Beautiful Soup的简介(3) CSS选择器

CSS修饰器中ID是不会重复，class是会重复. 

soup.select('#title')  #代表找处id为title的元素
soup.select('.link')    #代表找出class为link的元素

css选取属性方法:

soup.select('a')[0]['href']   #代表将a标签里面的href属性拿出来

html = """
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    <div class="panel-body">
        <ul class="list" id="list-1" name="elements">
            <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">Foo</li>
            <li class="element">Bar</li>
        </ul>
    </div>
</div>
"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'html5lib')
print(1, soup.select('.panel .panel-heading'))  #凡是选择class里面的标签，在选择器中写入.panel这样类似的方式，这里表示查找panel里面的panel-heading，中间需要使用空格表示
print(2, soup.select('ul li'))  # 直接选择标签，标签前不用添加.，这里代表选择ul里面的li
print(3, soup.select('#list-2 .element')) # 如果需要选择id里面的内，则要选择#，这里是id='list-2'的element标签
print(4, type(soup.select('ul')[0]))　

1 [<div class="panel-heading">
        <h4>Hello</h4>
    <div class="panel-body">
        <ul class="list" id="list-1" name="elements">
            <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">Foo</li>
            <li class="element">Bar</li>
        </ul>
    </div>
</div>]
2 [<li class="element">Foo</li>, <li class="element">Bar</li>, <li class="element">Jay</li>, <li class="element">Foo</li>, <li class="element">Bar</li>]
3 [<li class="element">Foo</li>, <li class="element">Bar</li>]
4 <class 'bs4.element.Tag'>

html = """
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    <div class="panel-body">
        <ul class="list" id="list-1" name="elements">
            <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">Foo</li>
            <li class="element">Bar</li>
        </ul>
    </div>
</div>
"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'html5lib')
for ul in soup.select('ul'):
    print(ul.select('li'))   #层层迭代的方式打印

[<li class="element">Foo</li>, <li class="element">Bar</li>, <li class="element">Jay</li>]
[<li class="element">Foo</li>, <li class="element">Bar</li>]

获取属性

html = """
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    <div class="panel-body">
        <ul class="list" id="list-1" name="elements">
            <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">Foo</li>
            <li class="element">Bar</li>
        </ul>
    </div>
</div>
"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'html5lib')
for ul in soup.select('ul'):
    print(ul['id'])
    print(ul.attrs['id'])

list-1
list-1
list-2
list-2

获取内容

html = """
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</h4>
    <div class="panel-body">
        <ul class="list" id="list-1" name="elements">
            <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">Foo</li>
            <li class="element">Bar</li>
        </ul>
    </div>
</div>
"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'html5lib')
for li in soup.select('li'):
    print(li.get_text())　

Foo
Bar
Jay
Foo
Bar