转载自：https://blog.csdn.net/qq_42732153/article/details/81105725
Python 用Beautiful Soup解析选择的节点元素
子节点和子孙节点
html = """
<html>
<head>
<title>The Dormouse's story</title>
</head>
<body>
<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">
<span>Elsie</span>
</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, 'lxml')
print(soup.p.contents)
print(soup.p.children)
for i, child in enumerate(soup.p.children, start=1):
print(i, child)
#所有的子孙节点
print(soup.p.descendants)
for i, child in enumerate(soup.p.descendants, start=1):
print(i, child)
print（’----------------------------------------------‘—)
# 父节点和祖先节点
html = """
<html>
<head>
<title>The Dormouse's story</title>
</head>
<body>
<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"
<span>Elsie</span>
</a>
</p>
<p class="story">...</p>
"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(soup.a.parent)
# 所有的祖先节点
print("------------------------------------------------------")
html = """
<html>
<body>
<p class="story">
<a href="http://example.com/elsie" class="sister" id="link1">
<span>Elsie</span>
</a>
</p>
"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print(type(soup.a.parents))
print(list(enumerate(soup.a.parents)))
# 兄弟节点
print("--------------------------------------------------------")
html = """
<html>
<body>
<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">
<span>Elsie</span>
</a>
Hello
<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>
"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print('Next Sibling', soup.a.next_sibling)
print('Prev Sibling', soup.a.previous_sibling)
print('Next Siblings', list(enumerate(soup.a.next_siblings)))
print('Prev Siblings', list(enumerate(soup.a.previous_siblings)))
# 提取信息
print('------------------------------------------------------------')
html = """
<html>
<body>
<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">Bob</a><a href="http://example.com/locie"
class="sister" id="link2">Locie</a>
</p>
"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, 'lxml')
print('Next Sibling:')
print(type(soup.a.next_sibling))
print(soup.a.next_sibling)
print(soup.a.next_sibling.string)
print('Parent')
print(type(soup.a.parents))
print(list(soup.a.parents)[0])
print(list(soup.a.parents)[0].attrs['class'])
网友评论