爬虫之PyQuery库的使用（八）

PyQuery 概念

初始化：

字符串初始化

html='''
<div>
    <ul>
          <li class="item-0">frist 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</a></li>	   
          '''
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')#这里的demo.html是已经保存好的html文件
print(doc("li"))

css选择器

#代表id .代表class

html='''
<div id="container">
    <ul class="list">
          <li class="item-0">frist 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</a></li>	   
          '''
from pyquery import PyQuery as pq
doc=pq(html)
print(doc('#container .list li'))#表示id为container的节点，选择其内部的class为list的节点内部的所有li节点，然后打印输出

查找元素

查子元素

html='''
<div id="container">
    <ul class="list">
          <li class="item-0">frist 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</a></li>	   
          '''
from pyquery import PyQuery as pq
doc=pq(html)
items=doc(".list")
print(type(items))#<class 'pyquery.pyquery.PyQuery'>
print(items)
lis=items.find('li')#  查找ul下面的li元素
print(type(lis))
print(lis)

查找父元素

html='''
<div class="warp">
<div id="container">
    <ul class="list">
          <li class="item-0">frist 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</a></li>	   
          '''
from pyquery import PyQuery as pq
doc=pq(html)
items=doc(".list")
print(type(items.parent()))
print(items.parent())# 把直接父节点也打印出来
print(items.parents())# 把外层的所有节点   分别   都给打印处出来；返回所有的祖先节点
print(items.parents(".warp"))   # 将指定的曾祖父打印处理，就不会像parents一样打印多种情况

查找兄弟节点

html='''
<div class="warp">
<div id="container">
    <ul class="list">
          <li class="item-0">frist 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</a></li>	   
          '''
from pyquery import PyQuery as pq
doc=pq(html)
li=doc(".list .item-0.active")
print(li.siblings())
print("**************")
print(li.siblings(".active"))

遍历

单个元素

html='''
<div class="warp">
<div id="container">
    <ul class="list">
          <li class="item-0">frist 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</a></li>	   
          '''
from pyquery import PyQuery as pq
doc=pq(html)
li=doc(".list .item-0.active")
print(li)
# 打印结果：
#<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>  

多个元素

html='''
<div class="warp">
<div id="container">
    <ul class="list">
          <li class="item-0">frist 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</a></li>	   
          '''
from pyquery import PyQuery as pq
doc=pq(html)
li=doc("li").items()# 就会生成一个迭代器  <class 'generator'>
print(type(li))
for i in li:
    print(i)

获取信息

获取属性

doc=pq(html)
a=doc(".item-0.active a")
print(a)
print(a.attr("href"))
print(a.attr.href) #与前面的等价

获取文本

doc=pq(html)
a=doc(".item-0.active a")
print(a)
print(a.text())
print(a.text('heelo'))#为其中添加text属性的值

获取html

doc=pq(html)
li=doc(".item-0.active")
print(li)
print(li.html('<span>changed item</span>'))#为其中添加html属性的值

DOM操作

doc=pq(html)
li=doc(".item-0.active")
print(li)
li.removeClass('active')#移除节点中的active
print(li)
li.addClass('active')#添加节点中的active
print(li)
# 打印结果：
#<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> 

参考文档:
链接: 参考文档:.

修改和增加 css，attr属性

from pyquery import PyQuery as pq
doc=pq(html)
li=doc(".item-0.active")
li.attr('name','link')#  如果属性中有name了，就会用link覆盖原来的值
print(li)
li.css('font-size','14px')
print(li)
#打印结果：
#<li class="item-0 active" name="link"><a href="link3.html"><span class="bold">third item</span></a></li>        
          
#<li class="item-0 active" name="link" style="font-size: 14px"><a href="link3.html"><span class="bold">third item</span></a></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())

打印结果：
Hello,World
This is a paragraph
Hello,World

伪类选择器

html='''
<div>
    <ul>
          <li class="item-0">frist 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</a></li>	   
          '''
from pyquery import PyQuery as pq
doc=pq(html)
li=doc('li:first-child')
print(li)
print("---------1-------")
li=doc('li:last-child')
print(li)
print("---------2-------")
li=doc('li:nth-child(2)')
print(li)
print("----------3------")
li=doc('li:gt(2)')#大于2编号以后的内容
print(li)
print("----------4------")
li=doc('li:contains(second)')#获取包含second的
print(li)
print("----------------")
#---------1-------
#<li class="item-1 active"><a href="link4.html">fourth</a></li>     
          
#---------2-------
#<li class="item-1"><a href="link2.html">second item</a></li>    
          
#----------3------
#<li class="item-1 active"><a href="link4.html">fourth</a></li>     
          
#----------4------
#<li class="item-1"><a href="link2.html">second item</a></li>    
          
----------------