python—pyquery

PyQuery

"""
强大又灵活的网页解析库
pip install pyquery
官方文档
http://pyquery.readthedocs.io/

API风格和前段jquery 相似
"""

初始化

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">fifth item</a></li>
     </ul>
 </div>
'''
from pyquery import PyQuery as pq
doc = pq(html) # 创建一个对象
print(doc('li')) #传入css选择器,jQuery也是css选择器
# 选择id 就使用#
# 选择class 前面加.
# 标签名 什么也不加，直接传

URL初始化

# 自动请求url，把得到的html传递给函数
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

"""
选择id 就使用#
选择class 前面加.
标签名 什么也不加，直接传

"""

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>
'''
from pyquery import PyQuery as pq
doc = pq(html)
print(doc('#container .list li'))

#这里我们需要注意的一个地方是doc('#container .list li')，这里的三者之间的并不是必须要挨着，只要是层级关系就可以,

常用CSS选择器方法

class	.color	选择class='color’内的所有元素
#id	#info	选择id='info’的所有元素
*	*	选择所有元素
element	p	选择所有的p元素
element,element	div,p	选择所有div和p元素
element element	div p	选择所有div内的p元素
[attribute]	[target]	选择所有带target属性的元素
[attribute=value]	[target=_blank]	选择target="_blank"的所有元素

查找元素

from pyquery import PyQuery as pq
doc = pq(html)
items = doc('.list')
print(type(items))
print(items)
lis = items.find('li') # 向里面查找li
print(type(lis))
print(lis)

# 查找子元素
li = items.children() 
print(type(li))
print(li)


#父元素
from pyquery import PyQuery as pq
doc = pq(html)
items = doc('.list')
container = items.parent()
print(type(container))
print(container)

#祖先元素
from pyquery import PyQuery as pq
doc = pq(html)
items = doc('.list')
parents = items.parents()
print(type(parents))
print(parents)


# 兄弟元素
from pyquery import PyQuery as pq
doc = pq(html)
li = doc('.list .item-0.active')
print(li.siblings())

获取信息

# 获取属性
"""
pyquery对象.attr(属性名)
pyquery对象.attr.属性名

"""
from pyquery import PyQuery as pq
doc = pq(html)
a = doc('.item-0.active a')
print(a)
print(a.attr('href'))
print(a.attr.href)
"""
<a href="link3.html"><span class="bold">third item</span></a>
link3.html
link3.html
"""



# 获取文本
from pyquery import PyQuery as pq
doc = pq(html)
a = doc('.item-0.active a')
print(a)
print(a.text())
"""
<a href="link3.html"><span class="bold">third item</span></a>
third item
"""

# 获取html
from pyquery import PyQuery as pq
doc = pq(html)
li = doc('.item-0.active')
print(li)
print(li.html())

DOM操作

# 添加和删除属性

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">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')
print(li)
li.addClass('active')
print(li)
"""
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
             
<li class="item-0"><a href="link3.html"><span class="bold">third item</span></a></li>
             
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
"""

# 同样的我们可以通过attr给标签添加和修改属性，
from pyquery import PyQuery as pq
doc = pq(html)
li = doc('.item-0.active')
print(li)
li.attr('name', 'link')
print(li)
li.css('font-size', '14px')
print(li)

# remove
# 有时候我们获取文本信息的时候可能并列的会有一些其他标签干扰，这个时候通过remove就可以将无用的或者干扰的标签直接删除，从而方便操作
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())
"""
Hello, World This is a paragraph.
Hello, World

其他DOM方法
http://pyquery.readthedocs.io/en/latest/api.html
"""

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">fifth item</a></li>
         </ul>
     </div>
 </div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
li = doc('li:first-child')
print(li)
li = doc('li:last-child')
print(li)
li = doc('li:nth-child(2)')
print(li)
li = doc('li:gt(2)')
print(li)
li = doc('li:nth-child(2n)')
print(li)
li = doc('li:contains(second)')
print(li)

"""
<li class="item-0">first item</li>
             
<li class="item-0"><a href="link5.html">fifth item</a></li>
         
<li class="item-1"><a href="link2.html">second item</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>
         
<li class="item-1"><a href="link2.html">second item</a></li>
             <li class="item-1 active"><a href="link4.html">fourth item</a></li>
             
<li class="item-1"><a href="link2.html">second item</a></li>


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