python字符串专题 以及Unicode应用小例子

''' Created on 2011-9-29 @author: xgzhao ''' # The repetition of sequence seq*expr seq = ['a', 'b', 'c', 'd'] print seq*2 #cut the last alphabet each time #range(3) returns a sequence [0, 1, 2] s = 'abcdefg' i = -1 for i in [None] + range(-1, -len(s), -1): print s[:i] print len(s) #built-in string import string print string.uppercase print string.lowercase print string.letters print string.digits #simple example:check names that must begin with a alphabet or '_', followed with #alphabets, '_', or digits alphas = string.letters + '_' nums = string.digits print 'Welcome to the Identifier checker 1.0' print 'Testees must be at least 2 chars long' myInput = raw_input('Identifier to test?') if(len(myInput)>1): if myInput[0] not in alphas: print '''invalid: first symbol must be alphabetic''' else: for otherchar in myInput[1:]: if otherchar not in alphas + nums: print '''invalid: remaining symbols must be alphanumeric''' break else: print 'Okay as an identifier' #+ and join m = ' '.join(('Spanish', 'Inquisition', 'made easy')) print m print "str".upper() print str(m).upper() #16 output print "%x" % 108 #template that uses ${}, be careful of '${}' from string import Template t = Template('There are ${howmany} ${lang} Quotation symbols') print t.substitute(lang="Python", howmany=3) #primary string print r'\n' #f = open(r'c:\windows\test\two', 'r') #in case that '\t' was interpreted as \t #max() and min() strMax = "abdc" strMin = "efda" print max(strMax) print min(strMin) #enumerate() eStr= 'foobar' for i, t in enumerate(s): print i, t z1Str = 'adf' z2Str = 'dfd' print zip(z1Str, z2Str) # ''' Created on 2011-9-29 @author: xgzhao ''' "An example of reading and writing Unicode strings" CODEC = 'utf-8' FILE = 'unicode.txt' hello_out = u"Hello World\n" bytes_out = hello_out.encode(CODEC) f = open(FILE, 'w') f.write(bytes_out) f.close() f = open(FILE, 'r') bytes_in = f.read() f.close() hello_in = bytes_in.decode(CODEC) print hello_in