本文共 1494 字，大约阅读时间需要 4 分钟。

python_字符串处理&正则

String ManipulationString Object Methodsval = 'a,b,  guido'val.split(',')pieces = [x.strip() for x in val.split(',')]piecesfirst, second, third = piecesfirst + '::' + second + '::' + third'::'.join(pieces)'guido' in valval.index(',')val.find(':')val.index(':')val.count(',')val.replace(',', '::')val.replace(',', '')Regular Expressionsimport retext = "foo    bar\t baz  \tqux"re.split('\s+', text)regex = re.compile('\s+')regex.split(text)regex.findall(text)text = """Dave dave@google.comSteve steve@gmail.comRob rob@gmail.comRyan ryan@yahoo.com"""pattern = r'[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,4}'​# re.IGNORECASE makes the regex case-insensitiveregex = re.compile(pattern, flags=re.IGNORECASE)regex.findall(text)m = regex.search(text)mtext[m.start():m.end()]print(regex.match(text))print(regex.sub('REDACTED', text))pattern = r'([A-Z0-9._%+-]+)@([A-Z0-9.-]+)\.([A-Z]{2,4})'regex = re.compile(pattern, flags=re.IGNORECASE)m = regex.match('wesm@bright.net')m.groups()regex.findall(text)print(regex.sub(r'Username: \1, Domain: \2, Suffix: \3', text))Vectorized String Functions in pandasdata = {   'Dave': 'dave@google.com', 'Steve': 'steve@gmail.com',        'Rob': 'rob@gmail.com', 'Wes': np.nan}data = pd.Series(data)datadata.isnull()data.str.contains('gmail')patterndata.str.findall(pattern, flags=re.IGNORECASE)matches = data.str.match(pattern, flags=re.IGNORECASE)matchesmatches.str.get(1)matches.str[0]data.str[:5]pd.options.display.max_rows = PREVIOUS_MAX_ROWSConclusion