Python正則表達(dá)式的應(yīng)用詳解

import re

username = input('請(qǐng)輸入用戶名：')
# 通過(guò)compile編譯正則表達(dá)式創(chuàng)建Pattern對(duì)象
username_pattern = re.compile(r'^\w{6,20}$')
print(type(username_pattern))
# 通過(guò)給Pattern對(duì)象發(fā)消息實(shí)現(xiàn)匹配檢查
matcher = username_pattern.match(username)
print(type(matcher))
if matcher is None:
    print('無(wú)效的用戶名')
else:
    print(matcher.group())

username = input('請(qǐng)輸入用戶名：')
matcher = re.fullmatch(r'\w{6,20}', username)
#^是開始符，$是結(jié)束符
# matcher = re.match(r'^\w{6,20}$', username)
if matcher is None:
    print('用戶名不合法！?。?)
else:
    print(matcher)
    print(matcher.group())

import re

content = """報(bào)警電話：110，我們班是Python-2105班，
我的QQ是9597658，我的手機(jī)號(hào)是13811223344，謝謝！"""

searcher = re.search(r'1[3-9]\d{9}', content)
if not searcher:
    print('沒(méi)有找到手機(jī)號(hào)')
else:
    print(searcher.group())

import re

content = """報(bào)警電話：110，我們班是Python-2105班，
我的QQ是9597658，我的手機(jī)號(hào)是13811223344，謝謝！"""

pattern = re.compile(r'\d+')
matcher = pattern.search(content)
while matcher:
    print(matcher.group())
    # 從上一次匹配成功的結(jié)束位置開始搜索
    matcher = pattern.search(content, matcher.end())

import re

content = """報(bào)警電話：110，我們班是Python-2105班，
我的QQ是9597658，我的手機(jī)號(hào)是13811223344，謝謝！"""

pattern = re.compile(r'\d+')
results = pattern.findall(content)
# 沒(méi)有創(chuàng)建正則表達(dá)式對(duì)象時(shí)，也可以用這種方法
# results = re.findall(r'\d+', content)
for result in results:
    print(result)

import re

import requests

resp = requests.get('https://www.sohu.com/')
# .表示任意字符，+表示匹配一個(gè)或任意多個(gè)，？表示惰性匹配，盡可能短的匹配
pattern = re.compile(r'href="http.+?"')
# 拿到搜狐首頁(yè)
content = resp.text
matcher = pattern.search(content)
while matcher:
    print(matcher.group()[6:-1])
    matcher = pattern.search(content, matcher.end())

pattern2 = re.compile(r'title=".+?"')
title_list = pattern2.findall(content)
for title in title_list:
    print(title[7:-1])

import re

import requests

resp = requests.get('https://www.sohu.com/')
# 匹配整個(gè)a標(biāo)簽，但是只捕獲()中的內(nèi)容 ---> 正則表達(dá)式的捕獲組
# .*連在一起就意味著任意數(shù)量的不包含換行的字符
pattern = re.compile(r'a\s.*?href="(.+?)".*?title="(.+?)".*?>')
content = resp.text
results = pattern.findall(content)
for href, title in results:
    print(title)
    if not href.startswith('https://www.sohu.com'):
         + href
    print(href)

import re

content = '你真是一個(gè)沙雕煞筆，F(xiàn)uck you!'
# pattern = re.compile(r'[傻沙煞][逼筆雕鄙]|馬化騰|fuck|shit', flags=re.IGNORECASE)
# modified_content = pattern.sub('*', content)
# print(modified_content)
# |表示分支
modified_content = re.sub(r'[傻沙煞][逼筆雕鄙]|fuck|shit', '*', content, flags=re.I)
print(modified_content)

import re

poem = '床前明月光，疑是地上霜，舉頭望明月，低頭思故鄉(xiāng)。'
# sentences_list = re.split(r'[，。]', poem)
# sentences_list = re.split(r'，|。', poem)
pattern = re.compile(r'[，。]')
sentences_list = pattern.split(poem)
# sentences_list = [sentence for sentence in sentences_list if sentence]
# print(sentences_list)
for sentence in sentences_list:
    print(sentence)