pyquery

強大又靈活的網頁解析庫，如果你覺得正則寫起來太麻煩，如果你覺得BeautifuiSoup語法太難記，如果你熟悉JQuery的語法，那么PyQuery就是你的絕對選擇。

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)#聲明一個對象 print(doc('li'))#傳入一個選擇器

doc(‘li’) 選擇器，如果選擇標簽直接加名字，如果選擇id，加#，如果選擇class，前面加.點。

2URL初始化

from pyquery import PyQuery as pq doc = pq(url='https://www.2345.com/?38001')#傳入一個網址 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選擇器

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，標簽名

doc(’#container .list li’)中list不一定是container的直接子對象，只要有層級關系就可以，中間需要用空格隔開。如果沒有空格表示并列，表示條件需要同時滿足。如（a.b）表示條件要同時滿足ab。ab之間沒有層級關系。

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('具體子元素') lis = items.children('.active') print(lis)

items = doc(’.list’)，items是一個查找對象，對對象可以調用查找方法，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('父親以及祖輩') 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('具體某一兄弟') print(li.siblings('.active'))

遍歷單個元素

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="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)

獲取信息

獲取屬性

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="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'))#查找網址 print(a.attr.href)

獲取文本

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之間沒有空格，表示class同時是item-0，active。有空格表示層級關系，如active a print(a) print(a.text())#獲取文本

獲取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,屬性之間無空格，表示同時滿足 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

偽類選擇器

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')#獲取第一個Li標簽 print(li) li = doc('li:last-child')#獲取最后一個li標簽 print(li) li = doc('li:nth-child(2)')#獲取第二個li標簽 print(li) li = doc('li:gt(2)')#獲取第二個li標簽 print(li) li = doc('li:nth-child(2n)')#獲取第二個li標簽 print(li) li = doc('li:contains(second)')#獲取第二個li標簽 print(li)

作者：電氣-余登武。寫作屬實不容易，如果你覺得本文不錯，點個贊再走。

總結

以上是生活随笔為你收集整理的爬虫笔记：pyquery详解的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。