正则表达式（1） python
- import re
import re x1='I' x2='she' x='I will meet you.' print(re.search(x1,x)) #在x中寻找x1 print(re.search(x2,x))
print(re.search(r"m[A-Z]t", "I met you")) print(re.search(r"m[a-z]t", "I meet you")) print(re.search(r"m[0-9]t", "I m0t you")) print(re.search(r"m[0-9a-z]t", "I met you"))
- \d : 任何数字
- \D : 不是数字
- \s : 任何 white space, 如 [\t\n\r\f\v]
- \S : 不是 white space
- \w : 任何大小写字母, 数字和 “” [a-zA-Z0-9]
- \W : 不是 \w
- \b : 空白字符 (只在某个字的开头或结尾)
- \B : 空白字符 (不在某个字的开头或结尾)
- \\ : 匹配 \
- . : 匹配任何字符 (除了 \n)
- ^ : 匹配开头
- $ : 匹配结尾
- ? : 前面的字符可有可无
# \d : decimal digit print(re.search(r"r\dn", "run r4n")) # <_sre.SRE_Match object; span=(4, 7), match='r4n'> # \D : any non-decimal digit print(re.search(r"r\Dn", "run r4n")) # <_sre.SRE_Match object; span=(0, 3), match='run'> # \s : any white space [\t\n\r\f\v] print(re.search(r"r\sn", "r\nn r4n")) # <_sre.SRE_Match object; span=(0, 3), match='r\nn'> # \S : opposite to \s, any non-white space print(re.search(r"r\Sn", "r\nn r4n")) # <_sre.SRE_Match object; span=(4, 7), match='r4n'> # \w : [a-zA-Z0-9_] print(re.search(r"r\wn", "r\nn r4n")) # <_sre.SRE_Match object; span=(4, 7), match='r4n'> # \W : opposite to \w print(re.search(r"r\Wn", "r\nn r4n")) # <_sre.SRE_Match object; span=(0, 3), match='r\nn'> # \b : empty string (only at the start or end of the word) print(re.search(r"\bruns\b", "dogruns runs to cat runs")) # <_sre.SRE_Match object; span=(8, 12), match='runs'> # \B : empty string (but not at the start or end of a word) print(re.search(r"\Bruns\B", "dogrunso runs to cat runs")) #<_sre.SRE_Match object; span=(3, 7), match='runs'> print(re.search(r"\B runs \B", "dog runs to cat")) # <_sre.SRE_Match object; span=(8, 14), match=' runs '> # \\ : match \ print(re.search(r"runs\\", "runs\ to me")) # <_sre.SRE_Match object; span=(0, 5), match='runs\\'> # . : match anything (except \n) print(re.search(r"r.n", "r[ns to me")) # <_sre.SRE_Match object; span=(0, 3), match='r[n'> # ^ : match line beginning print(re.search(r"^dog", "dog runs to cat")) # <_sre.SRE_Match object; span=(0, 3), match='dog'> print(re.search(r"^dog", "ccdog runs to cat")) # None # $ : match line ending print(re.search(r"cat$", "dog runs to cat")) # <_sre.SRE_Match object; span=(12, 15), match='cat'> print(re.search(r"cat$", "dog runs to cat.")) # None # ? : may or may not occur print(re.search(r"Mon(day)?", "Monday")) # <_sre.SRE_Match object; span=(0, 6), match='Monday'> print(re.search(r"Mon(day)?", "Mon")) # <_sre.SRE_Match object; span=(0, 3), match='Mon'>
- 匹配非第一行的字符串：flags=re.MULTILINE或者flags=re.M
*: 重复零次或多次+: 重复一次或多次{n, m}: 重复 n 至 m 次{n}: 重复 n 次
string=""" People ran to square. SShhhhout and cheer. She was also very exited. """ print(re.search(r"^Sh*",string,flags=re.MULTILINE)) #<_sre.SRE_Match object; span=(23, 24), match='S'> print(re.search(r"^Sh+",string,flags=re.MULTILINE)) #<_sre.SRE_Match object; span=(44, 46), match='Sh'>
- match.group() ：如下例，匹配有2个group，分别对应re.search中打括号的2个地方，即"(\d+)"和"(.+)"
match = re.search(r"(\d+), Date: (.+)", "ID: 021523, Date: Feb/12/2017") print(match.group()) print(match.group(1)) print(match.group(2))
- match.group() ：
?P<名字>给这个组定义了一个名字. 然后就能用这个名字找到这个组的内容.
match = re.search(r"(?P<id>\d+), Date: (?P<date>.+)", "ID: 021523, Date: Feb/12/2017") print(match.group('id')) print(match.group('date'))
- re.findall()：上述都只匹配第一个出现的项，findall可以匹配所有出现的项：
# findall print(re.findall(r"me+t", "met meet meat")) # | : or print(re.findall(r"(met|meet)", "met meet meat"))
- re.sub()：功能是先匹配，再替换，比string.replace()更灵活：
print(re.sub(r"^[Nn]ongfu", "Wahaha", "Nongfu Spring"))
- re.split()：分割，注意分割的结果不包括分割项：
print(re.split(r"[,;\.]", "a;b,c.d;e")) print(re.split(r"[sS][h]", "Shout,cheer,she,sheet"))
- re.compile()：使之可以被重复使用：
compiled=re.compile(r"m[e]+t") print(compiled.search("I will meet you.")) print(compiled.search("I met you yesterday."))
- 小抄：
- 下一篇： 爬虫入门(1)
- 参考：莫烦python
