Python_PyQuery使用

颛孙博易

2023-12-01

PyQuery(from pyquery import PyQuery as pq)

Pyquery是一个类似jquery（一个js库）的库，使用 lxml 进行快速 xml 和 html 操作，利用它可以直接解析DOM节点的结构，并通过DOM节点的一些属性快速进行内容提取。
Pyquery中常用的比较多的是利用CSS选择器来提取DOM节点。
CSS选择器用法：https://www.w3school.com.cn/cssref/css_selectors.asp

1、准备工作

安装：pip install pyquery
官方文档：PyQuery API文档

2、初始化

PyQuery初始化有三种：

通过字符串(text)初始化PyQuery对象
通过网址(url)初始化PyQuery对象
通过文件名(filename)初始化PyQuery对象

initialize.html文件代码如下：

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>通过文件进行初始化PyQuery对象</title>
</head>
<body>
    <ul id="container">
        <li class="item">1</li>
        <li class="item">2</li>
        <li class="item">3</li>
    </ul>
</body>
</html>

初始化代码如下：

'''
    功能如下：
    初始化PyQuery对象的三种方式：
        1. 通过字符串(text)初始化PyQuery对象
        2. 通过网址(url)初始化PyQuery对象
        3. 通过文件名(filename)初始化PyQuery对象
'''

from pyquery import PyQuery as pq

html = '''
<html lang="en">
    <head>
        <title>PyQuery学习</title>
    </head>
    <body>
        <ul id="container">
            <li class="object-1"/>
            <li class="object-2"/>
            <li class="object-3"/>
        </ul>
    </body>
</html>
'''

# 通过字符串(text)初始化PyQuery对象
doc = pq(html)
print(doc('title').text())

# 运行结果
# PyQuery学习

# 通过网址(url)初始化PyQuery对象
doc = pq(url='http://www.baidu.com', encoding='utf-8')
print(doc('title').text())

# 运行结果
# 百度一下，你就知道

# 通过文件名(filename)初始化PyQuery对象
# 但是这种方式不适用于大文件。。。
with open('initialize.html', 'r', encoding='utf-8') as f:
    res = f.read()

doc = pq(res)
print(doc('title').text())

# 运行结果
# 通过文件进行初始化PyQuery对象

注意点：如果在读取文件使报错如下：UnicodeDecodeError: 'gbk' codec can't decode byte 0xa1 in position 98: illegal multibyte sequence
可以查看如下文章进行解决：GBK解码报错解决方案

3、查找节点

pyquery对象.items() 转换为生成器对象（迭代器的一种），再for循环遍历
CSS选择器：使用PyQuery时，CSS选择器能解决大部分的问题。
find()方法：查找所有的子孙节点。
children()方法：查找子节点。
parent()方法：获取某个节点的父节点。
parents()方法：获取某个节点的父节点和祖先节点
siblings()方法：获取兄弟节点

from pyquery import PyQuery as pq
html = '''
<div class='wrap'>
<div id="container">
    <ul class="list">
         <li class="item-0"><a href="link1.html">first item</a></li>
         <li class="item-1"><a href="link2.html">second item</a></li>
         <li class="item-0 active"><a href="link3.html">third 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>
     </ul>
 </div>
 </div>
'''
doc = pq(html)

'''pyquery对象.items() 转换为生成器对象（迭代器的一种），再for循环遍历'''
data = doc('li').items()  # 返回生成器对象
print(type(data))
for i in data:
    print(i)
# 运行结果
# <class 'generator'>
# <li class="item-0"><a href="link1.html">first item</a></li>
# <li class="item-1"><a href="link2.html">second item</a></li>
# <li class="item-0 active"><a href="link3.html">third 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>

'''选取id为container中class为list的节点'''
ul_item = doc('#container .list')
print(type(ul_item))
print(ul_item)

#运行结果
# <class 'pyquery.pyquery.PyQuery'>
# <li class="item-0"><a href="link1.html">first item</a></li>
#          <li class="item-1"><a href="link2.html">second item</a></li>
#          <li class="item-0 active"><a href="link3.html">third 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>

'''选取其内部所有的li节点，find()查找所有子孙节点'''
lis = ul_item.find('li')
print(type(lis))
print(lis)

#运行结果
# <class 'pyquery.pyquery.PyQuery'>
# <li class="item-0"><a href="link1.html">first item</a></li>
#          <li class="item-1"><a href="link2.html">second item</a></li>
#          <li class="item-0 active"><a href="link3.html">third 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>

'''选取其内部子节点，children()查找子节点'''
lis = ul_item.children()
print(type(lis))
print(lis)

#运行结果
# <class 'pyquery.pyquery.PyQuery'>
# <li class="item-0"><a href="link1.html">first item</a></li>
#          <li class="item-1"><a href="link2.html">second item</a></li>
#          <li class="item-0 active"><a href="link3.html">third 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>

'''筛选出子节点中class为active的节点'''
lis = ul_item.children('.active')
print(type(lis))
print(lis)

#运行结果
# <class 'pyquery.pyquery.PyQuery'>
# <li class="item-0 active"><a href="link3.html">third item</a></li>
#          <li class="item-1 active"><a href="link4.html">fourth item</a></li>

'''#parent()获取某个节点的父节点'''
container = ul_item.parent()
print(type(container))
print(container)

#运行结果
# <class 'pyquery.pyquery.PyQuery'>
# <div id="container">
#     <ul class="list">
#          <li class="item-0"><a href="link1.html">first item</a></li>
#          <li class="item-1"><a href="link2.html">second item</a></li>
#          <li class="item-0 active"><a href="link3.html">third 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>
#      </ul>
#  </div>

'''parents()获取某个节点的祖先节点,返回所有祖先节点'''
parents = ul_item.parents()
for parent in parents.items():
    print(type(parent))
    print(parent)

#运行结果
# <class 'pyquery.pyquery.PyQuery'>
# <div class="wrap">
# <div id="container">
#     <ul class="list">
#          <li class="item-0"><a href="link1.html">first item</a></li>
#          <li class="item-1"><a href="link2.html">second item</a></li>
#          <li class="item-0 active"><a href="link3.html">third 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>
#      </ul>
#  </div>
#  </div>
# <class 'pyquery.pyquery.PyQuery'>
# <div id="container">
#     <ul class="list">
#          <li class="item-0"><a href="link1.html">first item</a></li>
#          <li class="item-1"><a href="link2.html">second item</a></li>
#          <li class="item-0 active"><a href="link3.html">third 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>
#      </ul>
#  </div>

'''parents()获取wrap祖先节点的数据'''
parents = ul_item.parents('.wrap')
print(type(parents))
print(parents)

#运行结果
# <class 'pyquery.pyquery.PyQuery'>
# <div class="wrap">
# <div id="container">
#     <ul class="list">
#          <li class="item-0"><a href="link1.html">first item</a></li>
#          <li class="item-1"><a href="link2.html">second item</a></li>
#          <li class="item-0 active"><a href="link3.html">third 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>
#      </ul>
#  </div>
#  </div>

'''siblings()获取兄弟节点'''
li = doc('.list .item-0.active')
print(li.siblings())
print(li.siblings('.active'))

#运行结果
# <li class="item-1"><a href="link2.html">second item</a></li>
# <li class="item-0"><a href="link1.html">first 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 active"><a href="link4.html">fourth item</a></li>

4、伪类选择器

方法	说明
:first-child	获取第一个节点
:last-child	获取最后一个节点
:nth-child(N)	获取第N个节点,N=1,2,…
:nth-child(2n)	获取偶数位置的全部节点
:nth-child(2n-1)	获取奇数位置的全部节点
:gt(N)	获取索引大于N的节点，N=0,1,…
:contains(‘first item’)	获取文本包含"first item"的节点

from pyquery import PyQuery as pq
html = '''
<div class='wrap'>
<div id="container">
    <ul class="list">
         <li class="item-0"><a href="link1.html">first item</a></li>
         <li class="item-1"><a href="link2.html">second item</a></li>
         <li class="item-0 active"><a href="link3.html">third 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>
     </ul>
 </div>
 </div>
'''
doc = pq(html)

'''选择第一个节点'''
li = doc('li:first-child')
print(type(li))
print(li)
# 运行结果
# <li class="item-0"><a href="link1.html">first item</a></li>

'''获取最后一个节点'''
li = doc('li:last-child')
print(type(li))
print(li)
# 运行结果
# <li class="item-0"><a href="link5.html">fifth item</a></li>

'''获取第N个节点,N=1,2,...'''
li = doc('li:nth-child(1)')  # 节点从1开始算起
print(type(li))
print(li)
# 运行结果
# <class 'pyquery.pyquery.PyQuery'>
# <li class="item-0"><a href="link1.html">first item</a></li>

'''获取偶数位置的全部节点'''
li = doc('li:nth-child(2n)')  # 节点从1开始算起
print(type(li))
print(li)
# 运行结果
# <class 'pyquery.pyquery.PyQuery'>
# <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>

'''获取奇数位置的全部节点'''
li = doc('li:nth-child(2n-1)')  # 节点从1开始算起
print(type(li))
print(li)
# 运行结果
# <class 'pyquery.pyquery.PyQuery'>
# <li class="item-0"><a href="link1.html">first item</a></li>
#          <li class="item-0 active"><a href="link3.html">third item</a></li>
#          <li class="item-0"><a href="link5.html">fifth item</a></li>

'''获取索引大于N的节点，N=0,1,...'''
li = doc('li:gt(0)')  # 节点从0开始算起,>0说明排除第一个
print(type(li))
print(li)
# 运行结果
# <class 'pyquery.pyquery.PyQuery'>
# <li class="item-1"><a href="link2.html">second item</a></li>
#          <li class="item-0 active"><a href="link3.html">third 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>

'''获取文本包含"first item"的节点'''
li = doc('li > a:contains("first item")')
print(type(li))
print(li)
# 运行结果
# <class 'pyquery.pyquery.PyQuery'>
# <a href="link1.html">first item</a>

5、获取节点信息

attr()方法：获取属性名
text()方法：获取文本
html()方法：获取节点内部的HTML文本

from pyquery import PyQuery as pq
html = '''
<div class='wrap'>
<div id="container">
    <ul class="list">
         <li class="item-0"><a href="link1.html">first item</a></li>
         <li class="item-1"><a href="link2.html">second item</a></li>
         <li class="item-0 active"><a href="link3.html">third 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>
     </ul>
 </div>
 </div>
'''
doc = pq(html)

'''获取属性值——attr()'''
print(doc('li:first-child').attr('class'))
# 运行结果
# item-0

'''获取文本——text()'''
print(doc('li:first-child').text())
# 运行结果
# first item

'''获取节点内部的HTML文本——html()'''
print(doc('li:first-child').html())
# 运行结果
# <a href="link1.html">first item</a>

6、节点操作

PyQuery中的常见用法如下：

remove()方法：移除指定节点
remove_class()方法：移除class属性
remove_attr()方法：移除一个属性
addClass()方法：增加class属性

from pyquery import PyQuery as pq
html = '''
<div class='wrap'>
<div id="container">
    <ul class="list">
         <li class="item-0"><a href="link1.html">first item</a></li>
         <li class="item-1"><a href="link2.html">second item</a></li>
         <li class="item-0 active"><a href="link3.html">third 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>
     </ul>
 </div>
 </div>
'''
doc = pq(html)

'''移除指定节点——remove()'''
print(doc('li:first-child').remove())  # 删除li的第一个节点
print(doc)
# 运行结果
# <div class="wrap">
# <div id="container">
#     <ul class="list">
#
#          <li class="item-1"><a href="link2.html">second item</a></li>
#          <li class="item-0 active"><a href="link3.html">third 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>
#      </ul>
#  </div>
#  </div>

'''移除class属性——remove_class()'''
print(doc('li:nth-child(3)').remove_class('active'))
print(doc)
# 运行结果
# <div class="wrap">
# <div id="container">
#     <ul class="list">
#
#          <li class="item-1"><a href="link2.html">second item</a></li>
#          <li class="item-0 active"><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>
#  </div>

'''移除某一个属性——remove_attr()'''
print(doc('li:last-child').remove_attr('class'))
print(doc)
# 运行结果
# <div class="wrap">
# <div id="container">
#     <ul class="list">
#
#          <li class="item-1"><a href="link2.html">second item</a></li>
#          <li class="item-0 active"><a href="link3.html">third item</a></li>
#          <li class="item-1"><a href="link4.html">fourth item</a></li>
#          <li><a href="link5.html">fifth item</a></li>
#      </ul>
#  </div>
#  </div>

'''增加class属性——addClass()'''
print(doc('li:last-child').add_class('item5'))
print(doc)
# 运行结果
# <div class="wrap">
# <div id="container">
#     <ul class="list">
#
#          <li class="item-1"><a href="link2.html">second item</a></li>
#          <li class="item-0 active"><a href="link3.html">third item</a></li>
#          <li class="item-1"><a href="link4.html">fourth item</a></li>
#          <li class="item5"><a href="link5.html">fifth item</a></li>
#      </ul>
#  </div>
#  </div>

Python_PyQuery使用

PyQuery(from pyquery import PyQuery as pq)

1、准备工作

2、初始化

3、查找节点

4、伪类选择器

5、获取节点信息

6、节点操作

相关阅读

相关文章

相关问答

相关文档