BeautifulSoup与Xpath解析库总结

一、BeautifulSoup解析库

　　1、快速开始

html_doc = """
<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" class="sister" >Elsie</a>,
<a href="http://example.com/lacie" class="sister" >Lacie</a> and
<a href="http://example.com/tillie" class="sister" >Tillie</a>;
and they lived at the bottom of a well.</p>

<p class="story">...</p>
"""

from bs4 import BeautifulSoup
soup = BeautifulSoup(html_doc)

print(soup.prettify()) # 结构化输出文档
print(soup.title) # 获取title标签
print(soup.title.name) # 获取title标签名称 
print(soup.title.parent.name)
print(soup.p['class'])

　　从文档中找到所有<a>标签的链接：

for link in soup.find_all('a'):
    print(link.get('href'))

　　从文档中获取所有文字内容：

　print(soup.get_text())

　　2、标签选择器

#1、标签选择器：即直接通过标签名字选择，选择速度快，如果存在多个相同的标签则只返回第一个
#2、获取标签的名称
#3、获取标签的属性
#4、获取标签的内容
#5、嵌套选择
#6、子节点、子孙节点
#7、父节点、祖先节点
#8、兄弟节点

#1、标签选择器：即直接通过标签名字选择，选择速度快，如果存在多个相同的标签则只返回第一个
html_doc = """
<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" class="sister" >Elsie</a>,
<a href="http://example.com/lacie" class="sister" >Lacie</a> and
<a href="http://example.com/tillie" class="sister" >Tillie</a>;
and they lived at the bottom of a well.</p>

<p class="story">...</p>
"""

from bs4 import BeautifulSoup
soup=BeautifulSoup(html_doc,'lxml')
print(soup.head)
print(type(soup.head)) #<class 'bs4.element.Tag'>

print(soup.p) #存在多个相同的标签则只返回第一个
print(soup.a) #存在多个相同的标签则只返回第一个

#2、获取标签的名称
print(soup.p.name)

#3、获取标签的属性
print(soup.p.attrs)

#4、获取表的内容
print(soup.p.string)

'''
对下面的这种结构，soup.p.string 返回为None,因为里面有a
<p id='list-1'>
    哈哈哈哈
    <a class='sss'>
        <span>
            <h1>aaaa</h1>
        </span>
    </a>
    <b>bbbbb</b>
</p>
'''

#5、嵌套选择
print(soup.head.title.string)
print(soup.body.a.string)

#6、子节点、子孙节点
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title">
    <b>The Dormouse's story</b>
    Once upon a time there were three little sisters; and their names were
    <a href="http://example.com/elsie" class="sister" >
        <span>Elsie</span>
    </a>,
    <a href="http://example.com/lacie" class="sister" >Lacie</a> and
    <a href="http://example.com/tillie" class="sister" >Tillie</a>;
    and they lived at the bottom of a well.
</p>
<p class="story">...</p>
"""
from bs4 import BeautifulSoup
soup=BeautifulSoup(html_doc,'lxml')

print(soup.p.contents) #p下所有子节点
print(soup.p.children) #得到一个迭代器,包含p下所有子节点
for i,child in enumerate(soup.p.children):
    print(i,child)

print(soup.p.descendants) #获取子孙节点,p下所有的标签都会选择出来
for i,child in enumerate(soup.p.descendants):
    print(i,child)

#7、父节点、祖先节点
print(soup.a.parent) #获取a标签的父节点
print(soup.a.parents) #找到a标签所有的祖先节点，父亲的父亲，父亲的父亲的父亲...


#8、兄弟节点
print(soup.a.next_siblings) #得到生成器对象
print(soup.a.previous_siblings) #得到生成器对象

示例