Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -17,12 +17,11 @@
*/
package com.kohlschutter.boilerpipe.sax;

import org.apache.xerces.parsers.AbstractSAXParser;

import com.kohlschutter.boilerpipe.BoilerpipeDocumentSource;
import com.kohlschutter.boilerpipe.document.TextBlock;
import com.kohlschutter.boilerpipe.document.TextDocument;
import com.kohlschutter.boilerpipe.org.cyberneko.html.HTMLConfiguration;
import org.apache.xerces.parsers.AbstractSAXParser;
import org.cyberneko.html.HTMLConfiguration;

/**
* A simple SAX Parser, used by {@link BoilerpipeSAXInput}. The parser uses <a
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@
import java.util.regex.Pattern;

import org.apache.xerces.parsers.AbstractSAXParser;
import org.cyberneko.html.HTMLConfiguration;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.InputSource;
Expand All @@ -38,7 +39,6 @@
import com.kohlschutter.boilerpipe.BoilerpipeProcessingException;
import com.kohlschutter.boilerpipe.document.TextBlock;
import com.kohlschutter.boilerpipe.document.TextDocument;
import com.kohlschutter.boilerpipe.org.cyberneko.html.HTMLConfiguration;

/**
* Highlights text blocks in an HTML document that have been marked as "content" in the
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
import java.util.Map;

import org.apache.xerces.parsers.AbstractSAXParser;
import org.cyberneko.html.HTMLConfiguration;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.InputSource;
Expand All @@ -38,7 +39,6 @@
import com.kohlschutter.boilerpipe.document.Image;
import com.kohlschutter.boilerpipe.document.TextBlock;
import com.kohlschutter.boilerpipe.document.TextDocument;
import com.kohlschutter.boilerpipe.org.cyberneko.html.HTMLConfiguration;

/**
* Extracts the images that are enclosed by extracted content.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -31,8 +31,8 @@ public class Oneliner {
public static void main(final String[] args) throws Exception {
final URL url =
new URL(
"http://blog.openshift.com/day-18-boilerpipe-article-extraction-for-java-developers/"
// "http://www.dn.se/nyheter/vetenskap/annu-godare-choklad-med-hjalp-av-dna-teknik"
// "http://blog.openshift.com/day-18-boilerpipe-article-extraction-for-java-developers/"
"http://www.dn.se/nyheter/vetenskap/annu-godare-choklad-med-hjalp-av-dna-teknik"
);

System.out.println(ArticleExtractor.INSTANCE.getText(url));
Expand Down