):    '''    read file and print file line count    '''    f = open(fileName, 'r')    try:        line_list = f.readlines()        #read file each line without '\n'        #line_list = f.read().splitlines()        #line_list = f.read().split('\n')        #line_list = [L.rstrip('\n') for L in f.readlines()]        print len(line_list)    finally:        f.close()def read_file_by_chunks(fileName, chunksize=100):    file_object = open(fileName, 'rb')    while True:        chunk = file_object.read(chunksize)        if not chunk:            break;        yield chunk    file_object.close()def search_replace_text_infile(stext='', rtext='', input_file=sys.stdin, output_file=sys.stdout):    if isinstance(input_file, basestring):        ifile = open(input_file, 'r')    else:        ifile = input_file        if isinstance(output_file, basestring):        ofile = open(output_file, 'w')    else:        ofile = output_file        for s in ifile:        ofile.write(s.replace(stext, rtext))        if isinstance(ifile, basestring):        ifile.close()    if isinstance(ofile, basestring):        ofile.close()    def getline(filename, desired_line_number):    if desired_line_number < 1:        return ''        for current_line, line in enumerate(open(filename, 'rU')):        if desired_line_number-1 == current_line:            return line.rstrip('\n')    return ''def linecount_w(filename):    sys_cmd = 'wc -l ' + filename    return int(os.popen(sys_cmd).read().split()[0])    def linecount_1(filename):    return len(open(filename, 'r').readlines())    def linecount_2(filename):    linecount = -1    for linecount, line in enumerate(open(filename, 'r')):        pass    return linecount+1def linecount_3(filename):    linecount = 0    f = open(filename, 'r')    while True:        chunk = f.read(65535)        if not chunk:            break        linecount += chunk.count('\n')    return linecountdef words_of_file_in_firstline(filename, line_to_words=str.split):    firstline = getline(filename, 1)    for word in line_to_words(firstline):        yield word    def read_from_zip_file(filename):    zipf = zipfile.ZipFile(filename, 'r')    for fname in zipf.namelist():        bytes = zipf.read(fname)        print 'File %s in %s has %d bytes' % (fname, filename, len(bytes))    zipf.close()def just_for_fun():    #create a temp file with zip suffix    handle, tmpFileName = tempfile.mkstemp('.zip')    os.close(handle)        #open temp zip file    tmpZfile = zipfile.ZipFile(tmpFileName, 'w')    #write something to temp zip file    #paremeter 1:the name of the file in temp file    #parameter 2:The file contents is the string 'bytes'    tmpZfile.writestr('hello.py', 'def f(): \                                        return "hello world from " + __file__\n')    tmpZfile.close()    #set python module search path    #put temp zip file into first one    sys.path.insert(0, tmpFileName)    #import 'hello' module    import hello    #call hello module's f function    print hello.f()    os.unlink(tmpFileName)    try:    from cStringIO import StringIOexcept ImportError:    from StringIO import StringIOclass ZipString(zipfile.ZipFile):    '''    read zip file content from a string    '''    def __init__(self, dataString):        zipfile.ZipFile.__init__(self, StringIO(dataString))def make_tar(source_folder, dest_folder, compression='bz2'):    if compression:        file_ext = '.' + compression        compressionPara = ':' + compression    else:        file_ext = ''        compressionPara = ''        arcname = os.path.basename(source_folder)    dest_file = "%s.tar%s" % (arcname, file_ext)    dest_path = os.path.join(dest_folder, dest_file)        out = tarfile.TarFile.open(dest_path, 'w'+compressionPara)    out.add(source_folder, arcname)    out.close()    return dest_pathCHUNK_SIZE = 16 * 1024def adapte_file(fileObj):    '''    use file-like object to adapte a real file object    '''    if isinstance(fileObj, file):        return fileObj        tmpFileObj = tempfile.TemporaryFile()    while True:        data = fileObj.read(CHUNK_SIZE)        if not data:            break        tmpFileObj.write(data)        fileObj.close()    tmpFileObj.seek(0)    return tmpFileObjdef all_files(rootPath, patterns='*', single_level=False):    patterns = patterns.split(';')    for path, dirs, files in os.walk(rootPath):        files.sort()        for file in files:            for pattern in patterns:                #test whether filename matchs pattern                if fnmatch.fnmatch(file, pattern):                    yield os.path.join(path, file)                    break        if single_level:            breakdef swapextensions(rootPath, before, after):    if before[:1] != '.':        before = '.' + before    extLen = -len(before)    if after[:1] != '.':        after = '.' + after        swapCount = 0    for path, dirs, files in os.walk(rootPath):        for file in files:            if file[extLen:] == before:                oldfile = os.path.join(path, file)                newfile = oldfile[:extLen] + after                os.rename(oldfile, newfile)                swapCount += 1    return swapCountdef search_file(filename, searchPath, pathsep=os.pathsep):    for path in searchPath.split(pathsep):        candidate = os.path.join(path, filename)        if os.path.isfile(candidate):            return os.path.abspath(candidate)def addPythonSearchPath(newPath):    '''    add new path to module search path of python    return:    1  -  success    0  -  added path already on sys.path    -1 -  added path doesn't exist    '''    if not os.path.exists(newPath):        return -1    newPath = os.path.abspath(newPath)        if sys.platform == 'win32':        newPath = newPath.lower()    for searchPath in sys.path:        searchPath = os.path.abspath(searchPath)        if sys.platform == 'win32':            searchPath = searchPath.lower()        else:            if newPath in (searchPath, searchPath + os.sep):                return 0        sys.path.append(newPath)    return 1if __name__ == '__main__':    read_file('apache_log')        totalbytes = 0    for chunk in read_file_by_chunks('twittericon.png'):        totalbytes += len(chunk)    print 'twittericon.png file size is %d bytes' % totalbytes        #search_replace_text_infile('who', '***')        desired_line_number = 1    print 'The %d line in "apache_log" is "%s"' % (desired_line_number, getline('apache_log', desired_line_number))        import linecache    #also relate clearcache, checkcache    print 'The %d line in "sample.txt" is "%s"' % (desired_line_number, linecache.getline('sample.txt', desired_line_number).rstrip('\n'))        for f in linecount_w, linecount_1, linecount_2, linecount_3:        print f.__name__, f('apache_log')            wordlist = []    for word in words_of_file_in_firstline('apache_log'):        #revert each word        wordlist.append(word[::-1])    print ' '.join(wordlist)        read_from_zip_file('Archive.zip')        just_for_fun()        #print make_tar('./OCP', '.')        for path in all_files('./OCP', '*.py'):        print path            path = './OCP'    before = 'html'    after = 'htm'    print 'the count of swap extensions from %s to %s at path "%s" is %d' % (before, after, path, swapextensions(path, before, after))        searchpath = '/bin' + os.pathsep + '/usr/bin'    find_file = search_file('ls', searchpath)    if find_file:        print 'File "ls" found at %s.' % find_file    else:        print 'File "ls" not found.'        print 'origin search path:'    for x in sys.path:        print x    print "add new path to module search path of python, result:%d" % addPythonSearchPath('./OCP')    print 'New search path:'    for x in sys.path:        print x

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.