007 PyQuery

1.安装PyQuery

pip install pyquery

2.PyQuery

1.初始化

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>
\'''
from pyquery import PyQuery as pq
doc = pq(html)
print(doc('li'))
2.URL初始化
from pyquery import PyQuery as pq
doc = pq(url='http://www.baidu.com')
print(doc('head'))
3.文件初始化
from pyquery import PyQuery as pq
doc = pq(filename='demo.html')
print(doc('li'))

2.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 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'))

3.查找元素

1.子元素
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)
items = doc('.list')
print(type(items))
print(items)
lis = items.find('li')
print(type(lis))
print(lis)
lis = items.children()
print(type(lis))
print(lis)
lis = items.children('.active')
print(lis)
2.父元素
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)
items = doc('.list')
container = items.parent()
print(type(container))
print(container)
\```

html = ”’


\”’
from pyquery import PyQuery as pq
doc = pq(html)
items = doc(‘.list’)
parents = items.parents()
print(type(parents))
print(parents)
#### 3.兄弟元素

html = ”’


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

html = ”’


\”’
from pyquery import PyQuery as pq
doc = pq(html)
li = doc(‘.list .item-0.active’)
print(li.siblings(‘.active’))
### 4.遍历
#### 1.单个元素

html = ”’


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

html = ”’


\”’
from pyquery import PyQuery as pq
doc = pq(html)
lis = doc(‘li’).items()
print(type(lis))
for li in lis:
print(li)
\<class 'generator'\>
\<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\>

### 5.获取信息
#### 1.获取属性

html = ”’


\”’
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

#### 2.获取文本

html = ”’


\”’
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

#### 3.获取HTML

html = ”’


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

\<a href="link3.html"\>\<span class="bold"\>third item\</span\>\</a\>

### 6.DOM操作
#### 1.addClass、removeClass

html = ”’


\”’
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\>

#### 2.attr、css

html = ”’


\”’
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)
\<li class="item-0 active"\>\<a href="link3.html"\>\<span class="bold"\>third item\</span\>\</a\>\</li\>

\<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\>

#### 3.remove

html = ”’

Hello, World

This is a paragraph.

\”’
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

### 7.其他DOM方法
[pyquery文档]http://pyquery.readthedocs.io/en/latest/api.html

### 8.伪类选择器

html = ”’


\”’
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)
“`
\
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

豆豆orz

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值