python的字符串操作通过2部分的方法函数基本上就可以解决所有的字符串操作需求:
- python的字符串属性函数
- python的string模块
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- 字符串属性函数
系统版本:CentOS release 6.2 (Final)2.6.32-220.el6.x86_64
python版本:Python 2.6.6
字符串属性方法
字符串格式输出对齐
- 1.>>> str=‘stRINg lEArn‘
-
- 2.>>>
-
- 3.>>> str.center(20)
-
- 4.‘ stRINg lEArn ‘
-
- 5.>>>
-
- 6.>>> str.ljust(20)
-
- 7.‘stRINg lEArn ‘
-
- 8.>>>
-
- 9.>>> str.rjust(20)
-
- 10.‘ stRINg lEArn‘
-
- 11.>>>
-
- 12.>>> str.zfill(20)
-
- 13.‘00000000stRINg lEArn‘
大小写转换
- 1.>>> str=‘stRINg lEArn‘
-
- 2.>>>
-
- 3.>>> str.upper()
-
- 4.‘STRING LEARN‘
-
- 5.>>>
-
- 6.>>> str.lower()
-
- 7.‘string learn‘
-
- 8.>>>
-
- 9.>>> str.capitalize()
-
- 10.‘String learn‘
-
- 11.>>>
-
- 12.>>> str.swapcase()
-
- 13.‘STrinG LeaRN‘
-
- 14.>>>
-
- 15.>>> str.title()
-
- 16.‘String Learn‘
字符串条件判断
- 1.>>> str=‘0123‘
-
- 2.>>> str.isalnum()
- 3.True
-
- 4.>>> str.isdigit()
- 5.True
-
- 6.
-
- 7.>>> str=‘abcd‘
-
- 8.>>> str.isalnum()
-
- 9.True
-
- 10.>>> str.isalpha()
- 11.True
-
- 12.>>> str.islower()
- 13.True
-
- 14.
-
- 15.>>> str=‘abcd0123‘
-
- 16.>>> str.islower()
-
- 17.True
-
- 18.>>> str.isalnum()
-
- 19.True
-
- 20.
-
- 21.>>> str=‘ ‘
-
- 22.>>> str.isspace()
- 23.True
-
- 24.>>> str=‘ABC‘
-
- 25.>>> str.isupper()
- 26.True
-
- 27.>>> str=‘Abb Acc‘
-
- 28.>>> str.istitle()
- 29.True
- 30.
-
- 31.>>> str=‘string learn‘
- 32.>>> str.startswith(‘str‘)
- 33.True
- 34.>>> str.endswith(‘arn‘)
- 35.True
字符串搜索定位与替换
- 1.>>> str=‘string lEARn‘
-
- 2.>>>
-
- 3.>>> str.find(‘a‘)
-
- 4.-1
-
- 5.>>> str.find(‘n‘)
-
- 6.4
-
- 7.>>> str.rfind(‘n‘)
-
- 8.11
-
- 9.>>>
-
- 10.>>> str.index(‘a‘)
-
- 11.Traceback (most recent call last):
-
- 12. File "<stdin>", line 1, in <module>
-
- 13.ValueError: substring not found
-
- 14.>>> str.index(‘n‘)
-
- 15.4
-
- 16.>>> str.rindex(‘n‘)
-
- 17.11
-
- 18.>>>
-
- 19.>>> str.count(‘a‘)
-
- 20.0
-
- 21.>>> str.count(‘n‘)
-
- 22.2
-
- 23.>>>
-
- 24.>>> str.replace(‘EAR‘,‘ear‘)
-
- 25.‘string learn‘
-
- 26.>>> str.replace(‘n‘,‘N‘)
-
- 27.‘striNg lEARN‘
-
- 28.>>> str.replace(‘n‘,‘N‘,1)
-
- 29.‘striNg lEARn‘
-
- 30.>>>
-
- 31.>>>
-
- 32.>>> str.strip(‘n‘)
-
- 33.‘string lEAR‘
-
- 34.>>> str.lstrip(‘n‘)
-
- 35.‘string lEARn‘
-
- 36.>>> str.rstrip(‘n‘)
-
- 37.‘string lEAR‘
-
- 38.>>>
-
- 39.>>> str=‘ tab‘
-
- 40.>>> str.expandtabs()
-
- 41.‘ tab‘
-
- 42.>>> str.expandtabs(2)
-
- 43.‘ tab‘
字符串编码与解码
- 1.>>> str=‘字符串学习‘
-
- 2.>>> str
-
- 3.‘xe5xadx97xe7xacxa6xe4xb8xb2xe5xadxa6xe4xb9xa0‘
-
- 4.>>>
-
- 5.>>> str.decode(‘utf-8‘)
-
- 6.u‘u5b57u7b26u4e32u5b66u4e60‘
-
- 7.
-
- 8.>>> str.decode(‘utf-8‘).encode(‘gbk‘)
-
- 9.‘xd7xd6xb7xfbxb4xaexd1xa7xcfxb0‘
-
- 10.>>> str.decode(‘utf-8‘).encode(‘utf-8‘)
-
- 11.‘xe5xadx97xe7xacxa6xe4xb8xb2xe5xadxa6xe4xb9xa0‘
字符串分割变换
- 1.>>> str=‘Learn string‘
-
- 2.>>> ‘-‘.join(str)
-
- 3.‘L-e-a-r-n- -s-t-r-i-n-g‘
-
- 4.>>> l1=[‘Learn‘,‘string‘]
-
- 5.>>> ‘-‘.join(l1)
-
- 6.‘Learn-string‘
-
- 7.>>>
-
- 8.>>> str.split(‘n‘)
-
- 9.[‘Lear‘, ‘ stri‘, ‘g‘]
-
- 10.>>> str.split(‘n‘,1)
-
- 11.[‘Lear‘, ‘ string‘]
-
- 12.>>> str.rsplit(‘n‘,1)
-
- 13.[‘Learn stri‘, ‘g‘]
-
- 14.>>>
-
- 15.>>> str.splitlines()
-
- 16.[‘Learn string‘]
-
- 17.>>>
-
- 18.>>> str.partition(‘n‘)
-
- 19.(‘Lear‘, ‘n‘, ‘ string‘)
-
- 20.>>> str.rpartition(‘n‘)
-
- 21.(‘Learn stri‘, ‘n‘, ‘g‘)
string模块源代码
- 1.
-
- 21.
-
- 22.
-
- 23.whitespace = ‘ tnrvf‘
-
- 24.lowercase = ‘abcdefghijklmnopqrstuvwxyz‘
-
- 25.uppercase = ‘ABCDEFGHIJKLMNOPQRSTUVWXYZ‘
-
- 26.letters = lowercase + uppercase
-
- 27.ascii_lowercase = lowercase
-
- 28.ascii_uppercase = uppercase
-
- 29.ascii_letters = ascii_lowercase + ascii_uppercase
-
- 30.digits = ‘0123456789‘
-
- 31.hexdigits = digits + ‘abcdef‘ + ‘ABCDEF‘
-
- 32.octdigits = ‘01234567‘
-
- 33.punctuation =
-
- 34.printable = digits + letters + punctuation + whitespace
-
- 35.
-
- 36.
-
- 37.
-
- 38.l = map(chr, xrange(256))
-
- 39._idmap = str(‘‘).join(l)
-
- 40.del l
-
- 41.
-
- 42.
-
- 43.
-
- 44.
-
- 45.def capwords(s, sep=None):
-
- 46.
-
- 56. return (sep or ‘ ‘).join(x.capitalize() for x in s.split(sep))
-
- 57.
-
- 58.
-
- 59.
-
- 60._idmapL = None
-
- 61.def maketrans(fromstr, tostr):
-
- 62.
-
- 69. if len(fromstr) != len(tostr):
-
- 70. raise ValueError, "maketrans arguments must have same length"
-
- 71. global _idmapL
-
- 72. if not _idmapL:
-
- 73. _idmapL = list(_idmap)
-
- 74. L = _idmapL[:]
-
- 75. fromstr = map(ord, fromstr)
-
- 76. for i in range(len(fromstr)):
-
- 77. L[fromstr[i]] = tostr[i]
-
- 78. return ‘‘.join(L)
-
- 79.
-
- 80.
-
- 81.
-
- 82.
-
- 83.import re as _re
-
- 84.
-
- 85.class _multimap:
-
- 86.
-
- 91. def __init__(self, primary, secondary):
-
- 92. self._primary = primary
-
- 93. self._secondary = secondary
-
- 94.
-
- 95. def __getitem__(self, key):
-
- 96. try:
-
- 97. return self._primary[key]
-
- 98. except KeyError:
-
- 99. return self._secondary[key]
-
- 100.
-
- 101.
-
- 102.class _TemplateMetaclass(type):
-
- 103. pattern = r
-
- 111.
-
- 112. def __init__(cls, name, bases, dct):
-
- 113. super(_TemplateMetaclass, cls).__init__(name, bases, dct)
-
- 114. if ‘pattern‘ in dct:
-
- 115. pattern = cls.pattern
-
- 116. else:
-
- 117. pattern = _TemplateMetaclass.pattern % {
-
- 118. ‘delim‘ : _re.escape(cls.delimiter),
-
- 119. ‘id‘ : cls.idpattern,
-
- 120. }
-
- 121. cls.pattern = _re.compile(pattern, _re.IGNORECASE | _re.VERBOSE)
-
- 122.
-
- 123.
-
- 124.class Template:
-
- 125.
-
- 126. __metaclass__ = _TemplateMetaclass
-
- 127.
-
- 128. delimiter = ‘$‘
-
- 129. idpattern = r‘[_a-z][_a-z0-9]*‘
-
- 130.
-
- 131. def __init__(self, template):
-
- 132. self.template = template
-
- 133.
-
- 134.
-
- 135.
-
- 136. def _invalid(self, mo):
-
- 137. i = mo.start(‘invalid‘)
-
- 138. lines = self.template[:i].splitlines(True)
-
- 139. if not lines:
-
- 140. colno = 1
-
- 141. lineno = 1
-
- 142. else:
-
- 143. colno = i - len(‘‘.join(lines[:-1]))
-
- 144. lineno = len(lines)
-
- 145. raise ValueError(‘Invalid placeholder in string: line %d, col %d‘ %
-
- 146. (lineno, colno))
-
- 147.
-
- 148. def substitute(self, *args, **kws):
-
- 149. if len(args) > 1:
-
- 150. raise TypeError(‘Too many positional arguments‘)
-
- 151. if not args:
-
- 152. mapping = kws
-
- 153. elif kws:
-
- 154. mapping = _multimap(kws, args[0])
-
- 155. else:
-
- 156. mapping = args[0]
-
- 157.
-
- 158. def convert(mo):
-
- 159.
-
- 160. named = mo.group(‘named‘) or mo.group(‘braced‘)
-
- 161. if named is not None:
-
- 162. val = mapping[named]
-
- 163.
-
- 164.
-
- 165. return ‘%s‘ % (val,)
-
- 166. if mo.group(‘escaped‘) is not None:
-
- 167. return self.delimiter
-
- 168. if mo.group(‘invalid‘) is not None:
-
- 169. self._invalid(mo)
-
- 170. raise ValueError(‘Unrecognized named group in pattern‘,
-
- 171. self.pattern)
-
- 172. return self.pattern.sub(convert, self.template)
-
- 173.
-
- 174. def safe_substitute(self, *args, **kws):
-
- 175. if len(args) > 1:
-
- 176. raise TypeError(‘Too many positional arguments‘)
-
- 177. if not args:
-
- 178. mapping = kws
-
- 179. elif kws:
-
- 180. mapping = _multimap(kws, args[0])
-
- 181. else:
-
- 182. mapping = args[0]
-
- 183.
-
- 184. def convert(mo):
-
- 185. named = mo.group(‘named‘)
-
- 186. if named is not None:
-
- 187. try:
-
- 188.
-
- 189.
-
- 190. return ‘%s‘ % (mapping[named],)
-
- 191. except KeyError:
-
- 192. return self.delimiter + named
-
- 193. braced = mo.group(‘braced‘)
-
- 194. if braced is not None:
-
- 195. try:
-
- 196. return ‘%s‘ % (mapping[braced],)
-
- 197. except KeyError:
-
- 198. return self.delimiter + ‘{‘ + braced + ‘}‘
-
- 199. if mo.group(‘escaped‘) is not None:
-
- 200. return self.delimiter
-
- 201. if mo.group(‘invalid‘) is not None:
-
- 202. return self.delimiter
-
- 203. raise ValueError(‘Unrecognized named group in pattern‘,
-
- 204. self.pattern)
-
- 205. return self.pattern.sub(convert, self.template)
-
- 206.
-
- 207.
-
- 208.
-
- 209.
-
- 210.
-
- 211.
-
- 212.
-
- 213.
-
- 214.index_error = ValueError
-
- 215.atoi_error = ValueError
-
- 216.atof_error = ValueError
-
- 217.atol_error = ValueError
-
- 218.
-
- 219.
-
- 220.def lower(s):
-
- 221.
-
- 226. return s.lower()
-
- 227.
-
- 228.
-
- 229.def upper(s):
-
- 230.
-
- 235. return s.upper()
-
- 236.
-
- 237.
-
- 238.def swapcase(s):
-
- 239.
-
- 245. return s.swapcase()
-
- 246.
-
- 247.
-
- 248.def strip(s, chars=None):
-
- 249.
-
- 257. return s.strip(chars)
-
- 258.
-
- 259.
-
- 260.def lstrip(s, chars=None):
-
- 261.
-
- 267. return s.lstrip(chars)
-
- 268.
-
- 269.
-
- 270.def rstrip(s, chars=None):
-
- 271.
-
- 277. return s.rstrip(chars)
-
- 278.
-
- 279.
-
- 280.
-
- 281.def split(s, sep=None, maxsplit=-1):
-
- 282.
-
- 292. return s.split(sep, maxsplit)
-
- 293.splitfields = split
-
- 294.
-
- 295.
-
- 296.def rsplit(s, sep=None, maxsplit=-1):
-
- 297.
-
- 305. return s.rsplit(sep, maxsplit)
-
- 306.
-
- 307.
-
- 308.def join(words, sep = ‘ ‘):
-
- 309.
-
- 318. return sep.join(words)
-
- 319.joinfields = join
-
- 320.
-
- 321.
-
- 322.def index(s, *args):
-
- 323.
-
- 328. return s.index(*args)
-
- 329.
-
- 330.
-
- 331.def rindex(s, *args):
-
- 332.
-
- 337. return s.rindex(*args)
-
- 338.
-
- 339.
-
- 340.def count(s, *args):
-
- 341.
-
- 348. return s.count(*args)
-
- 349.
-
- 350.
-
- 351.def find(s, *args):
-
- 352.
-
- 361. return s.find(*args)
-
- 362.
-
- 363.
-
- 364.def rfind(s, *args):
-
- 365.
-
- 374. return s.rfind(*args)
-
- 375.
-
- 376.
-
- 377._float = float
-
- 378._int = int
-
- 379._long = long
-
- 380.
-
- 381.
-
- 382.def atof(s):
-
- 383.
-
- 388. return _float(s)
-
- 389.
-
- 390.
-
- 391.
-
- 392.def atoi(s , base=10):
-
- 393.
-
- 403. return _int(s, base)
-
- 404.
-
- 405.
-
- 406.
-
- 407.def atol(s, base=10):
-
- 408.
-
- 419. return _long(s, base)
-
- 420.
-
- 421.
-
- 422.
-
- 423.def ljust(s, width, *args):
-
- 424.
-
- 431. return s.ljust(width, *args)
-
- 432.
-
- 433.
-
- 434.def rjust(s, width, *args):
-
- 435.
-
- 442. return s.rjust(width, *args)
-
- 443.
-
- 444.
-
- 445.def center(s, width, *args):
-
- 446.
-
- 453. return s.center(width, *args)
-
- 454.
-
- 455.
-
- 456.
-
- 457.
-
- 458.def zfill(x, width):
-
- 459.
-
- 465. if not isinstance(x, basestring):
-
- 466. x = repr(x)
-
- 467. return x.zfill(width)
-
- 468.
-
- 469.
-
- 470.
-
- 471.def expandtabs(s, tabsize=8):
-
- 472.
-
- 479. return s.expandtabs(tabsize)
-
- 480.
-
- 481.
-
- 482.def translate(s, table, deletions=""):
-
- 483.
-
- 492. if deletions or table is None:
-
- 493. return s.translate(table, deletions)
-
- 494. else:
-
- 495.
-
- 496.
-
- 497.
-
- 498. return s.translate(table + s[:0])
-
- 499.
-
- 500.
-
- 501.def capitalize(s):
-
- 502.
-
- 508. return s.capitalize()
-
- 509.
-
- 510.
-
- 511.def replace(s, old, new, maxsplit=-1):
-
- 512.
-
- 519. return s.replace(old, new, maxsplit)
-
- 520.
-
- 521.
-
- 522.
-
- 523.
-
- 524.
-
- 525.
-
- 526.
-
- 527.try:
-
- 528. from strop import maketrans, lowercase, uppercase, whitespace
-
- 529. letters = lowercase + uppercase
-
- 530.except ImportError:
-
- 531. pass
-
- 532.
-
- 533.
-
- 534.
-
- 535.
-
- 536.
-
- 537.
-
- 538.
-
- 539.
-
- 540.
-
- 541.
-
- 542.
-
- 543.class Formatter(object):
-
- 544. def format(self, format_string, *args, **kwargs):
-
- 545. return self.vformat(format_string, args, kwargs)
-
- 546.
-
- 547. def vformat(self, format_string, args, kwargs):
-
- 548. used_args = set()
-
- 549. result = self._vformat(format_string, args, kwargs, used_args, 2)
-
- 550. self.check_unused_args(used_args, args, kwargs)
-
- 551. return result
-
- 552.
-
- 553. def _vformat(self, format_string, args, kwargs, used_args, recursion_depth):
-
- 554. if recursion_depth < 0:
-
- 555. raise ValueError(‘Max string recursion exceeded‘)
-
- 556. result = []
-
- 557. for literal_text, field_name, format_spec, conversion in
-
- 558. self.parse(format_string):
-
- 559.
-
- 560.
-
- 561. if literal_text:
-
- 562. result.append(literal_text)
-
- 563.
-
- 564.
-
- 565. if field_name is not None:
-
- 566.
-
- 567.
-
- 568.
-
- 569.
-
- 570.
-
- 571. obj, arg_used = self.get_field(field_name, args, kwargs)
-
- 572. used_args.add(arg_used)
-
- 573.
-
- 574.
-
- 575. obj = self.convert_field(obj, conversion)
-
- 576.
-
- 577.
-
- 578. format_spec = self._vformat(format_spec, args, kwargs,
-
- 579. used_args, recursion_depth-1)
-
- 580.
-
- 581.
-
- 582. result.append(self.format_field(obj, format_spec))
-
- 583.
-
- 584. return ‘‘.join(result)
-
- 585.
-
- 586.
-
- 587. def get_value(self, key, args, kwargs):
-
- 588. if isinstance(key, (int, long)):
-
- 589. return args[key]
-
- 590. else:
-
- 591. return kwargs[key]
-
- 592.
-
- 593.
-
- 594. def check_unused_args(self, used_args, args, kwargs):
-
- 595. pass
-
- 596.
-
- 597.
-
- 598. def format_field(self, value, format_spec):
-
- 599. return format(value, format_spec)
-
- 600.
-
- 601.
-
- 602. def convert_field(self, value, conversion):
-
- 603.
-
- 604. if conversion == ‘r‘:
-
- 605. return repr(value)
-
- 606. elif conversion == ‘s‘:
-
- 607. return str(value)
-
- 608. elif conversion is None:
-
- 609. return value
-
- 610. raise ValueError("Unknown converion specifier {0!s}".format(conversion))
-
- 611.
-
- 612.
-
- 613.
-
- 614.
-
- 615.
-
- 616.
-
- 617.
-
- 618.
-
- 619.
-
- 620. def parse(self, format_string):
-
- 621. return format_string._formatter_parser()
-
- 622.
-
- 623.
-
- 624.
-
- 625.
-
- 626.
-
- 627.
-
- 628.
-
- 629. def get_field(self, field_name, args, kwargs):
-
- 630. first, rest = field_name._formatter_field_name_split()
-
- 631.
-
- 632. obj = self.get_value(first, args, kwargs)
-
- 633.
-
- 634.
-
- 635.
-
- 636. for is_attr, i in rest:
-
- 637. if is_attr:
-
- 638. obj = getattr(obj, i)
-
- 639. else:
-
- 640. obj = obj[i]
-
- 641.
-
- 642. return obj, first