Commit | Line | Data |
---|---|---|
920dae64 AT |
1 | <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN"> |
2 | <html> | |
3 | <head> | |
4 | <link rel="STYLESHEET" href="lib.css" type='text/css' /> | |
5 | <link rel="SHORTCUT ICON" href="../icons/pyfav.png" type="image/png" /> | |
6 | <link rel='start' href='../index.html' title='Python Documentation Index' /> | |
7 | <link rel="first" href="lib.html" title='Python Library Reference' /> | |
8 | <link rel='contents' href='contents.html' title="Contents" /> | |
9 | <link rel='index' href='genindex.html' title='Index' /> | |
10 | <link rel='last' href='about.html' title='About this document...' /> | |
11 | <link rel='help' href='about.html' title='About this document...' /> | |
12 | <link rel="prev" href="module-HTMLParser.html" /> | |
13 | <link rel="parent" href="module-HTMLParser.html" /> | |
14 | <link rel="next" href="module-sgmllib.html" /> | |
15 | <meta name='aesop' content='information' /> | |
16 | <title>13.1.1 Example HTML Parser Application </title> | |
17 | </head> | |
18 | <body> | |
19 | <DIV CLASS="navigation"> | |
20 | <div id='top-navigation-panel' xml:id='top-navigation-panel'> | |
21 | <table align="center" width="100%" cellpadding="0" cellspacing="2"> | |
22 | <tr> | |
23 | <td class='online-navigation'><a rel="prev" title="13.1 HTMLParser " | |
24 | href="module-HTMLParser.html"><img src='../icons/previous.png' | |
25 | border='0' height='32' alt='Previous Page' width='32' /></A></td> | |
26 | <td class='online-navigation'><a rel="parent" title="13.1 HTMLParser " | |
27 | href="module-HTMLParser.html"><img src='../icons/up.png' | |
28 | border='0' height='32' alt='Up One Level' width='32' /></A></td> | |
29 | <td class='online-navigation'><a rel="next" title="13.2 sgmllib " | |
30 | href="module-sgmllib.html"><img src='../icons/next.png' | |
31 | border='0' height='32' alt='Next Page' width='32' /></A></td> | |
32 | <td align="center" width="100%">Python Library Reference</td> | |
33 | <td class='online-navigation'><a rel="contents" title="Table of Contents" | |
34 | href="contents.html"><img src='../icons/contents.png' | |
35 | border='0' height='32' alt='Contents' width='32' /></A></td> | |
36 | <td class='online-navigation'><a href="modindex.html" title="Module Index"><img src='../icons/modules.png' | |
37 | border='0' height='32' alt='Module Index' width='32' /></a></td> | |
38 | <td class='online-navigation'><a rel="index" title="Index" | |
39 | href="genindex.html"><img src='../icons/index.png' | |
40 | border='0' height='32' alt='Index' width='32' /></A></td> | |
41 | </tr></table> | |
42 | <div class='online-navigation'> | |
43 | <b class="navlabel">Previous:</b> | |
44 | <a class="sectref" rel="prev" href="module-HTMLParser.html">13.1 HTMLParser </A> | |
45 | <b class="navlabel">Up:</b> | |
46 | <a class="sectref" rel="parent" href="module-HTMLParser.html">13.1 HTMLParser </A> | |
47 | <b class="navlabel">Next:</b> | |
48 | <a class="sectref" rel="next" href="module-sgmllib.html">13.2 sgmllib </A> | |
49 | </div> | |
50 | <hr /></div> | |
51 | </DIV> | |
52 | <!--End of Navigation Panel--> | |
53 | ||
54 | <H2><A NAME="SECTION0015110000000000000000"></A><A NAME="htmlparser-example"></A> | |
55 | <BR> | |
56 | 13.1.1 Example HTML Parser Application | |
57 | </H2> | |
58 | ||
59 | <P> | |
60 | As a basic example, below is a very basic HTML parser that uses the | |
61 | <tt class="class">HTMLParser</tt> class to print out tags as they are encountered: | |
62 | ||
63 | <P> | |
64 | <div class="verbatim"><pre> | |
65 | from HTMLParser import HTMLParser | |
66 | ||
67 | class MyHTMLParser(HTMLParser): | |
68 | ||
69 | def handle_starttag(self, tag, attrs): | |
70 | print "Encountered the beginning of a %s tag" % tag | |
71 | ||
72 | def handle_endtag(self, tag): | |
73 | print "Encountered the end of a %s tag" % tag | |
74 | </pre></div> | |
75 | ||
76 | <DIV CLASS="navigation"> | |
77 | <div class='online-navigation'> | |
78 | <p></p><hr /> | |
79 | <table align="center" width="100%" cellpadding="0" cellspacing="2"> | |
80 | <tr> | |
81 | <td class='online-navigation'><a rel="prev" title="13.1 HTMLParser " | |
82 | href="module-HTMLParser.html"><img src='../icons/previous.png' | |
83 | border='0' height='32' alt='Previous Page' width='32' /></A></td> | |
84 | <td class='online-navigation'><a rel="parent" title="13.1 HTMLParser " | |
85 | href="module-HTMLParser.html"><img src='../icons/up.png' | |
86 | border='0' height='32' alt='Up One Level' width='32' /></A></td> | |
87 | <td class='online-navigation'><a rel="next" title="13.2 sgmllib " | |
88 | href="module-sgmllib.html"><img src='../icons/next.png' | |
89 | border='0' height='32' alt='Next Page' width='32' /></A></td> | |
90 | <td align="center" width="100%">Python Library Reference</td> | |
91 | <td class='online-navigation'><a rel="contents" title="Table of Contents" | |
92 | href="contents.html"><img src='../icons/contents.png' | |
93 | border='0' height='32' alt='Contents' width='32' /></A></td> | |
94 | <td class='online-navigation'><a href="modindex.html" title="Module Index"><img src='../icons/modules.png' | |
95 | border='0' height='32' alt='Module Index' width='32' /></a></td> | |
96 | <td class='online-navigation'><a rel="index" title="Index" | |
97 | href="genindex.html"><img src='../icons/index.png' | |
98 | border='0' height='32' alt='Index' width='32' /></A></td> | |
99 | </tr></table> | |
100 | <div class='online-navigation'> | |
101 | <b class="navlabel">Previous:</b> | |
102 | <a class="sectref" rel="prev" href="module-HTMLParser.html">13.1 HTMLParser </A> | |
103 | <b class="navlabel">Up:</b> | |
104 | <a class="sectref" rel="parent" href="module-HTMLParser.html">13.1 HTMLParser </A> | |
105 | <b class="navlabel">Next:</b> | |
106 | <a class="sectref" rel="next" href="module-sgmllib.html">13.2 sgmllib </A> | |
107 | </div> | |
108 | </div> | |
109 | <hr /> | |
110 | <span class="release-info">Release 2.4.2, documentation updated on 28 September 2005.</span> | |
111 | </DIV> | |
112 | <!--End of Navigation Panel--> | |
113 | <ADDRESS> | |
114 | See <i><a href="about.html">About this document...</a></i> for information on suggesting changes. | |
115 | </ADDRESS> | |
116 | </BODY> | |
117 | </HTML> |