PyQuery库的使用
官方文档:http://pyquery.readthedocs.io/
1 初始化
from pyquery import PyQuery as pq
1.1 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>
'''
doc = pq(html)
1.2 URL初始化
doc = pq(url='http://www.baidu.com')
1.3 文件初始化
doc = pq(filename='demo.html')
2 基本CSS选择器
2.1 查找标签元素
.代表class,#代表id,空格隔开是搜索下一级,无空格隔开是搜索同级。
html = '''
<div id="container">
<ul>
<div class = "list">
<li class="item-0 active">first item</li>
<li class="item-1">我是<a href="link2.html">中国人</a></li>
</div>
</ul>
</div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
print(type(doc)) # <class 'pyquery.pyquery.PyQuery'>
(1)直接子元素
print(doc('.list').children()) # 输出所有子元素
print(doc('.list').children('.item-0'))
(2)子孙元素
print(doc('#container .list li'))
print(doc('#container').find('.list li'))
print(doc('#container')('.list li'))
print(doc('#container .list li.item-0'))
(4)直接父元素
print(doc('li').parent())
(5)祖先元素
print(doc('li').parents())
print(doc('li').parents('#container'))
print(doc('li').parents('ul'))
(6)兄弟元素
print(doc('li.item-0').siblings())
print(doc('li.item-0').siblings('.item-1'))
2.2 遍历元素
lis = doc('li').items()
print(type(lis)) # <class 'generator'>
for li in lis:
print(li)
2.3 获取属性、文本
li = doc('li.item-0.active')
print(li.attr('class'))
print(li.attr.class_)
li = doc('li.item-1')
print(li.text())
2.4 获取html
该标签去掉首位的本标签符号。
doc = pq(html)
ul = doc('ul')
print(ul.html())
2.5 DOM操作
li = doc('li.item-0.active')
(1)添加/修改属性
li.attr('name', 'link')
(2)添加/修改class属性
li.removeClass('active')
li.addClass('active')
(3)添加/修改style属性
li.css('font-size', '14px')
(4)删除标签
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()) # Hello, World This is a paragraph.
wrap.find('p').remove()
print(wrap.text()) # Hello, World
其他DOM方法:http://pyquery.readthedocs.io/en/latest/api.html
3 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">second item</li>
<li class="item-0 active">third item</span></li>
<li class="item-1 active">fourth item</li>
<li class="item-0">fifth item</li>
</ul>
</div>
</div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
li = doc('li:first-child') # 首个元素
li = doc('li:last-child') # 最后一个元素
li = doc('li:nth-child(2)') # 第二个元素
li = doc('li:gt(2)') # 第0、1、2 之后的元素
li = doc('li:nth-child(2n)') # 第偶数个元素
li = doc('li:contains("second item")') # 文本包含“second item”的元素