1. 安装
sudo pip3 install beautifulsoup4
2. 导包
from bs4 import BeautifulSoup
3. 测试代码
from bs4 import BeautifulSoup
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>
"""
soup = BeautifulSoup(html_doc, 'html.parser') # html.parse解析器名称，取值可以是：html.parse、lxml、xml、html5lib#soup = BeautifulSoup(html_doc, 'lxml')
print(soup.prettify())
print(soup.title) # 打印title标签print(soup.title.string) # 打印title标签文本内容
print(soup.title.parent.name) # 打印title标签父元素的标签名
print(soup.p) # 打印第一个p标签
print(soup.p.next_sibling) #打印下一个p标签。print(soup.find_all('a')) # 打印所有的a标记，返回列表
print(soup.find(id="link3")) # 通过id属性查找对应的标签
for link in soup.find_all('a'): # 查找所有的a标记并遍历读取href值和文本内容值
print(link.get('href'))
print(link['href'])
print(link.get_text())
#将一段文档传入BeautifulSoup 的构造方法,就能得到一个文档的对象,
#可以传入一段字符串或一个文件句柄.
#soupF = BeautifulSoup(open("index.html"))
#soupF = BeautifulSoup("<html>data</html>")
#首先,文档被转换成Unicode,并且HTML的实例都被转换成Unicode编码#Beautiful Soup将复杂HTML文档转换成一个复杂的树形结构,
#每个节点都是Python对象,所有对象可以归纳为4种:
#Tag, NavigableString, BeautifulSoup, Comment.
#tag中最重要的属性: name和attributes
print("tag.name: ", tag.name)
print('tag["class"]: ', tag["class"])
print("tag.attrs: ",tag.attrs)
862
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
