Python爬虫【解析库之pyquery】

时间:2023-03-09 00:12:15
Python爬虫【解析库之pyquery】

该库跟jQuery的使用方法基本一样 

http://pyquery.readthedocs.io/ 官方文档

解析库的安装

pip3 install pyquery

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)
print(doc('li'))

2.URL初始化

from pyquery import PyQuery as pq
doc = pq(url='http://www.baidu.com')
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选择器 doc(CSS选择器)

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'))

查找元素

子元素 E.children()

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)
lis = items.find('li')
print(type(lis))
print(lis)
"""
<class 'pyquery.pyquery.PyQuery'>
<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> <class 'pyquery.pyquery.PyQuery'>
<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> """

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')
lis = items.children()
print(type(lis))
print(lis)
"""
<class 'pyquery.pyquery.PyQuery'>
<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>
"""

children

父元素 E.parent() E.parents()

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')
container = items.parent()
print(type(container))
print(container)
"""
<class 'pyquery.pyquery.PyQuery'>
<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>"""

parent()

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()
print(type(parents))
print(parents)
"""
<class 'pyquery.pyquery.PyQuery'>
<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><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>
"""

parents()

parent = items.parents('.wrap')
print(parent)
"""
<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>
"""

parents(css选择)

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(li.siblings())
"""
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-0">first item</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>
"""
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(li.siblings('.active'))

遍历

单个元素

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('.item-0.active')
print(li) """
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
"""

多个元素 doc(xx).items()

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) """
<class 'generator'>
<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>
"""

获取信息

获取属性 E.attr(name) or E.attr.name

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'))
print(a.attr.href)
"""
<a href="link3.html"><span class="bold">third item</span></a>
link3.html
link3.html
"""

获取文本 E.text()

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.text())
"""
<a href="link3.html"><span class="bold">third item</span></a>
third item
"""

获取HTML E.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())
"""
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li> <a href="link3.html"><span class="bold">third item</span></a>
"""

DOM操作

类属性的添加与移除 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')
print(li)
li.removeClass('active')
print(li)
li.addClass('active')
print(li)
"""
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li> <li class="item-0"><a href="link3.html"><span class="bold">third item</span></a></li> <li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
"""

addClass removeClass

属性操作 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)
"""
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li> <li class="item-0 active" name="link"><a href="link3.html"><span class="bold">third item</span></a></li> <li class="item-0 active" name="link" style="font-size: 14px"><a href="link3.html"><span class="bold">third item</span></a></li>
"""

attr, css

删除元素 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()) """
Hello, World This is a paragraph.
Hello, World
"""

remove

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

伪类选择器

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')
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) """
<li class="item-0">first item</li> <li class="item-0"><a href="link5.html">fifth item</a></li> <li class="item-1"><a href="link2.html">second item</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> <li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-1 active"><a href="link4.html">fourth item</a></li> <li class="item-1"><a href="link2.html">second item</a></li>
"""

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