PyQuery库详解

通过这篇文章为大家介绍崔庆才老师对Python爬虫PyQuery库的讲解，包括基本原理及其理论知识点

本文代码较多，建议阅读时间10分钟，并且注重理论与实践相结合

觉得文章比较枯燥和用电脑观看的可以点击阅读原文即可跳转到CSDN网页

目录：

一、什么是PyQuery库？

二、安装

三、PyQuery库详解

一、什么是PyQuery库？

强大而灵活的网页解析库。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就是你的绝佳选择！！！

二、安装

pip install pyquery

三、PyQuery用法讲解

1. 初始化（3种）

   
   

2. #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="boid">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'))#选择器实际上就是CSS选择器，即：选id就加“#”，选class前面加“.”
   
   
   #URL初始化
   doc1 = pq(url = "http://www.baidu.com")
   
   print(doc1("head"))
   
   #文件初始化
   doc2 = pq(filename = "demo.html")#自己下载一个HTML文件
   
   print(doc2('li'))

3. 基本CSS选择器

   
   

4. #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="boid">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>
   '''
   
   doc3 = pq(html)
   
   print(doc3("#container .list li"))#注意空格，空格代表嵌套关系

5. 查找元素

   子元素

6. #子元素（find）
   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="boid">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")#首先选中url标签
   
   print(type(items))
   
   print(items)
   
   lis = items.find('li')#实际上也是一个CSS选择器，将里面所有的li标签都打印出来；只要在它里面的标签都可以找到
   
   print(type(lis))
   
   print(lis)
   #查找直接子元素
   lis2 = items.children()
   
   print(type(lis2))
   
   
   print(lis2)
   
   lis3 = items.children('.active')
   
   print(lis3)

   父元素

7. #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="boid">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")#首先选中url标签
   #每个标签外面肯定只能套一个父元素
   container = items.parent()
   
   print(type(container))
   
   print(container)

   
   

8. #父元素2
   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="boid">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")#首先选中url标签
   
   #将所有祖先节点返回
   parents = items.parents()
   
   print(parents)
   
   print(type(parents))#打印出两个div
   #在其中进行搜索
   doc = pq(html)
   
   items = doc(".list")
   
   parents1 = items.parents(".wrap")
   
   print(parents1)#通过筛选，只剩下一个div

   兄弟元素

9. #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="boid">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')#首先选class=“.list”，空格即使选择list里面的标签，再选class=“item-0”，并列active（实际就是一个整体）
   
   print(li.siblings())#获取所有的兄弟元素
   
   #在向其中筛选
   print(li.siblings('.active'))

10. 遍历 

    
    

11. #单个元素
    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="boid">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)
    
    lis = doc('li').items()#多个元素，进行遍历，生成一个产生器
    
    print(type(lis))
    
    for li in lis:
        print(li)

12. 获取信息

    
    

13. #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="boid">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")#选择class同时为item-0和active，在选择class里面的啊标签，中间注意空格
    
    print(a)
    
    print(a.attr("href"))
    
    print(a.attr.href)#结果同上
    
    #获取文本
    
    print(a.text())#将上面的选中的class中包围的文字
    
    #获取HTML
    
    a1 = doc(".item-0.active")
    
    print(a1.html())

14. DOM操作

    
    

15. #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="boid">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")#移除active
    
    print(li)
    
    li.addClass("active")#增加active
    
    print(li)
    
    #attr、css
    
    doc = pq(html)
    li = doc(".item-0.active")
    
    li.attr("name","link")#若存在，就会覆盖
    
    print(li)
    
    li.css("font-size","14px")#增加style属性
    
    print(li)

    
    

16. #remove
    html1 = '''
    <div class="wrap">
        Hello,World
        <p>This is a paragraph.</p>
    </div>
    '''
    
    from pyquery import PyQuery as pq
    
    doc = pq(html1)
    
    wrap = doc(".wrap")
    
    print(wrap.text())
    
    wrap.find('p').remove()
    
    print(wrap.text())

    其他DOM方法： http://pythonhosted.org/pyquery/
    

    
    

17. #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="boid">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")#第一个
    
    print(li)            
    
    li1 = doc('li:last-child')#最后一个
    
    print(li1)        
    
    li2 = doc('li:nth-child(2)')#指定缩写顺序，第二个
    
    print(li2)
    
    li3 = doc("li:gt(2)")#大于2的
    
    print(li3)
    
    li4 = doc("li:nth-child(2n)")#偶数
    
    print(li4)
    
    li5 = doc("li:contains(second)")#内容包含second
    
    print(li5)

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