爬虫学习——Beautiful Soup实例

如果你还是不知道该如何使用，那就多去实践，多看大佬的代码，先模仿后创造。

 1 #coding:utf-8   
 2 
 3 from bs4 import BeautifulSoup
 4 import re
 5 html_doc = """
 6 <html><head><title>The Dormouse's story</title></head>
 7 <body>
 8 <p class="title"><b>The Dormouse's story</b></p>
 9 
10 <p class="story">Once upon a time there were three little sisters; and their names were
11 <a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
12 <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
13 <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
14 and they lived at the bottom of a well.</p>
15 
16 <p class="story">...</p>
17 """
18 
19 soup = BeautifulSoup(html_doc,"html.parser",from_encoding="utf-8")
20 
21 print "获取所有链接："
22 links = soup.find_all('a')
23 
24 for link in links:
25    print link.name,link['href'],link.get_text()
26 
27 
28 
29 print "获取Lacie的链接："
30 link_node = soup.find('a', href='http://example.com/lacie')
31 print link_node.name, link_node['href'], link_node.get_text()
32 
33 print "获取Lacie的链接："
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段落字段"
38 p_node = soup.find('p',class_="title")
39 print p_node.name,p_node.get_text()