PyQuery的基本使用详解

0.安装：pip3 install pyquery

1.初始化

1.字符串初始化

# 字符串初始化
html = """
<div>
    <ul>
        <li class="item-0">first item</li>
        <li class="item-1"><a href="link2.html">second item</a></li>
        <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
        <li class="item-1 active"><a href="link4.html">fourth item</a></li>
        <li class="item-0"><a href="link5.html">fifth item</a></li>
    </ul>
</div>
"""

from pyquery import PyQuery as pq
doc = pq(html)
print(doc('li'))

2.URL初始化

from pyquery import PyQuery as pq
doc = pq(url='http://www.baidu.com')
print(doc('head'))

3.文件初始化

from pyquery import PyQuery as pq
doc = pq(filename='demo.html')
print(doc('li'))

2.基本CSS选择器

html = """
<div id="container">
    <ul class='list'>
        <li class="item-0">first item</li>
        <li class="item-1"><a href="link2.html">second item</a></li>
        <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
        <li class="item-1 active"><a href="link4.html">fourth item</a></li>
        <li class="item-0"><a href="link5.html">fifth item</a></li>
    </ul>
</div>
"""

from pyquery import PyQuery as pq
doc = pq(html)
print(doc('#container .list li'))

3.查找元素

1.子元素

html = """
<div id="container">
    <ul class='list'>
        <li class="item-0">first item</li>
        <li class="item-1"><a href="link2.html">second item</a></li>
        <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
        <li class="item-1 active"><a href="link4.html">fourth item</a></li>
        <li class="item-0"><a href="link5.html">fifth item</a></li>
    </ul>
</div>
"""

from pyquery import PyQuery as pq
doc = pq(html)
items = doc('.list')
print(items)

# 查询li标签
lis = items.find('li')
print(lis)

# 查询孩子
lis = items.children()
print(type(lis))
print(lis)

# 查询带有'.active'的孩子
lis = items.children('.active')
print(lis)

2.父元素

html = """
<div class='wrap'>
    <div id="container">
        <ul class='list'>
            <li class="item-0">first item</li>
            <li class="item-1"><a href="link2.html">second item</a></li>
            <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
            <li class="item-1 active"><a href="link4.html">fourth item</a></li>
            <li class="item-0"><a href="link5.html">fifth item</a></li>
        </ul>
    </div>
</div>
"""

from pyquery import PyQuery as pq
doc = pq(html)
items = doc('.list')
print(items)

parents = items.parents()
print(parents)

parent = items.parents('.wrap')
print(parent)

3.兄弟元素

html = """
<div class='wrap'>
    <div id="container">
        <ul class='list'>
            <li class="item-0">first item</li>
            <li class="item-1"><a href="link2.html">second item</a></li>
            <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
            <li class="item-1 active"><a href="link4.html">fourth item</a></li>
            <li class="item-0"><a href="link5.html">fifth item</a></li>
        </ul>
    </div>
</div>
"""

from pyquery import PyQuery as pq
doc = pq(html)

items = doc('.list .item-0.active')
print(items)
print(items.siblings())
print(items.siblings('.active'))

4.遍历

html = """
<div class='wrap'>
    <div id="container">
        <ul class='list'>
            <li class="item-0">first item</li>
            <li class="item-1"><a href="link2.html">second item</a></li>
            <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
            <li class="item-1 active"><a href="link4.html">fourth item</a></li>
            <li class="item-0"><a href="link5.html">fifth item</a></li>
        </ul>
    </div>
</div>
"""

from pyquery import PyQuery as pq
doc = pq(html)
# 单个元素
items = doc('.item-0.active')
print(items)
# 遍历元素
lis = doc('li').items()
print(lis)
# <generator object PyQuery.items at 0x0000000003A84468>
for item in lis:
    print(item)

5.获取信息

1.获取属性

html = """
<div class='wrap'>
    <div id="container">
        <ul class='list'>
            <li class="item-0">first item</li>
            <li class="item-1"><a href="link2.html">second item</a></li>
            <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
            <li class="item-1 active"><a href="link4.html">fourth item</a></li>
            <li class="item-0"><a href="link5.html">fifth item</a></li>
        </ul>
    </div>
</div>
"""

from pyquery import PyQuery as pq
doc = pq(html)
a = doc('.item-0.active a')
print(a)
print(a.attr('href'))
print(a.attr.href)

2.获取文本

html = """
<div class='wrap'>
    <div id="container">
        <ul class='list'>
            <li class="item-0">first item</li>
            <li class="item-1"><a href="link2.html">second item</a></li>
            <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
            <li class="item-1 active"><a href="link4.html">fourth item</a></li>
            <li class="item-0"><a href="link5.html">fifth item</a></li>
        </ul>
    </div>
</div>
"""

from pyquery import PyQuery as pq
doc = pq(html)

a = doc('.item-0.active a')
print(a)
print(a.text())

3.获取HTML

html = """
<div class='wrap'>
    <div id="container">
        <ul class='list'>
            <li class="item-0">first item</li>
            <li class="item-1"><a href="link2.html">second item</a></li>
            <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
            <li class="item-1 active"><a href="link4.html">fourth item</a></li>
            <li class="item-0"><a href="link5.html">fifth item</a></li>
        </ul>
    </div>
</div>
"""

from pyquery import PyQuery as pq
doc = pq(html)

li = doc('.item-0.active')
print(li)
print(li.html())

6.DOM操作

1.addclass、removeclass

html = """
<div class='wrap'>
    <div id="container">
        <ul class='list'>
            <li class="item-0">first item</li>
            <li class="item-1"><a href="link2.html">second item</a></li>
            <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
            <li class="item-1 active"><a href="link4.html">fourth item</a></li>
            <li class="item-0"><a href="link5.html">fifth item</a></li>
        </ul>
    </div>
</div>
"""

from pyquery import PyQuery as pq
doc = pq(html)

li = doc('.item-0.active')
print(li)

li.removeClass('active')
print(li)

li.addClass('active')
print(li)

2. attr、css

html = """
<div class='wrap'>
    <div id="container">
        <ul class='list'>
            <li class="item-0">first item</li>
            <li class="item-1"><a href="link2.html">second item</a></li>
            <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
            <li class="item-1 active"><a href="link4.html">fourth item</a></li>
            <li class="item-0"><a href="link5.html">fifth item</a></li>
        </ul>
    </div>
</div>
"""

from pyquery import PyQuery as pq
doc = pq(html)

li = doc('.item-0.active')
print(li)

li.attr('name','apollo')
print(li)

li.css('font-size','14px')
print(li)

3. remove

html = """
<div class='wrap'>
    Hello World
    <p>This is paragraph</p>
</div>
"""

from pyquery import PyQuery as pq
doc = pq(html)
wrap = doc('.wrap')
print('移除前：',wrap.text())
wrap.find('p').remove()
print('移除后：',wrap.text())

4.其他DOM方法

https://pyquery.readthedocs.io/en/latest/api.html

7.伪类选择器

---

html = """
<div class='wrap'>
    <div id="container">
        <ul class='list'>
            <li class="item-0">first item</li>
            <li class="item-1"><a href="link2.html">second item</a></li>
            <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
            <li class="item-1 active"><a href="link4.html">fourth item</a></li>
            <li class="item-0"><a href="link5.html">fifth item</a></li>
        </ul>
    </div>
</div>
"""

from pyquery import PyQuery as pq
doc = pq(html)
li = doc('li:first-child')
print(li)
li = doc('li:last-child')
print(li)
li = doc('li:nth-child(2)')
print(li)
li = doc('li:gt(2)')
print(li)
li = doc('li:nth-child(2n)')
print(li)
li = doc('li:contains(second)')
print(li)

官网

https://pyquery.readthedocs.io