📄 gettext.html
字号:
<HTML>
<HEAD>
<META http-equiv="Content-Type" content="text/html; charset=UTF-8">
<TITLE>Getting the Text in an HTML Document
(Java Developers Almanac Example)
</TITLE>
<META CONTENT="Patrick Chan" NAME="AUTHOR">
<META CONTENT="Code Examples from The Java Developers Almanac 1.4" NAME="DESCRIPTION">
<META CONTENT="Addison-Wesley/Patrick Chan" NAME="OWNER">
<META CONTENT="3/20/02" NAME="revision">
<STYLE TYPE="text/css">
<!-- BODY CODE {font-family: Courier, Monospace; font-size: 11pt} TABLE, BODY {font-family: Verdana, Arial, Helvetica, sans-serif; font-size: 10pt} PRE {font-family: Courier, Monospace; font-size: 10pt} H3 {font-family: Verdana, Arial, Helvetica, sans-serif; font-size: 11pt} A.eglink {text-decoration: none} A:hover.eglink {text-decoration: underline} -->
</STYLE>
</HEAD>
<BODY>
<TABLE CELLSPACING="0" CELLPADDING="0" BORDER="0">
<TR>
<TD rowspan="3"><A HREF="/?l=ex"><IMG BORDER="0" ALIGN="BOTTOM" HSPACE="10" SRC="/egs/almanac14a.jpg"></A></TD><TD VALIGN="top"><font face="Times" size="6"><b>The Java Developers Almanac 1.4</b></font>
<br>
Order this book from <a href="/cgi-bin/scripts/redirect.pl?l=ex&url=http://www.amazon.com/exec/obidos/ASIN/0201752808/xeo">Amazon</a>.
</TD>
</TR>
<TR>
<TD align="right" valign="bottom">
<FORM method="get" action="/cgi-bin/search/find.pl">
<INPUT size="25" name="words" type="text"><INPUT value="Search" type="submit">
</FORM>
</TD>
</TR>
</TABLE>
<HR color="#6666cc">
<DIV ALIGN="LEFT">
<A HREF="/">Home</A>
>
<A HREF="../index.html">List of Packages</A>
>
<B><A HREF="../javax.swing.text.html/pkg.html">javax.swing.text.html</A></B><font color="#666666" SIZE="-2">
[2 examples]
</font>
</DIV><P>
<h3>
e1017.
Getting the Text in an HTML Document</h3>
<pre>
// This method takes a URI which can be either a filename (e.g. file://c:/dir/file.html)
// or a URL (e.g. http://host.com/page.html) and returns all text in the document.
public static String getText(String uriStr) {
final StringBuffer buf = new StringBuffer(<font color="#0066ff"><i>1000</i></font>);
try {
// Create an HTML document that appends all text to buf
HTMLDocument doc = new HTMLDocument() {
public HTMLEditorKit.ParserCallback getReader(int pos) {
return new HTMLEditorKit.ParserCallback() {
// This method is whenever text is encountered in the HTML file
public void handleText(char[] data, int pos) {
buf.append(data);
buf.append('\n');
}
};
}
};
// Create a reader on the HTML content
URL url = new URI(uriStr).toURL();
URLConnection conn = url.openConnection();
Reader rd = new InputStreamReader(conn.getInputStream());
// Parse the HTML
EditorKit kit = new HTMLEditorKit();
kit.read(rd, doc, 0);
} catch (MalformedURLException e) {
} catch (URISyntaxException e) {
} catch (BadLocationException e) {
} catch (IOException e) {
}
// Return the text
return buf.toString();
}
</pre>
<P><table width="600" CELLSPACING="0" CELLPADDING="2" BORDER="0">
<tr>
<td bgcolor="#6666cc" align="center"><font color="#ffffff">
Related Examples
</font></td>
</tr>
</table>
e1016. <a class="eglink" href="GetLinks.html?l=rel">
Getting the Links in an HTML Document
</a>
<br>
<br>
<br>
<FONT FACE="Verdana, Arial, Helvetica, sans-serif" SIZE="0">
© 2002 Addison-Wesley.
</FONT>
</BODY>
</HTML>
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -