慕课爬虫
https://www.crummy.com/software/BeautifulSoup/
1 #!/usr/bin/python 2 # coding=utf-8 3 4 from bs4 import BeautifulSoup 5 import re 6 7 html_doc = """ 8 <html><head><title>The Dormouse's story</title></head> 9 <body> 10 <p class="title"><b>The Dormouse's story</b></p> 11 12 <p class="story">Once upon a time there were three little sisters; and their names were 13 <a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>, 14 <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and 15 <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>; 16 and they lived at the bottom of a well.</p> 17 18 <p class="story">...</p> 19 """ 20 21 soup = BeautifulSoup(html_doc,'html.parser',from_encoding = 'utf-8') 22 23 print '获取所有的链接' 24 links = soup.find_all('a') 25 for link in links: 26 print link.name, link['href'],link.get_text() 27 28 print '获取lacie的链接' 29 link_node = soup.find('a',href='http://example.com/lacie') 30 print link_node.name, link_node['href'],link_node.get_text() 31 32 print '正则匹配 ill' 33 #r"" ,字符串中反斜线 只用写一次 34 link_node = soup.find('a',href=re.compile(r"ill") ) 35 print link_node.name, link_node['href'],link_node.get_text() 36 37 print '获取p段落文字' 38 #r"" ,字符串中反斜线 只用写一次 39 p_node = soup.find('p',class_="title" ) 40 print p_node.name, p_node.get_text()
结果:
获取所有的链接 a http://example.com/elsie Elsie a http://example.com/lacie Lacie a http://example.com/tillie Tillie 获取lacie的链接 a http://example.com/lacie Lacie 正则匹配 ill a http://example.com/tillie Tillie 获取p段落文字 p The Dormouse's story