body {
font-family: SimSun;
font-size: 22px;
font-style: italic;
font-weight: bold;
color: # 00F;
}
I do not know how to get rid , seeking help heroes
java part of the code :
package format.conversion;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStreamReader;
import javax.servlet.jsp.tagext.BodyTag;
import javax.swing.JFileChooser;
import javax.swing.filechooser.FileNameExtensionFilter;
import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.filters.OrFilter;
import org.htmlparser.nodes.RemarkNode;
import org.htmlparser.nodes.TextNode;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.tags.MetaTag;
import org.htmlparser.tags.StyleTag;
import org.htmlparser.tags.TitleTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
import org.htmlparser.visitors.HtmlPage;
public class HtmlToTxt {
public static void main (String [] args) throws Exception {
HtmlToTxt test = new HtmlToTxt ();
test.go ();
}
public void go () {
try {
JFileChooser fileSave = new JFileChooser (".");
FileNameExtensionFilter extension = new FileNameExtensionFilter ("txt Files (. txt)", "txt");
fileSave.setFileFilter (extension);
fileSave.showSaveDialog (null);
File file = fileSave.getSelectedFile ();
if (! file.getPath (). endsWith (". txt")) {
file = new File (file.getPath () + ". txt");
}
String outputFile = file.toString ();
FileWriter writer = new FileWriter (outputFile);
String content = readTextFile ("WebRoot / Report.html", "UTF-8");
String txtcontent = getText (content);
writer.write (txtcontent);
writer.close ();
System.out.println ("txt file saved successfully ! " ) ;
System.out.println (" file path is :" + new File (outputFile). toURI (). toURL ());
} catch (IOException ex) {
System.out.println ("txt file failed ! " ) ;
} catch (ParserException ex) {
System.out.println (" Character conversion failed " ) ;
}
}
/ * ---------------- access to text content and title ----------------- ----- * /
public static String getText (String content) throws ParserException {
Parser myParser; / / htmlParser right parse html page
NodeList nodeList = null;
StringBuilder result = new StringBuilder ();
myParser = Parser.createParser (content, "UTF-8");
NodeFilter textFilter = new NodeClassFilter (TextNode.class NodeFilter linkFilter = new NodeClassFilter (LinkTag . class
OrFilter lastFilter = new OrFilter ();
lastFilter.setPredicates (new NodeFilter [] {textFilter, linkFilter});
nodeList = myParser.parse (lastFilter) ;/ / Get the list of nodes
Node [] nodes = nodeList.toNodeArray (); / / get array of nodes
String line = "";
for (int i = 0; i
if (anode instanceof TextNode) { TextNode textnode = (TextNode) anode;
line = textnode.getText ();
} else if (anode instanceof LinkTag) {
LinkTag linknode = (LinkTag) anode;
line = linknode.getLink ();
}
if (isTrimEmpty (line))
continue;
result.append (line);
}
return result.toString ();
}
/ * ------------------- read html file --------------- ---- * /
public static String readTextFile (String sFileName, String sEncode) {
StringBuffer sbStr = new StringBuffer (); / / string variable
try {
File ff = new File (sFileName);
InputStreamReader read = new InputStreamReader (new FileInputStream (
ff), sEncode); BufferedReader ins = new BufferedReader (read);
String dataLine = "";
while (null! = (dataLine = ins.readLine ())) {
sbStr.append (dataLine);
sbStr.append ("\ r \ n");
}
ins.close ();
} catch (Exception e) {
e.printStackTrace ();
}
return sbStr.toString ();
}
public static boolean isTrimEmpty (String astr) {
if ((null == astr) | | (astr.length () == 0)) {
return true;
}
if (isBlank (astr.trim ())) {
return true;
}
return false;
}
public static boolean isBlank (String astr) {
if ((null == astr) | | (astr.length () == 0)) {
return true;
} else {
return false;
}
}
}
------ Solution ------------------------------------ --------
error
Exception in thread "main" java.lang.Error: Unresolved compilation problems:
The method replace (char, char) in the type String is not applicable for the arguments (s)
Syntax error on token "?", delete this token
s cannot be resolved to a type
Syntax error, insert ")" to complete MethodInvocation
Syntax error, insert ";" to complete Statement
body cannot be resolved to a variable
Syntax error on tokens, delete these tokens
Syntax error, insert "}" to complete Block
at format.conversion.HtmlToTxt.go (HtmlToTxt.java: 60)
at format.conversion.HtmlToTxt.main (HtmlToTxt.java: 39)
compiler tool you use is what ? Eclipse it is not
html.replace ("(? s) body {(. *?)}", "");
less added a two "sign
I use myEclipse, I tried html.replace ("(? s) body {(. *?)}", ""); although no error, but the text inside or txt unable to remove the body {}
Are you sure about okay
you is body {}
or body {}
middle of no spaces.
Or String str = html.replaceAll ("(? s) body. \ \ {. *? \ \}", ""); so as not to worry there are no spaces of . {
In addition to special characters , the above I forgot to escape the
------ For reference only --------------------- ------------------
html.replace ((? s) body {(. *?)}, "");
------ For reference only ---------------------------------- -----
error
Exception in thread "main" java.lang.Error: Unresolved compilation problems:
The method replace (char, char) in the type String is not applicable for the arguments (s)
Syntax error on token "?", delete this token
s cannot be resolved to a type
Syntax error, insert ")" to complete MethodInvocation
Syntax error, insert ";" to complete Statement
body cannot be resolved to a variable
Syntax error on tokens, delete these tokens
Syntax error, insert "}" to complete Block
at format.conversion.HtmlToTxt.go (HtmlToTxt.java: 60)
at format.conversion.HtmlToTxt.main (HtmlToTxt.java: 39)
------ For reference only ------------------ ---------------------
error
Exception in thread "main" java.lang.Error: Unresolved compilation problems:
The method replace (char, char) in the type String is not applicable for the arguments (s)
Syntax error on token "?", delete this token
s cannot be resolved to a type
Syntax error, insert ")" to complete MethodInvocation
Syntax error, insert ";" to complete Statement
body cannot be resolved to a variable
Syntax error on tokens, delete these tokens
Syntax error, insert "}" to complete Block
at format.conversion.HtmlToTxt.go (HtmlToTxt.java: 60)
at format.conversion.HtmlToTxt.main (HtmlToTxt.java: 39)
compiler tool you use is what ? Eclipse it is not
html.replace ("(? s) body {(. *?)}", "");
less added a two "sign
------ For reference only ------------------------- --------------
error
Exception in thread "main" java.lang.Error: Unresolved compilation problems:
The method replace (char, char) in the type String is not applicable for the arguments (s)
Syntax error on token "?", delete this token
s cannot be resolved to a type
Syntax error, insert ")" to complete MethodInvocation
Syntax error, insert ";" to complete Statement
body cannot be resolved to a variable
Syntax error on tokens, delete these tokens
Syntax error, insert "}" to complete Block
at format.conversion.HtmlToTxt.go (HtmlToTxt.java: 60)
at format.conversion.HtmlToTxt.main (HtmlToTxt.java: 39)
compiler tool you use is what ? Eclipse it is not
html.replace ("(? s) body {(. *?)}", "");
less added a two "sign
I use myEclipse, I tried html.replace ("(? s) body {(. *?)}", ""); although no error, but the text inside or txt unable to remove the body {}
------ For reference only ------------------------------- --------
error
Exception in thread "main" java.lang.Error: Unresolved compilation problems:
The method replace (char, char) in the type String is not applicable for the arguments (s)
Syntax error on token "?", delete this token
s cannot be resolved to a type
Syntax error, insert ")" to complete MethodInvocation
Syntax error, insert ";" to complete Statement
body cannot be resolved to a variable
Syntax error on tokens, delete these tokens
Syntax error, insert "}" to complete Block
at format.conversion.HtmlToTxt.go (HtmlToTxt.java: 60)
at format.conversion.HtmlToTxt.main (HtmlToTxt.java: 39)
compiler tool you use is what ? Eclipse it is not
html.replace ("(? s) body {(. *?)}", "");
less added a two "sign
I use myEclipse, I tried html.replace ("(? s) body {(. *?)}", ""); although no error, but the text inside or txt unable to remove the body {}
Are you sure about okay
you is body {}
or body {}
middle of no spaces.
Or String str = html.replaceAll ("(? s) body. \ \ {. *? \ \}", ""); so as not to worry there are no spaces of . {
In addition to special characters , I forgot to escape the above
yes
body {
font-family: SimSun;
font-size: 22px;
font-style: italic;
font-weight: bold;
color: # 00F;
}
html page that is used to set the font format, color code
------ For reference only ---------------------- -----------------
error
Exception in thread "main" java.lang.Error: Unresolved compilation problems:
The method replace (char, char) in the type String is not applicable for the arguments (s)
Syntax error on token "?", delete this token
s cannot be resolved to a type
Syntax error, insert ")" to complete MethodInvocation
Syntax error, insert ";" to complete Statement
body cannot be resolved to a variable
Syntax error on tokens, delete these tokens
Syntax error, insert "}" to complete Block
at format.conversion.HtmlToTxt.go (HtmlToTxt.java: 60)
at format.conversion.HtmlToTxt.main (HtmlToTxt.java: 39)
compiler tool you use is what ? Eclipse it is not
html.replace ("(? s) body {(. *?)}", "");
less added a two "sign
I use myEclipse, I tried html.replace ("(? s) body {(. *?)}", ""); although no error, but the text inside or txt unable to remove the body {}
Are you sure about okay
you is body {}
or body {}
middle of no spaces.
Or String str = html.replaceAll ("(? s) body. \ \ {. *? \ \}", ""); so as not to worry there are no spaces of . {
In addition to special characters , I forgot to escape the above
Thank you very much , with this can
------ For reference only ---------------------------------------
error
Exception in thread "main" java.lang.Error: Unresolved compilation problems:
The method replace (char, char) in the type String is not applicable for the arguments (s)
Syntax error on token "?", delete this token
s cannot be resolved to a type
Syntax error, insert ")" to complete MethodInvocation
Syntax error, insert ";" to complete Statement
body cannot be resolved to a variable
Syntax error on tokens, delete these tokens
Syntax error, insert "}" to complete Block
at format.conversion.HtmlToTxt.go (HtmlToTxt.java: 60)
at format.conversion.HtmlToTxt.main (HtmlToTxt.java: 39)
compiler tool you use is what ? Eclipse it is not
html.replace ("(? s) body {(. *?)}", "");
less added a two "sign
I use myEclipse, I tried html.replace ("(? s) body {(. *?)}", ""); although no error, but the text inside or txt unable to remove the body {}
Are you sure about okay
you is body {}
or body {}
middle of no spaces.
Or String str = html.replaceAll ("(? s) body. \ \ {. *? \ \}", ""); so as not to worry there are no spaces of . {
In addition to special characters , I forgot to escape the above
yes
body {
font-family: SimSun;
font-size: 22px;
font-style: italic;
font-weight: bold;
color: # 00F;
}
html page that is used to set the font format, color code
rid of this paragraph is to chant
String str = html.replaceAll ("(? s) body \ \ s {0,1} \ \ {. *? \ \}", "");
This should be no problem, I tested .
was last written str. Not html
------ For reference only ------------------------------------ ---
error
Exception in thread "main" java.lang.Error: Unresolved compilation problems:
The method replace (char, char) in the type String is not applicable for the arguments (s)
Syntax error on token "?", delete this token
s cannot be resolved to a type
Syntax error, insert ")" to complete MethodInvocation
Syntax error, insert ";" to complete Statement
body cannot be resolved to a variable
Syntax error on tokens, delete these tokens
Syntax error, insert "}" to complete Block
at format.conversion.HtmlToTxt.go (HtmlToTxt.java: 60)
at format.conversion.HtmlToTxt.main (HtmlToTxt.java: 39)
compiler tool you use is what ? Eclipse it is not
html.replace ("(? s) body {(. *?)}", "");
less added a two "sign
I use myEclipse, I tried html.replace ("(? s) body {(. *?)}", ""); although no error, but the text inside or txt unable to remove the body {}
Are you sure about okay
you is body {}
or body {}
middle of no spaces.
Or String str = html.replaceAll ("(? s) body. \ \ {. *? \ \}", ""); so as not to worry there are no spaces of . {
In addition to special characters , I forgot to escape the above
yes
body {
font-family: SimSun;
font-size: 22px;
font-style: italic;
font-weight: bold;
color: # 00F;
}
html page that is used to set the font format, color code
rid of this paragraph is to chant
String str = html.replaceAll ("(? s) body \ \ s {0,1} \ \ {. *? \ \}", "");
This should be no problem, I tested .
was last written str. Not html
ah , ah , thank you ~
没有评论:
发表评论