python爬虫知识点总结（七）PyQuery详解

官方学习文档：http://pyquery.readthedocs.io/en/latest/api.html

一、什么是PyQuery?

答：强大有灵活的网页解析库，模仿jQuery实现。如果你觉得正则表达式写起来太麻烦，如果你觉的BeautifulSoup语法太难记，如果你熟悉jQuery的语法，那么PyQuery就是你的绝佳选择。

二、安装

pip3 install pyquery

三、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="blod">thrid 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、文本初始化

from pyquery import PyQuery as pq
doc = pq(filename = 'demo.html')
print(doc('li'))

四、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="blod">thrid 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'))

1、查找元素

　　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="blod">thrid 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)

　　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="blod">thrid 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 = '''
<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="blod">thrid 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')
container = items.parents()
print(type(container))
print(container)

parent = items.parents('.wrap')
print(parents)

　　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="blod">thrid 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(li.siblings())

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="blod">thrid 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(li.siblings('.active'))

五、遍历

1、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="blod">thrid 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)

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="blod">thrid 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)

2、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="blod">thrid 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'))
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="blod">thrid 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'))
print(a.text())

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="blod">thrid 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())

六、DOM操作

1、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="blod">thrid 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.removeClass('active')
print(li)
li.addClass('active')
print(li)

2、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="blod">thrid 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)

　3、remove

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="blod">thrid 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)
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

七、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="blod">thrid 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")
print(li)
li = doc("li:last-child")
print(li)
# 标签从0开始
li = doc("li:nth-child(2)") # ntj-child（2）获取第2个标签
print(li)
li = doc("li:gt(2)") # gt-child(2)获取比2大的标签
print(li)
li = doc("li:nth-child(2n)") # nth-child(2n)获取偶数的标签
print(li)
li = doc("li:contains(second)") # contains(second)获取包含second文本的标签
print(li)

更多CSS选择器可以查看 http://www.w3school.com.cn/css/index.html

官方文档网站：http://pyquery.readthedocs.io

jQuery官方文档：http://jquery.cuishifeng.cn/

转载于:https://www.cnblogs.com/cthon/p/9410588.html

python爬虫知识点总结（七）PyQuery详解相关推荐

Python爬虫之selenium库使用详解
Python爬虫之selenium库使用详解本章内容如下: 什么是Selenium selenium基本使用声明浏览器对象访问页面查找元素多个元素查找元素交互操作交互动作执行JavaS ...
python爬虫图片实例-【图文详解】python爬虫实战——5分钟做个图片自动下载器...
我想要(下)的,我现在就要 python爬虫实战--图片自动下载器之前介绍了那么多基本知识[Python爬虫]入门知识(没看的赶紧去看)大家也估计手痒了.想要实际做个小东西来看看,毕竟: talk ...
python代码案例详解-新手必学Python爬虫之Scrapy框架案例详解
Scrapy简介 Scrapy是用纯Python实现一个为了爬取网站数据.提取结构性数据而编写的应用框架,用途非常广泛. 框架的力量,用户只需要定制开发几个模块就可以轻松的实现一个爬虫,用来抓取网页内 ...
python爬虫-urllib2的使用方法详解(python3)
文章目录 python编程快速上手(持续更新中-) python爬虫从入门到精通 urllib2概述 python2与python3对比 urlopen Request User-Agent 添加更多 ...
python爬虫requests的库使用详解
Requests是python实现的简单易用的HTTP库,使用起来比urllib简洁很多,Requests库是用pythony语言开发,基urllib,采用Apache2 Licens ...
万字博文教你python爬虫Beautiful Soup库【详解篇】
python爬虫多线程是什么意思_python爬虫中多线程的使用详解
queue介绍 queue是python的标准库,俗称队列.可以直接import引用,在python2.x中,模块名为Queue.python3直接queue即可在python中,多个线程之间的数据 ...
爬虫解析利器PyQuery详解及使用实践
作者:叶庭云整理:Lemon 爬虫解析利器 PyQuery详解及使用实践之前跟大家分享了 selenium.Scrapy.Pyppeteer 等工具的使用. 今天来分享另一个好用的爬虫解析工具 P ...
Python爬虫教程-Python爬取股票数据过程详解
这篇文章主要介绍了基于Python爬取股票数据过程详解,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友可以参考下基本环境配置 python 3.6 pycha ...
python镜像下载包_python包详解
干货大礼包!21天带你轻松学Python(文末领取更多福利) 点击查看课程视频地址本课程来自于千锋教育在阿里云开发者社区学习中心上线课程<Python入门2020最新大课>,主讲人姜伟. ...

python爬虫知识点总结（七）PyQuery详解

其他DOM方法

python爬虫知识点总结（七）PyQuery详解相关推荐

最新文章

热门文章