beautifulsoup soup code example

Example 1: beautifulsoup

>>> from bs4 import BeautifulSoup
>>> soup = BeautifulSoup("<p>Some<b>bad<i>HTML")
>>> print soup.prettify()
<html>
<body>
<p>
Some
<b>
bad
<i>
HTML
</i>
</b>
</p>
</body>
</html>
>>> soup.find(text="bad")
u'bad'
>>> soup.i
<i>HTML</i>
#
>>> soup = BeautifulSoup("<tag1>Some<tag2/>bad<tag3>XML", "xml")
#
>>> print soup.prettify()
<?xml version="1.0" encoding="utf-8">
<tag1>
Some
<tag2 />
bad
<tag3>
XML
</tag3>
</tag1>

Example 2: BeautifulSoup

from bs4 import BeautifulSoup
soup = BeautifulSoup(html_doc, 'html.parser')

print(soup.prettify())
# <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 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>

Example 3: BeautifulSoup

soup.title
# <title>The Dormouse's story</title>

soup.title.name
# u'title'

soup.title.string
# u'The Dormouse's story'

soup.title.parent.name
# u'head'

soup.p
# <p class="title"><b>The Dormouse's story</b></p>

soup.p['class']
# u'title'

soup.a
# <a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>

soup.find_all('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>]

soup.find(id="link3")
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>

Tags:

Shell Example

Recent Posts