Python pyquery 使用

https://cuiqingcai.com/5551.html

Table of Contents

https://cuiqingcai.com/5551.html

基本CSS选择器

查找节点

find() 查找子孙节点

children() 查找子节点

parent() 查找父节点

siblings()  兄弟节点

遍历

单个节点可以直接打印输出

多个节点需要调用items()方法

获取信息

获取属性: 调用 attr() 方法获取属性 或 attr 属性获取

获取文本: text() 获取节点内所有文本信息  html() 获取第一个节点内的html信息

节点操作

addClass 和   removeClass

attr、text 和   html

remove() 移除

伪类选择器

---

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 a'))
print(doc('.list span'))
print(doc('.bold'))


# <a href="link2.html">second item</a><a href="link3.html"><span class="bold">third item</span></a><a href="link4.html">fourth item</a><a href="link5.html">fifth item</a>
# <span class="bold">third item</span>
# <span class="bold">third item</span>

---

查找节点

find() 查找子孙节点

children() 查找子节点

parent() 查找父节点

siblings()  兄弟节点

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)

# 子孙节点
print(doc('.list').find('.active'))

# 子节点
print(doc('#container').children('.active'))

# 子节点
print(doc('.list').children('.active'))

# 父节点
print(doc('.bold').parent())

# 兄弟节点
print(doc('.item-0.active').siblings())

---

遍历

单个节点可以直接打印输出

多个节点需要调用items()方法

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)

# 单个节点
li = doc('.item-0.active')
print(li)
print(str(li))


# 多个节点
print('*'*20)
lis = doc('li').items()
for i in lis:
    print(i)

---

获取信息

获取属性: 调用 attr() 方法获取属性 或 attr 属性获取

获取文本: text() 获取节点内所有文本信息  html() 获取第一个节点内的html信息

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)

# attr方法 和 attr属性
a = doc('.item-1.active a')
print(a.attr('href'))
print(a.attr.href)

# attr方法 和 attr属性
print(list(doc('div .item-0').items())[2].find('a').attr('href'))
print(list(doc('div .item-0').items())[2].find('a').attr.href)

# text() 获取文本
print(doc('.item-1.active a').text())
print(doc('.item-1.active a').html())

# 获取第一个 li 的文本
print(doc('li').html())
# 获取所有 li 的文本
print(doc('li').text())

---

节点操作

addClass 和   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)

# 移除 class
li.removeClass('active')
print(li)

# 添加 class
li.addClass('test')
print(li)

attr、text 和   html

html = '''
<ul class="list">
     <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
</ul>
'''
from pyquery import PyQuery as pq
doc = pq(html)

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

# 添加 name
li.attr('name', 'link')
print(li)

# 修改 text 纯文本
li.text('changed item')
print(li)

# 修改 html 文本
li.html('<span>changed item</span>')
print(li)

remove() 移除

html = '''
<div class="wrap">
    Hello, World
    <p>This is a paragraph.</p>
 </div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
wrap = doc('.wrap')
print(wrap.text())

wrap.find('p').remove()
print(wrap)
print(wrap.text())

---

伪类选择器

http://www.w3school.com.cn/css/index.asp

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)