Python爬虫【解析库之pyquery】
程序员文章站
2022-05-29 13:29:59
该库跟jQuery的使用方法基本一样 http://pyquery.readthedocs.io/ 官方文档 解析库的安装 初始化 1.字符串初始化 2.URL初始化 3.文件初始化 基本CSS选择器 doc(CSS选择器) 查找元素 子元素 E.children() html = '''
子元素
children
parent()
parents()
parents(css选择)
view code
view code
view code
addclass removeclass
attr, css
remove
该库跟jquery的使用方法基本一样
官方文档
解析库的安装
pip3 install pyquery
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'))
基本css选择器 doc(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'))
查找元素
子元素 e.children()
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) """ <class 'pyquery.pyquery.pyquery'> <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> <class 'pyquery.pyquery.pyquery'> <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> """
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') lis = items.children() print(type(lis)) print(lis) """ <class 'pyquery.pyquery.pyquery'> <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> """
父元素 e.parent() e.parents()
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) """ <class 'pyquery.pyquery.pyquery'> <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>"""
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() print(type(parents)) print(parents) """ <class 'pyquery.pyquery.pyquery'> <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><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> """
parent = items.parents('.wrap') print(parent) """ <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> """
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(li.siblings()) """ <li class="item-1"><a href="link2.html">second item</a></li> <li class="item-0">first item</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> """
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(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) li = doc('.item-0.active') print(li) """ <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li> """
多个元素 doc(xx).items()
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) """ <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> """
获取信息
获取属性 e.attr(name) or e.attr.name
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')) print(a.attr.href) """ <a href="link3.html"><span class="bold">third item</span></a> link3.html link3.html """
获取文本 e.text()
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.text()) """ <a href="link3.html"><span class="bold">third item</span></a> third item """
获取html e.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()) """ <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> """
dom操作
类属性的添加与移除 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') 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> """
属性操作 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) """ <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> """
删除元素 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()) """ hello, world this is a paragraph. hello, world """
其他dom方法
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') 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) """ <li class="item-0">first item</li> <li class="item-0"><a href="link5.html">fifth item</a></li> <li class="item-1"><a href="link2.html">second item</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> <li class="item-1"><a href="link2.html">second item</a></li> <li class="item-1 active"><a href="link4.html">fourth item</a></li> <li class="item-1"><a href="link2.html">second item</a></li> """
想更多了解css选择器可以查看
上一篇: js函数传参
下一篇: 1的个数 南阳acm514