正则表达式学习进程（三）

#re.findall()
#搜索字符串，以列表形式返回全部能匹配的子串
html = """<div id="songs-list">
    <h2 class="title">经典老歌</h2>
    <p class="introduction">
        经典老歌列表
    </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="任贤齐">沧海一声笑</a>
        </li>
        <li data-view="4" class="active">
            <a href="/3.mp3" singer="齐秦">往事随风</a>
        </li>
        <li data-view="6"><a href="/4.mp3" singer="beyond">光辉岁月</a></li>
        <li data-view="5"><a href="/5.mp3" singer="陈慧琳">记事本</a></li>
        <li data-view="5">
            <a href="/6.mp3" singer="邓丽君"><i class="fa fa-user"></i>但愿人长久</a>
        </li>
    </ul>
</div>
"""
print("##############################")
result = re.findall('<li.*?singer="(.*?)">(.*?)</a>',html,re.S)

print(result)#[('任贤齐', '沧海一声笑'), ('齐秦', '往事随风'), ('beyond', '光辉岁月'), ('陈慧琳', '记事本'), ('邓丽君', '<i class="fa fa-user"></i>但愿人长久')]
print(len(result))# 5
for value in result:
    print(value)
"""
('任贤齐', '沧海一声笑')
('齐秦', '往事随风')
('beyond', '光辉岁月')
('陈慧琳', '记事本')
('邓丽君', '<i class="fa fa-user"></i>但愿人长久')

"""
results = re.findall('<li.*?href="(.*?)".*?singer="(.*?)">(.*?)</a>', html, re.S)
print(results)
#[('/2.mp3', '任贤齐', '沧海一声笑'), ('/3.mp3', '齐秦', '往事随风'), ('/4.mp3', 'beyond', '光辉岁月'), ('/5.mp3', '陈慧琳', '记事本'), ('/6.mp3', '邓丽君', '<i class="fa fa-user"></i>但愿人长久')]


results = re.findall('<li.*?>\s*?(<a.*?>)?(\w+)(</a>)?\s*?</li>', html, re.S)
print(results)
for result in results:
    print(result[1])
"""
[('', '一路上有你', ''), ('<a href="/2.mp3" singer="任贤齐">', '沧海一声笑', '</a>'), ('<a href="/3.mp3" singer="齐秦">', '往事随风', '</a>'), ('<a href="/4.mp3" singer="beyond">', '光辉岁月', '</a>'), ('<a href="/5.mp3" singer="陈慧琳">', '记事本', '</a>'), ('<a href="/6.mp3" singer="邓丽君">', '但愿人长久', '</a>')]
一路上有你
沧海一声笑
往事随风
光辉岁月
记事本
但愿人长久
"""

#re.sub
#替换字符串中每一个匹配的子串后,返回替换后的字符串。


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

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


content = 'Extra stings Hello 1234567 World_This is a Regex Demo Extra stings'
content = re.sub('(\d+)', r'\1 8910', content)#\1 将第一个()中的内容做了替换 r是保证原字符串内容不变
print(content)  #Extra stings Hello 1234567 8910 World_This is a Regex Demo Extra stings

html = re.sub('<a.*?>|</a>', '', html)
print(html)
results = re.findall('<li.*?>(.*?)</li>', html, re.S)
print(results)
for result in results:
    print(result.strip())

"""
<div id="songs-list">
    <h2 class="title">经典老歌</h2>
    <p class="introduction">
        经典老歌列表
    </p>
    <ul id="list" class="list-group">
        <li data-view="2">一路上有你</li>
        <li data-view="7">
            沧海一声笑
        </li>
        <li data-view="4" class="active">
            往事随风
        </li>
        <li data-view="6">光辉岁月</li>
        <li data-view="5">记事本</li>
        <li data-view="5">
            <i class="fa fa-user"></i>但愿人长久
        </li>
    </ul>
</div>

['一路上有你', '\n            沧海一声笑\n        ', '\n            往事随风\n        ', '光辉岁月', '记事本', '\n            <i class="fa fa-user"></i>但愿人长久\n        ']
一路上有你
沧海一声笑
往事随风
光辉岁月
记事本
<i class="fa fa-user"></i>但愿人长久
"""


#re.compile
#将正则字符串编译成正则表达式对象
content = '''Hello 1234567 World_This
is a Regex Demo'''
pattern = re.compile('Hello.*Demo', re.S)
result = re.match(pattern, content)
#result = re.match('Hello.*Demo', content, re.S)
print(result)#<_sre.SRE_Match object; span=(0, 40), match='Hello 1234567 World_This\nis a Regex Demo'>


#实战
import requests
content = requests.get('https://book.douban.com/').text
pattern = re.compile('<li.*?cover.*?href="(.*?)".*?title="(.*?)".*?more-meta.*?author">(.*?)</span>.*?year">(.*?)</span>.*?publisher">(.*?)</span>.*?</li>', re.S)
results = re.findall(pattern, content)
for result in results:
    url, name, author, date ,publisher= result
    author = re.sub('\s', '', author)
    date = re.sub('\s', '', date)
    print(url, name, author, date)