PyQuery用法详解

PyQuery是强大而又灵活的网页解析库，如果你觉得正则写起来太麻烦，如果你觉得BeautifulSoup语法太难记，如果你熟悉jQuery的语法
那么，PyQuery就是你绝佳的选择。

一、初始化方式，有三种，可以传入字符串，传入url，传入文件。
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)#声明pq对象
print(doc('li'))#用css选择器来实现，如果要选id前面加#，如果选class，前面加.，如果选标签名，什么也不加

URL初始化
也可以直接传入URL，进行URL初始化，程序会自动请求URL，获得html并返回要查找的字符串
from pyquery import PyQuery as pq
doc = pq(url='http://www.baidu.com')#程序会自动请求url
print(doc('head'))#返回head标签

文件初始化
from pyquery import PyQuery as pq
doc = pq(filename='D://demo.html')#直接传入文件名称及路径，程序会自动寻找并请求
print(doc('li'))

二、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'))#会查找id为container class为list，标签为li的对象，只是层级关系，没有后者一定是前者的子对象

查找元素
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>
'''

子元素
from pyquery import PyQuery as pq
doc = pq(html)
items = doc('.list')#拿到items
print(type(items))
print(items)
lis = items.find('li')#利用find方法，查找items里面的li标签，得到的lis也可以继续调用find方法往下查找，层层剥离
print(type(lis))
print(lis)

也可以用.children()查找直接子元素
lis = items.children()
print(type(lis))
print(lis)
lis = items.children('.active')
print(lis)

父元素
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')
container = items.parent()#.parent()查找对象的父元素
print(type(container))
print(container)

祖先节点
parents = items.parents()#.parents（）祖先节点
parent = items.parents('.wrap')#当然也可以传入参数
print(parent)

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)
li = doc('.list .item-0.active')#空格表示里面，没有空格表示整体
print(li.siblings())#.siblings()兄弟元素，即同级别的元素，不包括自己

三、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)
lis = doc('li').items()#.items会是一个生成器
print(type(lis))
for li in lis:
    print(li)

四、获取信息
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'))#定义a标签的href属性用于指定超链接目标的URL。 如果用户选择了a标签中的内容，那么浏览器会尝试检索并显示href属性指定的URL所表示的文档，或者执行JavaScript表达式、方法和函数的列表。
print(a.attr.href)
结果：
<a href="link3.html"><span class="bold">third item</span></a>
link3.html
link3.html

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）#.text()获取文本信息

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())#.html（）获取所在html

五、DOM操作

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')#删除
print(li)
li.addClass('active')#增加
print(li)

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', 'link')#增加一个属性
print(li)
li.css('font-size', '14px')#增加一个css
print(li)
结果：
< 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" style="font-size: 14px" > < a href="link3.html" > < span class ="bold" > third item < / span > < / a > < / li >

remove
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()#找到p标签然后删除
print(wrap.text())
结果：
Hello, World This is a paragraph.
Hello, World

其他DOM方法
http://pyquery.readthedocs.io/en/latest/api.html

六、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)
结果：
< 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 >

更多CSS选择器可以查看 http://www.w3school.com.cn/css/index.asp

官方文档
http://pyquery.readthedocs.io/