from pyquery import PyQuery as pq

html = '''
<div>
<ul>
<li class="item-0"><a href="link1.html">first item</a></li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
'''

doc = pq(html)
print(doc("li"))

结果：
<li class="item-0"><a href="link1.html">first item</a></li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</li>

把HTML字符串当作参数传递给PyQuery类，这样就成功完成了初始化。初始化的对象传入CSS选择器，通过参数li，获取到li的所有节点

2、URL初始化

初始化的参数不仅可以以字符串的形式传递，还可以传入网页的URL，此时只需要指定参数为RUL即可

from pyquery import PyQuery as pq

doc = pq(url="https://www.taobao.com/")
print(doc("title"))

结果：
<title>淘宝网 - 淘！我喜欢</title>

这样传递的话，PyQuery对象会首先请求这个URL，然后用得到的HTML内容完成初始化。相当于用网页的源代码；

from pyquery import PyQuery as pq
import requests
doc =pq(requests.get("https://www.taobao.com").text)
print(doc("title"))

结果：
<title>淘宝网 - 淘！我喜欢</title>

3、文件初始化

除了URL，还可以传递本地的文件名，此时将参数指定为filename即可：

from pyquery import PyQuery as pq

doc =pq(filename="test.html")
print(doc("li"))

结果：
<li class="item-0"><a href="link1.html">first item</a></li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</li>

读取本地的文件内容，然后用文件内容以字符串的形式传递给PyQuery类初始化

基本CSS 选择器

from pyquery import PyQuery as pq

html = '''
<div id="container">
<ul class="list">
<li class="item-0"><a href="link1.html">first item</a></li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
'''

doc = pq(html)
print(doc('#container .list li'))
print(type(doc('#container .list li')))

结果:
<li class="item-0"><a href="link1.html">first item</a></li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</li>
<class 'pyquery.pyquery.PyQuery'>

选取id为container节点，然后再选取其内部的class为list内部的所有节点，然后打印输出。

查找节点

1、子节点

需要用到find() 方法

from pyquery import PyQuery as pq

html = '''
<div>
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
</div>
'''

doc = pq(html)

print(doc('.list'))
print(type(doc('.list')))

print(doc('.list').find('li'))
print(type(doc('.list').find('li')))

结果：
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</li></ul>

<class 'pyquery.pyquery.PyQuery'>
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</li>
<class 'pyquery.pyquery.PyQuery'>

选取class为list的节点然后调用find() 方法，传入CSS选择器的li节点，最后打印输出。find() 方法会将符合条件的所有节点选择出来，结果类型是PyQuery类型

find() 查找子孙节点

from pyquery import PyQuery as pq

html = '''
<div>
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
</div>
'''

doc = pq(html)

items = doc('.list')
lis = items.children()
print(type(lis))
print(lis)


结果：
<class 'pyquery.pyquery.PyQuery'>
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</li>

筛选所有子节点中符合条件的节点，比如向筛选子节点中class为active的节点向children() 方法传入CSS选择器.active

from pyquery import PyQuery as pq

html = '''
<div>
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
</div>
'''

doc = pq(html)

items = doc('.list')
lis = items.children(".active")
print(type(lis))
print(lis)


结果：
<class 'pyquery.pyquery.PyQuery'>
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>

2、父节点

可以使用parent() 方法获取某个节点的父节点

from pyquery import PyQuery as pq

html = '''
<div>
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
</div>
'''

doc = pq(html)

items = doc('.list')
lis = items.parent()
print(type(lis))
print(lis)


结果：
<class 'pyquery.pyquery.PyQuery'>
<div>
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</li></ul>
</div>

使用parents() 返回所有的节点

from pyquery import PyQuery as pq

html = '''
<div class="warp">
<div id="container">
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
</div>
'''

doc = pq(html)

items = doc('.list')
lis = items.parents()
print(type(lis))
print(lis)


结果：
<class 'pyquery.pyquery.PyQuery'>
<html><body><div class="warp">
<div id="container">
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</li></ul>
</div>
</div>
</body></html><body><div class="warp">
<div id="container">
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</li></ul>
</div>
</div>
</body><div class="warp">
<div id="container">
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</li></ul>
</div>
</div>
<div id="container">
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</li></ul>
</div>

可以看到返回一个是class为wrap的节点，一个为id为container的节点

如果想要获取其中的一个节点信使用CSS来选择

items = doc('.list')
lis = items.parents(".warp")

3、兄弟节点

使用siblings() 方法获取

from pyquery import PyQuery as pq

html = '''
<div class="warp">
<div id="container">
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
</div>
'''

doc = pq(html)
items = doc('.list .item-0.active')
print(items.siblings())

结果：
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</li>

选择class为list的节点内部class为item-0和active的节点，也就是第三个li节点，他的兄弟节点有四个

在对兄弟节点中再次进行选择

from pyquery import PyQuery as pq

html = '''
<div class="warp">
<div id="container">
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
</div>
'''

doc = pq(html)
items = doc('.list .item-0.active')
print(items.siblings(".active"))

结果：
<li class="item-1 active"><a href="link2.html">second item</a></li>

遍历

pyquery的选择结果可能是多个节点，也可能是单个节点，类型都是Pyquesr类型，并没有返回Beautiful Soup那样的列表

对于单个节点我们可以直接答应

from pyquery import PyQuery as pq

html = '''
<div class="warp">
<div id="container">
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
</div>
'''

doc = pq(html)
li = doc('.list .item-0.active')
print(li)
print(str(li))

结果:
<li class="item-0 active"><a href="link1.html">first item</a></li>

<li class="item-0 active"><a href="link1.html">first item</a></li>

对于多个结果就需要循环遍历来取了

from pyquery import PyQuery as pq

html = '''
<div class="warp">
<div id="container">
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
</div>
'''

doc = pq(html)
lis = doc('li').items()
print(type(lis))
for li in lis:
    print(li,type(li))

结果：
<class 'generator'>
<li class="item-0 active"><a href="link1.html">first item</a></li>
 <class 'pyquery.pyquery.PyQuery'>
<li class="item-1 active"><a href="link2.html">second item</a></li>
 <class 'pyquery.pyquery.PyQuery'>
<li class="item-inactive"><a href="link3.html">third item</a></li>
 <class 'pyquery.pyquery.PyQuery'>
<li class="item-1"><a href="link4.html">fourth item</a></li>
 <class 'pyquery.pyquery.PyQuery'>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</li> <class 'pyquery.pyquery.PyQuery'>

调用items() 方法后会得到一个生成器，遍历一下，就可以得到li节点对象了

获取信息

1、获取属性

得到某个PyQuery类型的节点后，就可以调用attr() 方法来获取属性值

from pyquery import PyQuery as pq

html = '''
<div class="warp">
<div id="container">
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
</div>
'''

doc = pq(html)
a = doc('.item-0.active a')
print(type(a))
print(a.attr("href"))
print(a.attr.href)


结果：
<class 'pyquery.pyquery.PyQuery'>
link1.html
link1.html

2、获取文本

使用节点之后的一个主要操作就是获取其内部的文本了，测试可以调用text() 方法来实现

from pyquery import PyQuery as pq

html = '''
<div class="warp">
<div id="container">
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
</div>
'''

doc = pq(html)
a = doc('.item-0.active a')
print(a)
print(a.text())


结果：
<a href="link1.html">first item</a>
first item

这里获取的内部信息，他会忽略掉节点内部包含的所有HTML，只返回纯文本内容，但如果想要获取这个节点内部的HTML文本，就要用html() 方法


doc = pq(html)
li = doc('.item-0.active')
print(li)
print(li.html())

结果：
<li class="item-0 active"><a href="link1.html">first item</a></li>

<a href="link1.html">first item</a>

这里返回的节点中所有的HTML文本

那如果有多个节点，test() 和 html() 会返回什么？


doc = pq(html)
li = doc('li')
print(li.html())
print(li.text())
print(type(li.text()))

结果：
<a href="link1.html">first item</a>
first item second item third item fourth item fifth item
<class 'str'>

html() 方法返回的是第一个li节点的内部HTML文本，而text() 则返回了所有的li节点的纯文本，中间用一个空格隔开，即返回结果过是一个字符串

节点操作

1、add_class和remove_class

add_calss、remove_class这些方法可以动态改变节点的class属性

from pyquery import PyQuery as pq

html = '''
<div class="warp">
<div id="container">
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
</div>
'''

doc = pq(html)
li = doc('.item-0.active')
print(li)
li.remove_class("active")
print(li)
li.add_class("active")
print(li)

结果：
<li class="item-0 active"><a href="link1.html">first item</a></li>

<li class="item-0"><a href="link1.html">first item</a></li>

<li class="item-0 active"><a href="link1.html">first item</a></li>

调用 remove_class() 方法，将li节点的active 这个class 移除，后来又调 add_calss() 方法，将 class添加回来。每执行一次操作，就打印输出当前 li 节点的内容，一共输出了3次，第二次输出时， li 节点的 active 这个 class 被移除了，第三次class 又添加回来

2、attr、text和html

可以使用attr() 方法对属性进行操作，text() 和html() 来改变节点内部的内容

doc = pq(html)
li = doc('.item-0.active')
print(li)
li.attr("name","link")
print(li)
li.text("chamge item")
print(li)
li.html("<span> chanage item </span>")
print(li)

结果：
<li class="item-0 active"><a href="link1.html">first item</a></li>

<li class="item-0 active" name="link"><a href="link1.html">first item</a></li>

<li class="item-0 active" name="link">chamge item</li>

<li class="item-0 active" name="link"><span> chanage item </span></li>

attr()方法只传入第一个参数的属性名，则是获取这个属性值如果传入第二个参数，可以用来修改属性值 text() 和 html()方法如果不传参数，则是获取节点内纯文本和 HTML文本本；如果传人参数，则进行赋值

3、remove()

remove()方法就是移除，它有时会为信息的提取带来非常大的便利

html='''
<div class="wrap">
Hellow，World
<p>This is a paragraph.</p>
</div> 
'''
from pyquery import PyQuery as pq
doc=pq(html)
wrap = doc(".wrap")
print(wrap.text())

结果：
Hellow，World
This is a paragraph.

想要提取Hellow, Word，而不需要 This is paragraphs；先定位到wrap节点，去除p节点内部的文本

html='''
<div class="wrap">
Hellow，World
<p>This is a paragraph.</p>
</div> 
'''
from pyquery import PyQuery as pq
doc=pq(html)
wrap = doc(".wrap")
wrap.find("p").remove()
print(wrap.text())

结果：

Hellow，World

其他操作参考：http: //pyquery.readthedocs.io/en/latest/api.html

伪类选择器

css 选择器之所以强大，还有个很重要的原因，那就是它支持多种多样的伪类选择器，例如选择第一个节点、最后一个节点、奇偶数节点、包含某一文本的节点等

from pyquery import PyQuery as pq

html = '''
<div class="warp">
<div id="container">
<ul class="list">
<li class="item-0 active"><a href="link1.html">first item</a></li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a hrer="link5.html">fifth item</a>
</ul>
</div>
</div>
'''

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)

结果：
<li class="item-0 active"><a href="link1.html">first item</a></li>

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

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

<li class="item-1 active"><a href="link2.html">second item</a></li>

CSS3的伪类选择器，一次选择第一个li节点，左后一个li节点，第二个li节点，偶数位置的li节点，包含secnd文本的li节点；可以操作http://www.w3school.com.cn/css

标签：pyquery,doc,爬虫,li,item,html,print,解析,节点
来源： https://blog.csdn.net/Smart_look/article/details/122180996