python爬虫知识点总结_python爬虫知识点总结（七）PyQuery详解

一、什么是PyQuery?

答：强大有灵活的网页解析库，模仿jQuery实现。如果你觉得正则表达式写起来太麻烦，如果你觉的BeautifulSoup语法太难记，如果你熟悉jQuery的语法，那么PyQuery就是你的绝佳选择。

二、安装

pip3 install pyquery

三、初始化

1、字符串初始化

html = '''

first item

second item

thrid item

fourth item

fifth item

'''

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、文本初始化

from pyquery import PyQuery as pq

doc = pq(filename = 'demo.html')

print(doc('li'))

四、基本CSS选择器

html = '''

first item

second item

thrid item

fourth item

fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

print(doc('#container .list li'))

1、查找元素

子元素

html = '''

first item

second item

thrid 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)

lis = items.children()

print(type(lis))

print(lis)

lis = items.children('.active')

print(lis)

父元素

html = '''

first item

second item

thrid 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)

html = '''

first item

second item

thrid item

fourth item

fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

items = doc('.list')

container = items.parents()

print(type(container))

print(container)

parent = items.parents('.wrap')

print(parents)

兄弟元素

html = '''

first item

second item

thrid item

fourth item

fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

li = doc('.list .item-0.active')

print(li.siblings())

html = '''

first item

second item

thrid item

fourth item

fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

li = doc('.list .item-0.active')

print(li.siblings('.active'))

五、遍历

1、单个元素

html = '''

first item

second item

thrid item

fourth item

fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

li = doc('.item-0.active')

print(li)

html = '''

first item

second item

thrid 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)

2、获取信息

获取属性

html = '''

first item

second item

thrid 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)

获取文本

html = '''

first item

second item

thrid 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.text())

获取HTML

html = '''

first item

second item

thrid item

fourth item

fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

li = doc('.item-0.active')

print(li)

print(li.html())

六、DOM操作

1、addClass\removeClass

html = '''

first item

second item

thrid 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)

2、attr、css

html = '''

first item

second item

thrid 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)

3、remove

html = '''

first item

second item

thrid item

fourth item

fifth item

'''

from pyquery import PyQuery as pq

doc = pq(html)

wrap = doc('.wrap')

print(wrap.text())

wrap.find('p').remove()

print(wrap.text())

其他DOM方法

七、伪类选择器

html = '''

first item

second item

thrid 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)

# 标签从0开始

li = doc("li:nth-child(2)") # ntj-child（2）获取第2个标签

print(li)

li = doc("li:gt(2)") # gt-child(2)获取比2大的标签

print(li)

li = doc("li:nth-child(2n)") # nth-child(2n)获取偶数的标签

print(li)

li = doc("li:contains(second)") # contains(second)获取包含second文本的标签

print(li)