PyQuery用法详解
本文转自：
https://blog.csdn.net/jeremyjone/article/details/80450236
前言
PyQuery 是灵活而又强大的网页解析库，而在爬虫框架 PySpider 和 Scrapy 中又随处可以 PyQuery 的身影。
本节，我们通过一连串的极其简易的实例，来深入学习 PyQuery。
那我们开始吧！
一、初始化方式
有三种，可以传入字符串，传入url，传入文件。
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)#声明pq对象
print(doc('li'))#用css选择器来实现，如果要选id前面加#，如果选class，前面加.，如果选标签名，什么也不加
print(type(doc('li')))
for item in doc('li'):
print(item)
first item
second item
third item
fourth item
fifth item
URL初始化
直接传入URL，进行URL初始化，程序会自动请求URL，获得html并返回要查找的字符串
from pyquery import PyQuery as pq
doc = pq(url='http://www.baidu.com')#程序会自动请求url
print(doc('head'))#返回head标签
ç™¾åº¦ä¸€ä¸‹ï¼Œä½ å°±çŸ¥é“
文件初始化
from pyquery import PyQuery as pq
doc = pq(filename='D://demo.html')#直接传入文件名称及路径，程序会自动寻找并请求
print(doc('li'))
二、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'))#会查找id为container class为list，标签为li的对象，只是层级关系，并没有后者一定是前者的子对象
first item
second item
third item
fourth item
fifth item
查找元素
#查找元素
html = '''
- first item
- second item
- third item
- fourth item
- fifth item
'''
#子元素
from pyquery import PyQuery as pq
doc = pq(html)
items = doc('.list')#拿到items
print(type(items))
print(items)
lis = items.find('li')#利用find方法，查找items里面的li标签，得到的lis也可以继续调用find方法往下查找，层层剥离
print(type(lis))
print(lis)
- first item
- second item
- third item
- fourth item
- fifth item
first item
second item
third item
fourth item
fifth item
first item
second item
third item
fourth item
fifth item
third item
fourth item
也可以用.children()查找直接子元素
#也可以用.children()查找直接子元素
html = '''
- first item
- second item
- third item
- fourth item
- fifth item
'''
lis = items.children()
print(type(lis))
print(lis)
lis = items.children('.active')
print(lis)
first item
second item
third item
fourth item
fifth item
third item
fourth item
父元素
#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()#.parent()查找对象的父元素
print(type(container))
print(container)
#祖先节点
parents = items.parents()#.parents（）祖先节点
parent = items.parents('#container')#当然也可以传入参数
print('parent:', parent)
- first item
- second item
- third item
- fourth item
- fifth item
parent:
- first item
- second item
- third item
- fourth item
- fifth item
兄弟元素
#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')#空格表示里面，没有空格表示整体
print(li.siblings())#.siblings()兄弟元素，即同级别的元素，不包括自己
second item
first item
fourth item
fifth item
三、获取信息
获取属性
#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'))#定义a标签的href属性用于指定超链接目标的URL。 如果用户选择了a标签中的内容，那么浏览器会尝试检索并显示href属性指定的URL所表示的文档，或者执行JavaScript表达式、方法和函数的列表。
print(a.attr.href)
third item
link3.html
link3.html
获取文本
#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)#.text()获取文本信息
third item
]>
获取HTML
#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())#.html（）获取所在html
third item
third item
四、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')#删除
print(li)
li.addClass('active')#增加
print(li)
third item
third item
third item
attr、css
#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')#增加一个属性
print(li)
li.css('font-size', '14px')#增加一个css
print(li)
third item
third item
third item
remove
#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()#找到p标签然后删除
print(wrap.text())
Hello, World
This is a paragraph.
Hello, World
其他DOM方法
其他DOM方法
http://pyquery.readthedocs.io/en/latest/api.html
五、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)
first item
fifth item
second item
fourth item
fifth item
second item
fourth item
second item