python爬蟲知識點總結（七）PyQuery詳解

標籤：for   擷取資訊   port   pytho   資訊   com   font   實現   ext   

官方學習文檔：http://pyquery.readthedocs.io/en/latest/api.html

一、什麼是PyQuery?

答：強大有靈活的網頁解析庫，模仿jQuery實現。如果你覺得Regex寫起來太麻煩，如果你覺的BeautifulSoup文法太難記，如果你熟悉jQuery的文法，那麼PyQuery就是你的絕佳選擇。

二、安裝

pip3 install pyquery

三、初始化

1、字串初始化

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 pqdoc = pq(html)print(doc(‘li‘))

　　

2、URL初始化

from pyquery import PyQuery as pqdoc = pq(url="http://www.baidu.com")print(doc(‘head‘))

　　

3、文本初始化

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

　　

四、基本CSS選取器

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 pqdoc = pq(html)print(doc(‘#container .list li‘))

　　

1、尋找元素

　　子項目

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 pqdoc = 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 pqdoc = 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 pqdoc = 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 pqdoc = 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 pqdoc = pq(html)li = doc(‘.list .item-0.active‘)print(li.siblings(‘.active‘))

　　

五、遍曆

1、單個元素

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 pqdoc = 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 pqdoc = pq(html)lis = doc(‘li‘).items()print(type(lis))for li in lis:    print(li)

　　

2、擷取資訊

　　擷取屬性

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 pqdoc = pq(html)a = doc(‘.item-0.active a‘)print(a)print(a.attr(‘href‘))print(a.attr.href)

　　

　　擷取文本

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 pqdoc = pq(html)a = doc(‘.item-0.active a‘)print(a)print(a.attr(‘href‘))print(a.text())

　　

擷取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 pqdoc = 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 pqdoc = 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 pqdoc = 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 pqdoc = 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、偽類別選取器

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 pqdoc = pq(html)li = doc("li:first-child")print(li)li = doc("li:last-child")print(li)# 標籤從0開始li = doc("li:nth-child(2)") # ntj-child（2）擷取第2個標籤print(li)li = doc("li:gt(2)") # gt-child(2)擷取比2大的標籤print(li)li = doc("li:nth-child(2n)") # nth-child(2n)擷取偶數的標籤print(li)li = doc("li:contains(second)") # contains(second)擷取包含second文本的標籤print(li)

　　

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

官方文檔網站：http://pyquery.readthedocs.io

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

 

python爬蟲知識點總結（七）PyQuery詳解