PyQuery

安装

pip install pyquery

字符串初始化

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

doc CSS选择器，输出5个"li"标签

URL初始化

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

输出head标签

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

id为# class为 .    查找id为container 下的class 为list的li标签

查找元素

items = doc('.list')
print(type(items))
lis = items.find('li')
print(type(lis))
print(lis)

使用find方法，type is pyquery.pyquery.PyQuery

lis = items.chilren()
pirnt(type(lis))
print(lis)

使用chilren查找直接子元素

lis = items.chilren('.active')
print(lis)

查找class为active的元素

父元素

from pyquery import PyQuery as pq
doc = pq(html)
items = doc('.list')
container = items.parent()
print(type(container))
print(container)

from pyquery import PyQuery as pq
doc = pq(html)
items = doc('.list')
parents= items.parents()
print(type(parents))
print(parents)

parent是查找父节点，parents是查找祖先节点

parent = items.parents('.wrap')
print(parent)

可以继续筛选

兄弟元素

from pyquery import PyQuery as pq
doc = pq(html)
li = doc('.list item-0.active')
print(li.siblings())

active前面没有加空格，意味着是并列的意思，item-0和active是一个整体，现在要查找的是同时包含item-0和active的标签

siblings方法是获取兄弟元素

from pyquery import PyQuery as pq
doc = pq(html)
li = doc('.list item-0.active')
print(li.siblings('.active'))

siblings中加入参数，为筛选class为active的兄弟元素

遍历

单个元素

from pyquery import PyQuery as pq
doc = pq(html)
li = doc('item-0.active')
print(li)

是输出单个元素

from pyquery import PyQuery as pq
doc = pq(html)
lis = doc('li').items()
print(type(lis))
for li in lis:
 print(li)

items方法为选择器

获取信息

获取属性

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)

获取a元素的href属性内容

获取文本

from pyquery import PyQuery as pq
doc = pq(html)
li = doc('item-0.active')
print(a)
print(a.text())

获取HTML

from pyquery import PyQuery as pq
doc = pq(html)
a = doc('item-0.active')
print(a)
print(a.html())

DOM操作

addClass、removeClass

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)

attr、css

from pyquery import PyQuery as pq
doc = pq(html)
li = doc('item-0.active')
print(li)
li.attr('nane','link')
print(li)
li.css('font-size','14px')
print(li)

remove

from pyquery import PyQuery as pq
doc = pq(html)
wrap = doc('.wrap')
print(wrap.text())
wrap.find('p').remove()
print(wrap.text())