史上最全的BeautifulSoup解析（基本選擇器，標準選擇器，css選擇器）
阿新 • • 發佈：2018-12-26
#寫在前面
基本使用
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> """ from bs4 import BeautifulSoup soup = BeautifulSoup(html, 'lxml')#傳入解析器 print(soup.prettify())#將程式碼的格式標準化 print(soup.title.string)#崎嶇title標籤內的文字
輸出：
<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 class="sister" href="http://example.com/elsie" id="link1"> <!-- Elsie --> </a> , <a class="sister" href="http://example.com/lacie" id="link2"> Lacie </a> and <a class="sister" href="http://example.com/tillie" id="link3"> Tillie </a> ; and they lived at the bottom of a well. </p> <p class="story"> ... </p> </body> </html>
The Dormouse's story
標籤選擇器
示例程式碼如下：
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> """
1，選擇元素
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')#傳入解析器
print(soup.title)#將title標籤裡的內容包括其便籤全部輸出
print(type(soup.title))
print(soup.head)
print(soup.p)輸出結果如下：
<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 class="sister" href="http://example.com/elsie" id="link1">
<!-- Elsie -->
</a>
,
<a class="sister" href="http://example.com/lacie" id="link2">
Lacie
</a>
and
<a class="sister" href="http://example.com/tillie" id="link3">
Tillie
</a>
;
and they lived at the bottom of a well.
</p>
<p class="story">
...
</p>
</body>
</html>
The Dormouse's storyfrom bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.title.name)#獲取標籤的名稱輸出如下：
title3，獲取屬性
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.p.attrs['name'])#獲取標籤的屬性
print(soup.p['name'])#獲取標籤的屬性輸出如下：
dromouse
dromouse4，獲取內容
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.p.string)#獲取標籤內的內容輸出如下：
The Dormouse's story
5，巢狀迴圈選擇
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.head.title.string)#層層迭代，獲取head標籤裡的title標籤裡的文字輸出如下：
The Dormouse's story6，子節點和子孫節點
#方法一：獲取p標籤裡的所有子節點，以list儲存
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.p.contents)#獲取p標籤裡的所有子節點，以list儲存輸出如下：
['\n Once upon a time there were three little sisters; and their names were\n ', <a class="sister" href="http://example.com/elsie" id="link1">
<span>Elsie</span>
</a>, '\n', <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>, ' \n and\n ', <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>, '\n and they lived at the bottom of a well.\n ']
# 方法二：獲取p標籤裡的所有子節點，以迭代輸出
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.p.children)
for i, child in enumerate(soup.p.children):
print(i, child)輸出如下：
<list_iterator object at 0x04BA7550>
0
Once upon a time there were three little sisters; and their names were
1 <a class="sister" href="http://example.com/elsie" id="link1">
<span>Elsie</span>
</a>
2
3 <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>
4
and
5 <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
6
and they lived at the bottom of a well.
# 方法三：獲取p標籤裡的所有子節點以及子孫節點（子節點對應的子節點）
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.p.descendants)
for i, child in enumerate(soup.p.descendants):
print(i, child)輸出如下：
<generator object descendants at 0x06030C00>
0
Once upon a time there were three little sisters; and their names were
1 <a class="sister" href="http://example.com/elsie" id="link1">
<span>Elsie</span>
</a>
2
3 <span>Elsie</span>
4 Elsie
5
6
7 <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>
8 Lacie
9
and
10 <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
11 Tillie
12
and they lived at the bottom of a well.
#方法一：獲取標籤的父節點（前一級的節點）
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.a.parent)<p class="story">
Once upon a time there were three little sisters; and their names were
<a class="sister" href="http://example.com/elsie" id="link1">
<span>Elsie</span>
</a>
<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>
and
<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
and they lived at the bottom of a well.
</p># #方法二：獲取標籤所有的祖先節點（父節點的父節點的父節點。。。直到最頂層（把整個文件輸出））
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(list(enumerate(soup.a.parents)))[(0, <p class="story">
Once upon a time there were three little sisters; and their names were
<a class="sister" href="http://example.com/elsie" id="link1">
<span>Elsie</span>
</a>
<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>
and
<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
and they lived at the bottom of a well.
</p>), (1, <body>
<p class="story">
Once upon a time there were three little sisters; and their names were
<a class="sister" href="http://example.com/elsie" id="link1">
<span>Elsie</span>
</a>
<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>
and
<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
and they lived at the bottom of a well.
</p>
<p class="story">...</p>
</body>), (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 class="sister" href="http://example.com/elsie" id="link1">
<span>Elsie</span>
</a>
<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>
and
<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
and they lived at the bottom of a well.
</p>
<p class="story">...</p>
</body></html>), (3, <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 class="sister" href="http://example.com/elsie" id="link1">
<span>Elsie</span>
</a>
<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>
and
<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
and they lived at the bottom of a well.
</p>
<p class="story">...</p>
</body></html>)]
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(list(enumerate(soup.a.next_siblings)))
print(list(enumerate(soup.a.previous_siblings)))輸出結果如下：
[(0, '\n'), (1, <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>), (2, ' \n and\n '), (3, <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>), (4, '\n and they lived at the bottom of a well.\n ')]
[(0, '\n Once upon a time there were three little sisters; and their names were\n ')]
標準選擇器
示例程式碼如下：
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>
'''1，find_all方法
find_all( name , attrs , recursive , text , **kwargs )
可根據標籤名、屬性、內容查詢文件
name（標籤名字選擇）
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.find_all('ul'))#查詢所有便籤為ul的元素
print(type(soup.find_all('ul')[0]))輸出如下：
[<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>]
<class 'bs4.element.Tag'># 巢狀搜尋
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
for ul in soup.find_all('ul'):
print(ul.find_all('li'))輸出如下：
[<li class="element">Foo</li>, <li class="element">Bar</li>, <li class="element">Jay</li>]
[<li class="element">Foo</li>, <li class="element">Bar</li>]attr（標籤的屬性選擇）
#使用標籤的的屬性查詢
#方法一：使用字典引數查詢
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.find_all(attrs={'id': 'list-1'}))
print(soup.find_all(attrs={'name': 'elements'}))輸出如下：
[<ul class="list" id="list-1" name="elements">
<li class="element">Foo</li>
<li class="element">Bar</li>
<li class="element">Jay</li>
</ul>]
[<ul class="list" id="list-1" name="elements">
<li class="element">Foo</li>
<li class="element">Bar</li>
<li class="element">Jay</li>
</ul>]#方法二：
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.find_all(id='list-1'))
#只選擇element屬性的內容
print(soup.find_all(class_='element'))輸出如下：
[<ul class="list" id="list-1" name="elements">
<li class="element">Foo</li>
<li class="element">Bar</li>
<li class="element">Jay</li>
</ul>]
[<li class="element">Foo</li>, <li class="element">Bar</li>, <li class="element">Jay</li>, <li class="element">Foo</li>, <li class="element">Bar</li>]text（文字選擇）
#只返回text文字，適合內容匹配，不適合文字查詢
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.find_all(text='Foo'))輸出如下：
['Foo', 'Foo']2，find方法
find( name , attrs , recursive , text , **kwargs )
find返回單個元素，find_all返回所有元素
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>
'''
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.find('ul'))
print(type(soup.find('ul')))
print(soup.find('page'))輸出如下：
<ul class="list" id="list-1">
<li class="element">Foo</li>
<li class="element">Bar</li>
<li class="element">Jay</li>
</ul>
<class 'bs4.element.Tag'>
None3，其他的一些find方法
find_parents() find_parent()
find_parents()返回所有祖先節點，find_parent()返回直接父節點。
find_next_siblings() find_next_sibling()
find_next_siblings()返回後面所有兄弟節點，find_next_sibling()返回後面第一個兄弟節點。
find_previous_siblings() find_previous_sibling()
find_previous_siblings()返回前面所有兄弟節點，find_previous_sibling()返回前面第一個兄弟節點。
find_all_next() find_next()
find_all_next()返回節點後所有符合條件的節點, find_next()返回第一個符合條件的節點
find_all_previous() 和 find_previous()
find_all_previous()返回節點後所有符合條件的節點, find_previous()返回第一個符合條件的節點
CSS選擇器
通過select()直接傳入CSS選擇器即可完成選擇
例項程式碼如下：
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>
'''from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.select('.panel .panel-heading'))#選擇class的型別
print(soup.select('ul li'))#直接選擇標籤
print(soup.select('#list-2 .element'))#選擇id的型別
print(type(soup.select('ul')[0]))輸出如下：
[<div class="panel-heading">
<h4>Hello</h4>
</div>]
[<li class="element">Foo</li>, <li class="element">Bar</li>, <li class="element">Jay</li>, <li class="element">Foo</li>, <li class="element">Bar</li>]
[<li class="element">Foo</li>, <li class="element">Bar</li>]
<class 'bs4.element.Tag'>#把每一組ul的li輸出
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
for ul in soup.select('ul'):
print(ul.select('li'))輸出如下：
#把每一組ul的li輸出
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
for ul in soup.select('ul'):
print(ul.select('li'))from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
for ul in soup.select('ul'):
print(ul['id'])#這兩種方法都能獲取標籤的屬性（id或其他）
print(ul.attrs['id'])輸出如下：
list-1
list-1
list-2
list-24，獲取內容
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
for li in soup.select('li'):
print(li.get_text())#輸出li裡的內容輸出如下：
Foo
Bar
Jay
Foo
Bar總結
- 推薦使用lxml解析庫，必要時使用html.parser
- 標籤選擇篩選功能弱但是速度快
- 建議使用find()、find_all() 查詢匹配單個結果或者多個結果
- 如果對CSS選擇器熟悉建議使用select()
- 記住常用的獲取屬性和文字值的方法
至此，三種選擇器的基本語法都講解完畢，希望大家有所收穫。