Python爬虫之pyquery库的基本使用

 # 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">fifthth item</a></li>
     </ul>
 </div>
 '''

 from pyquery import PyQuery as pq
 doc = pq(html)
 print(doc('li'))

 # url初始化
 from pyquery import  PyQuery as pq
 doc = pq(url = "http://www.baidu.com")
 print(doc("head"))

 # 文件初始化
 from pyquery import PyQuery as pq
 doc = pq(filename = "demo.html")
 print(doc('li'))

 # 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">fifthth item</a></li>
     </ul>
 </div>
 '''
 from pyquery import PyQuery as pq
 doc = pq(html)
 # 注意下面id 前面需要加上#,class 前面需要加上.
 print(doc('#container .list li'))

 # 查找元素
 # 子元素
 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">fifthth item</a></li>
     </ul>
 </div>
 '''
 from pyquery import PyQuery as pq
 doc = pq(html)
 items = doc('.list')
 print(type(items))
 print(items)
 lis = items.find('li')
 print(type(lis))
 print(lis)

 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">fifthth item</a></li>
     </ul>
 </div>
 '''
 from pyquery import PyQuery as pq
 doc = pq(html)
 items = doc('.list')
 container = items.parent()
 print(type(container))
 print(container)

 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">fifthth item</a></li>
         </ul>
     </div>
 </div>
 '''
 from pyquery import PyQuery as pq
 doc = pq(html)
 items = doc('.list')
 parents = items.parents()
 print(type(parents))
 print(parents)

 parents = items.parents('.wrap')
 print(parents)

 # 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">fifthth item</a></li>
         </ul>
     </div>
 </div>
 '''
 from pyquery import PyQuery as pq
 doc = pq(html)
 # 注意下面item-0后面直接是. 没有空格
 li = doc('.list .item-0.active')
 print(li.siblings())

 print(li.siblings('.active'))

 # 遍历
 # 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 = "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">fifthth item</a></li>
         </ul>
     </div>
 </div>
 '''
 from pyquery import PyQuery as pq
 doc = pq(html)
 li = doc('.item-0.active')
 print(li)

 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">fifthth item</a></li>
         </ul>
     </div>
 </div>
 '''
 from pyquery import PyQuery as pq
 doc = pq(html)
 lis = doc('li').items()
 print(type(lis))
 for li in lis:
     print(li)

 # 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">fifthth item</a></li>
         </ul>
     </div>
 </div>
 '''
 from pyquery import PyQuery as pq
 doc = pq(html)
 a = doc('.item-0.active a')
 print(a)
 # 获取属性的两种方法
 print(a.attr('href'))
 print(a.attr.href)

 # 获取文本
 print(a.text())

 # 获取html
 from pyquery import PyQuery as pq
 doc = pq(html)
 li = doc('.item-0.active')
 print(li)
 # 得到<li>标签里面的代码
 print(li.html())

 # DOM操作
 # addClass、removeClass
 from pyquery import PyQuery as pq
 doc = pq(html)
 li = doc('.item-0.active')
 print(li)
 li.remove_class('active')
 print(li)
 li.add_class('active')
 print(li)

 # attr CSS
 li.attr('name', 'link')
 print(li)
 li.css('font-size', '14px')
 print(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()
 print(wrap.text())

 # 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">fifthth item</a></li>
         </ul>
     </div>
 </div>
 '''
 from pyquery import PyQuery as pq
 doc = pq(html)
 # 获取第一个元素
 li = doc('li:first-child')
 print(li)
 # 获取最后一个元素
 li = doc('li:last-child')
 print(li)
 # 获取第二个元素
 li = doc('li:nth-child(2)')
 print(li)
 # 获取下标为2的元素后面的所有元素（下标从0开始）
 li = doc('li:gt(2)')
 print(li)
 # 获取下标为偶数的元素
 li = doc('li:nth-child(2n)')
 print(li)
 # 获取内容包含second 的元素
 li = doc('li:contains(second)')
 print(li)