解析库的使用——使用BeautifulSoup_<p class=""typo-rel"">-优快云博客

本文链接：https://blog.youkuaiyun.com/weixin_41988545/article/details/113621289
from bs4 import BeautifulSoup
html= """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b>The Dormouse's story</b></p>
<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" class="sister" id="link3">Tillie</a>
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""
soup = BeautifulSoup(html,'lxml')
print(soup.prettify())#格式化了标签
#节点选择器
print(soup.title)
print(soup.title.string)
print(type(soup.title))
print(soup.head)
print(soup.p)
#利用name可以获得节点的名称
print(soup.title.name)
#获取属性,所有属性信息
print(soup.p.attrs)
print(soup.p.attrs['class'])
#也可以soup.p['class']

#节点嵌套
print(soup.head.title.string)

#子节点和子孙节点
print(soup.p.contents)#p里面即包含文本也包含节点
#同样可以用children属性得到相应的结果
print(soup.body.children)
for i,child in enumerate(soup.body.children):
    print(i,child)


print("-----------------------------------------------------")
#如果要得到所有子孙节点的话，可以调用descendants属性
print(soup.body.descendants)
for i,child in enumerate(soup.body.descendants):
    print(i,child)

#获取某个节点父节点
print(soup.p.parent)#body
print()
#祖先节点是parents
print(list(enumerate(soup.p.parents)))

#兄弟节点
print("Next Sibling",soup.a.next_sibling)
print("Prev Sibling",soup.a.previous_sibling)
print("next Siblings",list(enumerate(soup.a.next_siblings)))
print("Prev Siblings",list(enumerate(soup.a.previous_siblings)))

#方法选择器
html='''
<div class="panel">
    <div class="panel-heading">
        <h4>Hello,this is a link</h4>
    </div>
    <div class="panel-body">
        <ul class="list" id="list-1">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
            <li class="element">Jay</li>
        </ul>
        <ul class="list list-small" id="list-2">
            <li class="element">Foo</li>
            <li class="element">Bar</li>
        </ul>
    </div>
</div>
'''
soup = BeautifulSoup(html,'lxml')
#1.find_all方法
print(soup.find_all(name='ul'))
print(type(soup.find_all(name='ul')[0]))
#因为依然是tag类型，所以依然可以在此基础上查询
for ul in soup.find_all(name='ul'):
    print(ul.find_all(name='li'))
    for li in ul.find_all(name='li'):
        print(li.string)

#2.也可属性attrs
print("属性",soup.find_all(attrs={'id':'list-1'}))
print(soup.find_all(attrs={'class':'element'}))
#3.Text,匹配文本,传入的形式可以是字符串也可以是正则表达式
import re
print(soup.find_all(text=re.compile('link')))

#2.find方法，返回第一个匹配的元素

#3.CSS选择器
print(soup.select('.panel .panel-heading'))#类
print(soup.select('ul li'))#元素
print(soup.select('#list-2 .element'))#id