BeautifulSoup

Posted on | In

BeautifulSoup

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，之后遍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。

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
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" id="link1">Els<span>f</span>ie</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.</div>
ad<br/>sf
<p class="story">...</p>
</body>
</html>
"""
 
soup = BeautifulSoup(html_doc, features="html.parser")
# 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')

安装：

1
pip3 install beautifulsoup4

使用示例：

1
2
3
4
5
6
7
8
9
10
11
from bs4 import BeautifulSoup
 
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
    ...
</body>
</html>
"""
 
soup = BeautifulSoup(html_doc, features="html.parser")

name 标签名称

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

attr 标签属性

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

children 所有子标签

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

descendants 所有子子孙孙标签

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

clear 将标签的所有子标签全部清空（保留标签名）

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

decompose 递归的删除所有的标签

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

extract 递归的删除所有的标签，并获取删除的标签

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

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

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

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

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

find 获取匹配的第一个标签

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

find_all 获取匹配的所有标签

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

has_attr 检查标签是否具有该属性

1
2
3
tag = soup.find('a')
v = tag.has_attr('id')
print(v)

get_text 获取标签内部文本内容

1
2
3
tag = soup.find('a')
v = tag.get_text('id')
print(v)

index 检查标签在某标签中的索引位置

1
2
3
4
5
6
7
tag = soup.find('body')
v = tag.index(tag.find('div'))
print(v)
 
tag = soup.find('body')
for i,v in enumerate(tag):
print(i,v)

is_empty_element 是否是空标签(是否可以是空)或者自闭合标签

判断是否是如下标签：’br’ , ‘hr’, ‘input’, ‘img’, ‘meta’,’spacer’, ‘link’, ‘frame’, ‘base’

1
2
3
tag = soup.find('br')
v = tag.is_empty_element
print(v)

当前的关联标签

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
# soup.next
# soup.next_element
# soup.next_elements
# soup.next_sibling
# soup.next_siblings
 
#
# tag.previous
# tag.previous_element
# tag.previous_elements
# tag.previous_sibling
# tag.previous_siblings
 
#
# tag.parent
# tag.parents

查找某标签的关联标签

1
2
3
4
5
6
7
8
9
10
11
12
13
14
# tag.find_next(...)
# tag.find_all_next(...)
# tag.find_next_sibling(...)
# tag.find_next_siblings(...)
 
# tag.find_previous(...)
# tag.find_all_previous(...)
# tag.find_previous_sibling(...)
# tag.find_previous_siblings(...)
 
# tag.find_parent(...)
# tag.find_parents(...)
 
# 参数同find_all

select,select_one, CSS选择器

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
soup.select("title")
 
soup.select("p nth-of-type(3)")
 
soup.select("body a")
 
soup.select("html head title")
 
tag = soup.select("span,a")
 
soup.select("head > title")
 
soup.select("p > a")
 
soup.select("p > a:nth-of-type(2)")
 
soup.select("p > #link1")
 
soup.select("body > a")
 
soup.select("#link1 ~ .sister")
 
soup.select("#link1 + .sister")
 
soup.select(".sister")
 
soup.select("[class~=sister]")
 
soup.select("#link1")
 
soup.select("a#link2")
 
soup.select('a[href]')
 
soup.select('a[href="http://example.com/elsie"]')
 
soup.select('a[href^="http://example.com/"]')
 
soup.select('a[href$="tillie"]')
 
soup.select('a[href*=".com/el"]')
 
 
from bs4.element import Tag
 
def default_candidate_generator(tag):
    for child in tag.descendants:
        if not isinstance(child, Tag):
            continue
        if not child.has_attr('href'):
            continue
        yield child
 
tags = soup.find('body').select("a", _candidate_generator=default_candidate_generator)
print(type(tags), tags)
 
from bs4.element import Tag
def default_candidate_generator(tag):
    for child in tag.descendants:
        if not isinstance(child, Tag):
            continue
        if not child.has_attr('href'):
            continue
        yield child
 
tags = soup.find('body').select("a", _candidate_generator=default_candidate_generator, limit=1)
print(type(tags), tags)

标签的内容

1
2
3
4
5
6
7
8
9
10
11
12
13
tag = soup.find('span')
print(tag.string)          # 获取
tag.string = 'new content' # 设置
print(soup)
 
tag = soup.find('body')
print(tag.string)
tag.string = 'xxx'
print(soup)
 
tag = soup.find('body')
v = tag.stripped_strings  # 递归内部获取所有标签的文本
print(v)

append 在当前标签内部追加一个标签

1
2
3
4
5
6
7
8
9
10
tag = soup.find('body')
tag.append(soup.find('a'))
print(soup)

from bs4.element import Tag
obj = Tag(name='i',attrs={'id': 'it'})
obj.string = '我是一个新来的'
tag = soup.find('body')
tag.append(obj)
print(soup)

insert在当前标签内部指定位置插入一个标签

1
2
3
4
5
6
from bs4.element import Tag
obj = Tag(name='i', attrs={'id': 'it'})
obj.string = '我是一个新来的'
tag = soup.find('body')
tag.insert(2, obj)
print(soup)

insert_after,insert_before 在当前标签后面或前面插入

1
2
3
4
5
6
7
from bs4.element import Tag
obj = Tag(name='i', attrs={'id': 'it'})
obj.string = '我是一个新来的'
tag = soup.find('body')
#tag.insert_before(obj)
#tag.insert_after(obj)
print(soup)

replace_with 在当前标签替换为指定标签

1
2
3
4
5
6
from bs4.element import Tag
obj = Tag(name='i', attrs={'id': 'it'})
obj.string = '我是一个新来的'
tag = soup.find('div')
tag.replace_with(obj)
print(soup)

创建标签之间的关系

1
2
3
4
tag = soup.find('div')
a = soup.find('a')
tag.setup(previous_sibling=a)
print(tag.previous_sibling)

wrap 将指定标签把当前标签包裹起来

1
2
3
4
5
6
7
8
9
10
11
from bs4.element import Tag
obj1 = Tag(name='div', attrs={'id': 'it'})
obj1.string = '我是一个新来的'

tag = soup.find('a')
v = tag.wrap(obj1)
print(soup)
 
tag = soup.find('a')
v = tag.wrap(soup.find('p'))
print(soup)

unwrap 去掉当前标签，将保留其包裹的标签

1
2
3
tag = soup.find('a')
v = tag.unwrap()
print(soup)