PyQuery库是一个非常强大的网页解析库，如果你有前端开发经验的，都应该接触过jQuery,那么PyQuery就是你非常绝佳的选择，PyQuery 是 Python 仿照 jQuery 的严格实现。它的语法与 jQuery 几乎完全相同，所以不用再去费心记一些奇怪的方法了。
官网地址：http://pyquery.readthedocs.io/en/latest/
jQuery参考文档： http://jquery.cuishifeng.cn/
1、字符串的初始化
from pyquery import PyQuery as pq
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>'''
doc = pq(html)
print(doc)
print(type(doc))
print(doc('li'))
2、打开html文件
注意路径问题
from pyquery import PyQuery as pq
doc = pq(filename='index.html')
print(doc)
print(doc('head'))
3、打开某个网站
doc = pq('https://www.baidu.com')
# doc1 = pq(url='https://www.baidu.com')
print(doc)
print(doc('head'))
4、基于CSS选择器查找
from pyquery import PyQuery as pq
html = '''<div>
<ul id = 'haha'>
<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>'''
doc = pq(html)
print(doc)
#id等于haha下面的class等于item-0下的a标签下的span标签（注意层级关系以空格隔开）
print(doc('#haha .item-0 a span'))
5、可以通过已经查找到的标签，查找这个标签下的子标签或者父标签，而不用从头开始查找。
from pyquery import PyQuery as pq
html = '''<div class=‘content’>
<ul id = 'haha'>
<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>'''
doc = pq(html)
item = doc('div ul')
print(item)
#我们可以通过已经查找到的标签，再次查找这个标签下面的标签
print(item.parent())
print(item.children())
----------------------------------------------------------------
from pyquery import PyQuery as pq
html = '''<div class=‘content’>
<ul id = 'haha'>
<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>'''
doc = pq(html)
item = doc('div ul')
print(item)
#注意这里查找ul标签的所有子标签，也就是li标签，下面是查找class属性的标签，如果你把class换成href肯定不行，它指的只是儿子并不是子子孙孙
print(item.children('[class]'))
6、获取属性值
from pyquery import PyQuery as pq
html = '''<div class=‘content’>
<ul id = 'haha'>
<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>'''
doc = pq(html)
#注意class=item-0 active是一个class的属性，但是在pyquery里面要是中间也是空格隔开的话，
#就变成了item-0下的active标签下的a标签了，所以这里空格必须改成点
item = doc(".item-0.active a")
print(type(item))
print(item)
#获取属性值的两种方法
print(item.attr.href)
print(item.attr('href'))
7、获取标签的内容
from pyquery import PyQuery as pq
html = '''<div class=‘content’>
<ul id = 'haha'>
<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>'''
doc = pq(html)
a = doc("a").text()
print(a)
8、Dom操作
1、属性的增加删除操作
from pyquery import PyQuery as pq
html = '''<div class=‘content’>
<ul id = 'haha'>
<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>'''
doc = pq(html)
li = doc('.item-0.active')
print(li)
#删除classactive
print(li.removeClass('active'))
#增加class属性haha
print(li.addClass('haha'))
2、attrs和css
注意：下列操作有则改之，无则加之。
from pyquery import PyQuery as pq
html = '''<div class=‘content’>
<ul id = 'haha'>
<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>'''
doc = pq(html)
li = doc('.item-0.active')
print(li)
print(li.attr('id','id_test'))
print(li.css('font-size','20px'))
3、删除某个标签，在爬取过程中我们通常抓取到的内容总会有一些不想要的标签，这个时候我们可以用以下类似的方法来删除这些标签。
from pyquery import PyQuery as pq
html = '''<div class='content'>
<ul id = 'haha'>
<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>'''
doc = pq(html)
data = doc('.content')
print(data.text())
#删除所有a标签
data.find('a').remove()
#再次打印
print(data.text())