pyquery用法详解
左丘子平
PyQuery库也是一个非常强大又灵活的网页解析库，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。语法与 jQuery 几乎完全相同，所以不用再去费心去记一些奇怪的方法了。
官网地址：http://pyquery.readthedocs.io/en/latest/
pyquery的安装，可参考博客：http://blog.csdn.net/qq_29186489/article/details/78581249
pyquery的初始化
初始化方式：字符串初始化、URL初始化、文件初始化
from pyquery import PyQuery as pq
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>
'''
#字符串初始化
doc=pq(html)
print(doc("li"))
#URL初始化
doc=pq(url="http://www.baidu.com")
print(doc("head"))
#文件初始化
doc=pq(filename="demo.html")
print(doc("li"))基本的CSS选择器
# -*- coding: utf-8 -*-
from pyquery import PyQuery as pq
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>
'''
doc=pq(html)
print(doc(".item-1"))子元素
# -*- coding: utf-8 -*-
from pyquery import PyQuery as pq
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>
'''
doc=pq(html)
item=doc(".list")
print(type(item))
print(item)
lis=item.find(".item-1")
print(type(lis))
print(lis)
lis=item.children()
print(lis)
lis=item.children(".item-0")
print(lis)父元素
# -*- coding: utf-8 -*-
from pyquery import PyQuery as pq
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>
'''
doc=pq(html)
item=doc(".item-0")
container=item.parent()
print(type(container))
print(container)
parents=item.parents()
print(parents)
parents=item.parents(".list")
print(parents)兄弟元素
# -*- coding: utf-8 -*-
from pyquery import PyQuery as pq
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>
'''
doc=pq(html)
item=doc(".item-0.active")
s=item.siblings()
print(type(s))
print(s)
s=item.siblings(".active")
print(s)遍历元素
# -*- coding: utf-8 -*-
from pyquery import PyQuery as pq
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>
'''
doc=pq(html)
items=doc(".item-0").items()
for item in items:
print(item)获取信息
获取属性信息
# -*- coding: utf-8 -*-
from pyquery import PyQuery as pq
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>
'''
doc=pq(html)
item=doc(".item-0.active a")
print(item.attr("href"))
print(item.attr.href)获取文本
# -*- coding: utf-8 -*-
from pyquery import PyQuery as pq
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>
'''
doc=pq(html)
item=doc(".item-0.active a")
print(item.text())获取HTML
# -*- coding: utf-8 -*-
from pyquery import PyQuery as pq
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>
'''
doc=pq(html)
item=doc(".item-0.active a")
print(item.html())DOM操作
移除类和增加类：removeClass、addClass
# -*- coding: utf-8 -*-
from pyquery import PyQuery as pq
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>
'''
doc=pq(html)
item=doc(".item-0.active")
print(item)
item.removeClass("active")
print(item)
item.addClass("active")
print(item)add、css
# -*- coding: utf-8 -*-
from pyquery import PyQuery as pq
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>
'''
doc=pq(html)
item=doc(".item-0.active")
print(item)
item.attr("name","link")
print(item)
item.css("font-size","14px")
print(item)remove
# -*- coding: utf-8 -*-
from pyquery import PyQuery as pq
html='''
<div id="container">
hello world!
<p>This is a paragram</p>
</div>
'''
doc=pq(html)
item=doc("#container")
print(item.text())
item.find("p").remove()
print(item.text())伪类选择器
# -*- coding: utf-8 -*-
from pyquery import PyQuery as pq
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>
'''
doc=pq(html)
#第一个元素
li=doc("li:first-child")
print(li)
#最后一个元素
li=doc("li:last-child")
print(li)
#第二个元素
li=doc("li:nth-child(2)")
print(li)
#索引大于2的元素
li=doc("li:gt(2)")
print(li)
#包含某项内容的元素
li=doc("li:contains(fifth)")
print(li)
类似资料：