1、安装
pip install beautifulsoup4
from bs4 import BeautifulSoup
html_doc = """
<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>
"""soup = BeautifulSoup(html_doc, 'html.parser')print(soup.prettify())
#Finding Elements
soup.title
# <title>The Dormouse's story</title>
soup.title.name
# 'title'
soup.title.string
# 'The Dormouse's story'
soup.title.parent.name
# 'head'
soup.p
# <p class="title"><b>The Dormouse's story</b></p>
soup.p['class']
# ['title']
#Searching by Class and ID
soup.find_all('a', class_='sister')
# Returns all <a> tags with class "sister"
soup.find(id="link3")
# Returns the element with id "link3"
#Extracting all URLs
for link in soup.find_all('a'):
print(link.get('href'))
#Getting Text
print(soup.get_text())