from bs4 import BeautifulSoup
import re
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>
"""
'''根據網頁字符串創建soup對象'''
soup = BeautifulSoup(
html_doc, # HTML 文檔字符串
'html.parser', # HTML 解析器
from_encoding='utf-8', # HTML 文檔編碼
)
print(' Get all links')
links = soup.find_all('a')
for link in links:
print(link.name, link['href'], link.get_text())
print(' Get Lacie"s links')
links_node = soup.find('a', href='http://example.com/lacie') # 應使用find方法取標籤。
print(links_node.name, links_node['href'], links_node.get_text())
print(' Get regular expression')
links_node = soup.find('a', href=re.compile(r"ill")) # 應使用find方法取標籤。
print(links_node.name, links_node['href'], links_node.get_text())