import re
# match从头开始匹配
# 常规匹配
content = 4;fsadf5666asd"
ret = re.match("\w+", content)
print(len(content))
print(ret)
print(ret.group())
print(ret.span())
"""
12
<_sre.SRE_Match object; span=(0, 12), match='fsadf5666asd'>
fsadf5666asd
(0, 12)
"""
# 泛匹配
ret = re.match(".*", content)
print(ret)
# <_sre.SRE_Match object; span=(0, 8), match='fsadfasd'>
# 目标匹配
ret = re.match("[a-z]+(\d+)", content)
print(ret)
print(ret.group())
print(ret.group(0))
print(ret.group(1))
"""
<_sre.SRE_Match object; span=(0, 9), match='fsadf5666'>
fsadf5666
fsadf5666
5666
"""
# 贪婪匹配
ret = re.match(".*(\d+)", content)
print(ret)
print(ret.group(0))
print(ret.group(1))
"""
<_sre.SRE_Match object; span=(0, 9), match='fsadf5666'>
fsadf5666
6
"""
# 非贪婪匹配
ret = re.match(".*?(\d+)", content)
print(ret)
print(ret.group(0))
print(ret.group(1))
"""
<_sre.SRE_Match object; span=(0, 9), match='fsadf5666'>
fsadf5666
5666
"""
# 匹配模式
content = """sadfasd34345sdfa
sdfasdf"""
# 匹配换行符
ret = re.match(".*?(\d+).*", content, re.S)
print(ret)
print(ret.group(1))
"""
<_sre.SRE_Match object; span=(0, 24), match='sadfasd34345sdfa\nsdfasdf'>
34345
"""
# 转义
content = "sdfasdf$55.334"
# 匹配换行符
ret = re.match(".*?(\$\d+\.\d+)", content, re.S)
print(ret)
print(ret.group(1))
"""
<_sre.SRE_Match object; span=(0, 14), match='sdfasdf$55.334'>
$55.334
"""
# 总结:
# 尽量使用泛匹配,使用括号得到匹配目标,
# 尽量使用非贪婪模式,有换行符就用re.S
# search扫描整个字符串
# 能用search就不用match
content = "fsadf5666asd"
ret = re.match("\d+", content)
print(ret)
ret = re.search("\d+", content)
print(ret)
"""
None
<_sre.SRE_Match object; span=(5, 9), match='5666'>
"""
# findall 找到所有
content = "fsadf5666asd234"
ret = re.findall("\d+", content)
print(ret)
# ['5666', '234']
# sub 替换字符串
content = "fsadf5666asd234"
ret = re.sub("\d+", "", content)
print(ret)
# fsadfasd
# compile 编译成正则对象,便于复用
content = "fsadf5666asd234"
pattern = re.compile("\d+")
ret = pattern.findall(content)
print(ret)
# ['5666', '234']
发表评论