pyquery 的简单使用

pyquery 的初步了解（实例引入）

简单举例

复制
from pyquery import PyQuery as pq
 
html = '''
<div>
<ul>
<li class="item-O"><a href="linkl.html">first item</a></li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a href="link5.html">fifth item</a>
</ul>
</div>
'''
 
doc = pq(html)
print(doc)
 
 
# 输出：
<div>
<ul>
<li class="item-O"><a href="linkl.html">first item</a></li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a href="link5.html">fifth item</a>
</li></ul>
</div>

字符串

复制
from pyquery import PyQuery as pq
import requests
 
# doc1 与 doc2 功能相同
doc1 = pq(url='https://www.cnblogs.com/liyihua/')
print(doc1('title'))
 
doc2 = pq(requests.get('https://www.cnblogs.com/liyihua/').text)
print(doc1('title'))
 
 
1# 输出：
<title>李亦华 - 博客园</title>&#13;
  
<title>李亦华 - 博客园</title>&#13;

URL

复制
from pyquery import PyQuery as pq
 
doc = pq(filename='test.html')
print(doc('li'))
 
 
# 输出：
<li class="item-O"><a href="linkl.html">first item</a></li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a href="link5.html">fifth item</a>
</li>
 
 
# 文件内容：
<div>
<ul>
<li class="item-O"><a href="linkl.html">first item</a></li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a href="link5.html">fifth item</a>
</ul>
</div>

pyquery 中的基本CSS选择器

实例切入：

复制
from pyquery import PyQuery as pq
 
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>
'''
 
doc = pq(html)
print(doc('#container .list li'))
 
print(
    type(
        doc('#container .list li')
    )
)
 
 
# 输出：
<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>
     
<class 'pyquery.pyquery.PyQuery'>

查找节点

获取子孙节点

说明：find()方法查找的是所有子孙节点，如果只查找子节点，可以使用children()方法。

复制
from pyquery import PyQuery
 
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>
'''
 
doc = PyQuery(html)
items = doc('.list')
 
print(
    type(items),
    items,
    sep='\n'
)
 
print(
    type(items.find('li')),
    items.find('li'),
    sep='\n'
)

复制
# 输出：
<class 'pyquery.pyquery.PyQuery'>
<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>
 
<class 'pyquery.pyquery.PyQuery'>
<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>

获取父节点

复制
from pyquery import PyQuery
 
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>
1</div>
13 '''
 
doc = PyQuery(html)
items = doc('.list')
 
print(items, '\n')
 
print(
    type(items.parent()),
    items.parent(),
    sep='\n'
)

复制
# 输出：
<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>
 
 
<class 'pyquery.pyquery.PyQuery'>
<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>

兄弟节点

复制
from pyquery import PyQuery
 
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>
'''
 
doc = PyQuery(html)
 
# 选择class为list的节点内部class为item-0和active的节点
items = doc('.list .item-0.active')
 
print(
    type(items.siblings()),
    items.siblings(),
    sep='\n'
)
 
print("\n", items.siblings('.active'))

复制
# 输出：
<class 'pyquery.pyquery.PyQuery'>
<li class="item-1"><a href="link2.html">second item</a></li>
         <li class="item-0">first item</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>
     
 
 <li class="item-1 active"><a href="link4.html">fourth item</a></li>

遍历节点

复制
from pyquery import PyQuery
 
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>
'''
 
doc = PyQuery(html)
lis = doc('li').items()             # 调用items()方法，得到一个生成器
 
for li in lis:
    print(
        li, 
        type(li)
    )

复制
# 输出：
<li class="item-0">first item</li>
          <class 'pyquery.pyquery.PyQuery'>
<li class="item-1"><a href="link2.html">second item</a></li>
          <class 'pyquery.pyquery.PyQuery'>
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
          <class 'pyquery.pyquery.PyQuery'>
<li class="item-1 active"><a href="link4.html">fourth item</a></li>
          <class 'pyquery.pyquery.PyQuery'>
<li class="item-0"><a href="link5.html">fifth item</a></li>
      <class 'pyquery.pyquery.PyQuery'>

获取信息

1. attr()方法获取属性

   复制
   from pyquery import PyQuery
    
   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>
   '''
    
   doc = PyQuery(html)
   a = doc('.item-0.active a')
   print(
       a,
       type(a),
       a.attr('href'),             # 也可以用a.attr.href，两者作用相同
       sep='\n'
   )

   复制
   # 输出：
   <a href="link3.html"><span class="bold">third item</span></a>
   <class 'pyquery.pyquery.PyQuery'>
   link3.html

2. text()方法获取文本

   复制
   from pyquery import PyQuery
    
   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>
   '''
    
   doc = PyQuery(html)
   li = doc('li')
    
   print(
       li.html(),                  # 获取节点的内部文本
       li.text(),                  # 获取节点文本，返回结果是纯文字内容
       type(li.text()),
       sep='\n'
   )

   复制
   # 输出：
   first item
   first item second item third item fourth item fifth item
   <class 'str'>

节点操作

添加和移除class

复制
add_class() 和 remove_class() ---- 添加class、移除class

复制
from pyquery import PyQuery
 
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>
'''
 
doc = PyQuery(html)
li = doc('.item-0.active')
 
print(li)
print(li.remove_class('active'))
print(li.add_class('active'))

复制
# 输出：
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
         
<li class="item-0"><a href="link3.html"><span class="bold">third item</span></a></li>
         
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
         

attr、text 和 html 方法

复制
from pyquery import PyQuery
 
html = '''
<div id="container">
    <ul class="list">
         <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
     </ul>
</div>
'''
 
doc = PyQuery(html)
 
li = doc('.item-0.active')
print(li)
 
li.attr('name', 'link')         # 添加属性name，属性值为link
print(li)
 
li.text('change item')          # 将节点内部的内容改为'change item'
print(li)
 
li.html('<span>change item</span>')         # 将节点内部的内容改为'<span>change item</span>'
print(li)
 
 
# 输出：
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
   
<li class="item-0 active" name="link"><a href="link3.html"><span class="bold">third item</span></a></li>
     
<li class="item-0 active" name="link">change item</li>
    
<li class="item-0 active" name="link"><span>change item</span></li>

复制
# 输出：
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
   
<li class="item-0 active" name="link"><a href="link3.html"><span class="bold">third item</span></a></li>
     
<li class="item-0 active" name="link">change item</li>
    
<li class="item-0 active" name="link"><span>change item</span></li>

删除节点

复制
from pyquery import PyQuery
 
html = '''
<div class="LeeHua">
LiYihua
<ul class="201802004731">liyihua</ul>
</div>
'''
 
doc = PyQuery(html)
Leehua = doc('.LeeHua')
print("移除节点ul前的输出：\n"+Leehua.text())
 
Leehua.find('ul').remove()
print("移除节点ul后的输出：\n"+Leehua.text())

复制
# 输出：
移除节点ul前的输出：
LiYihua
liyihua
移除节点ul后的输出：
LiYihua

伪选择器

示例：

复制
from pyquery import PyQuery
 
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>
'''
 
doc = PyQuery(html)
 
# 选择属于父元素的第一个子元素的每个 <li> 元素。
li = doc('li:first-child')
print(li)
 
# 选择属于父元素的最后一个子元素的每个 <li> 元素。
li = doc('li:last-child')
print(li)
 
# 选择属于其父元素的第二个子元素的每个 <li> 元素
li = doc('li:nth-child(2)')
print(li)
 
# 选择属于其父元素的最后两个子元素的每个 <li> 元素
li = doc('li:gt(2)')
print(li)
 
# 选择属于父元素的第偶个子元素的每个 <li> 元素。
li = doc('li:nth-child(2n)')
print(li)
 
# 选择包含'second'的每个元素
li = doc('li:contains(second)')
print(li)

复制
# 输出：
<li class="item-0">first item</li>
            
<li class="item-0"><a href="link5.html">fifth item</a></li>
       
<li class="item-1"><a href="link2.html">second item</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>
        
<li class="item-1"><a href="link2.html">second item</a></li>
            <li class="item-1 active"><a href="link4.html">fourth item</a></li>
            
<li class="item-1"><a href="link2.html">second item</a></li>

CSS 选择器的用法：http://www.w3school.com.cn/cssref/css_selectors.asp