BeautifulSoup是一个模块,该模块用于接收一个HTML或XML字符串,然后将其进行格式化,之后便可以使用他提供的方法进行快速查找指定元素,从而使得在HTML或XML中查找指定元素变得简单。

from bs4 import BeautifulSoup
 
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
asdf
    <div class="title">
        <b>The Dormouse's story总共</b>
        <h1>f</h1>
    </div>
<div class="story">Once upon a time there were three little sisters; and their names were
    <a  class="sister0" >Els<span>f</span>ie</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.</div>
ad<br/>sf
<p class="story">...</p>
</body>
</html>
"""
 
soup = BeautifulSoup(html_doc, features="lxml")
# 找到第一个a标签
tag1 = soup.find(name='a')
# 找到所有的a标签
tag2 = soup.find_all(name='a')
# 找到id=link2的标签
tag3 = soup.select('#link2')

简单示例

 

1. name,标签名称

1 # tag = soup.find('a')
2 # name = tag.name # 获取
3 # print(name)
4 # tag.name = 'span' # 设置
5 # print(soup)

2. attr,标签属性

1 # tag = soup.find('a')
2 # attrs = tag.attrs    # 获取
3 # print(attrs)
4 # tag.attrs = {'ik':123} # 设置
5 # tag.attrs['id'] = 'iiiii' # 设置
6 # print(soup)

3. children,所有子标签

1 # body = soup.find('body')
2 # v = body.children

4. descendants,所有子子孙孙标签

1 # body = soup.find('body')
2 # v = body.descendants

5. clear,将标签的所有子标签全部清空(保留标签名)

1 # tag = soup.find('body')
2 # tag.clear()
3 # print(soup)

6. decompose,递归的删除所有的标签

1 # body = soup.find('body')
2 # body.decompose()
3 # print(soup)

7. extract,递归的删除所有的标签,并获取删除的标签

1 # body = soup.find('body')
2 # v = body.extract()
3 # print(soup)

8. decode,转换为字符串(含当前标签);decode_contents(不含当前标签)

1 # body = soup.find('body')
2 # v = body.decode()
3 # v = body.decode_contents()
4 # print(v)

9. encode,转换为字节(含当前标签);encode_contents(不含当前标签)

1 # body = soup.find('body')
2 # v = body.encode()
3 # v = body.encode_contents()
4 # print(v)

10. find,获取匹配的第一个标签

1 # tag = soup.find('a')
2 # print(tag)
3 # tag = soup.find(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie')
4 # tag = soup.find(name='a', class_='sister', recursive=True, text='Lacie')
5 # print(tag)

11. find_all,获取匹配的所有标签

爬虫之BeautifulSoup
 1 # tags = soup.find_all('a')
 2 # print(tags)
 3  
 4 # tags = soup.find_all('a',limit=1)
 5 # print(tags)
 6  
 7 # tags = soup.find_all(name='a', attrs={'class': 'sister'}, recursive=True, text='Lacie')
 8 # # tags = soup.find(name='a', class_='sister', recursive=True, text='Lacie')
 9 # print(tags)
10  
11  
12 # ####### 列表 #######
13 # v = soup.find_all(name=['a','div'])
14 # print(v)
15  
16 # v = soup.find_all(class_=['sister0', 'sister'])
17 # print(v)
18  
19 # v = soup.find_all(text=['Tillie'])
20 # print(v, type(v[0]))
21  
22  
23 # v = soup.find_all(id=['link1','link2'])
24 # print(v)
25  
26 # v = soup.find_all(href=['link1','link2'])
27 # print(v)
28  
29 # ####### 正则 #######
30 import re
31 # rep = re.compile('p')
32 # rep = re.compile('^p')
33 # v = soup.find_all(name=rep)
34 # print(v)
35  
36 # rep = re.compile('sister.*')
37 # v = soup.find_all(class_=rep)
38 # print(v)
39  
40 # rep = re.compile('http://www.oldboy.com/static/.*')
41 # v = soup.find_all(href=rep)
42 # print(v)
43  
44 # ####### 方法筛选 #######
45 # def func(tag):
46 # return tag.has_attr('class') and tag.has_attr('id')
47 # v = soup.find_all(name=func)
48 # print(v)
49  
50  
51 # ## get,获取标签属性
52 # tag = soup.find('a')
53 # v = tag.get('id')
54 # print(v)
爬虫之BeautifulSoup