#!/usr/bin/env python #coding: utf8 #python2 #BeautifulSoup4 解析库的使用 from bs4 import BeautifulSoup html_doc = """ <html><head><title>The Dormouse's story</title></head> <body> <p class="sister"><b>$37</b></p> <p class="story" id="p">Once upon a time there were three little sisters; and their names were <a href="http://example.com/elsie" class="sister" >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> "" " # Python comes parsing library # soup = BeautifulSoup (html_doc, 'html.parser') # call object instance of a soup bs4 objects soup = BeautifulSoup (html_doc, ' lxml ' ) # BS4 objects Print (Soup) Print ( ' \ n- ' ) Print ( ' \ n- ' ) Print ( ' \ n- ' ) # BS4 type Print (type (Soup)) # beautification html = soup. prettify() print(html)