参考官方文档http://beautifulsoup.readthedocs.io/zh_CN/latest/#id20
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, 'html.parser')
soup.select("title") # [<title>The Dormouse's story</title>] soup.select("p:nth-of-type(3)")
# [<p class="story">...</p>]
通过tag标签逐层查找:
soup.select("body 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.select("html head title") # [<title>The Dormouse's story</title>]
找到某个tag标签下的直接子标签
soup.select("head > title") # [<title>The Dormouse's story</title>] soup.select("p > 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.select("p > a:nth-of-type(2)") # [<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>] soup.select("p > #link1") # [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>] soup.select("body > a") # []找到兄弟节点标签:
soup.select("#link1 ~ .sister") # [<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.select("#link1 + .sister") # [<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]通过CSS的类名查找:
soup.select(".sister") # [<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.select("[class~=sister]") # [<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>]通过tag的id查找:
soup.select("#link1") # [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>] soup.select("a#link2") # [<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]同时用多种CSS选择器查询元素:
soup.select("#link1,#link2") # [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>, # <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
通过是否存在某个属性来查找:
soup.select('a[href]') # [<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>]
通过属性的值来查找:
soup.select('a[href="http://example.com/elsie"]') # [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>] soup.select('a[href^="http://example.com/"]') # [<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.select('a[href$="tillie"]') # [<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>] soup.select('a[href*=".com/el"]') # [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>]返回查找到的元素的第一个
soup.select_one(".sister") # <a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>