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>
"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html_doc)
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="link2">
# Tillie
# </a>
# ; and they lived at the bottom of a well.
# </p>
# <p class="story">
# ...
# </p>
# </body>
# </html>
for link in soup.find_all('a'):
print(link.get('href'))
# http://example.com/elsie
# http://example.com/lacie
# http://example.com/tillie
从文档中获取所有文字内容:
print(soup.get_text())
# The Dormouse's story
#
# The Dormouse's story
#
# 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.
#
# ...
QQ群⑧：
窥视卡
雷达卡
发表于 2017-5-1 14:49:12
提升卡
置顶卡
沉默卡
喧嚣卡
变色卡
千斤顶
显身卡