Python3 正則表達式基礎

此文爲學習筆記

正則表達式

re.match

re.match 嘗試從字符串的起始位置匹配一個模式,如果不是起始位置匹配成功的話, match()就返回none

re.match(pattern, string, flags=0)

最常規的匹配

import re

content = 'Hello 123 4567 World_This is a Regex Demo'
print(len(content))
result = re.match('^Hello\s\d\d\d\s\d{4}\s\w{10}.*Demo$', content)
print(result)
print(result.group())
print(result.span())

泛匹配

import re

content = 'Hello 123 4567 World_This is a Regex Demo'
result = re.match('^Hello.*Demo$', content)
print(result)
print(result.group())
print(result.span())

匹配目標

import re

content = 'Hello 1234567 World_This is a Regex Demo'
result = re.match('^Hello\s(\d+)\sWorld.*Demo$', content)
print(result)
print(result.group(1))
print(result.span())

貪婪匹配

import re

content = 'Hello 1234567 World_This is a Regex Demo'
result = re.match('^He.*(\d+).*Demo$', content)
print(result)
print(result.group(1))

非貪婪匹配

import re

content = 'Hello 1234567 World_This is a Regex Demo'
result = re.match('^He.*?(\d+).*Demo$', content)
print(result)
print(result.group(1))

匹配模式

import re

#  re.S 匹配所有字符包括換行符
content = '''Hello 1234567 World_This
is a Regex Demo
'''
result = re.match('^He.*?(\d+).*?Demo$', content, re.S)
print(result)
print(result.group(1))

轉義

import re
# 直接匹配特殊字符,無法匹配
content = 'price is $5.00'
result = re.match('price is $5.00', content)
print(result)

import re

# 使用 \ 轉義, 可以匹配
content = 'price is $5.00'
result = re.match('price is \$5\.00', content)
print(result)

總結: 儘量使用泛匹配,使用括號得到匹配目標,儘量使用非貪婪模式,有換行符就用 re.S

re.search

re.search 掃描整個字符串並返回第一個成功的匹配

import re

content = 'Extra strings Hello 1234567 World_This is a Regex Demo Extra strings'
result = re.search('Hello.*?(\d+).*?Demo', content)
print(result)
print(result.group(1))

總結: 爲匹配方便,能用search就不用match

匹配練習

import re

html = '''<div id="songs-list">
    <h2 class="title">經典老歌</h2>
    <p class="introduction">
      經典老歌列表
    </p>
    <ul id="list" class="list-group">
        <li data-view="2">一路上有你</li>
        <li data-view="7">
            <a href="/2.mp3" singer="任賢齊">滄海一聲笑</a>
        </li>
        <li data-view="4" class="active">
            <a href="/3.mp3" singer="齊秦">往事隨風</a>
        </li>
        <li data-view="6"><a href="/4.mp3" singer="beyond">光輝歲月</a></li>
        <li data-view="5"><a href="/5.mp3" singer="陳慧琳">筆記本</a></li>
        <li data-view="5">
            <a href="/6.mp3" singer="鄧麗君"><i class="fa fa-user"></i>但願人長久</a>
        </li>
    </ul>
</div>'''

result = re.search('<li.*?active.*?singer="(.*?)">(.*?)</a>', html, re.S)
if result:
    print(result.group(1), result.group(2))

import re

html = '''<div id="songs-list">
    <h2 class="title">經典老歌</h2>
    <p class="introduction">
      經典老歌列表
    </p>
    <ul id="list" class="list-group">
        <li data-view="2">一路上有你</li>
        <li data-view="7">
            <a href="/2.mp3" singer="任賢齊">滄海一聲笑</a>
        </li>
        <li data-view="4" class="active">
            <a href="/3.mp3" singer="齊秦">往事隨風</a>
        </li>
        <li data-view="6"><a href="/4.mp3" singer="beyond">光輝歲月</a></li>
        <li data-view="5"><a href="/5.mp3" singer="陳慧琳">筆記本</a></li>
        <li data-view="5">
            <a href="/6.mp3" singer="鄧麗君"><i class="fa fa-user"></i>但願人長久</a>
        </li>
    </ul>
</div>'''

result = re.search('<li.*?singer="(.*?)">(.*?)</a>', html)
if result:
    print(result.group(1), result.group(2))

re.findall

搜索字符串,以列表形式返回全部能匹配的子串.

import re

html = '''<div id="songs-list">
    <h2 class="title">經典老歌</h2>
    <p class="introduction">
      經典老歌列表
    </p>
    <ul id="list" class="list-group">
        <li data-view="2">一路上有你</li>
        <li data-view="7">
            <a href="/2.mp3" singer="任賢齊">滄海一聲笑</a>
        </li>
        <li data-view="4" class="active">
            <a href="/3.mp3" singer="齊秦">往事隨風</a>
        </li>
        <li data-view="6"><a href="/4.mp3" singer="beyond">光輝歲月</a></li>
        <li data-view="5"><a href="/5.mp3" singer="陳慧琳">筆記本</a></li>
        <li data-view="5">
            <a href="/6.mp3" singer="鄧麗君">但願人長久</a>
        </li>
    </ul>
</div>'''

results = re.findall('<li.*?href="(.*?)".*?singer=(.*?)>(.*?)</a>', html, re.S)
print(results)
for result in results:
    print(result[0], result[1], result[2])

import re

html = '''<div id="songs-list">
    <h2 class="title">經典老歌</h2>
    <p class="introduction">
      經典老歌列表
    </p>
    <ul id="list" class="list-group">
        <li data-view="2">一路上有你</li>
        <li data-view="7">
            <a href="/2.mp3" singer="任賢齊">滄海一聲笑</a>
        </li>
        <li data-view="4" class="active">
            <a href="/3.mp3" singer="齊秦">往事隨風</a>
        </li>
        <li data-view="6"><a href="/4.mp3" singer="beyond">光輝歲月</a></li>
        <li data-view="5"><a href="/5.mp3" singer="陳慧琳">筆記本</a></li>
        <li data-view="5">
            <a href="/6.mp3" singer="鄧麗君">但願人長久</a>
        </li>
    </ul>
</div>'''

results = re.findall('<li.*?>\s*?(<a.*?>)?(\w+)(</a>)?\s*?</li>', html, re.S)
print(results)
for result in results:
    print(result[1])

re.sub

替換字符串中每一個匹配的子串後返回替換後的字符串

import re

content = 'Extra strings Hello 1234567 World_This is a Regex Demo Extra strings'
content = re.sub('\d+', '', content)
print(content)

import re

content = 'Extra strings Hello 1234567 World_This is a Regex Demo Extra strings'
content = re.sub('\d+', 'MMMMQS', content)
print(content)

re.compile

將正則字符串編譯成正則表達式對象

import re

content = '''Hello 1234567 World_This
is a Regex Demo'''

pattern = re.compile('He.*?(\d+).*?Demo', re.S)
result = re.match(pattern, content)
print(result.group(1))

實戰練習

import requests
import re

content = requests.get('https://book.douban.com/').text
# print(content)
pattern  = re.compile('<li.*?cover.*?href="(.*?)".*?</li>', re.S)
results = re.findall(pattern, content)
if result:
    for result in results:
        print(result)