爬虫笔记:pyquery详解

pyquery

强大又灵活的网页解析库,如果你觉得正则写起来太麻烦,如果你觉得BeautifuiSoup语法太难记,如果你熟悉JQuery的语法,那么PyQuery就是你的绝对选择。

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)#声明一个对象
print(doc('li'))#传入一个选择器

doc(‘li’) 选择器,如果选择标签直接加名字,如果选择id,加#,如果选择class,前面加.点。

2URL初始化

from pyquery import PyQuery as pq
doc = pq(url='https://www.2345.com/?38001')#传入一个网址
print(doc('head'))

3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 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'))#id,class,标签名

doc(’#container .list li’)中list不一定是container的直接子对象,只要有层级关系就可以,中间需要用空格隔开。如果没有空格表示并列,表示条件需要同时满足。如(a.b)表示条件要同时满足ab。ab之间没有层级关系。

查找子元素

### 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)

print('查找子元素')
lis = items.children()
print(type(lis))
print(lis)
print('具体子元素')
lis = items.children('.active')
print(lis)

items = doc(’.list’),items是一个查找对象,对对象可以调用查找方法,如find(查找子元素),children(直接子元素)。

查找父元素

html = '''
<div class="wrap">
    <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>
 </div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
items = doc('.list')
parents = items.parents()
parent = items.parent()
print('父亲以及祖辈')
print(parents)
print('直接父元素')
print(parent)

查找兄弟元素

html = '''
<div class="wrap">
    <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>
 </div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
li = doc('.list .item-0.active')
print('所有兄弟')
print(li.siblings())
print('具体某一兄弟')
print(li.siblings('.active'))

遍历单个元素

html = '''
<div class="wrap">
    <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>
 </div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
lis = doc('li').items()
print(type(lis))
for li in lis:
    print(li)

获取信息

获取属性

html = '''
<div class="wrap">
    <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>
 </div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
a = doc('.item-0.active a')
print(a)
print(a.attr('href'))#查找网址
print(a.attr.href)

获取文本

html = '''
<div class="wrap">
    <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>
 </div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
a = doc('.item-0.active a')#.item-0.active之间没有空格,表示class同时是item-0,active。有空格表示层级关系,如active a
print(a)
print(a.text())#获取文本

获取HTML

html = '''
<div class="wrap">
    <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>
 </div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
li = doc('.item-0.active')
print(li)
print(li.html())

DOM操作

addClass、removeClass

html = '''
<div class="wrap">
    <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>
 </div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
li = doc('.item-0.active')#.item-0.active,属性之间无空格,表示同时满足
print(li)
li.removeClass('active')
print(li)
li.addClass('active')
print(li)

attr、css

html = '''
<div class="wrap">
    <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>
 </div>
'''
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())

其他DOM方法

http://pyquery.readthedocs.io/en/latest/api.html

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"><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>
 </div>
'''
from pyquery import PyQuery as pq
doc = pq(html)
li = doc('li:first-child')#获取第一个Li标签
print(li)
li = doc('li:last-child')#获取最后一个li标签
print(li)
li = doc('li:nth-child(2)')#获取第二个li标签
print(li)
li = doc('li:gt(2)')#获取第二个li标签
print(li)
li = doc('li:nth-child(2n)')#获取第二个li标签
print(li)
li = doc('li:contains(second)')#获取第二个li标签
print(li)

在这里插入图片描述

作者:电气-余登武。写作属实不容易,如果你觉得本文不错,点个赞再走。

评论 2
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

总裁余(余登武)

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