爬虫--PyQuery
什么是PyQuery？
PyQuery
初始化
字符串初始化
from pyquery import PyQuery as pq 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">f
ourth item
</a>
</li>
<li class="item-0">
<a href="link5.html">
fifth item
</a>
</li>
</ul>
</div>
""" doc=pq(html)
print(doc("li"))
<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
</a>
</li>
<li class="item-1 active">
<a href="link4.html">f
ourth item
</a>
</li>
<li class="item-0">
<a href="link5.html">
fifth item
</a>
</li>
打印后的结果为：
URL初始化
from pyquery import PyQuery as pq doc = pq(url="http://www.baidu.com")
print(doc("head"))
<head><meta http-equiv="content-type" content="text/html;charset=utf-8"/><meta http-equiv="X-UA-Compatible" content="IE=Edge"/><meta content="always" name="referrer"/><link rel="stylesheet" type="text/css" href="http://s1.bdstatic.com/r/www/cache/bdorz/baidu.min.css"/><title>ç¾åº¦ä¸ä¸ï¼ä½ å°±ç¥é</title></head>
打印后的结果为：
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
from pyquery import PyQuery as pq html= """
<div id = "container">
<ul>
<li class="item-0">
first item
</li>
<li class="item-1">
<a href="link2.html">second item</a>
</li>
<li class="item-2 active">
<a href="link3.html>
<span class="bold">third item</span>
</a>
</li>
<li class="item-3 active">
<a href="link4.html">f
ourth item
</a>
</li>
<li class="item-4">
<a href="link5.html">
fifth item
</a>
</li>
</ul>
</div>
"""
doc = pq(html)
print(doc("#container .item-0"))
<li class="item-0">
first item
</li>
打印的结果为：
查找元素
子元素
from pyquery import PyQuery as pq 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-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
"""
doc = pq(html)
items = doc(".list")
print(type(items))
docs = doc.find("li")
print(type(docs))
print(docs)
<class 'pyquery.pyquery.PyQuery'>
<class 'pyquery.pyquery.PyQuery'>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-2 active"><a href="link3.html><span class=" bold="">third item</a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
打印后的结果为：
from pyquery import PyQuery as pq 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-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
"""
doc = pq(html)
items = doc(".list")
docs = items.children() # 查找所有的直接子元素
docs1 = items.children(".active")
print(docs)
print(docs1)
<li class="item-0">first item</li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-2 active"><a href="link3.html><span class=" bold="">third item</a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
<li class="item-2 active"><a href="link3.html><span class=" bold="">third item</a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
打印后的结果为：
父元素
from pyquery import PyQuery as pq 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-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
"""
doc = pq(html)
items = doc(".list")
docs = items.parent() # 查找所有的直接父元素
print(docs)
print(type(docs))
<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-2 active"><a href="link3.html><span class=" bold="">third item</a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div> <class 'pyquery.pyquery.PyQuery'>
打印后的结果：
from pyquery import PyQuery as pq 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-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
""" doc = pq(html)
items = doc(".list")
docs = items.parents() # 查找所有的直接子元素
print(type(docs))
print(docs)
<class 'pyquery.pyquery.PyQuery'>
<html><body><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-2 active"><a href="link3.html><span class=" bold="">third item</a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
</div></div></body></html><body><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-2 active"><a href="link3.html><span class=" bold="">third item</a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
</div></div></body><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-2 active"><a href="link3.html><span class=" bold="">third item</a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
</div></div><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-2 active"><a href="link3.html><span class=" bold="">third item</a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
打印后的结果为：
兄弟元素
from pyquery import PyQuery as pq 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-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
""" doc = pq(html)
items = doc(".item-0")
print(type(items.siblings()))
print(items.siblings())
<class 'pyquery.pyquery.PyQuery'>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-2 active"><a href="link3.html><span class=" bold="">third item</a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
打印后的结果为：
from pyquery import PyQuery as pq 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-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
""" doc = pq(html)
items = doc(".item-0active") # 同时匹配.item-0和active，若都包含item-0 + active则打印，否则不打印
item = doc(".item-0")
print(item.siblings())
print(type(items.siblings()))
print(items.siblings())
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-2 active"><a href="link3.html><span class=" bold="">third item</a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li> <class 'pyquery.pyquery.PyQuery'>
打印后的结果为：
遍历
单个元素
from pyquery import PyQuery as pq html= """
<div class = "wrap">
<div id = "container">
<ul class="list">
<li class="item-0 active">first item</li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
""" doc = pq(html)
items = doc(".item-0.active") # 同时匹配.item-0和active，若都包含item-0 + active则打印，否则不打印
print(type(items))
print(items)
<class 'pyquery.pyquery.PyQuery'>
<li class="item-0 active">first item</li>
打印后的结果为：
from pyquery import PyQuery as pq html= """
<div class = "wrap">
<div id = "container">
<ul class="list">
<li class="item-0 active">first item</li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
""" doc = pq(html)
items = doc("li").items() # 遍历items ,此时的items是一个迭代器
print(type(items))
for li in items:
print(li)
<class 'generator'>
<li class="item-0 active">first item</li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-2 active"><a href="link3.html><span class=" bold="">third item</a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
打印后的结果为：
获取信息
获取属性
from pyquery import PyQuery as pq html= """
<div class = "wrap">
<div id = "container">
<ul class="list">
<li class="item-0 active">first item</li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
""" doc = pq(html)
items = doc(".item-1 a")
print(items.attr("href"))
print(items.attr.href)
link2.html
link2.html
打印后的结果为：
获取文本
from pyquery import PyQuery as pq html= """
<div class = "wrap">
<div id = "container">
<ul class="list">
<li class="item-0 active">first item</li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
""" doc = pq(html)
items = doc(".item-1")
print(items.text())
second item
打印后的结果为：
获取html
from pyquery import PyQuery as pq html= """
<div class = "wrap">
<div id = "container">
<ul class="list">
<li class="item-0 active">first item</li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
""" doc = pq(html)
items = doc(".item-1")
print(items)
print(items.html())
<li class="item-1"><a href="link2.html">second item</a></li> <a href="link2.html">second item</a>
打印后的结果为：
DOM操作
addClass , removeClass
from pyquery import PyQuery as pq html= """
<div class = "wrap">
<div id = "container">
<ul class="list">
<li class="item-0 active">first item</li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
""" doc = pq(html)
items = doc(".item-1")
print(items.remove_class("active"))
print(items.add_class("actives"))
<li class="item-1"><a href="link2.html">second item</a></li> <li class="item-1 actives"><a href="link2.html">second item</a></li>
打印后的结果为：
attr , css
from pyquery import PyQuery as pq html= """
<div class = "wrap">
<div id = "container">
<ul class="list">
<li class="item-0 active">first item</li>
<li class="item-1 active"><a href="link2.html">second item</a></li>
<li class="item-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
""" doc = pq(html)
items = doc(".item-1")
print(items.attr("name","names"))
print(items.css("font-size","14px"))
<li class="item-1 active" name="names"><a href="link2.html">second item</a></li> <li class="item-1 active" name="names" style="font: 14px"><a href="link2.html">second item</a></li>
打印后的结果为：
remove
from pyquery import PyQuery as pq html= """
<div class = "wrap">
<div id = "container">
<ul class="list">
<li class="item-0 active">first item</li>
<li class="item-1 active"><a href="link2.html">second item<p>Third times</p></a></li>
<li class="item-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
""" doc = pq(html)
items = doc(".item-1")
print(items.text())
print("---------------")
items.find('p').remove()
print(items.text())
second item
Third times
---------------
second item
打印后的结果为：
其他DOM方法
https://pythonhosted.org/pyquery/api.html
伪类选择器
from pyquery import PyQuery as pq html= """
<div class = "wrap">
<div id = "container">
<ul class="list">
<li class="item-0 active">first item</li>
<li class="item-1 active"><a href="link2.html">second item<p>Third times</p></a></li>
<li class="item-2 active"><a href="link3.html><span class="bold">third item</span></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
</ul>
</div>
<div>
""" doc = pq(html)
li = doc("li:first-child")
print(li)
print("------------------------------------------------------------")
li = doc("li:last-child")
print(li)
print("------------------------------------------------------------")
li = doc("li:gt(2)")
print(li)
print("------------------------------------------------------------")
li = doc("li:nth-child(2)") # 指定一个索引顺序，获取第二个li标签
print(li)
print("------------------------------------------------------------")
li = doc("li:nth-child(2n)") # 指定一个索引顺序，获取偶数的li标签
print(li)
print("------------------------------------------------------------")
li = doc("li:contains(second)") # 查找包含second的文本标签
print(li)
<li class="item-0 active">first item</li>
------------------------------------------------------------
<li class="item-4"><a href="link5.html">fifth item</a></li>
------------------------------------------------------------
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
<li class="item-4"><a href="link5.html">fifth item</a></li>
------------------------------------------------------------
<li class="item-1 active"><a href="link2.html">second item<p>Third times</p></a></li>
------------------------------------------------------------
<li class="item-1 active"><a href="link2.html">second item<p>Third times</p></a></li>
<li class="item-3 active"><a href="link4.html">fourth item</a></li>
------------------------------------------------------------
<li class="item-1 active"><a href="link2.html">second item<p>Third times</p></a></li>
打印后的结果为：
更多的CSS选择器可以查看：http://www.w3school.com.cn/css/index.asp
Pyquery的官方文档可以查看：https://pythonhosted.org/pyquery/api.html
爬虫--PyQuery的更多相关文章
- 一起学爬虫——PyQuery常用用法总结
什么是PyQuery PyQuery是一个类似于jQuery的解析网页工具,使用lxml操作xml和html文档,它的语法和jQuery很像.和XPATH,Beautiful Soup比起来,PyQu ...
- Python爬虫-- PyQuery库
PyQuery库 PyQuery库也是一个非常强大又灵活的网页解析库,PyQuery 是 Python 仿照 jQuery 的严格实现.语法与 jQuery 几乎完全相同,所以不用再去费心去记一些奇怪 ...
- 爬虫--pyquery使用
强大又灵活的网页解析库. 初始化 字符串初始化 html = ''' <div> <ul> <li class="item-0">first ...
- Python新手需要掌握的知识点
一.基础语法 1 变量 2 逻辑判断 3 循环 4 函数 二.数据结构 1 数字(加减乘除) 2 字符串(一串字符) 3 布尔 (真假) 4 元组 (不能修改的列表) 5 列表(Python的苦力,最 ...
- 一起学爬虫——使用selenium和pyquery爬取京东商品列表
layout: article title: 一起学爬虫--使用selenium和pyquery爬取京东商品列表 mathjax: true --- 今天一起学起使用selenium和pyquery爬 ...
- Python爬虫之PyQuery使用（六）
Python爬虫之PyQuery使用 PyQuery简介 pyquery能够通过选择器精确定位 DOM 树中的目标并进行操作.pyquery相当于jQuery的python实现,可以用于解析HTML网 ...
- Python爬虫利器六之PyQuery的用法
前言 你是否觉得 XPath 的用法多少有点晦涩难记呢? 你是否觉得 BeautifulSoup 的语法多少有些悭吝难懂呢? 你是否甚至还在苦苦研究正则表达式却因为少些了一个点而抓狂呢? 你是否已经有 ...
- PYTHON 爬虫笔记十:利用selenium+PyQuery实现淘宝美食数据搜集并保存至MongeDB（实战项目三）
利用selenium+PyQuery实现淘宝美食数据搜集并保存至MongeDB 目标站点分析 淘宝页面信息很复杂的,含有各种请求参数和加密参数,如果直接请求或者分析Ajax请求的话会很繁琐.所以我们可 ...
- 小白学 Python 爬虫（23）：解析库 pyquery 入门
人生苦短,我用 Python 前文传送门: 小白学 Python 爬虫(1):开篇 小白学 Python 爬虫(2):前置准备(一)基本类库的安装 小白学 Python 爬虫(3):前置准备(二)Li ...
随机推荐
- crontab部署定时任务
1.安装cron工具:apt-getinstall cron 2.开启定时任务:crontab –e 定时任务语句格式为:执行周期+命令. 周期有5个域,分别是分,时,日(day of month), ...
- Halcon 笔记2 Blob分析
1. 数组操作 2. 可视化-更新窗口 (1)单步模式-总是:则可以自动显示图像: (2)单步模式-从不:需要调用显示函数才能显示图像. (3)单步模式-清空显示:将原图清除,再显示新图 3. 图像处 ...
- 使用salt-cloud创建虚拟机
salt-cloud也是基于openstack来做的,它可以支持多种云的使用.比如:Aliyun.Azure.DigitalOcean.EC2.Google Compute Engine.HP Clo ...
- es6中对象转数组,转map
//对象转数组let array = Object.keys(userPermission).map(key=> userPermission[key]) console.log(array) ...
- 方法调用时候 传入this 谁调用 传入谁
方法调用时候 传入this 谁调用 传入谁
- Omeed 线段树
目录 题面 题解 代码 题面 2.12 - - - 题解 大概还是挺妙的? 首先基础分和连击分互不干扰,所以可以分开统计. 基础分的统计比较简单,等于: \[A \sum_{i = l}^{r} p_ ...
- A2W W2A等所需要的文件
1.包含头文件 #include <atlbase.h> #include <atlconv.h> 2.在使用前加上,注意,不是在文件都定义. USES_CONVERSION;
- bzip2 --安装
下载源文件安装包: http://www.bzip.org/downloads.html 解压: tar -xzvf bzip2-1.0.6.tar.gz 进入解压后的目录: cd bzip2-1.0 ...
- 电子商务(电销)平台中商品模块(Product)数据库设计明细
以下是自己在电子商务系统设计中的数据库设计经验总结,而今发表出来一起分享,如有不当,欢迎跟帖讨论~ 商品表 (product)|-- 自动编号 (product_id)|-- 商品名称 (produc ...
- 「CodePlus 2017 12 月赛」可做题2（矩阵快速幂+exgcd+二分）
昨天这题死活调不出来结果是一个地方没取模,凉凉. 首先有个一眼就能看出来的规律... 斐波那契数列满足$a_1, a_2, a_1+a_2, a_1+2a_2, 2a_1+3a_2, 3a_1+5a_ ...