Beautiful Soup的使用

来源：互联网发布：centos debian 稳定性编辑：程序博客网时间：2024/05/22 12:53

# coding:utf8from bs4 import BeautifulSoupimport rehtml_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',from_encoding='utf-8')print('获取所有的链接')links = soup.find_all('a')for link in links:    print(link.name+link['href']+link.get_text())print('获取lacie的链接')link_node = soup.find('a',href='http://example.com/lacie')print(link_node.name+link_node['href']+link_node.get_text())print('正则匹配')link_node = soup.find('a',href=re.compile(r'ill'))print(link_node.name+link_node['href']+link_node.get_text())print('获取p段落文字')#因为class是关键字所以要加个下划线p_node = soup.find('p',class_='title')print(p_node.name+p_node.get_text())

阅读全文

0 0