Python3爬虫 解析库的使用之pyquery

Posted 2020-11-02 Infi_chu

 Infi-chu:

http://www.cnblogs.com/Infi-chu/

pyquery专门针对CSS和jQuery的操作处理

1.初始化
字符串初始化

from pyquery import PyQuery as pq
doc = pq(html)	# 传入html文本
print(doc(\'li\'))

URL初始化

from pyquery import PyQuery as pq
doc = pq(url=\'www.baidu.com\')
print(doc(\'title\'))
# 另一种方法
from pyquery import PyQuery as pq
import requests
doc = pq(requests.get(\'http://www.baidu.com\'))
print(doc(\'title\'))

文件初始化

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

2.基本CSS选择器

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

3.查找节点
子节点

from pyquery import PyQuery as pq
doc = pq(url=\'http://www.baidu.com\')
items = doc(\'.head_wrapper\')
print(type(items))
print(items)
lis = items.find(\'a\')	# find()是查找符合条件的所有子孙节点，只查找子节点的可以使用children()
print(type(lis))
print(lis)

父节点
使用parent()方法获取该节点的父节点
使用parents()方法获取该节点的祖先节点

兄弟节点
使用siblings()方法获取兄弟节点

4.遍历

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

5.获取信息
获取属性
使用attr()方法获取属性（值）

from pyquery import PyQuery as pq
doc = pq(url=\'http://www.baidu.com\')
items = doc(\'.head_wrapper\')
print(items.attr(\'href\'))
# 也可以写成
print(items.attr.href)

# 获取所有a的属性
from pyquery import PyQuery as pq
doc = pq(url=\'http://www.baidu.com\')
a = doc(\'a\')
for i in a:
    print(i.attr.href)

获取文本
使用text()方法获取纯文本纯字符串内容

from pyquery import PyQuery as pq
doc = pq(url = \'http://www.baidu.com\')
a = doc(\'a\')
print(i.text())    # 无需遍历

使用html()方法保留标签内部的东西

from pyquery import PyQuery as pq
doc = pq(url = \'http://www.baidu.com\')
a = doc(\'a\')
for i in a:
    print(i)
    print(i.html())

6.节点操作
addClass和removeClass

from pyquery import PyQuery as pq
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 active"><a href="link5.html">fifth item</a></li>
</ul>
</div>
</div>
\'\'\'
doc = pq(html)
li = doc(\'.item-0 active\')
print(li)
li.removeClass(\'active\')
print(li)
li.addClass(\'active\')
print(li)

attr、text和html

from pyquery import PyQuery as pq
html = \'\'\'
<div class="div">
<p>ASD</p>
<ul class="list">
<li class="item-0 active"><a href="link3.html"><span class="bold">third item</span></a></li>
</ul>
</div>
\'\'\'
doc = pq(html)
li = doc(\'.item-0 active\')
print(li)
li.attr(\'name\',\'link\')
print(li)
li.text(\'changed item\')
print(li)
li.html(\'<span>changed item</span>\')
print(li)

remove()

from pyquery import PyQuery as pq
doc = pq(html)
res = doc(\'.div\')
print(res.find(\'ul\').remove().text())

7.伪类选择器
待完善