Python BeautifulSoup 使用
BS4库简单使用:
1.最好配合LXML库，下载：pip install lxml
2.最好配合Requests库，下载：pip install requests
3.下载bs4：pip install bs4
4.直接输入pip没用？解决：环境变量->系统变量->Path->新建：C:\Python27\Scripts
案例：获取网站标题
# -*- coding:utf-8 -*-
from bs4 import BeautifulSoup
import requests
url = "https://www.baidu.com"
response = requests.get(url)
soup = BeautifulSoup(response.content, 'lxml')
print soup.title.text
标签识别
示例1：
# -*- coding:utf-8 -*-
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" 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>
</body>
</html>
'''
soup = BeautifulSoup(html, 'lxml')
# BeautifulSoup中有内置的方法来实现格式化输出
print(soup.prettify())
# title标签内容
print(soup.title.string)
# title标签的父节点名
print(soup.title.parent.name)
# 标签名为p的内容
print(soup.p)
# 标签名为p的class内容
print(soup.p["class"])
# 标签名为a的内容
print(soup.a)
# 查找所有的字符a
print(soup.find_all('a'))
# 查找id='link3'的内容
print(soup.find(id='link3'))
示例2：
# -*- coding:utf-8 -*-
from bs4 import BeautifulSoup
html = '''
<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">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>
</body>
</html>
'''
soup = BeautifulSoup(html, 'lxml')
# 将p标签下的所有子标签存入到了一个列表中
print (soup.p.contents)
find_all示例:
# -*- coding:utf-8 -*-
from bs4 import BeautifulSoup
html = '''
<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, 'lxml')
# 查找所有的ul标签内容
print(soup.find_all('ul'))
# 针对结果再次find_all,从而获取所有的li标签信息
for ul in soup.find_all('ul'):
print(ul.find_all('li'))
# 查找id为list-1的内容
print(soup.find_all(attrs={'id': 'list-1'}))
# 查找class为element的内容
print(soup.find_all(attrs={'class': 'element'}))
# 查找所有的text='Foo'的文本
print(soup.find_all(text='Foo'))
CSS选择器示例：
# -*- coding:utf-8 -*-
from bs4 import BeautifulSoup
html = '''
<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, 'lxml')
# 获取class名为panel下panel-heading的内容
print(soup.select('.panel .panel-heading'))
# 获取class名为ul和li的内容
print(soup.select('ul li'))
# 获取class名为element，id为list-2的内容
print(soup.select('#list-2 .element'))
# 使用get_text()获取文本内容
for li in soup.select('li'):
print(li.get_text())
# 获取属性的时候可以通过[属性名]或者attrs[属性名]
for ul in soup.select('ul'):
print(ul['id'])
# print(ul.attrs['id'])
