python爬虫第八天，PyQuery详解

PyQuery

强大又灵活的网页解析库

初始化

字符串初始化

html='''
<div>
   <ul>
      <li class="item-0">first item</li>
      <li class="item-1"><a herf="link2.html">second item</li>
      <li class="item-0 active"><a herf="link3.html"><span class="bold">third item</span></a></li>
      <li class="item-1 active"><a herf="link4.html">fourth item</a></li>
      <li class="item-0"><a herf="link5.html">fifth item</a></li>
    </ul>
</div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
print(doc('li'))

URL初始化

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

html='''
<div id="container">
   <ul class="list">
      <li class="item-0">first item</li>
      <li class="item-1"><a herf="link2.html">second item</li>
      <li class="item-0 active"><a herf="link3.html"><span class="bold">third item</span></a></li>
      <li class="item-1 active"><a herf="link4.html">fourth item</a></li>
      <li class="item-0"><a herf="link5.html">fifth item</a></li>
    </ul>
</div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
print(doc('#container .list li'))

查找元素

子元素

![在这里插入代码片](https://img-blog.csdnimg.cn/20200920150723962.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQwNzA5MzAz,size_16,color_FFFFFF,t_70#pic_center)

lis = items.children()
print(type(lis))
print(lis)

lis = items.children('.active')
print(lis)

父元素

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

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())

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

遍历

单个元素

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

from pyquery import PyQuery as pq
doc = pq(html)
lis = doc('li').items()
print(type(li))
for li in lis:
    print(li)

获取信息

获取属性

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)

获取文本

from pyquery import PyQuery as pq
doc = pq(html)
a = doc('.item-0.active a')
print(a)
print(a.text())

获取HTML

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

DOM 操作

addClass 、removeClass

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)

attr、css

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

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())

伪类选择器

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)