爬虫基础学习 - Beautifulsoup

beautiful soup:

bs4

用于解析html and xml文档

解析器：html.parser、lxml解析器和XML的内置解析器

文档遍历：跟xpath差不多，也是整理成树形结构

搜索：find（） find_all()

修改：增删改查bs4都支持

提取数据

处理特殊字符

解析器：

html.parser（内置）还行

lxml 速度比较快

xml 速度比较快

html5lib 用的比较少速度慢

pip install bs4

节点选择器：

直接调用节点名既可选择该节点。

如果有多个标签，使用标签名来打印该节点的话，就是打印第一个

类型：

<class 'bs4.element.Tag'>

属性：

name:表示标签的名字

方法：

嵌套选择：

返回<class 'bs4.element.Tag'>，可以继续下一步的选择

关联选择：

有时候我们选择的时候不能一部到位，需要先选择某节点，然后选择他的父节点，子节点

子节点：

soup.p.children

子孙节点：

soup.p.descendants

父节点：

soup.a.parent

祖先节点：

soup.a.parents

上一个兄弟节点：

soup.a.previous_sibling

下一个兄弟节点：

soup.a.next_sibling

后面所有的兄弟节点：

soup.a.next_siblings

前面所有的兄弟节点：

soup.a.previous_siblings

方法选择器：

find_all,

find方法

CSS选择器：

调用select方法，传入对应的css

复制代码

#! /usr/bin/env python3

import re
from bs4 import BeautifulSoup


html = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title" name="dromouse"><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" id="link1"><!-- Elsie --></a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""

html_c = """
<html><head><title>The Dormouse's story</title></head>
<body>
"""

soup = BeautifulSoup("<p>hello</p>", 'lxml')
print(soup.p.string)

soup = BeautifulSoup(html, 'lxml')
print(soup.prettify())

soup = BeautifulSoup(html, 'lxml')

# 选择html 文档下的title标签
print(soup.title)

# 打印标签下的节点内容
print(soup.title.string)
print(soup.head)
print(soup.head.string)
print(soup.p)

# 存在多个节点，会选择第一个出现的节点
print(soup.p.string)

# <class 'bs4.element.Tag'>
print(type(soup.title))

# 用name 属性获取节点名称
print(soup.title.name)

# 获取属性 id class
print(soup.p.attrs)
print(soup.p.attrs['name'])

print(soup.p['name'])
print(soup.p['class'])

soup = BeautifulSoup(html_c, 'lxml')

# 嵌套选择：可以进一步选择
# 打印html文档里的title标签
print(soup.head.title)

# <class 'bs4.element.Tag'>
print(type(soup.head.title))
print(soup.head.title.string)

html_2 = """
<html>
    <head>
        <title>The Dormouse's story</title>
    </head>
    <body>
        <p class="story">
            Once upon a time there were three little sisters; and their names were
            <a href="http://example.com/elsie" class="sister" id="link1">
                <span>Elsie</span>
            </a>
            <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a>
            and
            <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>
            and they lived at the bottom of a well.
        </p>
        <p class="story">...</p>
"""

# 关联选择
soup = BeautifulSoup(html_2, 'lxml')
print(soup.p.contents)
print(soup.p.children)

for i, child in enumerate(soup.p.children):
    print(i)
    print(child)

print(soup.p.descendants)

for i, child in enumerate(soup.p.descendants):
    print(i, child)

soup1 = BeautifulSoup(html_2, 'lxml')
print(soup1.a.parent)
print(soup1.a.parents)
print(list(enumerate(soup1.a.parents)))

print(soup1.a.next_sibling)
print(soup1.a.previous_sibling)
print(list(enumerate(soup1.a.next_sibling)))
print(list(enumerate(soup1.a.previous_sibling)))

# 祖先节点
print(soup1.a.parents)
print(list(soup1.a.parents)[0])
print(list(soup1.a.parents)[0].attrs['class'])

html_3 = """
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</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_3, 'lxml')
print(soup.find_all(name='ul'))
print(soup.find_all(name='ul')[1])

for ul in soup.find_all(name='ul'):
    # 打印ul节点下的li元素
    print(type(ul.find_all(name='li')))
    for li in ul.find_all(name='li'):
        print(li.string)

# 使用find_all查询所有ID属性为'list-1'的属性
print(soup.find_all(attrs={'id': 'list-2'}))
print(soup.find_all(attrs={'class': 'element'}))
print(soup.find_all(class_='element'))

html_4 = """
<div class="panel">
    <div class="panel-body">
        <a>Hello, this is a link</a>
        <a>Hello, this is a link, too</a>
    </div>
"""

html_5 = """
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</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_4, 'lxml')
found_elements = soup.find_all(text=re.compile('link'))
print(found_elements)


soup = BeautifulSoup(html_5, 'lxml')

ul_tag = soup.find(name='ul')
print(ul_tag)

list_element = soup.find(class_='list')
print(list_element)

html_6 = """
<div class="panel">
    <div class="panel-heading">
        <h4>Hello</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_6, 'lxml')
print(soup.select('.panel .panel-heading'))
print(soup.select('ul li'))

print(soup.select('#list-2 .element'))

for ul in soup.select('ul'):
    print(ul.select('li'))
    print(ul['id'])
    print(ul.attrs['id'])

for li in soup.select('li'):
    print(li.string)
    print(li.get_text())