【Python爬虫】PyQuery解析库

PyQuery解析库

阅读目录

初始化
基本CSS选择器
查找元素
遍历
获取信息
DOM操作
伪类选择器

PyQuery 是 Python 仿照 jQuery 的严格实现。语法与 jQuery 几乎完全相同。

官方文档：http://pyquery.readthedocs.io/

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'))

class="item-0">first item
         class="item-1">"link2.html">second item
         class="item-0 active">"link3.html">class="bold">third item
         class="item-1 active">"link4.html">fourth item
         class="item-0">"link5.html">fifth item

输出结果

URL初始化

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

"content-type" content="text/html;charset=utf-8"/>"X-UA-Compatible" content="IE=Edge"/>"always" name="referrer"/>"stylesheet" type="text/css" href="http://s1.bdstatic.com/r/www/cache/bdorz/baidu.min.css"/>????o|??????????? ?°±??￥é??

输出结果

文件初始化

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

class="item-0">first item
         class="item-1">"link2.html">second item
         class="item-0 active">"link3.html">class="bold">third item
         class="item-1 active">"link4.html">fourth item
         class="item-0">"link5.html">fifth item

输出结果

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'))

class="item-0">first item
         class="item-1">"link2.html">second item
         class="item-0 active">"link3.html">class="bold">third item
         class="item-1 active">"link4.html">fourth item
         class="item-0">"link5.html">fifth item

输出结果

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)

<class 'pyquery.pyquery.PyQuery'>
class="list">
         class="item-0">first item
         class="item-1">"link2.html">second item
         class="item-0 active">"link3.html">class="bold">third item
         class="item-1 active">"link4.html">fourth item
         class="item-0">"link5.html">fifth item
     
 
<class 'pyquery.pyquery.PyQuery'>
class="item-0">first item
         class="item-1">"link2.html">second item
         class="item-0 active">"link3.html">class="bold">third item
         class="item-1 active">"link4.html">fourth item
         class="item-0">"link5.html">fifth item

输出结果

html = '''

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

<class 'pyquery.pyquery.PyQuery'>
class="item-0">first item
         class="item-1">"link2.html">second item
         class="item-0 active">"link3.html">class="bold">third item
         class="item-1 active">"link4.html">fourth item
         class="item-0">"link5.html">fifth item

输出结果

html = '''

    
         first item
         second item
         third item
         fourth item
         fifth item
     
 
'''
from pyquery import PyQuery as pq
doc = pq(html)
items = doc('.list')
lis = items.children('.active')
print(lis)

class="item-0 active">"link3.html">class="bold">third item
         class="item-1 active">"link4.html">fourth item

输出结果

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)

<class 'pyquery.pyquery.PyQuery'>
"container">
    class="list">
         class="item-0">first item
         class="item-1">"link2.html">second item
         class="item-0 active">"link3.html">class="bold">third item
         class="item-1 active">"link4.html">fourth item
         class="item-0">"link5.html">fifth item

输出结果

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)

<class 'pyquery.pyquery.PyQuery'>
class="wrap">
    "container">
        class="list">
             class="item-0">first item
             class="item-1">"link2.html">second item
             class="item-0 active">"link3.html">class="bold">third item
             class="item-1 active">"link4.html">fourth item
             class="item-0">"link5.html">fifth item
         
     
 
"container">
        class="list">
             class="item-0">first item
             class="item-1">"link2.html">second item
             class="item-0 active">"link3.html">class="bold">third item
             class="item-1 active">"link4.html">fourth item
             class="item-0">"link5.html">fifth item

输出结果

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

class="wrap">
    "container">
        class="list">
             class="item-0">first item
             class="item-1">"link2.html">second item
             class="item-0 active">"link3.html">class="bold">third item
             class="item-1 active">"link4.html">fourth item
             class="item-0">"link5.html">fifth item

输出结果

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())

class="item-1">"link2.html">second item
             class="item-0">first item
             class="item-1 active">"link4.html">fourth item
             class="item-0">"link5.html">fifth item

输出结果

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('.active'))

class="item-1 active">"link4.html">fourth item

输出结果

遍历

单个元素

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)

class="item-0 active">"link3.html">class="bold">third item

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)

<class 'generator'>
class="item-0">first item
             
class="item-1">"link2.html">second item
             
class="item-0 active">"link3.html">class="bold">third item
             
class="item-1 active">"link4.html">fourth item
             
class="item-0">"link5.html">fifth item

输出结果

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)

"link3.html">class="bold">third item
link3.html
link3.html

输出结果

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())

"link3.html">class="bold">third item
third item

输出结果

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())

class="item-0 active">"link3.html">class="bold">third item
             
"link3.html">class="bold">third item

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)

class="item-0 active">"link3.html">class="bold">third item
             
class="item-0">"link3.html">class="bold">third item
             
class="item-0 active">"link3.html">class="bold">third item

输出结果

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)

class="item-0 active">"link3.html">class="bold">third item
             
class="item-0 active" name="link">"link3.html">class="bold">third item
             
class="item-0 active" name="link" style="font-size: 14px">"link3.html">class="bold">third item

输出结果

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())

Hello, World This is a paragraph.
Hello, World

输出结果

其他DOM方法 http://pyquery.readthedocs.io/en/latest/api.html

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)

class="item-0">first item
             
class="item-0">"link5.html">fifth item
         
class="item-1">"link2.html">second item
             
class="item-1 active">"link4.html">fourth item
             class="item-0">"link5.html">fifth item
         
class="item-1">"link2.html">second item
             class="item-1 active">"link4.html">fourth item
             
class="item-1">"link2.html">second item

输出结果

更多CSS选择器可以查看 http://www.w3school.com.cn/css/index.asp

【Python爬虫】

【Python爬虫】PyQuery解析库

PyQuery解析库

阅读目录

初始化

字符串初始化

URL初始化

文件初始化

基本CSS选择器

查找元素

子元素

父元素

兄弟元素

遍历

单个元素

获取信息

获取属性

获取文本

获取HTML

DOM操作

addClass、removeClass

attr、css

remove

伪类选择器

相关

【Python爬虫】新发现一个高质量跳舞视频网站爬一下试试，男生都喜欢

【Python爬虫】制作微信好友头像拼接大图

标签