Python Cookbook (1) 文本
文本啊文本
1. 每个人都同意文本处理很有用。
2. 文本是一串字符,二进制是一串字节。
3. 基本文本操作:
1) 解析数据并将数据放入程序内部的结构中
2) 转成别的形式
3) 生成全新数据
4. 文本的来源
1) 文件
2) 网站
5. 文本应该属于应用程序层面,二进制属于底层
Example:
1 #!/usr/local/bin/python 2 import testlib 3 import string 4 5 #test book <<Python Cookbook>> 6 7 def test_string_template(): 8 new_style = string.Template('this is $thing') 9 print new_style.substitute({'thing':5}) 10 print new_style.substitute({'thing':'test'}) 11 # or 12 print new_style.substitute(thing=5) 13 print new_style.substitute(thing='test') 14 15 16 def test_string_unicode(): 17 unicodestr = u"Hello world" 18 print "unicodestr =", unicodestr 19 utf8str = unicodestr.encode("utf-8") 20 print "utf8str =", utf8str 21 asciistr = unicodestr.encode("ascii") 22 print "asciistr =", asciistr 23 plainstr = unicode(utf8str, "utf-8") 24 print "plainstr =", plainstr 25 26 def test_string(): 27 testlib.in_("test_string"); # from testlib write by self 28 str1="012345" 29 for s in str1 : 30 print s, #do_something_with(c) 31 print "\nstr1="+str1 32 print "str1[1:3] =", str1[1:3] 33 print "str1[0] =", str1[0] 34 print "str1[-2] =", str1[-2] 35 #list_of_lines = one_large_string.splitlines() 36 #one_large_string = '\n'.join(list_of_lines) 37 38 print "map(ord, 'ciao') =", map(ord, 'ciao') 39 40 print 'test center, ljust and rjust:' 41 print 'center'.center(20,'+') 42 print '|', 'hej'.ljust(20), '|', 'hej'.rjust(20), '|', 'hej'.center(20), '|' 43 44 print 'test lstrip, rstrip and strip:' 45 str2=' hej ' 46 print '|', str2.lstrip(), '|', str2.rstrip(), '|', str2.strip(), '|' 47 48 print 'test upper, lower, capitalize, title:' 49 str3='ONe Two tHree' 50 print "str3 =", str3 51 print "str3.upper =", str3.upper() 52 print "str3.lower =", str3.lower() 53 print "str3.capitalize =", str3.capitalize() 54 print "str3.title =", str3.title() 55 56 test_string_template() 57 test_string_unicode() 58 59 def testGo(): 60 test_string() 61 62 63 if __name__=="__main__" : 64 testGo()
PS:
testlib.py
1 #!/usr/local/bin/python 2 3 #test tools for all the test 4 5 def in_(arg): 6 print 7 print arg + " called"