Regex (正则表达式)

import re

re.match(pattern, s)      # 从开头匹配
re.search(pattern, s)     # 搜索第一个匹配
re.findall(pattern, s)    # 找出全部匹配，返回 list
re.sub(pattern, repl, s)  # 替换
re.fullmatch(pattern, s)  # 完全匹配整个字符串

bool(re.fullmatch(r"\d+", s))

bool(re.fullmatch(r"(00|60)\d+", s))

bool(re.fullmatch(r"[^@]+@[^@]+\.[^@]+", email))

re.findall(r"\d+", text)

re.findall(r"\d{4}-\d{2}-\d{2}", text)

re.findall(r"\b\d{6}\b", text)

m = re.search(r"(\d+)-(\d+)", "123-456")
m.group(1) # "123"
m.group(2) # "456"
m.groups() # ("123", "456")

m = re.search(r"(?P<code>\d{6})-(?P<name>\w+)", "600001-ABC")
m.group("code")
m.group("name")

re.sub(r"cat", "dog", text)

re.sub(r"\d+", "[NUM]", text)

def repl(m):
    return str(int(m.group()) * 2)

re.sub(r"\d+", repl, "1 2 3")
# "2 4 6"

pat = re.compile(r"\d{6}")
pat.findall(text)

re.findall(r"<.*>", "<a><b>")
# ['<a><b>']

re.findall(r"<.*?>", "<a><b>")
# ['<a>', '<b>']

re.findall(r"(?<=￥)\d+", "价格￥199元")

re.findall(r".+(?!\.jpg)$", filename)

re.findall(r"<div.*?</div>", html, flags=re.S)

is_stock = bool(re.fullmatch(r"(00|60)\d+", stock_code))
has_bad_title = bool(re.search(title_exclude_regex, title))

pattern = re.compile(r"(^|\.)(datetime_date)(__|$)")
pattern.sub(r"\1datetime::date\3", source)