PyQuery使用

强大灵活的网页解析库。如果你觉得正则写起来太麻烦，或者BeautifulSoup语法太难记，如果你熟悉jQuery的语法，那么pyquery就是最佳选择。它与jQuery api相同，可以无缝迁移

安装

pip install pyquery

初始化

字符串初始化

html = '''

    

         
first item
         
second item
         
third item
         
fourth item
         
fifth item
     
 
'''
from pyquery import PyQuery as pq
doc = pq(html)
print(doc('li'))

URL初始化

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

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

html = '''

    

         
first item
         
second item
         
third item
         
fourth item
         
fifth item
     
 
'''
from pyquery import PyQuery as pq
doc = pq(html)
print(doc('#container .list li'))

查找元素

子元素

html = '''

    

         
first item
         
second item
         
third item
         
fourth item
         
fifth item
     
 
'''
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)

lis = items.children()
print(type(lis))
print(lis)

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

父元素

html = '''

    

         
first item
         
second item
         
third item
         
fourth item
         
fifth item
     
 
'''
from pyquery import PyQuery as pq
doc = pq(html)
items = doc('.list')
container = items.parent()
print(type(container))
print(container)
html = '''

    

        

             
first item
             
second item
             
third item
             
fourth item
             
fifth item
         
     
 
'''
from pyquery import PyQuery as pq
doc = pq(html)
items = doc('.list')
parents = items.parents()
print(type(parents))
print(parents)
parent = items.parents('.wrap')
print(parent)

兄弟元素

html = '''

    

        

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

遍历

html = '''

    

        

             
first item
             
second item
             
third item
             
fourth item
             
fifth item
         
     
 
'''
from pyquery import PyQuery as pq
doc = pq(html)
lis = doc('li').items()
print(type(lis))
for li in lis:
    print(li)

获取信息

获取属性

html = '''

    

        

             
first item
             
second item
             
third item
             
fourth item
             
fifth item
         
     
 
'''
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)

获取文本

html = '''

    

        

             
first item
             
second item
             
third item
             
fourth item
             
fifth item
         
     
 
'''
from pyquery import PyQuery as pq
doc = pq(html)
a = doc('.item-0.active a')
print(a)
print(a.text())

获取HTML

html = '''

    

        

             
first item
             
second item
             
third item
             
fourth item
             
fifth item
         
     
 
'''
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 = '''

    

        

             
first item
             
second item
             
third item
             
fourth item
             
fifth item
         
     
 
'''
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

html = '''

    

        

             
first item
             
second item
             
third item
             
fourth item
             
fifth item
         
     
 
'''
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 = '''

    Hello, World
    
This is a paragraph.
 
'''
from pyquery import PyQuery as pq
doc = pq(html)
wrap = doc('.wrap')
print(wrap.text())
wrap.find('p').remove()
print(wrap.text())

伪类选择器

html = '''

    

        

             
first item
             
second item
             
third item
             
fourth item
             
fifth item
         
     
 
'''
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)

其他DOM方法

http://pyquery.readthedocs.io/en/latest/api.html