Python--开发简单爬虫

1 from bs4 import BeautifulSoup
2 
3 soup = BeautifulSoup(
4     html_doc,               #HTML文档字符串
5     ‘heml.parser‘,          #HTML解析器
6     from_encoding=‘utf-8‘   #HTML文档的编码
7 )

 1 from bs4 import BeautifulSoup
 2 import re
 3 
 4 html_doc = """
 5 <html><head><title>The Dormouse‘s story</title></head>
 6 <body>
 7 <p class="title"><b>The Dormouse‘s story</b></p>
 8 
 9 <p class="story">Once upon a time there were three little sisters; and their names were
10 <a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
11 <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
12 <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
13 and they lived at the bottom of a well.</p>
14 
15 <p class="story">...</p>
16 """
17 
18 soup = BeautifulSoup(
19     html_doc,               #HTML文档字符串
20     ‘html.parser‘,          #HTML解析器
21     from_encoding=‘utf-8‘   #HTML文档的编码
22 )
23 
24 print(‘获取所有的连接‘)
25 links = soup.find_all(‘a‘)
26 for link in links:
27     print(link.name,link[‘href‘],link.get_text())
28 
29 print(‘获取tillie的连接‘)
30 link_node = soup.find(‘a‘,href=‘http://example.com/tillie‘)
31 print(link_node.name,link_node[‘href‘],link_node.get_text())
32 
33 print(‘正则表达式匹配‘)
34 link_node2 = soup.find(‘a‘,href=re.compile(r‘lsi‘))
35 print(link_node2.name,link_node2[‘href‘],link_node2.get_text())
36 
37 print(‘获取P段落文字‘)
38 p_node = soup.find(‘p‘,class_=‘title‘)
39 print(p_node.name,p_node.get_text())

 1 获取所有的连接
 2 a http://example.com/elsie Elsie
 3 a http://example.com/lacie Lacie
 4 a http://example.com/tillie Tillie
 5 获取tillie的连接
 6 a http://example.com/tillie Tillie
 7 正则表达式匹配
 8 a http://example.com/elsie Elsie
 9 获取P段落文字
10 p The Dormouse‘s story