from bs4 import BeautifulSoup
import re
#一段代码
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>
"""
#打印html_doc所有代码
soup=BeautifulSoup(html_doc,"html.parser")#用html.parser解析器解析
print(soup.prettify())
print(soup.title)
#<title>The Dormouse's story</title>
print(soup.title.string)
#The Dormouse's story
print(soup.a)
#<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>
print(soup.p)
#<p class="title"><b>The Dormouse's story</b></p>
print(soup.p['class'])
#['title']
print(soup.findAll('a'))
'''
[<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>, <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>, <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
'''
for link in soup.findAll('a'):
print(link.string)
#Elsie
#Lacie
#Tillie
print(soup.find(id="link3"))
#<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>
print(soup.find('p'))
#<p class="title"><b>The Dormouse's story</b></p>
print(soup.find('p',{"class":"story"}))
'''
<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>
'''
print(soup.find('p',{'class':'story'}).get_text())
'''
Once upon a time there were three little sisters; and their names were
Elsie,
Lacie and
Tillie;
and they lived at the bottom of a well.
'''
正则表达式:
for tag in soup.find_all(re.compile("t")):
print(tag.name)
#html
#title
for tag in soup.find_all(re.compile("^b")):
print(tag.name)
# body
# b
data=soup.findAll('a',href=re.compile(r"^http://example\.com/"))
print(data)
'''
[<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>, <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>, <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
'''