python3字符串与文本处理
每个程序都回涉及到文本处理，如拆分字符串、搜索、替换、词法分析等。许多任务都可以通过内建的字符串方法来轻松解决，但更复杂的操作就需要正则表达式来解决。
1、针对任意多的分隔符拆分字符串
In [1]: line = 'asdf fjdk; afed, fjek,asdf, foo' #使用正则模块 In [2]: import re #使用正则split方法可以匹配多分割符 In [3]: re.split(r'[;,\s]\s*',line) Out[3]: ['asdf', 'fjdk', 'afed', 'fjek', 'asdf', 'foo'] #使用捕获组分割会将匹配的文本也包含在最终结果中 In [4]: re.split(r'(;|,|\s)\s*',line) Out[4]: ['asdf', ' ', 'fjdk', ';', 'afed', ',', 'fjek', ',', 'asdf', ',', 'foo'] #如果不想在结果中看到分隔符，可以受用?:的形式使用非捕获组 In [5]: re.split(r'(?:,|;|\s)\s*',line) Out[5]: ['asdf', 'fjdk', 'afed', 'fjek', 'asdf', 'foo']
2、在字符串的开头或结尾处做文本匹配
In [6]: url = 'https://www.baidu.com' #检查字符串的结尾，匹配则返回True In [7]: url.endswith('.com') Out[7]: True In [8]: url.endswith('.cn') Out[8]: False #检查字符串的开头，匹配则返回true In [10]: url.startswith('https:') Out[10]: True In [11]: url.startswith('http:') Out[11]: False In [1]: import os In [2]: filenames = os.listdir('.') In [3]: filenames Out[3]: ['.tcshrc', '.bash_logout', '.mysql_history', 'Python-3.7.0.tgz', '.bash_history', '.cache', 'anaconda-ks.cfg', '.ipython', '.cshrc', '.bashrc', '.viminfo', 'Python-3.7.0', 'mysql-boost-8.0.12.tar.gz', 'heapq_queue.py', 'mysql-8.0.12', '.bash_profile'] #应用匹配开头字符串过滤 In [4]: [i for i in filenames if i.startswith('.')] Out[4]: ['.tcshrc', '.bash_logout', '.mysql_history', '.bash_history', '.cache', '.ipython', '.cshrc', '.bashrc', '.viminfo', '.bash_profile'] #多个结果匹配时使用元组集合 In [5]: [i for i in filenames if i.endswith(('.py','.gz','.tgz'))] Out[5]: ['Python-3.7.0.tgz', 'mysql-boost-8.0.12.tar.gz', 'heapq_queue.py'] #判断目录中是否有.py结尾的文件 In [6]: any(i.endswith('.py') for i in filenames) Out[6]: True #应用列子解析网页或文本内容 from urllib.request import urlopen def read_date(name): if name.startswith(('http:','https:','ftp:')): return urlopen(name).read().decode() else: with open(name) as f: return f.read() result = read_date('test.txt') print(result) #也可以使用正则匹配 In [9]: import re In [10]: re.match('http:|https:|ftp:','https://www.baidu.com') Out[10]: <re.Match object; span=(0, 6), match='https:'>
3、利用shell通配符做字符串匹配
#利用fnmatch模块中的fnmatch和fnmatchcase函数匹配文本 In [12]: from fnmatch import fnmatch,fnmatchcase In [13]: fnmatch('foo.txt','*.txt') Out[13]: True In [14]: fnmatch('foo.txt','?oo.txt') Out[14]: True In [15]: names = ['dat01.csv','dat99.csv','config.ini','foo.py'] In [18]: [i for i in names if fnmatch(i,'dat[0-9]*.csv')] Out[18]: ['dat01.csv', 'dat99.csv'] #对于Windows操作系统时使用fnmatch函数时，匹配它不区分大小写，这时我们可以使用fnmatchcase函数来代替，它完全按照提供的字符串来匹配 In [2]: fnmatch('foo.txt','*.TXT') Out[2]: True In [3]: fnmatchcase('foo.txt','*.TXT') Out[3]: False #推倒式过滤文件名的字符串 In [20]: addresses = [ ...: '5412 N CLARK ST', ...: '1060 W ADDISON ST', ...: '1039 W GRANVILLE AVE', ...: '2122 N CLARK ST', ...: '4802 N BROADWAY', ...: ] In [21]: [i for i in addresses if fnmatch(i,'*ST')] Out[21]: ['5412 N CLARK ST', '1060 W ADDISON ST', '2122 N CLARK ST'] In [22]: [i for i in addresses if fnmatch(i,'*CLARK*')] Out[22]: ['5412 N CLARK ST', '2122 N CLARK ST']
4、文本模式的匹配和查找
对于简单的文字匹配我们只需要使用基本的字符串方法str.find()、str.endswith()、str.startswith()，对于更复杂的匹配就需要使用正则表达式模块re来匹配了
In [23]: text1 = 'today is 10/19/2018.Pycon starts 3/13/2019.' In [24]: import re In [25]: re.match(r'\d+/\d+/\d+',text1) In [28]: re.findall(r'\d+/\d+/\d+',text1) Out[28]: ['10/19/2018', '3/13/2019'] In [29]: text2 = '11/20/2018' In [30]: re.match(r'\d+/\d+/\d+',text2) Out[30]: <re.Match object; span=(0, 10), match='11/20/2018'> In [31]: result = re.match(r'(\d+)/(\d+)/(\d+)',text2) In [32]: result.groups() Out[32]: ('11', '20', '2018') In [33]: result.group(0) Out[33]: '11/20/2018' In [34]: result.group(1) Out[34]: '11' In [35]: result.group(2) Out[35]: '20' In [36]: result.group(3) Out[36]: '2018' #分组取出所有的日期并按格式输出 In [39]: text1 = 'today is 10/19/2018.Pycon starts 3/13/2019.' In [40]: for month,day,year in re.findall(r'(\d+)/(\d+)/(\d+)',text1): ...: print('{}-{}-{}'.format(year,month,day)) ...: 2018-10-19 2019-3-13 #如果文本数据比较大可以使用finditer()方法，以迭代器的方法匹配 In [43]: text1 = 'today is 10/19/2018.Pycon starts 3/13/2019.' In [44]: for i in re.finditer(r'(\d+)/(\d+)/(\d+)',text1): ...: print(i.groups()) ...: ('10', '19', '2018') ('3', '13', '2019')
5、查找和替换文本
对于简单的文本模式，可以使用str.replace()方法即可
In [45]: text = 'abcabcabcabc' In [46]: text.replace('a','ee') Out[46]: 'eebceebceebceebc'
针对更为复杂的匹配，可以使用re模块中的sub()方法
In [47]: text3 = 'today is 10/19/2018. pycon starts 3/13/2013.' In [49]: re.sub(r'(\d+)/(\d+)/(\d+)',r'\3-\1-\2',text3) Out[49]: 'today is 2018-10-19. pycon starts 2013-3-13.'
更为复杂的例子，如把日期换成字符格式
In [54]: text3 = 'today is 10/19/2018. pycon starts 3/13/2013.' In [55]: from calendar import month_abbr In [56]: def change_date(m): ...: mon_name = month_abbr[int(m.group(1))] ...: return '{} {} {}'.format(m.group(2),mon_name,m.group(3)) ...: ...: In [57]: re.sub(r'(\d+)/(\d+)/(\d+)',change_date,text3) Out[57]: 'today is 19 Oct 2018. pycon starts 13 Mar 2013.' #subn()可以返回完成了多少次替换 In [58]: re.subn(r'(\d+)/(\d+)/(\d+)',change_date,text3) Out[58]: ('today is 19 Oct 2018. pycon starts 13 Mar 2013.', 2)
6、以不区分大小写的方式对文本做查找和替换
要进行不分区大小写的文本操作时，可以使用re模块进程操作时都要加上re.IGNORECASE标记
In [60]: text = 'UPPER PYTHON,lower python, mixed Python' In [61]: re.findall('python',text,flags=re.IGNORECASE) Out[61]: ['PYTHON', 'python', 'Python']
import re def matchcase(word): def replace(m): text = m.group() if text.isupper(): return word.upper() elif text.islower(): return word.lower() elif text[0].isupper(): return word.capitalize() else: return word return replace #保持原字符大小写或首字母大写替换实例 text = 'UPPER PYTHON,lower python,Mixed Python' print(re.sub('python',matchcase('snake'),text,flags=re.IGNORECASE))
7、最短匹配的正则表达式
str_pat = re.compile(r'\"(.*)\"') text1 = 'computer says "no."' str_pat.findall(text1) Out[18]: ['no.'] text2 = 'computer says "no." phone says "yes."' str_pat.findall(text2) #在使用.*贪婪匹配时它将匹配尽可能多的匹配项 Out[20]: ['no." phone says "yes.'] str_pat = re.compile(r'\"(.*?)\"') #只需要在多匹配后加上?号，就会以最少的匹配模式进行匹配 str_pat.findall(text2) Out[22]: ['no.', 'yes.']
8、多行模式的正则表达式
comment = re.compile(r'python(.*?)end') text1 = 'python is ver good \n so so end' comment.findall(text1) #.*匹配不到换行符 Out[27]: [] comment = re.compile(r'python(.*?)end',flags=re.DOTALL) #加上标记re.DOTALL将匹配所有的字符包括换行符 comment.findall(text1) Out[29]: [' is ver good \n so so '] comment = re.compile(r'python((?:.|\n)*?)end') #（?:.|\n)会指定一个非捕获组，它只做匹配但不捕获结果，也不分配组号 comment.findall(text1) Out[31]: [' is ver good \n so so ']
9、将Unicode文本统一表示为规范形式是
s1 = 'spicy\u00f1o' #它使用的是（U+00F1)全组成的（fully composed) s2 = 'spicy\u0303o' #它使用的是（U+0303)拉丁字母组合而成 s1 == s2 #所以字符比较是不相等的 Out[35]: False s1 Out[36]: 'spicyño' s2 Out[37]: 'spicỹo'
10、从字符串中去掉不需要的字符
#strip()方法用来从字符串的开始和结尾处去掉字符，lstrip()和rstrip()分别从左或右开始执行去除字符操作，默认去除的是空格符，也可以指定 In [21]: s = ' hello world \n' In [22]: s.strip() Out[22]: 'hello world' In [23]: s.lstrip() Out[23]: 'hello world \n' In [24]: s.rstrip() Out[24]: ' hello world' In [25]: t = '-----hello=====' In [26]: t.lstrip('-') #指定去除字符 Out[26]: 'hello=====' In [27]: t.strip('-=') #可以指定多个字符 Out[27]: 'hello' #使用上面的方法不能去除中间的字符，要去除中间的字符可以使用replace()方法或正则表达式替换 In [28]: s.replace(' ','') Out[28]: 'helloworld\n' In [29]: re.sub('\s+', '',s) Out[29]: 'helloworld'
11、对齐文本字符串
#对应基本的字符串对齐，可以使用字符串方法ljust()、rjust()和center(),分别表示左对齐，右对齐和居中对齐，它还可以填充字符可选参数 In [31]: text = 'hello world' In [32]: text.ljust(30) Out[32]: 'hello world ' In [33]: text.rjust(30) Out[33]: ' hello world' In [34]: text.center(30) Out[34]: ' hello world ' In [35]: text.center(30,'=') Out[35]: '=========hello world==========' #format()函数也可以用来完成对齐任务，需要做的就是合理利用'<'、'>'和'^'字符分别表示左对齐、右对齐和居中对齐，并提供一个期望的宽度值，如果想指定填充字符，可以在对齐符前指定： In [36]: format(text,'>20') Out[36]: ' hello world' In [37]: format(text,'<20') Out[37]: 'hello world ' In [38]: format(text,'^20') Out[38]: ' hello world ' In [39]: format(text,'=^20') Out[39]: '====hello world=====' In [40]: format(text,'=^20s') Out[40]: '====hello world=====' In [41]: format(text,'*^20s') Out[41]: '****hello world*****' #当格式化多个值时，也可以使用format()方法 In [42]: '{:>10s}{:<10s}'.format('hello','world') Out[42]: ' helloworld ' In [43]: '{:#>10s} {:&<10s}'.format('hello','world') Out[43]: '#####hello world&&&&&'
12、字符串链接及合并
#合并的字符串在一个序列或可迭代对象中，最好的方法是使用join()方法 In [44]: data = ['I','like','is','python'] In [45]: ' '.join(data) Out[45]: 'I like is python' In [46]: ','.join(data) Out[46]: 'I,like,is,python' #利用生成器表达式转换后链接字符串会更高效 In [47]: ','.join(str(d) for d in data) Out[47]: 'I,like,is,python'
13、给字符串中的变量名做插值处理
#在字符串中给变量赋值一般常见的处理方式是使用format()方法 In [5]: str_variable = "{name} today {num} old year" In [6]: str_variable.format(name='zhang',num=20) Out[6]: 'zhang today 20 old year' #另一种方式是使用format_map()和vars()联合匹配当前环境中的变量名 In [7]: name = 'python' In [8]: num = 18 In [9]: str_variable.format_map(vars()) Out[9]: 'python today 18 old year' #vars()还可用在类实例上 In [10]: class info: ...: def __init__(self,name,num): ...: self.name = name ...: self.num = num ...: In [11]: a = info('shell',23) In [12]: str_variable.format_map(vars(a)) Out[12]: 'shell today 23 old year' #对于传递参数不够时将会抛出异常，可以定义一个带有__missing__()方法的字典类来处理 In [13]: class safesub(dict): ...: def __missing__(self,key): ...: return '{' + key + '}' ...: In [14]: del num In [15]: str_variable.format_map(safesub(vars())) Out[15]: 'python today {num} old year'
14、以固定的列数重新格式化文本
#textwrap模块可以以多种方式重新格式化字符串： >>> import textwrap >>> s = "look into eyes, look into my eyes, the eyes,the eyes, \ ... the eyes, not around the eyes, don't look around the eyes, \ ... look into my eyes, you're under." >>> print(textwrap.fill(s,70) ... ) look into eyes, look into my eyes, the eyes,the eyes, the eyes, not around the eyes, don't look around the eyes, look into my eyes, you're under. >>> print(textwrap.fill(s,40)) look into eyes, look into my eyes, the eyes,the eyes, the eyes, not around the eyes, don't look around the eyes, look into my eyes, you're under. >>> print(textwrap.fill(s,40,initial_indent=' ')) look into eyes, look into my eyes, the eyes,the eyes, the eyes, not around the eyes, don't look around the eyes, look into my eyes, you're under. >>> print(textwrap.fill(s,40,subsequent_indent=' ')) look into eyes, look into my eyes, the eyes,the eyes, the eyes, not around the eyes, don't look around the eyes, look into my eyes, you're under. #可以通过os.get_terminal_size()来获取终端的尺寸大小 >>> import os >>> print(textwrap.fill(s,os.get_terminal_size().columns)) look into eyes, look into my eyes, the eyes,the eyes, the eyes, not around the eyes, don't look around the eyes, look into my eyes, you're under. >>> print(os.get_terminal_size()) os.terminal_size(columns=105, lines=32)
15、在文本中处理HTML和XML实体
#使用html.escape()函数来替换HTML标签为文本样式 In [1]: s = 'Elements are written aa "<tag>text</tag>".' In [2]: import html In [3]: s Out[3]: 'Elements are written aa "<tag>text</tag>".' In [4]: html.escape(s) Out[4]: 'Elements are written aa "<tag>text</tag>".' #忽略quote标签 In [5]: html.escape(s,quote=False) Out[5]: 'Elements are written aa "<tag>text</tag>".' #处理ASCII文本 In [6]: s1 = 'Spicy "Jalapeño".' In [7]: from html.parser import HTMLParser In [9]: p = HTMLParser() In [11]: p.unescape(s1) Out[11]: 'Spicy "Jalapeño".' #生成ASCII文本 In [12]: s2 = p.unescape(s1) In [13]: s2.encode('ascii',errors='xmlcharrefreplace') Out[13]: b'Spicy "Jalapeño".' #处理XML实体 In [14]: s3 = 'the prompt is >>>' In [15]: from xml.sax.saxutils import unescape In [16]: unescape(s3) Out[16]: 'the prompt is >>>'
16、文本分词
#从左到右将字符串解析为标记流（stream of tokens） In [17]: text = 'foo = 23 + 42 * 10' In [18]: tokens= [('NAME','foo'),('EQ','='),('NUM','23'),('PLUS','+'),('NUM','42'),('TIMES','*'),('NUM',' ...: 10')] In [19]: import re #使用正则表达式 InIn [20]: NAME = r'(?P<NAME>[a-zA_][a-zA-Z_0-9]*)' In [21]: NUM = r'(?P<NUM>\d+)' In [22]: PLUS = r'(?P<PLUS>\+)' In [23]: TIMES = r'(?P<TIMES>\*)' In [24]: EQ = r'(?P<EQ>=)' In [25]: WS = r'(?P<WS>\s+)' In [26]: master_pat = re.compile('|'.join([NAME,NUM,PLUS,TIMES,EQ,WS])) #使用模式对象的scanner()方法来完成分词操作 In [27]: scanner = master_pat.scanner('foo = 42') #在给定的文本中重复调用match()方法，一次匹配一个模式，下面是匹配过程 In [28]: scanner.match() Out[28]: <re.Match object; span=(0, 3), match='foo'> In [29]: _.lastgroup,_.group() Out[29]: ('NAME', 'foo') In [30]: scanner.match() Out[30]: <re.Match object; span=(3, 4), match=' '> In [31]: _.lastgroup,_.group() Out[31]: ('WS', ' ') In [32]: scanner.match() Out[32]: <re.Match object; span=(4, 5), match='='> In [33]: _.lastgroup,_.group() Out[33]: ('EQ', '=') In [34]: scanner.match() Out[34]: <re.Match object; span=(5, 6), match=' '> In [35]: _.lastgroup,_.group() Out[35]: ('WS', ' ') In [36]: scanner.match() Out[36]: <re.Match object; span=(6, 8), match='42'> In [37]: _.lastgroup,_.group() Out[37]: ('NUM', '42') #通过生成器函数来转化为代码的形式 In [40]: from collections import namedtuple In [41]: token = namedtuple('token',['type','value']) In [42]: def generate_tokens(pat,text): ...: scanner = pat.scanner(text) ...: for m in iter(scanner.match,None): ...: yield token(m.lastgroup,m.group()) ...: In [43]: for tok in generate_tokens(master_pat,'foo = 42'): ...: print(tok) ...: token(type='NAME', value='foo') token(type='WS', value=' ') token(type='EQ', value='=') token(type='WS', value=' ') token(type='NUM', value='42') #过滤空格标记 In [45]: tokens = (tok for tok in generate_tokens(master_pat,text) if tok.type != 'WS') In [46]: for tok in tokens:print(tok) token(type='NAME', value='foo') token(type='EQ', value='=') token(type='NUM', value='23') token(type='PLUS', value='+') token(type='NUM', value='42') token(type='TIMES', value='*') token(type='NUM', value='10')
17、编写一个简单的递归下降解析器
import re import collections #定义文本分词变量 NUM = r'(?P<NUM>\d+)' PLUS = r'(?P<PLUS>\+)' MINUS = r'(?P<MINUS>-)' TIMES = r'(?P<TIMES>\*)' DIVIDE = r'(?P<DIVIDE>/)' LPAREN = r'(?P<LPAREN>\()' RPAREN = r'(?P<RPAREN>\))' WS = r'(?P<WS>\s+)' master_pat = re.compile('|'.join([NUM,PLUS,MINUS,TIMES,DIVIDE,LPAREN,RPAREN,WS])) Token = collections.namedtuple('Token',['type','value']) #过滤文本分词 def generate_tokens(text): scanner = master_pat.scanner(text) for m in iter(scanner.match,None): tok = Token(m.lastgroup,m.group()) if tok.type != 'WS': yield tok class ExpressionEvaluator: def parse(self,text): self.tokens = generate_tokens(text) self.nexttok = None self.tok = None self._advance() return self.expr() def _advance(self): self.tok,self.nexttok = self.nexttok,next(self.tokens,None) def _accept(self,toktype): if self.nexttok and self.nexttok.type == toktype: self._advance() return True else: return False def _expect(self,toktype): if not self._accept(toktype): raise SyntaxError('Expected' + toktype) def expr(self): exprval = self.term() while self._accept('PLUS') or self._accept('MINUS'): op = self.tok.type right = self.term() if op == 'PLUS': exprval += right elif op == 'MINUS': exprval -= right return exprval def term(self): termval = self.factor() while self._accept('TIMES') or self._accept('DIVIDE'): op = self.tok.type right = self.factor() if op == 'TIMES': termval *= right elif op == 'DIVIDE': termval /= right return termval def factor(self): if self._accept('NUM'): return int(self.tok.value) elif self._accept('LPAREN'): exprval = self.expr() self._expect('RPAREN') return exprval else: raise SyntaxError('Expected NUMBER or LPAREN') if __name__ == '__main__': e = ExpressionEvaluator() print(e.parse('2')) print(e.parse('2 + 3')) print(e.parse('2 + 3 * 4')) print(e.parse('2 + (3 + 4) * 5'))
18、在字节串上进行文本操作
In [2]: data = b'hello world' In [3]: data Out[3]: b'hello world' #切片 In [4]: data[0:5] Out[4]: b'hello' #分隔 In [6]: data.split() Out[6]: [b'hello', b'world'] #替换 In [7]: data.replace(b'hello',b'python') Out[7]: b'python world' #在返回单个切片时将返回ASCII字节表对应的位置 In [8]: data[0] Out[8]: 104
