本篇仅作为代码记录
#!/usr/bin/python
# -*- coding: UTF-8 -*-
# Author: RuiMing Lin
# DateTime: 2021/01/25 10:18
# Description: pyquery库
from pyquery import PyQuery as pq
import requests
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>
'''
# 传入字符串
flag = False
# flag = True
if flag:
doc = pq(html)
print(doc('li'))
# 传入一个url
flag = False
# flag = True
if flag:
doc = pq(url='http://cuiqingcai.com')
print(doc('title'))
# 传入一个response对象
flag = False
# flag = True
if flag:
doc = pq(requests.get('https://www.gdut.edu.cn/').text)
print(doc('a'))
# 传入一个本地文件
flag = False
# flag = True
if flag:
doc = pq(filename='files/demo.html')
print(doc('li'))
# css选择器
flag = False
# flag = True
if flag:
doc = pq(html)
print(doc('#container .list li'))
print(type(doc('#container .list li')))
# 子孙节点:find()
flag = False
# flag = True
if flag:
doc = pq(html)
items = doc('.list')
print(type(items))
print(items)
lis = items.find('li')
print(type(lis))
print(lis)
# 子节点:children()
flag = False
# flag = True
if flag:
doc = pq(html)
items = doc('.list')
lis = items.children('li')
print(type(lis))
print(lis)
# css 类选择器
flag = False
# flag = True
if flag:
doc = pq(html)
items = doc('.list')
lis = items.children('.active')
print(lis)
# parent() 直接父节点
flag = False
# flag = True
if flag:
doc = pq(html)
items = doc('.list')
container = items.parent()
print(type(container))
print(container)
# parents() 祖先节点
flag = False
# flag = True
if flag:
doc = pq(html)
items = doc('.list')
parents = items.parents()
print(type(parents))
print(parents)
# parents() + css选择器
flag = False
# flag = True
if flag:
doc = pq(html)
items = doc('.list')
parent = items.parents('.wrap')
print(parent)
# 兄弟节点
flag = False
# flag = True
if flag:
doc = pq(html)
li = doc('.list .item-0.active')
print(li.siblings())
# 兄弟节点 + css选择器
flag = False
# flag = True
if flag:
doc = pq(html)
li = doc('.list .item-0.active')
print(li.siblings('.active'))
# 结果 -> 字符串
flag = False
# flag = True
if flag:
doc = pq(html)
li = doc('.item-0.active')
print(li)
print(str(li))
# 遍历结果
flag = False
# flag = True
if flag:
doc = pq(html)
lis = doc('li').items()
print(type(lis))
for li in lis:
print(li, type(li))
# 获取属性信息
flag = False
# flag = True
if flag:
doc = pq(html)
a = doc('.item-0.active a')
print(a, type(a))
print(a.attr('href'))
# print(a.attr.href)
flag = False
# flag = True
if flag:
doc = pq(html)
a = doc('a')
for item in a.items():
print(item.attr('href'))
# 获取文本
flag = False
# flag = True
if flag:
doc = pq(html)
a = doc('.item-0.active a')
print(a)
print(a.text())
# 返回html文本
flag = False
# flag = True
if flag:
doc = pq(html)
li = doc('.item-0.active')
print(li)
print(li.html())
# 节点操作:添加属性和删除属性
flag = False
# flag = True
if flag:
doc = pq(html)
li = doc('.item-0.active')
print(li)
li.removeClass('active')
print(li)
li.addClass('active')
print(li)
# 使用attr、text 和 html改变属性
flag = False
# flag = True
if flag:
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()
flag = False
# flag = True
if flag:
html = '''
<div class="wrap">
Hello, World
<p>This is a paragraph.</p>
</div>
'''
doc = pq(html)
wrap = doc('.wrap')
print(wrap.text())
wrap.find('p').remove()
print(wrap.text())
# 伪类选择器,和css的伪类选择器一样
flag = False
flag = True
if flag:
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)