python正则表达式
对我!正则表达式主要应用在爬虫上 然而后来我选择了xpath
(一)基础演示
import re
pattern1 = "cat"
pattern2 = "bird"
string = "dog runs to cat"
print(re.search(pattern1, string))
#result: <_sre.SRE_Match object; span=(12, 15), match='cat'>
print(re.search(pattern2, string)) # result:None
ptn = r"r[au]n" # 选择
print(re.search(ptn, "dog runs to cat"))
# result:<_sre.SRE_Match object; span=(4, 7), match='run'>
import re
print(re.search(r"r[A-Z]n", "dog runs to cat")) # result:None没有出现大写
print(re.search(r"r[a-z]n", "dog runs to cat"))
tmep=re.compile("r[a-z]n") #定义变量匹配
print(tmep.search("dog runs to cat"))
# result:<_sre.SRE_Match object; span=(4, 7), match='run'>
print(re.search(r"r[0-9]n", "dog r2ns to cat"))
# result:<_sre.SRE_Match object; span=(4, 7), match='r2n'>
print(re.search(r"r[0-9a-z]n", "dog runs to cat"))
# result:<_sre.SRE_Match object; span=(4, 7), match='run'>
(二)特殊匹配方式
\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
import re
# \d : decimal digit
print(re.search(r"r\dn", "run r4n"))
#result: <_sre.SRE_Match object; span=(4, 7), match='r4n'>
# \D : any non-decimal digit
print(re.search(r"r\Dn", "run r4n"))
#result: <_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"))
#result: <_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"))
#result: <_sre.SRE_Match object; span=(4, 7), match='r4n'>
# \w : [a-zA-Z0-9_]
print(re.search(r"r\wn", "r\nn r4n"))
#result: <_sre.SRE_Match object; span=(4, 7), match='r4n'>
# \W : opposite to \w
print(re.search(r"r\Wn", "r\nn r4n"))
#result: <_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", "dog runs to cat"))
#result: <_sre.SRE_Match object; span=(4, 8), match='runs'>
# \B : empty string (but not at the start or end of a word)
print(re.search(r"\B runs \B", "dog runs to cat"))
#result: <_sre.SRE_Match object; span=(8, 14), match=' runs '>
# \\ : match \
print(re.search(r"runs\\", "runs\ to me"))
#!通俗来讲取消转义
#result: <_sre.SRE_Match object; span=(0, 5), match='runs\\'>
# . : match anything (除 \n)
print(re.search(r"r.n", "r[ns to me"))
#result: <_sre.SRE_Match object; span=(0, 3), match='r[n'>
# ^ : match line beginning
print(re.search(r"^dog", "dog runs to cat"))
#!匹配句首可以将每句话先进行的分离 re.M
# <_sre.SRE_Match object; span=(0, 3), match='dog'>
# $ : match line ending
print(re.search(r"cat$", "dog runs to cat"))
#!匹配句首可以将每句话先进行的分离 re.M
#result: <_sre.SRE_Match object; span=(12, 15), match='cat'>
# ? : may or may not occur
print(re.search(r"Mon(day)?", "Monday"))
#result: <_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'>
(三)重复匹配
*
: 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
import re
# * : occur 0 or more times
print(re.search(r"ab*", "a"))
#result: <_sre.SRE_Match object; span=(0, 1), match='a'>
print(re.search(r"ab*", "abbbbb"))
#result: <_sre.SRE_Match object; span=(0, 6), match='abbbbb'>
# + : occur 1 or more times
print(re.search(r"ab+", "a"))
#result: None
print(re.search(r"ab+", "abbbbb"))
#result: <_sre.SRE_Match object; span=(0, 6), match='abbbbb'>
# {n, m} : occur n to m times
print(re.search(r"ab{2,10}", "a"))
#result: None
print(re.search(r"ab{2,10}", "abbbbb"))
#result: <_sre.SRE_Match object; span=(0, 6), match='abbbbb'>
(四)分组
import re
match = re.search(r"(\d+), Date: (.+)", "ID: 021523, Date: Feb/12/2017")
print(match.group()) #result: 021523, Date: Feb/12/2017
print(match.group(1)) #result: 021523
print(match.group(2)) #result: Date: Feb/12/2017
(五)findall 返回匹配的全部内容
import re
# findall
print(re.findall(r"r[ua]n", "run ran ren"))
#result: ['run', 'ran']
# | : or
print(re.findall(r"(run|ran)", "run ran ren"))
#result:['run', 'ran']
(六)replace
!我们还能通过正则表达式匹配上一些形式的字符串然后再替代掉这些字符串. 使用这种匹配 re.sub()
, 将会比 python 自带的 string.replace()
要灵活多变.
import re
print(re.sub(r"r[au]ns", "catches", "dog runs to cat"))
#result: dog catches to cat
(七)split
!Python 中有个字符串的分割功能, 比如想获取一句话中所有的单词. 比如 "a is b".split(" ")
, 这样它就会产生一个列表来保存所有单词.
import re
print(re.split(r"[,;\.]", "a;b,c.d;e"))
#result: ['a', 'b', 'c', 'd', 'e']