安装
pip install pyquery
验证安装
In [1]: import pyquery
没报错即表示安装成功
pyquery
pyquery 介绍
虽然 xpath 与 Beautiful Soup 已经很强大了，不过语法还是过于啰嗦，pyquery提供了更加简洁优雅的语法，你可以像写jquery一般提取数据
数据初始化
In [1]: 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"><a href="link4.html">fourth item</a></li>
...: <li class="item-0"><a href="link5.html">fifth item</a></li>
...: </ul>
...: </div>
...: '''
In [2]: from pyquery import PyQuery as pq
In [3]: doc = pq(html)
In [4]: print(doc('li'))
<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"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a href="link5.html">fifth item</a></li>
初始化的数据还可以从url中获取
In [11]: doc_url = pq(url='https://www.python.org/')
In [12]: print(doc_url('title'))
<title>Welcome to Python.org</title>
除此，也可以传入文件初始化
doc_file = pq(filename='demo.html')
基本css选择器
In [2]: 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"><a href="link4.html">fourth item</a></li>
...: <li class="item-0"><a href="link5.html">fifth item</a></li>
...: </ul>
...: </div>
...: '''
In [4]: from pyquery import PyQuery as pq
In [5]: doc = pq(html)
In [6]: print(doc('#container .list li'))
<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"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a href="link5.html">fifth item</a></li>
In [7]: print(type(doc('#container .list li')))
<class 'pyquery.pyquery.PyQuery'>
查找节点
find()
In [8]: items = doc('.list')
In [10]: print(type(items))
<class 'pyquery.pyquery.PyQuery'>
In [11]: print(items)
<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"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a href="link5.html">fifth item</a></li>
</ul>
In [12]: lis = items.find('li')
In [13]: print(type(lis))
<class 'pyquery.pyquery.PyQuery'>
In [14]: print(lis)
<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"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a href="link5.html">fifth item</a></li>
find()的查找范围是节点的所有后代节点
children()
查找直接子节点
In [15]: lis = items.children()
In [16]: print(type(lis))
<class 'pyquery.pyquery.PyQuery'>
In [17]: print(lis)
<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"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a href="link5.html">fifth item</a></li>
In [18]: items.children('.active')
Out[18]: [<li.item-0.active>]
In [19]: print(items.children('.active'))
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
parent()
查找父节点
In [20]: container = items.parent()
In [21]: print(type(container))
<class 'pyquery.pyquery.PyQuery'>
In [22]: print(container)
<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"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a href="link5.html">fifth item</a></li>
</ul>
</div>
parents()
查找祖先节点
siblings()
兄弟节点
遍历节点
In [26]: lis = doc('li').items()
In [27]: print(type(lis))
<class 'generator'>
In [28]: for li in lis:
...: print(li, type(li))
...:
<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"><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'>
获取属性
# 选中class为item-0及active的a节点
In [29]: a = doc('.item-0.active a')
In [30]: print(a, type(a))
<a href="link3.html"><span class="bold">third item</span></a> <class 'pyquery.pyquery.PyQuery'>
In [31]: print(a.attr('href'))
link3.html
如果是多个节点的属性，就需要遍历节点获取
In [32]: a = doc('a')
In [33]: for item in a.items():
...: print(item.attr('href'))
...:
link2.html
link3.html
link4.html
link5.html
获取文本
text()
In [35]: a = doc('.item-0.active a')
In [36]: print(a)
<a href="link3.html"><span class="bold">third item</span></a>
In [37]: print(a.text())
third item
html()
In [38]: li = doc('.item-0.active')
In [39]: print(li)
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
In [41]: print(li.html())
<a href="link3.html"><span class="bold">third item</span></a>
在多个节点的情况下，如果要获取每个节点的内部html，需要遍历调用html()。而text()不需要遍历，会将所有节点取出文本后合并成一个字符串
节点操作
addClass 和 removeClass
In [42]: li = doc('.item-0.active')
In [43]: print(li)
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
In [44]: li.removeClass('active')
Out[44]: [<li.item-0>]
In [45]: print(li)
<li class="item-0"><a href="link3.html"><span class="bold">third item</span></a></li>
In [46]: li.addClass('active')
Out[46]: [<li.item-0.active>]
In [47]: print(li)
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
attr, text 和 html
In [48]: li = doc('.item-0.active')
In [49]: print(li)
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
In [50]: li.attr('name', 'link')
Out[50]: [<li.item-0.active>]
In [51]: print(li)
<li class="item-0 active" name="link"><a href="link3.html"><span class="bold">third item</span></a></li>
In [52]: li.text('changed item')
Out[52]: [<li.item-0.active>]
In [53]: print(li)
<li class="item-0 active" name="link">changed item</li>
In [54]: li.html('<span>changed item</span>')
Out[54]: [<li.item-0.active>]
In [55]: print(li)
<li class="item-0 active" name="link"><span>changed item</span></li>
remove
In [56]: text = '''
...: <div class="wrap">
...: Hello, World
...: <p>This is a paragraph</p>
...: </div>
...: '''
In [57]: doc = pq(text)
In [58]: wrap = doc('.wrap')
In [59]: print(wrap.text())
Hello, World
This is a paragraph
如果我们不想要p节点内的text，就可以用remove将其移除
In [60]: wrap.find('p').remove()
Out[60]: [<p>]
In [61]: print(wrap.text())
Hello, World
伪类选择器
In [62]: doc = pq(html)
In [63]: li = doc('li:first-child')
In [64]: print(li)
<li class="item-0">first item</li>
In [65]: li = doc('li:last-child')
In [66]: print(li)
<li class="item-0"><a href="link5.html">fifth item</a></li>
In [67]: li = doc('li:nth-child(2)')
In [68]: print(li)
<li class="item-1"><a href="link2.html">second item</a></li>
In [69]: li = doc('li:gt(2)')
In [70]: print(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>
In [71]: li = doc('li:nth-child(2n)')
In [72]: print(li)
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
In [73]: li = doc('li:contains(second)')
In [74]: print(li)
<li class="item-1"><a href="link2.html">second item</a></li>
