8586231_192932724000_2.jpg
- find_all方法返回的是BeautifulSoup特有的結果集，里面裝的是標簽對象
from bs4 import BeautifulSoup
import re
html = """
<html><head><title>The Dormouse's story</title><title>The Dormouse's story2</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" id="link1"><!-- Elsie --></a>,
<a class="sister" id="link2">Lacie</a> and
<a class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""
#解析字符串形式的html
soup=BeautifulSoup(html,'lxml')
①
data=soup.find_all('a')
print(type(data))
結果：
<class 'bs4.element.ResultSet'>
取值方法：
data=soup.find_all('a')
for i in data:
print(i.string)
結果：
Elsie
Lacie
Tillie
②
#根據正則表達式查找標簽
data1=soup.find_all(re.compile('^b'))
for i in data1:
print(data1)
返回結果為所有以b開頭的所有標簽
③
#根據屬性查找標簽
data2=soup.find_all(id='link2')
for i in data2:
print(data2)
結果：
[<a class="sister" id="link2">Lacie</a>]
④
#根據標簽內容獲取標簽內容
data3=soup.find_all(text='Tillie')
data4=soup.find_all(text=['Lacie','Tillie'])
data5=soup.find_all(text=re.compile("Do"))
print(data5)
結果：data3，data4，data5
['Tillie']
['Lacie', 'Tillie']
["The Dormouse's story", "The Dormouse's story2", "The Dormouse's story"]
