mirror of
https://github.com/yacy/yacy_search_server.git
synced 2024-09-19 00:01:41 +02:00
removed old rss parser (will be replaced with parser from cora package)
git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@7052 6c8d7289-2bf4-0310-a012-ef5d649a1542
This commit is contained in:
orbiter
parent
70dd26ec95
commit
933dc1a600
|
|
@ -172,7 +172,7 @@ public class Crawler_p {
|
|||
int repeat_time = Integer.parseInt(post.get("repeat_time", "-1"));
|
||||
final String repeat_unit = post.get("repeat_unit", "seldays"); // selminutes, selhours, seldays
|
||||
|
||||
if (recrawl.equals("scheduler")) {
|
||||
if (recrawl.equals("scheduler") && repeat_time > 0) {
|
||||
// set crawlingIfOlder attributes that are appropriate for scheduled crawling
|
||||
crawlingIfOlderCheck = true;
|
||||
crawlingIfOlderNumber = repeat_unit.equals("selminutes") ? 1 : repeat_unit.equals("selhours") ? repeat_time / 2 : repeat_time * 12;
|
||||
|
|
|
|||
|
|
@ -25,13 +25,12 @@
|
|||
//javac -classpath .:../Classes Status.java
|
||||
//if the shell's current path is HTROOT
|
||||
|
||||
import java.io.ByteArrayInputStream;
|
||||
import java.io.IOException;
|
||||
import java.net.MalformedURLException;
|
||||
|
||||
import net.yacy.document.Document;
|
||||
import net.yacy.document.Parser;
|
||||
import net.yacy.document.parser.rssParser;
|
||||
import net.yacy.cora.document.RSSReader;
|
||||
import net.yacy.kelondro.data.meta.DigestURI;
|
||||
import net.yacy.kelondro.logging.Log;
|
||||
|
||||
import de.anomic.crawler.CrawlProfile;
|
||||
import de.anomic.crawler.retrieval.Response;
|
||||
|
|
@ -77,14 +76,11 @@ public class RSSLoader_p {
|
|||
}
|
||||
|
||||
// now parse the content as rss
|
||||
ByteArrayInputStream bais = new ByteArrayInputStream(resource);
|
||||
rssParser parser = new rssParser();
|
||||
Document[] doc;
|
||||
RSSReader rss;
|
||||
try {
|
||||
doc = parser.parse(url, "text/rss", "UTF-8", bais);
|
||||
} catch (Parser.Failure e) {
|
||||
return prop;
|
||||
} catch (InterruptedException e) {
|
||||
rss = RSSReader.parse(resource);
|
||||
} catch (IOException e) {
|
||||
Log.logException(e);
|
||||
return prop;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -45,7 +45,6 @@ import net.yacy.document.parser.ooxmlParser;
|
|||
import net.yacy.document.parser.pdfParser;
|
||||
import net.yacy.document.parser.pptParser;
|
||||
import net.yacy.document.parser.psParser;
|
||||
import net.yacy.document.parser.rssParser;
|
||||
import net.yacy.document.parser.rtfParser;
|
||||
import net.yacy.document.parser.sevenzipParser;
|
||||
import net.yacy.document.parser.swfParser;
|
||||
|
|
@ -82,7 +81,6 @@ public final class TextParser {
|
|||
initParser(new pdfParser());
|
||||
initParser(new pptParser());
|
||||
initParser(new psParser());
|
||||
initParser(new rssParser());
|
||||
initParser(new rtfParser());
|
||||
initParser(new sevenzipParser());
|
||||
initParser(new swfParser());
|
||||
|
|
|
|||
|
|
@ -1,196 +0,0 @@
|
|||
//rssParser.java
|
||||
//------------------------
|
||||
//part of YaCy
|
||||
//(C) by Michael Peter Christen; mc@yacy.net
|
||||
//first published on http://www.anomic.de
|
||||
//Frankfurt, Germany, 2005
|
||||
//
|
||||
//this file is contributed by Martin Thelian
|
||||
//
|
||||
// $LastChangedDate$
|
||||
// $LastChangedRevision$
|
||||
// $LastChangedBy$
|
||||
//
|
||||
//This program is free software; you can redistribute it and/or modify
|
||||
//it under the terms of the GNU General Public License as published by
|
||||
//the Free Software Foundation; either version 2 of the License, or
|
||||
//(at your option) any later version.
|
||||
//
|
||||
//This program is distributed in the hope that it will be useful,
|
||||
//but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
//MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
//GNU General Public License for more details.
|
||||
//
|
||||
//You should have received a copy of the GNU General Public License
|
||||
//along with this program; if not, write to the Free Software
|
||||
//Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
|
||||
|
||||
package net.yacy.document.parser;
|
||||
|
||||
import java.io.ByteArrayInputStream;
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
import java.io.UnsupportedEncodingException;
|
||||
import java.io.Writer;
|
||||
import java.net.MalformedURLException;
|
||||
import java.nio.charset.Charset;
|
||||
import java.util.HashMap;
|
||||
import java.util.LinkedList;
|
||||
import java.util.Map;
|
||||
|
||||
import net.yacy.cora.document.Hit;
|
||||
import net.yacy.cora.document.MultiProtocolURI;
|
||||
import net.yacy.cora.document.RSSFeed;
|
||||
import net.yacy.cora.document.RSSReader;
|
||||
import net.yacy.document.AbstractParser;
|
||||
import net.yacy.document.Document;
|
||||
import net.yacy.document.Parser;
|
||||
import net.yacy.document.parser.html.AbstractScraper;
|
||||
import net.yacy.document.parser.html.ContentScraper;
|
||||
import net.yacy.document.parser.html.ImageEntry;
|
||||
import net.yacy.document.parser.html.TransformerWriter;
|
||||
import net.yacy.kelondro.io.CharBuffer;
|
||||
import net.yacy.kelondro.util.ByteBuffer;
|
||||
import net.yacy.kelondro.util.FileUtils;
|
||||
|
||||
|
||||
public class rssParser extends AbstractParser implements Parser {
|
||||
|
||||
public rssParser() {
|
||||
super("Rich Site Summary/Atom Feed Parser");
|
||||
SUPPORTED_EXTENSIONS.add("rss");
|
||||
SUPPORTED_EXTENSIONS.add("xml");
|
||||
SUPPORTED_MIME_TYPES.add("XML");
|
||||
SUPPORTED_MIME_TYPES.add("text/rss");
|
||||
SUPPORTED_MIME_TYPES.add("application/rss+xml");
|
||||
SUPPORTED_MIME_TYPES.add("application/atom+xml");
|
||||
}
|
||||
|
||||
public Document[] parse(final MultiProtocolURI location, final String mimeType, final String charset, final InputStream source) throws Parser.Failure, InterruptedException {
|
||||
|
||||
final LinkedList<String> feedSections = new LinkedList<String>();
|
||||
final HashMap<MultiProtocolURI, String> anchors = new HashMap<MultiProtocolURI, String>();
|
||||
final HashMap<MultiProtocolURI, ImageEntry> images = new HashMap<MultiProtocolURI, ImageEntry>();
|
||||
final ByteBuffer text = new ByteBuffer();
|
||||
final CharBuffer authors = new CharBuffer();
|
||||
|
||||
RSSFeed feed = null;
|
||||
try {
|
||||
feed = new RSSReader(source).getFeed();
|
||||
} catch (IOException e) {
|
||||
throw new Parser.Failure("reading feed failed: " + e.getMessage(), location);
|
||||
}
|
||||
if (feed == null) throw new Parser.Failure("no feed in document", location);
|
||||
|
||||
String feedTitle = "";
|
||||
String feedDescription = "";
|
||||
String feedPublisher = "";
|
||||
String[] feedSubject = {""};
|
||||
if (feed.getChannel() != null) {//throw new Parser.Failure("no channel in document",location);
|
||||
|
||||
// get the rss feed title and description
|
||||
feedTitle = feed.getChannel().getTitle();
|
||||
|
||||
// get feed creator
|
||||
final String feedCreator = feed.getChannel().getAuthor();
|
||||
if (feedCreator != null && feedCreator.length() > 0) authors.append(",").append(feedCreator);
|
||||
|
||||
// get the feed description
|
||||
feedDescription = feed.getChannel().getDescription();
|
||||
|
||||
// the feed publisher
|
||||
feedPublisher = feed.getChannel().getCopyright();
|
||||
|
||||
// the feed subject
|
||||
feedSubject = feed.getChannel().getSubject();
|
||||
}
|
||||
|
||||
if (feed.getImage() != null) {
|
||||
try {
|
||||
MultiProtocolURI imgURL = new MultiProtocolURI(feed.getImage());
|
||||
images.put(imgURL, new ImageEntry(imgURL, feedTitle, -1, -1, -1));
|
||||
} catch (MalformedURLException e) {}
|
||||
}
|
||||
|
||||
// loop through the feed items
|
||||
for (final Hit item: feed) {
|
||||
|
||||
final String itemTitle = item.getTitle();
|
||||
MultiProtocolURI itemURL = null;
|
||||
try {
|
||||
itemURL = new MultiProtocolURI(item.getLink());
|
||||
} catch (MalformedURLException e) {
|
||||
continue;
|
||||
}
|
||||
final String itemDescr = item.getDescription();
|
||||
final String itemCreator = item.getAuthor();
|
||||
if (itemCreator != null && itemCreator.length() > 0) authors.append(",").append(itemCreator);
|
||||
|
||||
feedSections.add(itemTitle);
|
||||
anchors.put(itemURL, itemTitle);
|
||||
|
||||
if ((text.length() != 0) && (text.byteAt(text.length() - 1) != 32)) text.append((byte) 32);
|
||||
text.append(AbstractScraper.stripAll(itemDescr).trim()).append(' ');
|
||||
|
||||
final String itemContent = item.getDescription();
|
||||
if ((itemContent != null) && (itemContent.length() > 0)) {
|
||||
|
||||
final ContentScraper scraper = new ContentScraper(itemURL);
|
||||
final Writer writer = new TransformerWriter(null, null, scraper, null, false);
|
||||
try {
|
||||
FileUtils.copy(new ByteArrayInputStream(itemContent.getBytes("UTF-8")), writer, Charset.forName("UTF-8"));
|
||||
} catch (UnsupportedEncodingException e) {
|
||||
continue;
|
||||
} catch (IOException e) {
|
||||
continue;
|
||||
}
|
||||
|
||||
final String itemHeadline = scraper.getTitle();
|
||||
if (itemHeadline != null && itemHeadline.length() > 0) {
|
||||
feedSections.add(itemHeadline);
|
||||
}
|
||||
|
||||
final Map<MultiProtocolURI, String> itemLinks = scraper.getAnchors();
|
||||
if (itemLinks != null && !itemLinks.isEmpty()) {
|
||||
anchors.putAll(itemLinks);
|
||||
}
|
||||
|
||||
final HashMap<MultiProtocolURI, ImageEntry> itemImages = scraper.getImages();
|
||||
if (itemImages != null && !itemImages.isEmpty()) {
|
||||
ContentScraper.addAllImages(images, itemImages);
|
||||
}
|
||||
|
||||
final byte[] extractedText = scraper.getText();
|
||||
if ((extractedText != null) && (extractedText.length > 0)) {
|
||||
if ((text.length() != 0) && (text.byteAt(text.length() - 1) != 32)) text.append((byte) 32);
|
||||
text.append(scraper.getText());
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
final Document[] docs = new Document[]{new Document(
|
||||
location,
|
||||
mimeType,
|
||||
"UTF-8",
|
||||
null,
|
||||
feedSubject,
|
||||
feedTitle,
|
||||
(authors.length() > 0)?authors.toString(1,authors.length()):"",
|
||||
feedPublisher,
|
||||
feedSections.toArray(new String[feedSections.size()]),
|
||||
feedDescription,
|
||||
text.getBytes(),
|
||||
anchors,
|
||||
images,
|
||||
false)};
|
||||
// close streams
|
||||
try {
|
||||
text.close();
|
||||
authors.close();
|
||||
} catch (IOException e) {
|
||||
}
|
||||
|
||||
return docs;
|
||||
}
|
||||
}
|
||||
Loading…
Reference in New Issue
Block a user