Python爬虫常用的正则表达式学习

Python通过re模块提供对正则表达式的支持。

import re

 

字符串匹配

# matching string
p1 = "cat"
p2 = "dog"
string = "dog runs to bird"
print (p1 in string)  # True
print (p2 in string)  # False

 

正则寻找配对

# regular expression
p1 = "cat"
p2 = "bird"
string = "dog runs to cat"
print(re.search(p1, string))  # <_sre.SRE_Match object; span=(12, 15), match='cat'>
print(re.search(p2, string))  # None

 

匹配多种可能  使用[]

# multiple patterns ("run" or "ran")
ptn = r"r[au]n"       # start with "r" means raw string
print(re.search(ptn, "dog runs to cat"))    # <_sre.SRE_Match object; span=(4, 7), match='run'>

 

匹配更多种可能

# continue
print(re.search(r"r[A-Z]n", "dog runs to cat"))     # None
print(re.search(r"r[a-z]n", "dog runs to cat"))     # <_sre.SRE_Match object; span=(4, 7), match='run'>
print(re.search(r"r[0-9]n", "dog r2ns to cat"))     # <_sre.SRE_Match object; span=(4, 7), match='r2n'>
print(re.search(r"r[0-9a-z]n", "dog runs to cat"))  # <_sre.SRE_Match object; span=(4, 7), match='run'>

 

特殊种类匹配

数字

# \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'>

空格

# \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'>

所有字母数字和"_"

# \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'>

空白字符

# \b : empty string (only at the start or end of the word)
print(re.search(r"\bruns\b", "dog runs to cat"))    # <_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"))  # <_sre.SRE_Match object; span=(8, 14), match=' runs '>

特殊字符（反斜杠）

# \\ : 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'>

句首句尾

# ^ : match line beginning
print(re.search(r"^dog", "dog runs to cat"))        # <_sre.SRE_Match object; span=(0, 3), match='dog'>
# $ : match line ending
print(re.search(r"cat$", "dog runs to cat"))        # <_sre.SRE_Match object; span=(12, 15), match='cat'>

是否

# ? : 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'>

多行匹配

# multi-line
string = """
dog runs to cat.
I run to dog.
"""
print(re.search(r"^I", string))                     # None
print(re.search(r"^I", string, flags=re.M))         # <_sre.SRE_Match object; span=(18, 19), match='I'>
                                       #M表示multiline

0或多次

# * : occur 0 or more times
print(re.search(r"ab*", "a"))                       # <_sre.SRE_Match object; span=(0, 1), match='a'>
print(re.search(r"ab*", "abbbbb"))                  # <_sre.SRE_Match object; span=(0, 6), match='abbbbb'>

1或多次

# + : occur 1 or more times
print(re.search(r"ab+", "a"))                       # None
print(re.search(r"ab+", "abbbbb"))                  # <_sre.SRE_Match object; span=(0, 6), match='abbbbb'>

可选次数

# {n, m} : occur n to m times
print(re.search(r"ab{2,10}", "a"))                  # None
print(re.search(r"ab{2,10}", "abbbbb"))             # <_sre.SRE_Match object; span=(0, 6), match='abbbbb'>

group组

match = re.search(r"(\d+), Date: (.+)", "ID: 021523, Date: Feb/12/2017")
print(match.group())                                # 021523, Date: Feb/12/2017
print(match.group(1))                               # 021523
print(match.group(2))                               # Date: Feb/12/2017

match = re.search(r"(?P<id>\d+), Date: (?P<date>.+)", "ID: 021523, Date: Feb/12/2017")
print(match.group('id'))                            # 021523
print(match.group('date'))                          # Date: Feb/12/2017

 

 

找到全部匹配

# findall
print(re.findall(r"r[ua]n", "run ran ren"))         # ['run', 'ran']
# | : or
print(re.findall(r"(run|ran)", "run ran ren"))      # ['run', 'ran']

 

替换

# re.sub() replace
print(re.sub(r"r[au]ns", "catches", "dog runs to cat"))     # dog catches to cat

 

分裂

# re.split()
print(re.split(r"[,;\.]", "a;b,c.d;e"))             # ['a', 'b', 'c', 'd', 'e']

 

compile

# compiled_re = re.compile(r"r[ua]n")
print(compiled_re.search("dog ran to cat")) # <_sre.SRE_Match object; span=(4, 7), match='ran'>

 

以上来源于学习视频：https://www.youtube.com/watch?v=l1MAW1z641E