css选择器

css选择器

"""
# css选择器
#######
#1 css选择器
#######
# 重点

# Tag对象.select("css选择器")
#  #ID号
#  .类名
#   div>p:儿子 和div p:子子孙孙
#   找div下最后一个a标签 div a:last-child


# css选择器,xpath选择器会用了,它就是个通行证(所有的都可以不会,会粘贴就行)

# bs4:自己的选择器,css选择器
# lxml:css选择器,xpath选择器
# selenium:自己的选择器,css选择器,xpath选择器
# scrapy框架:自己的选择器,css选择器,xpath选择器
# #select('.article')



#该模块提供了select方法来支持css,详见官网:https://www.crummy.com/software/BeautifulSoup/bs4/doc/index.zh.html#id37
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title">
    <b>The Dormouse's story</b>
    Once upon a time there were three little sisters; and their names were
    <a href="http://example.com/elsie" class="sister" id="link1">
        <span>Elsie</span>
    </a>
    <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
    <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
    <div class='panel-1'>
        <ul class='list' id='list-1'>
            <li class='element'>Foo</li>
            <li class='element'>Bar</li>
            <li class='element'>Jay</li>
        </ul>
        <ul class='list list-small' id='list-2'>
            <li class='element'><h1 class='yyyy'>Foo</h1></li>
            <li class='element xxx'>Bar</li>
            <li class='element'>Jay</li>
        </ul>
    </div>
    and they lived at the bottom of a well.
</p>
<p class="story">...</p>
"""
from bs4 import BeautifulSoup
soup=BeautifulSoup(html_doc,'lxml')


#1、CSS选择器(前端学的css选择)
print(soup.p.select('.sister'))
print(soup.select('.sister span'))

print(soup.select('#link1'))
print(soup.select('#link1 span'))

print(soup.select('#list-2 .element.xxx'))

print(soup.select('#list-2')[0].select('.element')) #可以一直select,但其实没必要,一条select就可以了

# 2、获取属性
print(soup.select('#list-2 h1')[0].attrs)

# 3、获取内容
print(soup.select('#list-2 h1')[0].get_text())
"""
posted @ 2020-04-09 20:34  alen_zhan  阅读(100)  评论(0编辑  收藏  举报
返回顶部