Python_Web_Pyquery

PyQuery

class – .
id – #

初始化

1、字符串的初始化

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">fourth item</a></li>
         <li class="item-0"><a href="link5.html">fifth item</a></li>
     </ul></div>'''

doc = pq(html)
print(doc)
print(type(doc))
# 提取li标签内所有内容
print(doc('li'))

2、URL初始化

from pyquery import PyQuery as pq
doc = pq(url=" ")
print(doc("li"))

3、通过文件初始化

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

CSS选择器

from pyquery import PyQuery as pq

html = '''<div>
    <ul id = 'haha'>
         <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>
     </ul></div>'''

doc = pq(html)
print(doc)
# id等于haha下面的class等于item-0下的a标签下的span标签
#（注意层级关系以空格隔开）
print(doc('#haha .item-0 a span'))

查找子标签

from pyquery import PyQuery as pq

html = '''<div>
    <ul id = 'haha'>
         <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>
     </ul></div>'''
 doc = pq(html)
 items = doc('.list')
 # 寻找同时含有Item-0和active属性的list内的标签
 # 其中item-0与active并列
 itema = doc('.list .item-0.active')
 print(type(items))
 list = items.find('li')
 print(list)
 # 查找含有active子元素的标签
 lis = items.children('.active')

兄弟元素

li = doc('.list .item-0.active')
print(li.siblings())
# 可再次筛选
print(li.siblings('.active'))