diff --git a/archiver/build.xml b/archiver/build.xml new file mode 100644 index 0000000..9ff75fa --- /dev/null +++ b/archiver/build.xml @@ -0,0 +1,45 @@ + + + Owark build file + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/archiver/java/src/org/owark/orbeon/FromWarcConverter.java b/archiver/java/src/org/owark/orbeon/FromWarcConverter.java new file mode 100644 index 0000000..ef3b672 --- /dev/null +++ b/archiver/java/src/org/owark/orbeon/FromWarcConverter.java @@ -0,0 +1,117 @@ +/** + * Copyright (C) 2012 Eric van der Vlist. + * + * This program is free software; you can redistribute it and/or modify it under the terms of the + * GNU Lesser General Public License as published by the Free Software Foundation; either version + * 2.1 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 Lesser General Public License for more details. + * + * The full text of the license is available at http://www.gnu.org/copyleft/lesser.html + */ +package org.owark.orbeon; + +import org.apache.commons.fileupload.FileItem; +import org.orbeon.oxf.pipeline.api.PipelineContext; +import org.orbeon.oxf.pipeline.api.XMLReceiver; +import org.orbeon.oxf.processor.ProcessorImpl; +import org.orbeon.oxf.processor.ProcessorInputOutputInfo; +import org.orbeon.oxf.processor.ProcessorOutput; +import org.orbeon.oxf.processor.serializer.BinaryTextXMLReceiver; +import org.orbeon.oxf.util.NetUtils; +import org.orbeon.oxf.xml.ContentHandlerHelper; +import org.owark.warc.*; + +import java.io.IOException; + +/** + * This processor converts a WARC archive into an XML representation + */ + +public class FromWarcConverter extends ProcessorImpl { + + static public String WARC_ELEMENT_ROOT_NAME = "warc"; + static public String RECORD_ELEMENT_NAME = "record"; + static public String HEADERS_ELEMENT_NAME = "headers"; + static public String HEADER_ELEMENT_NAME = "header"; + static public String NAME_ATTRIBUTE_NAME = "name"; + static public String CONTENT_ELEMENT_NAME = "content"; + + public FromWarcConverter() { + addInputInfo(new ProcessorInputOutputInfo(INPUT_DATA)); + addOutputInfo(new ProcessorInputOutputInfo(OUTPUT_DATA)); + } + + @Override + public ProcessorOutput createOutput(String outputName) { + final ProcessorOutput output = new ProcessorOutputImpl(FromWarcConverter.this,outputName) { + + @Override + protected void readImpl(PipelineContext pipelineContext, XMLReceiver xmlReceiver) { + // Get FileItem + try { + ContentHandlerHelper helper = new ContentHandlerHelper(xmlReceiver); + helper.startDocument(); + helper.startElement(WARC_ELEMENT_ROOT_NAME); + final FileItem fileItem = NetUtils.prepareFileItem(NetUtils.REQUEST_SCOPE); + // Read to OutputStream + readInputAsSAX(pipelineContext, INPUT_DATA, new BinaryTextXMLReceiver(null, fileItem.getOutputStream(), true, false, null, false, false, null, false)); + // as an archive + final WarcParser warcParser = new WarcParser(fileItem.getInputStream()); + while (warcParser.hasNext()) { + helper.startElement(RECORD_ELEMENT_NAME); + helper.startElement(HEADERS_ELEMENT_NAME); + WarcRecord record = warcParser.next(); + WarcRecordHeader recordHeader = record.getHeader(); + while (recordHeader.hasNext()) { + WarcField field = recordHeader.next(); + helper.startElement(HEADER_ELEMENT_NAME, new String[] {NAME_ATTRIBUTE_NAME, field.getKey()}); + helper.text(field.getValue()); + helper.endElement(); + } + helper.endElement(); + helper.startElement(CONTENT_ELEMENT_NAME); + WarcRecordContent content = record.getContent(); + if (content.hasRequestLine()) { + helper.startElement("request"); + WarcRecordContent.HttpRequestLine request = content.getRequestLine(); + helper.element("method", request.getMethod()); + helper.element("uri", request.getUri()); + helper.element("version", request.getVersion()); + helper.endElement(); + } else if (content.hasStatusLine()) { + helper.startElement("status"); + WarcRecordContent.HttpStatusLine status = content.getStatusLine(); + helper.element("version", status.getVersion()); + helper.element("status", status.getStatus()); + helper.element("reason", status.getReason()); + helper.endElement(); + } + if (content.hasFields()) { + helper.startElement(HEADERS_ELEMENT_NAME); + while (content.hasNext()) { + WarcField field = content.next(); + helper.startElement(HEADER_ELEMENT_NAME, new String[] {NAME_ATTRIBUTE_NAME, field.getKey()}); + helper.text(field.getValue()); + helper.endElement(); + } + helper.endElement(); + } + record.skipToEnd(); + helper.endElement(); + helper.endElement(); + } + helper.endElement(); + helper.endDocument(); + } catch (Exception e) { + e.printStackTrace(); //To change body of catch statement use File | Settings | File Templates. + } + + } + }; + addOutput(outputName, output); + return output; + } +} diff --git a/archiver/java/src/org/owark/warc/WarcField.java b/archiver/java/src/org/owark/warc/WarcField.java new file mode 100644 index 0000000..23b2f9e --- /dev/null +++ b/archiver/java/src/org/owark/warc/WarcField.java @@ -0,0 +1,49 @@ +/** + * Copyright (C) 2012 Eric van der Vlist. + * + * This program is free software; you can redistribute it and/or modify it under the terms of the + * GNU Lesser General Public License as published by the Free Software Foundation; either version + * 2.1 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 Lesser General Public License for more details. + * + * The full text of the license is available at http://www.gnu.org/copyleft/lesser.html + */ +package org.owark.warc; + +/** + * Created by IntelliJ IDEA. + * User: vdv + * Date: 25 avr. 2012 + * Time: 17:56:22 + * To change this template use File | Settings | File Templates. + */ +public class WarcField { + + + private String line; + private String key; + private String value; + + public WarcField(String line) { + this.line = line; + int sep = line.indexOf(":"); + this.key = line.substring(0, sep).trim(); + this.value = line.substring(sep + 1).trim(); + } + + public String getKey() { + return key; + } + + public String getLine() { + return line; + } + + public String getValue() { + return value; + } + +} diff --git a/archiver/java/src/org/owark/warc/WarcParser.java b/archiver/java/src/org/owark/warc/WarcParser.java new file mode 100644 index 0000000..81dbd47 --- /dev/null +++ b/archiver/java/src/org/owark/warc/WarcParser.java @@ -0,0 +1,123 @@ +/** + * Copyright (C) 2012 Eric van der Vlist. + * + * This program is free software; you can redistribute it and/or modify it under the terms of the + * GNU Lesser General Public License as published by the Free Software Foundation; either version + * 2.1 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 Lesser General Public License for more details. + * + * The full text of the license is available at http://www.gnu.org/copyleft/lesser.html + */ +package org.owark.warc; + +import java.io.BufferedInputStream; +import java.io.BufferedReader; +import java.io.IOException; +import java.io.InputStream; +import java.util.Iterator; + +/** + * Read WARC files + */ +public class WarcParser implements Iterator { + + public static int BUFFER_SIZE = 1024; + public static String CRLF = "\r\n"; + public static String CRLFCRLF = CRLF + CRLF; + public static String MAGIC = "WARC/"; + private InputStream is; + private byte[] buffer = new byte[BUFFER_SIZE]; + private int index = 0; + private int limit = -1; + private String magic; + private int recordCount; + + + public WarcParser(InputStream is) { + this.is = is; + resetBuffer(); + } + + public String getMagic() throws IOException, WarcException { + return this.magic; + } + + private void resetBuffer() { + index = 0; + } + + private void readUntil(String stringPattern) throws IOException, WarcException { + boolean matches = true; + for (int i=0; i< stringPattern.length() && limit != 0; i++) { + int c = read(); + buffer[index ++] = (byte) c; + if (stringPattern.codePointAt(i) != c) { + matches = false; + break; + } + } + if (matches) { + return; + } + readUntil(stringPattern); + } + + protected String readLine() throws IOException, WarcException { + readUntil(CRLF); + String line = new String(buffer, 0, index - CRLF.length(), "UTF-8"); + resetBuffer(); + return line; + } + + public boolean hasNext() { + limit = -1; + do { + try { + magic = readLine(); + } catch (Exception e) { + return false; + } + } while (! magic.startsWith(MAGIC)); + return true; + } + + public WarcRecord next() { + recordCount ++; + return new WarcRecord(this); + } + + public void remove() { + } + + public void setLimit(int limit) { + this.limit = limit; + } + + public boolean isLimitReached() { + return limit == 0; + } + + public int read() throws IOException { + if (limit == 0) { + return -1; + } + if (limit > 0) { + limit--; + } + int c = is.read(); + //System.out.print((char) c); + return c; + } + + public int getRecordCount() { + return recordCount; + } + + class WarcException extends Exception {} + class BufferOverflowException extends WarcException {} + class BadMagicException extends WarcException {} + +} diff --git a/archiver/java/src/org/owark/warc/WarcRecord.java b/archiver/java/src/org/owark/warc/WarcRecord.java new file mode 100644 index 0000000..7a8cf7d --- /dev/null +++ b/archiver/java/src/org/owark/warc/WarcRecord.java @@ -0,0 +1,84 @@ +/** + * Copyright (C) 2012 Eric van der Vlist. + * + * This program is free software; you can redistribute it and/or modify it under the terms of the + * GNU Lesser General Public License as published by the Free Software Foundation; either version + * 2.1 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 Lesser General Public License for more details. + * + * The full text of the license is available at http://www.gnu.org/copyleft/lesser.html + */ +package org.owark.warc; + +import java.io.IOException; + +/** + * Created by IntelliJ IDEA. + * User: vdv + * Date: 25 avr. 2012 + * Time: 17:29:35 + * To change this template use File | Settings | File Templates. + */ +public class WarcRecord { + + private WarcParser warcParser; + private WarcRecordHeader header; + private WarcRecordContent content; + + public WarcRecord(WarcParser warcParser) { + this.warcParser = warcParser; + } + + public Object getMagic() throws IOException, WarcParser.WarcException { + return warcParser.getMagic(); + } + + public WarcRecordHeader getHeader() { + if (header == null) { + header = new WarcRecordHeader(this); + } + return header; + } + + public String readLine() throws IOException, WarcParser.WarcException { + return warcParser.readLine(); + } + + public String getType() { + return header.getType(); + } + + public String getContentType() { + return header.getContentType(); + } + + public WarcRecordContent getContent() { + if (content == null) { + warcParser.setLimit(getContentLength()); + content = new WarcRecordContent(this); + } + return content; + } + + public int getContentLength() { + return header.getContentLength(); + } + + public boolean isLimitReached() { + return warcParser.isLimitReached(); + } + + public int read() throws IOException { + return warcParser.read(); + } + + public void skipToEnd() throws IOException { + getHeader(); + header.skipToEnd(); + getContent(); + content.skip(getContentLength()); + } +} diff --git a/archiver/java/src/org/owark/warc/WarcRecordContent.java b/archiver/java/src/org/owark/warc/WarcRecordContent.java new file mode 100644 index 0000000..eb60634 --- /dev/null +++ b/archiver/java/src/org/owark/warc/WarcRecordContent.java @@ -0,0 +1,177 @@ +/** + * Copyright (C) 2012 Eric van der Vlist. + * + * This program is free software; you can redistribute it and/or modify it under the terms of the + * GNU Lesser General Public License as published by the Free Software Foundation; either version + * 2.1 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 Lesser General Public License for more details. + * + * The full text of the license is available at http://www.gnu.org/copyleft/lesser.html + */ + +package org.owark.warc; + +import java.io.IOException; +import java.io.InputStream; +import java.util.Iterator; + +/** + * Created by IntelliJ IDEA. + * User: vdv + * Date: 25 avr. 2012 + * Time: 19:00:47 + * To change this template use File | Settings | File Templates. + */ +public class WarcRecordContent extends InputStream implements Iterator { + + private WarcRecord warcRecord; + private Exception e; + private String line; + + public WarcRecordContent(WarcRecord warcRecord) { + this.warcRecord = warcRecord; + } + + public boolean hasFields() { + return warcRecord.getContentType().equals("application/warc-fields") || isHTTP(); + } + + public boolean hasNext() { + try { + line = warcRecord.readLine(); + } catch (Exception e) { + this.e = e; + } + return ! (warcRecord.isLimitReached() || line.equals("")); + } + + public WarcField next() { + if (line == null) { + try { + line = warcRecord.readLine(); + } catch (Exception e) { + this.e = e; + } + } + if (line.equals("")) { + line = null; + return null; + } + WarcField field = new WarcField(line); + line = null; + return field; + } + + public void remove() { + //To change body of implemented methods use File | Settings | File Templates. + } + + @Override + public int read() throws IOException { + return warcRecord.read(); + } + + public boolean isHTTP() { + return warcRecord.getContentType().startsWith("application/http"); + } + + public boolean isRequest() { + return warcRecord.getType().equals("request"); + } + + public HttpStatusLine getStatusLine() throws IOException, WarcParser.WarcException { + return new HttpStatusLine(warcRecord.readLine()); + } + + public boolean hasStatusLine() { + return isHTTP() && ! isRequest(); + } + + public boolean hasRequestLine() { + return isHTTP() && isRequest(); + } + + public Object endOfContent() { + return warcRecord.isLimitReached(); + } + + public HttpRequestLine getRequestLine() throws IOException, WarcParser.WarcException { + return new HttpRequestLine(warcRecord.readLine()); + } + + public long getContentLength() { + return warcRecord.getContentLength(); + } + + + public class HttpStatusLine { + + private String line; + private String version; + private String status; + private String reason; + + + public String getLine() { + return line; + } + + public String getVersion() { + return version; + } + + public String getStatus() { + return status; + } + + public String getReason() { + return reason; + } + + + protected HttpStatusLine(String line) { + this.line = line; + String[] tokens = line.split(" ", 3); + this.version = tokens[0]; + this.status = tokens[1]; + this.reason = tokens[2]; + } + + } + + public class HttpRequestLine { + + private String line; + private String version; + private String method; + private String uri; + + public String getLine() { + return line; + } + + public String getVersion() { + return version; + } + + public String getMethod() { + return method; + } + + public String getUri() { + return uri; + } + + public HttpRequestLine(String line) { + this.line = line; + String[] tokens = line.split(" ", 3); + this.method = tokens[0]; + this.uri = tokens[1]; + this.version = tokens[2]; + } + } +} + diff --git a/archiver/java/src/org/owark/warc/WarcRecordHeader.java b/archiver/java/src/org/owark/warc/WarcRecordHeader.java new file mode 100644 index 0000000..371d8c9 --- /dev/null +++ b/archiver/java/src/org/owark/warc/WarcRecordHeader.java @@ -0,0 +1,103 @@ +/** + * Copyright (C) 2012 Eric van der Vlist. + * + * This program is free software; you can redistribute it and/or modify it under the terms of the + * GNU Lesser General Public License as published by the Free Software Foundation; either version + * 2.1 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 Lesser General Public License for more details. + * + * The full text of the license is available at http://www.gnu.org/copyleft/lesser.html + */ +package org.owark.warc; + +import java.util.Hashtable; +import java.util.Iterator; +import java.util.Map; + +/** + * Created by IntelliJ IDEA. + * User: vdv + * Date: 25 avr. 2012 + * Time: 17:50:01 + * To change this template use File | Settings | File Templates. + */ +public class WarcRecordHeader implements Iterator { + + + public static String WARC_TYPE = "WARC-Type"; + public static String CONTENT_TYPE = "Content-Type"; + public static String CONTENT_LENGTH = "Content-Length"; + + private WarcRecord warcRecord; + private String line; + private Exception e; + private Map headers; + private boolean endOfHeader = false; + + + public WarcRecordHeader(WarcRecord warcRecord) { + this.warcRecord = warcRecord; + headers = new Hashtable(); + } + + public boolean hasNext() { + if (endOfHeader) { + return false; + } + if (line == null) { + try { + line = warcRecord.readLine(); + } catch (Exception e) { + this.e = e; + return false; + } + } + if (line.equals("")) { + endOfHeader = true; + return false; + } + return true; + } + + public WarcField next() { + if (endOfHeader) { + return null; + } + if (line == null) { + try { + line = warcRecord.readLine(); + } catch (Exception e) { + this.e = e; + return null; + } + } + WarcField item = new WarcField(line); + line = null; + headers.put(item.getKey(), item.getValue()); + return item; + } + + public String getType() { + return headers.get(WARC_TYPE); + } + + public void remove() { + } + + public String getContentType() { + return headers.get(CONTENT_TYPE); + } + + public int getContentLength() { + return Integer.parseInt(headers.get(CONTENT_LENGTH)); + } + + public void skipToEnd() { + while (hasNext()) { + next(); + } + } +} diff --git a/archiver/java/test/org/owark/warc/WarcParserTest.java b/archiver/java/test/org/owark/warc/WarcParserTest.java new file mode 100644 index 0000000..3a052e8 --- /dev/null +++ b/archiver/java/test/org/owark/warc/WarcParserTest.java @@ -0,0 +1,297 @@ +/** + * Copyright (C) 2012 Eric van der Vlist. + * + * This program is free software; you can redistribute it and/or modify it under the terms of the + * GNU Lesser General Public License as published by the Free Software Foundation; either version + * 2.1 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 Lesser General Public License for more details. + * + * The full text of the license is available at http://www.gnu.org/copyleft/lesser.html + */ +package org.owark.warc; + +import org.junit.Assert; +import org.junit.Test; + +import java.io.*; + +/** + * Test cases for WarcParser + */ +public class WarcParserTest { + + private static WarcParser warcParser; + + @Test + public void testDyomedea() throws IOException, WarcParser.WarcException { + + // WARC + + File file = new File("/home/vdv/projects/owark/archiver/java/test/org/owark/warc/dyomedea.warc"); + WarcParser warcParser = new WarcParser(new FileInputStream(file)); + Assert.assertEquals(true, warcParser.hasNext()); + + // RECORD + + WarcRecord record = warcParser.next(); + Assert.assertEquals("WARC/1.0", warcParser.getMagic()); + Assert.assertNotNull(record); + Assert.assertEquals("WARC/1.0", record.getMagic()); + + // HEADER + + WarcRecordHeader header = record.getHeader(); + Assert.assertNotNull(header); + Assert.assertNull(header.getType()); + Assert.assertEquals(true, header.hasNext()); + WarcField headerItem = header.next(); + Assert.assertNotNull(headerItem); + Assert.assertEquals(WarcRecordHeader.WARC_TYPE, headerItem.getKey()); + Assert.assertEquals("warcinfo", headerItem.getValue()); + Assert.assertEquals("warcinfo", header.getType()); + Assert.assertEquals("warcinfo", record.getType()); + Assert.assertEquals(true, header.hasNext()); + headerItem = header.next(); + Assert.assertNotNull(headerItem); + Assert.assertEquals("WARC-Date", headerItem.getKey()); + Assert.assertEquals("2012-04-23T10:05:24Z", headerItem.getValue()); + headerItem = header.next(); + headerItem = header.next(); + headerItem = header.next(); + headerItem = header.next(); + Assert.assertNotNull(headerItem); + Assert.assertEquals("Content-Length", headerItem.getKey()); + Assert.assertEquals("369", headerItem.getValue()); + Assert.assertEquals(false, header.hasNext()); + headerItem = header.next(); + Assert.assertNull(headerItem); + Assert.assertEquals("application/warc-fields", record.getContentType()); + Assert.assertEquals(369, record.getContentLength()); + + // Content + + WarcRecordContent content = record.getContent(); + Assert.assertNotNull(content); + Assert.assertEquals(true, content.hasFields()); + Assert.assertEquals(false, content.isHTTP()); + Assert.assertEquals(false, content.hasStatusLine()); + Assert.assertEquals(false, content.hasRequestLine()); + Assert.assertEquals(true, content.hasNext()); + WarcField field = content.next(); + Assert.assertEquals(false, content.endOfContent()); + Assert.assertNotNull(field); + Assert.assertEquals("software", field.getKey()); + Assert.assertEquals("Heritrix/3.1.0 http://crawler.archive.org", field.getValue()); + field = content.next(); + field = content.next(); + field = content.next(); + field = content.next(); + field = content.next(); + field = content.next(); + field = content.next(); + field = content.next(); + Assert.assertNotNull(field); + Assert.assertEquals("http-header-user-agent", field.getKey()); + Assert.assertEquals("Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org)", field.getValue()); + Assert.assertEquals(false, content.hasNext()); + Assert.assertEquals(true, content.endOfContent()); + + // Next record + + Assert.assertEquals(true, warcParser.hasNext()); + record = warcParser.next(); + Assert.assertNotNull(record); + + // Header + + header = record.getHeader(); + Assert.assertNotNull(header); + Assert.assertNull(header.getType()); + Assert.assertEquals(true, header.hasNext()); + headerItem = header.next(); + Assert.assertNotNull(headerItem); + Assert.assertEquals(WarcRecordHeader.WARC_TYPE, headerItem.getKey()); + Assert.assertEquals("response", headerItem.getValue()); + + header.skipToEnd(); + + // Content + + content = record.getContent(); + Assert.assertNotNull(content); + Assert.assertEquals(false, content.hasFields()); + Assert.assertEquals(false, content.isHTTP()); + Assert.assertEquals(false, content.hasStatusLine()); + Assert.assertEquals(false, content.hasRequestLine()); + Assert.assertEquals(false, content.endOfContent()); + BufferedReader reader = new BufferedReader(new InputStreamReader(content, "UTF-8")); + String line = reader.readLine(); + Assert.assertEquals("20120423100524", line); + line = reader.readLine(); + Assert.assertEquals("dyomedea.com.\t\t1800\tIN\tA\t95.142.167.137", line); + line = reader.readLine(); + Assert.assertEquals(true, content.endOfContent()); + Assert.assertNull(line); + + // Next record + + Assert.assertEquals(true, warcParser.hasNext()); + record = warcParser.next(); + Assert.assertNotNull(record); + + // Header + + header = record.getHeader(); + Assert.assertNotNull(header); + Assert.assertNull(header.getType()); + Assert.assertEquals(true, header.hasNext()); + headerItem = header.next(); + Assert.assertNotNull(headerItem); + Assert.assertEquals(WarcRecordHeader.WARC_TYPE, headerItem.getKey()); + Assert.assertEquals("response", headerItem.getValue()); + + header.skipToEnd(); + + // Content + + content = record.getContent(); + Assert.assertNotNull(content); + Assert.assertEquals(true, content.hasFields()); + Assert.assertEquals(true, content.isHTTP()); + Assert.assertEquals(false, content.isRequest()); + Assert.assertEquals(true, content.hasStatusLine()); + Assert.assertEquals(false, content.hasRequestLine()); + WarcRecordContent.HttpStatusLine status = content.getStatusLine(); + Assert.assertNotNull(status); + Assert.assertEquals("HTTP/1.1 404 Introuvable", status.getLine()); + Assert.assertEquals("HTTP/1.1", status.getVersion()); + Assert.assertEquals("404", status.getStatus()); + Assert.assertEquals("Introuvable", status.getReason()); + field = content.next(); + Assert.assertNotNull(field); + Assert.assertEquals("Date", field.getKey()); + Assert.assertEquals("Mon, 23 Apr 2012 10:05:27 GMT", field.getValue()); + field = content.next(); + field = content.next(); + field = content.next(); + field = content.next(); + field = content.next(); + field = content.next(); + Assert.assertNotNull(field); + Assert.assertEquals("Connection", field.getKey()); + Assert.assertEquals("close", field.getValue()); + Assert.assertEquals(false, content.hasNext()); + Assert.assertEquals(false, content.endOfContent()); + reader = new BufferedReader(new InputStreamReader(content, "UTF-8")); + line = reader.readLine(); + Assert.assertEquals("Apache Tomcat/6.0.24 - Rapport d'erreur", line.substring(0, line.indexOf("

Etat HTTP 404 -

type Rapport d'état

message

description La ressource demandée () n'est pas disponible.

Apache Tomcat/6.0.24

+ +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://dyomedea.com/robots.txt +WARC-Date: 2012-04-23T10:05:27Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 212 + +GET /robots.txt HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dyomedea.com + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dyomedea.com/robots.txt +WARC-Date: 2012-04-23T10:05:27Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 230 + +force-fetch: +via: http://dyomedea.com/ +hopsFromSeed: P +fetchTimeMs: 58 +outlink: http://dyomedea.com/favicon.ico I =INFERRED_MISC +outlink: whois:95.142.167.137 I =INFERRED_MISC +outlink: whois:dyomedea.com I =INFERRED_MISC + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://dyomedea.com/ +WARC-Date: 2012-04-23T10:05:30Z +WARC-Payload-Digest: sha1:OB3F5F4PYIK6YISBPOAK2FR7IKW4JNZU +WARC-IP-Address: 95.142.167.137 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 6570 + +HTTP/1.1 200 OK +Date: Mon, 23 Apr 2012 10:05:30 GMT +Server: Apache-Coyote/1.1 +Last-Modified: Mon, 23 Apr 2012 10:05:30 GMT +Expires: Mon, 23 Apr 2012 10:05:30 GMT +Cache-Control: post-check=0, pre-check=0 +Pragma: +Content-Type: application/xhtml+xml;charset=utf-8 +Content-Length: 6234 +Via: 1.0 dyomedea.com +Connection: close + + + + + + + + Dyomedea : Guide de haute technologie XML + + + + + + + + + + + +
+
+

DYOMEDEA : Guide de haute technologie...

+
+ +
+
+

Dyomedea : Guide de haute technologie XML

+
+ +
+ +

Guilde XML

+ +
Eric van der Vlist fait partie de la Guilde XML, un + groupe d'experts qui partagent les mêmes méthodes et valeurs. +
+ +
+ logo de la Guilde XML +
La Guilde XML +
+ +

La Guilde XML (XML Guild) est un groupe composé + des meilleurs experts XML dans le + monde. [...] +

+ +

Nos membres ont une expérience approfondie des technologies + XML et des languages de balisage. + Nous sommes impliqués dans le développement de standards et de bonnes pratiques. Nous + sommes auteurs de nombreux livres, articles et documentations et sommes des conférenciers + renommés. +

+ +
+ +
+
+ +

Guide de haute technologie

+ +

Le Web 2.0 à la portée de tous

+ +

Notre mission est de guider nos clients dans l'utilisation des hautes technologies de + l'Internet les plus prometteuses telles que XML et le Web Sémantique et plus généralement ce que l'on appelle désormais le Web 2.0. +

+ + +

Votre guide est Eric van der Vlist, un expert XML reconnu au niveau international et basé à Paris. +

+ +

Nous vous proposons des missions de conseil et des formations et sommes engagés dans un programme de communication très ambitieux. +

+ +
+
+
à propos planxhtml 1.1 +  css 2.0

Mentions Légales

+
Dyomedea et XMLfr sont des marques + déposées. Tous droits réservés. © Dyomedea, 1999-2010
Dyomedea, SARL au + capital de 10 000 € - RCS: Paris B 422 260 208 - 75, rue de Lourmel 75015 + Paris.

 
+ + + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://dyomedea.com/ +WARC-Date: 2012-04-23T10:05:30Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 202 + +GET / HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dyomedea.com + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dyomedea.com/ +WARC-Date: 2012-04-23T10:05:30Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 1317 + +seed: +fetchTimeMs: 95 +outlink: http://dyomedea.com/styles/print.css E link/@href +outlink: http://dyomedea.com/ L a/@href +outlink: http://dyomedea.com/projets/ L a/@href +outlink: http://dyomedea.com/images/xml-guild-logo.png E img/@src +outlink: http://dyomedea.com/help/ L a/@href +outlink: http://dyomedea.com/styles/standard.css E link/@href +outlink: http://dyomedea.com/communication/ L a/@href +outlink: http://dyomedea.com/images/logo520.png E img/@src +outlink: http://dyomedea.com/map/ L a/@href +outlink: whois:95.142.167.137 I =INFERRED_MISC +outlink: http://dyomedea.com/formation/ L a/@href +outlink: http://xmlfr.org/actualites/decid/051201-0001 L a/@href +outlink: http://validator.w3.org/check/referer L a/@href +outlink: http://purl.org/dc/elements/1.1/ E link/@href +outlink: whois:dyomedea.com I =INFERRED_MISC +outlink: http://xmlguild.org/ L a/@href +outlink: http://dyomedea.com/vdv/ L a/@href +outlink: http://dyomedea.com/styles/screen.css E link/@href +outlink: http://dyomedea.com/dyomedea/ L a/@href +outlink: http://dyomedea.com/english/ L a/@href +outlink: http://dyomedea.com/favicon.ico I =INFERRED_MISC +outlink: http://dyomedea.com/images/bout.png E img/@src +outlink: http://jigsaw.w3.org/css-validator/check/referer L a/@href +outlink: http://dyomedea.com/conseil/ L a/@href + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: dns:purl.org +WARC-Date: 2012-04-23T10:05:31Z +WARC-IP-Address: 212.27.40.241 +WARC-Record-ID: +Content-Type: text/dns +Content-Length: 50 + +20120423100531 +purl.org. 36087 IN A 132.174.1.35 + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: whois://whois.arin.net/z+%2B+95.142.167.137 +WARC-Date: 2012-04-23T10:05:30Z +WARC-Record-ID: +Content-Type: text/plain +Content-Length: 1493 + +# +# The following results may also be obtained via: +# http://whois.arin.net/rest/nets;q=95.142.167.137?showDetails=true&showARIN=false&ext=netref2 +# + +NetRange: 95.0.0.0 - 95.255.255.255 +CIDR: 95.0.0.0/8 +OriginAS: +NetName: 95-RIPE +NetHandle: NET-95-0-0-0-1 +Parent: +NetType: Allocated to RIPE NCC +Comment: These addresses have been further assigned to users in +Comment: the RIPE NCC region. Contact information can be found in +Comment: the RIPE database at http://www.ripe.net/whois +RegDate: 2007-07-30 +Updated: 2009-05-18 +Ref: http://whois.arin.net/rest/net/NET-95-0-0-0-1 + +OrgName: RIPE Network Coordination Centre +OrgId: RIPE +Address: P.O. Box 10096 +City: Amsterdam +StateProv: +PostalCode: 1001EB +Country: NL +RegDate: +Updated: 2011-09-24 +Ref: http://whois.arin.net/rest/org/RIPE + +ReferralServer: whois://whois.ripe.net:43 + +OrgTechHandle: RNO29-ARIN +OrgTechName: RIPE NCC Operations +OrgTechPhone: +31 20 535 4444 +OrgTechEmail: hostmaster@ripe.net +OrgTechRef: http://whois.arin.net/rest/poc/RNO29-ARIN + +OrgAbuseHandle: RNO29-ARIN +OrgAbuseName: RIPE NCC Operations +OrgAbusePhone: +31 20 535 4444 +OrgAbuseEmail: hostmaster@ripe.net +OrgAbuseRef: http://whois.arin.net/rest/poc/RNO29-ARIN + +# +# ARIN WHOIS data and services are subject to the Terms of Use +# available at: https://www.arin.net/whois_tou.html +# + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: whois://whois.ripe.net:43/95.142.167.137 +WARC-Date: 2012-04-23T10:05:31Z +WARC-Record-ID: +Content-Type: text/plain +Content-Length: 1875 + +% This is the RIPE Database query service. +% The objects are in RPSL format. +% +% The RIPE Database is subject to Terms and Conditions. +% See http://www.ripe.net/db/support/db-terms-conditions.pdf + +% Note: this output has been filtered. +% To receive output for a database update, use the "-B" flag. + +% Information related to '95.142.160.0 - 95.142.167.255' + +inetnum: 95.142.160.0 - 95.142.167.255 +netname: GANDI-NET1 +descr: GANDI DEDICATED HOSTING SERVERS +country: FR +admin-c: LV314-RIPE +tech-c: GNO4-RIPE +status: ASSIGNED PA +mnt-by: GANDI-NOC +mnt-lower: GANDI-NOC +mnt-routes: GANDI-NOC +source: RIPE # Filtered + +role: Gandi Network Operations +address: 63-65 Boulevard Massena +address: 75013 Paris +address: France +phone: +33 1 70 39 37 55 +admin-c: LV314-RIPE +tech-c: LV314-RIPE +nic-hdl: GNO4-RIPE +remarks: Gandi SAS NOC Role +remarks: Gandi is an ICANN accredited Registrar +remarks: http://www.gandi.net/ +remarks: - Network Issues: noc@gandi.net +remarks: - Abuse/SPAM: abuse@gandi.net +abuse-mailbox: abuse@gandi.net +mnt-by: GANDI-NOC +source: RIPE # Filtered + +person: Leland Vandervort +address: Gandi SAS +address: 63-65 Boulevard Massena +address: 75013 Paris +address: France +phone: +33 1 70 39 37 55 +nic-hdl: LV314-RIPE +mnt-by: DISCPRO-MNT +source: RIPE # Filtered + +% Information related to '95.142.160.0/20AS29169' + +route: 95.142.160.0/20 +descr: GANDI is an ICANN accredited registrar +descr: GANDI is a virtual server provider +descr: for more information: +descr: Web: http://www.gandi.net +origin: AS29169 +mnt-by: GANDI-NOC +source: RIPE # Filtered + +% This query was served by the RIPE Database Query Service version 1.6.12 (WHOIS2) + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: whois://whois.iana.org/com +WARC-Date: 2012-04-23T10:05:31Z +WARC-Record-ID: +Content-Type: text/plain +Content-Length: 1830 + +% IANA WHOIS server +% for more information on IANA, visit http://www.iana.org +% This query returned 1 object + +domain: COM + +organisation: VeriSign Global Registry Services +address: 12061 Bluemont Way +address: Reston Virginia 20190 +address: United States + +contact: administrative +name: Registry Customer Service +organisation: VeriSign Global Registry Services +address: 12061 Bluemont Way +address: Reston Virginia 20190 +address: United States +phone: +1 703 925-6999 +fax-no: +1 703 948 3978 +e-mail: info@verisign-grs.com + +contact: technical +name: Registry Customer Service +organisation: VeriSign Global Registry Services +address: 12061 Bluemont Way +address: Reston Virginia 20190 +address: United States +phone: +1 703 925-6999 +fax-no: +1 703 948 3978 +e-mail: info@verisign-grs.com + +nserver: A.GTLD-SERVERS.NET 192.5.6.30 2001:503:a83e:0:0:0:2:30 +nserver: B.GTLD-SERVERS.NET 192.33.14.30 2001:503:231d:0:0:0:2:30 +nserver: C.GTLD-SERVERS.NET 192.26.92.30 +nserver: D.GTLD-SERVERS.NET 192.31.80.30 +nserver: E.GTLD-SERVERS.NET 192.12.94.30 +nserver: F.GTLD-SERVERS.NET 192.35.51.30 +nserver: G.GTLD-SERVERS.NET 192.42.93.30 +nserver: H.GTLD-SERVERS.NET 192.54.112.30 +nserver: I.GTLD-SERVERS.NET 192.43.172.30 +nserver: J.GTLD-SERVERS.NET 192.48.79.30 +nserver: K.GTLD-SERVERS.NET 192.52.178.30 +nserver: L.GTLD-SERVERS.NET 192.41.162.30 +nserver: M.GTLD-SERVERS.NET 192.55.83.30 +ds-rdata: 30909 8 2 E2D3C916F6DEEAC73294E8268FB5885044A833FC5459588F4A9184CFC41A5766 + +whois: whois.verisign-grs.com + +status: ACTIVE +remarks: Registration information: http://www.verisign-grs.com + +created: 1985-01-01 +changed: 2012-02-15 +source: IANA + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: whois://whois.verisign-grs.com/domain+dyomedea.com +WARC-Date: 2012-04-23T10:05:32Z +WARC-Record-ID: +Content-Type: text/plain +Content-Length: 2856 + + +Whois Server Version 2.0 + +Domain names in the .com and .net domains can now be registered +with many different competing registrars. Go to http://www.internic.net +for detailed information. + + Domain Name: DYOMEDEA.COM + Registrar: GANDI SAS + Whois Server: whois.gandi.net + Referral URL: http://www.gandi.net + Name Server: DNS1.DYOMEDEA.COM + Name Server: DNS2.DYOMEDEA.COM + Name Server: DNS3.DYOMEDEA.COM + Name Server: DNS4.DYOMEDEA.COM + Name Server: DNS5.DYOMEDEA.COM + Status: clientTransferProhibited + Updated Date: 12-mar-2012 + Creation Date: 10-mar-1999 + Expiration Date: 10-mar-2013 + +>>> Last update of whois database: Mon, 23 Apr 2012 10:04:53 UTC <<< + +NOTICE: The expiration date displayed in this record is the date the +registrar's sponsorship of the domain name registration in the registry is +currently set to expire. This date does not necessarily reflect the expiration +date of the domain name registrant's agreement with the sponsoring +registrar. Users may consult the sponsoring registrar's Whois database to +view the registrar's reported date of expiration for this registration. + +TERMS OF USE: You are not authorized to access or query our Whois +database through the use of electronic processes that are high-volume and +automated except as reasonably necessary to register domain names or +modify existing registrations; the Data in VeriSign Global Registry +Services' ("VeriSign") Whois database is provided by VeriSign for +information purposes only, and to assist persons in obtaining information +about or related to a domain name registration record. VeriSign does not +guarantee its accuracy. By submitting a Whois query, you agree to abide +by the following terms of use: You agree that you may use this Data only +for lawful purposes and that under no circumstances will you use this Data +to: (1) allow, enable, or otherwise support the transmission of mass +unsolicited, commercial advertising or solicitations via e-mail, telephone, +or facsimile; or (2) enable high volume, automated, electronic processes +that apply to VeriSign (or its computer systems). The compilation, +repackaging, dissemination or other use of this Data is expressly +prohibited without the prior written consent of VeriSign. You agree not to +use electronic processes that are automated and high-volume to access or +query the Whois database except as reasonably necessary to register +domain names or modify existing registrations. VeriSign reserves the right +to restrict your access to the Whois database in its sole discretion to ensure +operational stability. VeriSign may restrict or terminate your access to the +Whois database for failure to abide by these terms of use. VeriSign +reserves the right to modify these terms at any time. + +The Registry database contains ONLY .COM, .NET, .EDU domains and +Registrars. + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: whois://whois.gandi.net/dyomedea.com +WARC-Date: 2012-04-23T10:05:32Z +WARC-Record-ID: +Content-Type: text/plain +Content-Length: 2673 + +--- #YAML:1.0 +# GANDI Registrar whois database for .COM, .NET, .ORG., .INFO, .BIZ, .NAME +# +# Access and use restricted pursuant to French law on personal data. +# Copy of whole or part of the data without permission from GANDI +# is strictly forbidden. +# The sole owner of a domain is the entity described in the relevant +# 'domain:' record. +# Domain ownership disputes should be settled using ICANN's Uniform Dispute +# Resolution Policy: http://www.icann.org/udrp/udrp.htm +# For inquiries about 'by policy' protection, please check directly +# with the appropriate registry (Eurid, AFNIC, Red.es) +# +# Acces et utilisation soumis a la legislation francaise sur +# les donnees personnelles. +# Copie de tout ou partie de la base interdite sans autorisation de GANDI. +# Le possesseur d'un domaine est l'entite decrite dans +# l'enregistrement 'domain:' correspondant. +# Un desaccord sur la possession d'un nom de domaine peut etre resolu +# en suivant la Uniform Dispute Resolution Policy de l'ICANN: +# http://www.icann.org/udrp/udrp.htm +# Pour obtenir les informations en status 'Protected by policy', contactez +# directement le registre concerne (Eurid, AFNIC, Red.es) +# +# 2012-04-23 12:05:32 CEST + +domain: dyomedea.com +reg_created: 1999-03-10 00:00:00 +expires: 2013-03-10 05:00:00 +created: 2002-01-03 16:13:07 +changed: 2012-03-12 17:16:57 +transfer-prohibited: yes +ns0: dns3.dyomedea.com 82.236.32.56 +ns1: dns4.dyomedea.com 88.178.25.34 +ns2: DNS1.DYOMEDEA.COM 95.142.167.112 +ns3: DNS2.DYOMEDEA.COM 217.70.189.52 +ns4: dns5.dyomedea.com 95.142.167.137 +owner-c: + nic-hdl: EVD9-GANDI + owner-name: Dyomedea + organisation: Dyomedea + person: Eric van der Vlist + address: '22, rue Edgar Faure' + zipcode: 75015 + city: Paris + country: France + phone: +33.140563136 + fax: ~ + email: vdv@dyomedea.com + lastupdated: 2012-03-08 14:19:37 +admin-c: + nic-hdl: EVD9-GANDI + owner-name: Dyomedea + organisation: Dyomedea + person: Eric van der Vlist + address: '22, rue Edgar Faure' + zipcode: 75015 + city: Paris + country: France + phone: +33.140563136 + fax: ~ + email: vdv@dyomedea.com + lastupdated: 2012-03-08 14:19:37 +tech-c: + nic-hdl: EVD9-GANDI + owner-name: Dyomedea + organisation: Dyomedea + person: Eric van der Vlist + address: '22, rue Edgar Faure' + zipcode: 75015 + city: Paris + country: France + phone: +33.140563136 + fax: ~ + email: vdv@dyomedea.com + lastupdated: 2012-03-08 14:19:37 +bill-c: + nic-hdl: EVD9-GANDI + owner-name: Dyomedea + organisation: Dyomedea + person: Eric van der Vlist + address: '22, rue Edgar Faure' + zipcode: 75015 + city: Paris + country: France + phone: +33.140563136 + fax: ~ + email: vdv@dyomedea.com + lastupdated: 2012-03-08 14:19:37 + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://dyomedea.com/styles/print.css +WARC-Date: 2012-04-23T10:05:34Z +WARC-Payload-Digest: sha1:JQGKJC7SYSUKF7TOYKR56XQE54LEXTGP +WARC-IP-Address: 95.142.167.137 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 829 + +HTTP/1.1 200 OK +Date: Mon, 23 Apr 2012 10:05:33 GMT +Server: Apache-Coyote/1.1 +Last-Modified: Mon, 27 Apr 2009 21:16:19 GMT +Expires: Fri, 10 Aug 2012 13:46:29 GMT +Cache-Control: public +Pragma: +Content-Type: text/css +Content-Length: 517 +Via: 1.0 dyomedea.com +Vary: Accept-Encoding +Connection: close + +/* CSS Dyomeda.com */ + +/* version impression */ + + +body { + background: transparent; +} + +#divContenant { + width: 600px; + margin-right: auto; + margin-left: auto; +} + +#divMenu li.on a, #divMenu li.on a:visited { + color: #000000; + border-bottom: thin solid #000000; +} + +#divMenu li, #divMenu li a, #divMenu a:visited { + color: #646464; + +} + +#divContenu { + width: 580px; +} + +#divPiedPage { + width: 600px; +} + +#finTet { + display: none; +} + +.mentions { + color: #000000; +} + +pre { + border: none; + font-size: 0.65em; +} + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://dyomedea.com/styles/print.css +WARC-Date: 2012-04-23T10:05:34Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 249 + +GET /styles/print.css HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Referer: http://dyomedea.com/ +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dyomedea.com + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dyomedea.com/styles/print.css +WARC-Date: 2012-04-23T10:05:34Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 216 + +via: http://dyomedea.com/ +hopsFromSeed: E +fetchTimeMs: 66 +outlink: whois:dyomedea.com I =INFERRED_MISC +outlink: whois:95.142.167.137 I =INFERRED_MISC +outlink: http://dyomedea.com/favicon.ico I =INFERRED_MISC + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://purl.org/robots.txt +WARC-Date: 2012-04-23T10:05:34Z +WARC-Payload-Digest: sha1:6TRHDMHIOSVJ3GLUQ3OJRISRMTVQ5LJ6 +WARC-IP-Address: 132.174.1.35 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 1970 + +HTTP/1.1 404 Not Found +Date: Mon, 23 Apr 2012 10:05:34 GMT +Server: 1060 NetKernel v3.3 - Powered by Jetty +Connection: close +Expires: Thu, 01 Jan 1970 00:00:00 GMT +Content-Type: text/html;charset=UTF-8 +Content-Length: 1739 + + + + + + + PURL not found + + + + + + + + + + + + + + + +
+ Suggestion: +
+ Go To purl.org +
+ + + + + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://purl.org/robots.txt +WARC-Date: 2012-04-23T10:05:34Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 208 + +GET /robots.txt HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: purl.org + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://purl.org/robots.txt +WARC-Date: 2012-04-23T10:05:34Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 535 + +force-fetch: +via: http://purl.org/dc/elements/1.1/ +hopsFromSeed: EP +fetchTimeMs: 318 +outlink: http://zepheira.com/ L a/@href +outlink: http://purl.org/docs/images/oclclogo.png E img/@src +outlink: whois:132.174.1.35 I =INFERRED_MISC +outlink: http://purl.org/favicon.ico I =INFERRED_MISC +outlink: whois:purl.org I =INFERRED_MISC +outlink: http://purl.org/ L a/@href +outlink: http://purl.org/docs/style.css E link/@href +outlink: http://purl.org/docs/images/zepheiralogo.png E img/@src +outlink: http://www.oclc.org/ L a/@href + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://dyomedea.com/images/xml-guild-logo.png +WARC-Date: 2012-04-23T10:05:37Z +WARC-Payload-Digest: sha1:URHBRNQAAS4AIWJMNXIRCQC4LY7FPWNV +WARC-IP-Address: 95.142.167.137 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 5230 + +HTTP/1.1 200 OK +Date: Mon, 23 Apr 2012 10:05:36 GMT +Server: Apache-Coyote/1.1 +Last-Modified: Mon, 27 Apr 2009 21:16:21 GMT +Expires: Fri, 10 Aug 2012 13:46:32 GMT +Cache-Control: public +Pragma: +Content-Type: image/png +Content-Length: 4939 +Via: 1.0 dyomedea.com +Connection: close + +PNG + + IHDRPPPLTE + + +  !!!"""###$$$%%%&&&'''((()))***+++,,,---...///000111222333444555666777888999:::;;;<<<===>>>???@@@AAABBBCCCDDDEEEFFFGGGHHHIIIJJJKKKLLLMMMNNNOOOPPPQQQRRRSSSTTTUUUVVVWWWXXXYYYZZZ[[[\\\]]]^^^___```aaabbbcccdddeeefffggghhhiiijjjkkklllmmmnnnooopppqqqrrrssstttuuuvvvwwwxxxyyyzzz{{{|||}}}~~~A pHYs  tIME /IDATXYXTW(vĘfL`[PXVmIF5DVh-( ԙyڽDT`]"0~{.&~??~WZ"^> +~҅sg + u/J|¹'>t(/Б#G/8s.+ z-MZM4ae;vgK/=ꠅc sO*G9ei MԈx){4 RϭHvP!QR7AOi)zbN>@/Dz b>ܶI[nEyd}XwB8>(ŶtEѝxpWЁXccJwto>$`c$rm̽S>DWUY3$IT=!=h"A?xjH%{/MTaiYk 4Qy#=6vRp +"2ʄNߴ.3Gl0 )k[ ,蕕#\@hplGG46jQK/-#ڪ+) J}6U**1 F!PE!Z0'$3}$lsue5UmoJ9\)8҆:jT~ED Np0&,TBApG*DZ;b6t@Z8F#z +BŨhNu[Kf5ȧ==azkUAz'R:C΁>jq}nln,GUVSWu WUWz$ +.:P; rCu7#SÑk!uIX#l6ݧѩ>٬ek:fњFBJ@4I'>DW7'?V ۝ 沽R߯V0 sA';VhH;l4wBdwVMy!6ɲ\څIZE] ɣ:5 hvh3IS-{!Tw5nZHn:YOt-SL\ВYe]%v.}m*iTgE;e `1Qebx2DQH}pK`Ƃ/?Ħ40QjZjJD!Mn +K(>th7hHae0`"7NY1$QKſf~ʵxfQbUTGv{$ #fO̰V=),z9❒G)SDkBӷu{6AJ~21jSĐe)CGNwaDǩF*4|ؼh|/Ӯz|kvha(k_rzi.&/O9ǻaɰn|GUH]kkݺ]~>ff;Wvˇ mK#&vW.9n@ho=ӟ<rXy_7GАճ{m[n/rʢ-ҡ`Yy_19C:v ?t/Jaw˪Ef~0i℉>9w[W--5=ؘ1i2?p⿴Ǿ/.|EEžb~jߊ*T4oBIENDB` + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://dyomedea.com/images/xml-guild-logo.png +WARC-Date: 2012-04-23T10:05:37Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 258 + +GET /images/xml-guild-logo.png HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Referer: http://dyomedea.com/ +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dyomedea.com + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dyomedea.com/images/xml-guild-logo.png +WARC-Date: 2012-04-23T10:05:37Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 216 + +via: http://dyomedea.com/ +hopsFromSeed: E +fetchTimeMs: 58 +outlink: whois:dyomedea.com I =INFERRED_MISC +outlink: whois:95.142.167.137 I =INFERRED_MISC +outlink: http://dyomedea.com/favicon.ico I =INFERRED_MISC + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://purl.org/dc/elements/1.1/ +WARC-Date: 2012-04-23T10:05:37Z +WARC-Payload-Digest: sha1:MHEWMBBTZE7XH7EG62Y2LYXBJJTRHCU2 +WARC-IP-Address: 132.174.1.35 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 621 + +HTTP/1.1 302 Moved Temporarily +Date: Mon, 23 Apr 2012 10:05:37 GMT +Server: 1060 NetKernel v3.3 - Powered by Jetty +Connection: close +Location: http://dublincore.org/2010/10/11/dcelements.rdf# +Content-Type: text/html; charset=iso-8859-1 +X-Purl: 2.0; http://localhost:8080 +Expires: Thu, 01 Jan 1970 00:00:00 GMT +Content-Length: 281 + + + + + 302 Found + + +

Found

+ The resource requested is available here.

+ + + + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://purl.org/dc/elements/1.1/ +WARC-Date: 2012-04-23T10:05:37Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 245 + +GET /dc/elements/1.1/ HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Referer: http://dyomedea.com/ +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: purl.org + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://purl.org/dc/elements/1.1/ +WARC-Date: 2012-04-23T10:05:37Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 346 + +via: http://dyomedea.com/ +hopsFromSeed: E +fetchTimeMs: 1601 +outlink: whois:132.174.1.35 I =INFERRED_MISC +outlink: http://dublincore.org/2010/10/11/dcelements.rdf R Location: +outlink: http://purl.org/favicon.ico I =INFERRED_MISC +outlink: whois:purl.org I =INFERRED_MISC +outlink: http://dublincore.org/2010/10/11/dcelements.rdf L A/@HREF + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: dns:dublincore.org +WARC-Date: 2012-04-23T10:05:39Z +WARC-IP-Address: 212.27.40.241 +WARC-Record-ID: +Content-Type: text/dns +Content-Length: 57 + +20120423100539 +dublincore.org. 21312 IN A 211.185.62.34 + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://dyomedea.com/styles/standard.css +WARC-Date: 2012-04-23T10:05:40Z +WARC-Payload-Digest: sha1:UBFFHPH66ZNZ6DYS74J5TED37UM3CHA5 +WARC-IP-Address: 95.142.167.137 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 5214 + +HTTP/1.1 200 OK +Date: Mon, 23 Apr 2012 10:05:40 GMT +Server: Apache-Coyote/1.1 +Last-Modified: Mon, 27 Apr 2009 21:16:19 GMT +Expires: Fri, 10 Aug 2012 13:46:36 GMT +Cache-Control: public +Pragma: +Content-Type: text/css +Content-Length: 4901 +Via: 1.0 dyomedea.com +Vary: Accept-Encoding +Connection: close + +/* CSS Dyomeda.com */ + +/* version standard v.020805-1155 CSS 2.0 valid */ + +/* +incompatible IE 5.5 WIN : +@import url("screen.css") screen; +@import url("print.css") print; +incompatible IE 5.1 MAC : +@media screen {} +@media print {} +-> utilisation sur chaque page de + + + +*/ + + +/* --> BALISES */ + +body { + font-size: 10pt; + line-height: 14pt; + margin: 0; +} + +a { + text-decoration: none; + color: #80000a; + padding: 0; + margin: 0; +} + +a:visited { + text-decoration: none; + padding: 0 2px; + color: #410005; +} + +a:hover { + color: #ffc42e; +} + +img { + border: none; +} + +hr { + display: none; +} + +/**/ + +ul.activites { + padding-left: 20px; +} + +ul.activites li { + list-style: url(../images/puce.png); + padding: 0; + padding-left: 0; + margin-bottom: 3px; +} + +ul.sous-menus li { + font-weight: bold; + font-family: Verdana, Arial, Helvetica, sans-serif; + text-transform: uppercase; +} + +/**/ + +dl.formation dt { + font-weight: bold; + font-family: Courier New, Courier, monospace; +} + +dl.formation dd { + margin-bottom: 15px; +} + +/* --> CALQUES */ + +#divContenant { + position: relative; + padding: 0; + min-width: 580px; +} + +/**/ + +#debutTet { + position: absolute; + left: 0; + top: 0; +} + +#finTet { + position: absolute; + right: 0; + top: 0; +} + +#divTetiere { + position: relative; + margin-top: 5px; +} + +#divTetiere h1 { + margin: 0; + padding: 0; + display: block; +} + +#divTetiere h1 a{ + border: none; + display: block; + height: 105px; + text-decoration: none; +} + +/**/ + + +/**/ + +#divMenu { + line-height: 12pt; + position: relative; + padding: 0; + margin-top: 10px; + float: left; + clear: both; +} + + +#divMenu ul { + margin: 0; + padding: 0 4px; + float: right; + clear: both; +} + +#divMenu li { + text-transform: uppercase; + font: normal bold 0.8em Verdana, Arial, Helvetica, sans-serif; + padding: 0 2px; + margin: 0; + display: inline; +} + +#divMenu li a { + text-decoration: none; + margin: 0; + font-weight: inherit; + font-style: inherit; +} + +#divMenu li a:hover { + color: #FFC42E; +} + +#divMenu li.on a { + text-decoration: none; + margin: 0; + font-weight: inherit; + font-style: inherit; +} + +/**/ + +#divContenu { + position: relative; + background: white; + border: thin solid #000000; + margin-top: 20px; + float: left; + padding: 1%; + min-height: 400px; +} + +#divEncadre { + position: relative; + width: 25%; + padding: 5px; + float:left; + margin-right: 10px; +} + +/**/ + +#divArticle { + background: white; + position: relative; + padding: 0px; + float:left; + margin-top: 0; + width: 70%; + font-family: "Trebuchet MS", verdana, sans-serif; +} + +#divArticle h2 { + color: #646464; + margin-top: 30px; + margin-bottom: 0; + text-transform: uppercase; + font: bold 1.5em Helvetica, Arial, sans-serif; + border-bottom: thin dotted #646464; + letter-spacing: 0.05em; +} + +#divArticle h3 { + margin: 0; + font-style: italic; + font-size: 0.9em; + color: #5782a1; + line-height: 1.2em; +} + +#divArticle ul { + list-style: disc; +} + +/**/ + +/**/ + +#divPiedPage { + border: 1px none #000000; + margin-top: 20px; + position: relative; + float: left; + display: block; + padding: 0.5%; + margin-bottom: 2px; + margin-bottom: 20px; +} + +/**/ + +/* --> CLASSES */ + +.bloc { + display: block; + padding: 2px; + font: 0.8em 'Lucida Grande', 'Lucida Sans', 'Trebuchet MS', verdana, sans-serif; + margin-bottom: 5px; + background: #e6e6e6; +} + +.bloc h3 { + text-transform: uppercase; + display: block; + margin: 0; + padding: 1px; + color: #ffffff; + font: bold 1em Verdana, Arial, Helvetica, sans-serif; + background: #5782a1; + border-bottom: thin solid #5782a1; + position: relative; +} + +.bloc h5 { + font-size: 1em; + padding: 1px; + margin: 0 0 5px; +} + +.bloc ul { + padding: 3px; +} + +.bloc li { + margin-bottom: 5px; + padding-bottom: 3px; + display: block; +} + +.hide { + display: none; +} + +.mentions { + text-align: center; + font: 0.8em Arial, Helvetica, sans-serif; + clear: both; + display: block; +} + +.validations { + font: 0.9em "Trebuchet MS", verdana, sans-serif; + text-align: right; + float: right; + padding-right: 3px; + padding-left: 3px; +} + +.about { + font: 0.9em "Trebuchet MS", verdana, sans-serif; + text-align: left; + float: left; + padding-right: 3px; + padding-left: 3px; +} + +.livres { + text-align: center; + margin: 0; + padding: 0; +} + +.titre-menu { + text-transform: uppercase; + font: bold 0.8em Verdana, Arial, Helvetica, sans-serif; + color: #646464; + padding: 0; + margin: 0; + text-align: right; +} + +.entete { + margin:0; +} + +pre { + padding: 0.5em; + line-height:100%; +} + +ul.map li ul { + margin : 0; + padding-top: 0; + padding-bottom: 0; + padding-left: 15px; +} + +ul.map li { + padding: 0; + margin: 0; +} + +ul.map li p { + padding: 0; + margin: 0; +} + + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://dyomedea.com/styles/standard.css +WARC-Date: 2012-04-23T10:05:40Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 252 + +GET /styles/standard.css HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Referer: http://dyomedea.com/ +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dyomedea.com + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dyomedea.com/styles/standard.css +WARC-Date: 2012-04-23T10:05:40Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 400 + +via: http://dyomedea.com/ +hopsFromSeed: E +fetchTimeMs: 136 +outlink: http://dyomedea.com/styles/print.css E =EMBED_MISC +outlink: http://dyomedea.com/favicon.ico I =INFERRED_MISC +outlink: whois:95.142.167.137 I =INFERRED_MISC +outlink: http://dyomedea.com/images/puce.png E =EMBED_MISC +outlink: http://dyomedea.com/styles/screen.css E =EMBED_MISC +outlink: whois:dyomedea.com I =INFERRED_MISC + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: whois://whois.arin.net/z+%2B+132.174.1.35 +WARC-Date: 2012-04-23T10:05:38Z +WARC-Record-ID: +Content-Type: text/plain +Content-Length: 1499 + +# +# The following results may also be obtained via: +# http://whois.arin.net/rest/nets;q=132.174.1.35?showDetails=true&showARIN=false&ext=netref2 +# + +NetRange: 132.174.0.0 - 132.174.255.255 +CIDR: 132.174.0.0/16 +OriginAS: +NetName: OCLC +NetHandle: NET-132-174-0-0-1 +Parent: NET-132-0-0-0-0 +NetType: Direct Assignment +RegDate: 1989-03-01 +Updated: 2001-04-23 +Ref: http://whois.arin.net/rest/net/NET-132-174-0-0-1 + +OrgName: OCLC Online Computer Library Center, Inc. +OrgId: OCLC +Address: 6565 Frantz Road +City: Dublin +StateProv: OH +PostalCode: 43017-0702 +Country: US +RegDate: 1989-03-01 +Updated: 2011-09-24 +Ref: http://whois.arin.net/rest/org/OCLC + +OrgTechHandle: IO17-ARIN +OrgTechName: Online Computer Library Center Inc +OrgTechPhone: +1-800-848-5878 +OrgTechEmail: DNS-Admin@oclc.org +OrgTechRef: http://whois.arin.net/rest/poc/IO17-ARIN + +OrgAbuseHandle: IO17-ARIN +OrgAbuseName: Online Computer Library Center Inc +OrgAbusePhone: +1-800-848-5878 +OrgAbuseEmail: DNS-Admin@oclc.org +OrgAbuseRef: http://whois.arin.net/rest/poc/IO17-ARIN + +RTechHandle: IO17-ARIN +RTechName: Online Computer Library Center Inc +RTechPhone: +1-800-848-5878 +RTechEmail: DNS-Admin@oclc.org +RTechRef: http://whois.arin.net/rest/poc/IO17-ARIN + +# +# ARIN WHOIS data and services are subject to the Terms of Use +# available at: https://www.arin.net/whois_tou.html +# + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: whois://whois.iana.org/org +WARC-Date: 2012-04-23T10:05:41Z +WARC-Record-ID: +Content-Type: text/plain +Content-Length: 1680 + +% IANA WHOIS server +% for more information on IANA, visit http://www.iana.org +% This query returned 1 object + +domain: ORG + +organisation: Public Interest Registry (PIR) +address: 1775 Wiehle Avenue +address: Suite 102A +address: Reston Virginia 20190 +address: United States + +contact: administrative +name: Michelle Coon +organisation: Public Interest Registry (PIR) +address: 1775 Wiehle Avenue +address: Suite 200 +address: Reston Virginia 20190 +address: United States +phone: +1 703 889 5762 +fax-no: +1 703 889 5779 +e-mail: mcoon@pir.org + +contact: technical +name: Michelle Coon +organisation: Public Interest Registry (PIR) +address: 1775 Wiehle Avenue +address: Suite 200 +address: Reston Virginia 20190 +address: United States +phone: +1 703 889 5762 +fax-no: +1 703 889 5779 +e-mail: mcoon@pir.org + +nserver: A0.ORG.AFILIAS-NST.INFO 199.19.56.1 2001:500:e:0:0:0:0:1 +nserver: A2.ORG.AFILIAS-NST.INFO 199.249.112.1 2001:500:40:0:0:0:0:1 +nserver: B0.ORG.AFILIAS-NST.ORG 199.19.54.1 2001:500:c:0:0:0:0:1 +nserver: B2.ORG.AFILIAS-NST.ORG 199.249.120.1 2001:500:48:0:0:0:0:1 +nserver: C0.ORG.AFILIAS-NST.INFO 199.19.53.1 2001:500:b:0:0:0:0:1 +nserver: D0.ORG.AFILIAS-NST.ORG 199.19.57.1 2001:500:f:0:0:0:0:1 +ds-rdata: 21366 7 1 e6c1716cfb6bdc84e84ce1ab5510dac69173b5b2 +ds-rdata: 21366 7 2 96eeb2ffd9b00cd4694e78278b5efdab0a80446567b69f634da078f0d90f01ba + +whois: whois.pir.org + +status: ACTIVE +remarks: Registration information: http://www.pir.org + +created: 1985-01-01 +changed: 2010-07-23 +source: IANA + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: whois://whois.pir.org/purl.org +WARC-Date: 2012-04-23T10:05:41Z +WARC-Record-ID: +Content-Type: text/plain +Content-Length: 2933 + +Access to .ORG WHOIS information is provided to assist persons in +determining the contents of a domain name registration record in the +Public Interest Registry registry database. The data in this record is provided by +Public Interest Registry for informational purposes only, and Public Interest Registry does not +guarantee its accuracy. This service is intended only for query-based +access. You agree that you will use this data only for lawful purposes +and that, under no circumstances will you use this data to: (a) allow, +enable, or otherwise support the transmission by e-mail, telephone, or +facsimile of mass unsolicited, commercial advertising or solicitations +to entities other than the data recipient's own existing customers; or +(b) enable high volume, automated, electronic processes that send +queries or data to the systems of Registry Operator, a Registrar, or +Afilias except as reasonably necessary to register domain names or +modify existing registrations. All rights reserved. Public Interest Registry reserves +the right to modify these terms at any time. By submitting this query, +you agree to abide by this policy. + +Domain ID:D847251-LROR +Domain Name:PURL.ORG +Created On:01-Jan-1996 05:00:00 UTC +Last Updated On:05-Nov-2007 20:50:14 UTC +Expiration Date:31-Dec-2016 05:00:00 UTC +Sponsoring Registrar:Network Solutions LLC (R63-LROR) +Status:CLIENT TRANSFER PROHIBITED +Registrant ID:22297011-NSI +Registrant Name:OCLC Online Computer Library Center, Inc +Registrant Organization:OCLC Online Computer Library Center, Inc +Registrant Street1:6565 Kilgour Place +Registrant Street2: +Registrant Street3: +Registrant City:Dublin +Registrant State/Province:OH +Registrant Postal Code:43017 +Registrant Country:US +Registrant Phone:+1.614764606 +Registrant Phone Ext.: +Registrant FAX:+1.614718708 +Registrant FAX Ext.: +Registrant Email:buzashg@OCLC.ORG +Admin ID:15679845-NSI +Admin Name:OCLCOnlineComputer Library Center, Inc. +Admin Organization:OCLCOnlineComputer Library Center, Inc. +Admin Street1:6565 FRANTZ RD +Admin Street2: +Admin Street3: +Admin City:DUBLIN +Admin State/Province:OH +Admin Postal Code:43017-5308 +Admin Country:US +Admin Phone:+1.6147646057 +Admin Phone Ext.: +Admin FAX:+1.6147640740 +Admin FAX Ext.: +Admin Email:buzashg@OCLC.ORG +Tech ID:16690384-NSI +Tech Name:OCLCOnlineComputer Library Center +Tech Organization:OCLCOnlineComputer Library Center +Tech Street1:6565 FRANTZ RD +Tech Street2: +Tech Street3: +Tech City:DUBLIN +Tech State/Province:OH +Tech Postal Code:43017-5308 +Tech Country:US +Tech Phone:+1.8008485878 +Tech Phone Ext.: +Tech FAX:+1.6147646096 +Tech FAX Ext.: +Tech Email:DNS-Admin@OCLC.ORG +Name Server:DNS.OCLC.ORG +Name Server:DNS2.OCLC.ORG +Name Server: +Name Server: +Name Server: +Name Server: +Name Server: +Name Server: +Name Server: +Name Server: +Name Server: +Name Server: +Name Server: +DNSSEC:Unsigned + + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://dublincore.org/robots.txt +WARC-Date: 2012-04-23T10:05:42Z +WARC-Payload-Digest: sha1:WWBDOOKQFQZEMEAT5ZBZGUJFEYSBBV3R +WARC-IP-Address: 211.185.62.34 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 653 + +HTTP/1.1 200 OK +Date: Mon, 23 Apr 2012 08:51:18 GMT +Server: Apache/2.0.59 (Unix) DAV/2 mod_ssl/2.0.59 OpenSSL/0.9.8g SVN/1.4.3 +Last-Modified: Mon, 30 Jun 2008 03:54:54 GMT +ETag: "7cc42-167-38dddf80" +Accept-Ranges: bytes +Content-Length: 359 +Content-Type: text/plain +Connection: close + +# /robots.txt file for http://dublincore.org/ +# mail webteam@admin.dublincore.org for constructive criticism + +User-agent: * # directed to all spiders +Disallow: /images +Disallow: /ssi +Disallow: /temp +Disallow: /psd +Disallow: /ccs +Disallow: /js +Disallow: /templates +Disallow: /dcregistry +Disallow: /registry + + +User-agent: Linbot # override +Allow: / + + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://dublincore.org/robots.txt +WARC-Date: 2012-04-23T10:05:42Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 214 + +GET /robots.txt HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dublincore.org + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dublincore.org/robots.txt +WARC-Date: 2012-04-23T10:05:42Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 263 + +force-fetch: +via: http://dublincore.org/2010/10/11/dcelements.rdf +hopsFromSeed: ERP +fetchTimeMs: 843 +outlink: whois:dublincore.org I =INFERRED_MISC +outlink: http://dublincore.org/favicon.ico I =INFERRED_MISC +outlink: whois:211.185.62.34 I =INFERRED_MISC + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://dyomedea.com/images/logo520.png +WARC-Date: 2012-04-23T10:05:43Z +WARC-Payload-Digest: sha1:LNYO7FKFQTT45XP6NQWDYCKTOKXVTVJG +WARC-IP-Address: 95.142.167.137 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 7494 + +HTTP/1.1 200 OK +Date: Mon, 23 Apr 2012 10:05:43 GMT +Server: Apache-Coyote/1.1 +Last-Modified: Mon, 27 Apr 2009 21:16:21 GMT +Expires: Fri, 10 Aug 2012 13:46:39 GMT +Cache-Control: public +Pragma: +Content-Type: image/png +Content-Length: 7203 +Via: 1.0 dyomedea.com +Connection: close + +PNG + + IHDRih+gAMAOX2tEXtSoftwareAdobe ImageReadyqe<PLTEL_``00@@П 󘣾Cd2JMs=RU~?]ppdt:U>RRzPPWiPw5NgwJ]Hk~7Qq篯A`KouUU5m;ۯ@rZG8 ln_=ӈAl Px~*d n{==uwR!Ȣ_l~C7_@A +BAu&k.TWPTP4*٨KU|! &O#P8h_[C7zՅ B8d d+(N7TTf' +N! +ת.@?@N^WU0;4Ye[ 'OZf(oh|VPٍL^PаU>@fO(~Ꙁ7r a­x`phHpl9NJQ .6|‡c ?g~E쀋@q0@4Pj&JzbDz&h%Y +].U Z[pܼ)`Wm]P0dUG#F@),gpA/'QƩ5Pqx`Kp0Ì0"!zEg>zmz7\ UJ{v!—T# +|zw]61ҫcR }=qN⌝5rf!BPw~OLjtR͑g.;Or2MU[~ G +܄E|C4K9'm]j6Yp$k'66[l S DN29U_kWIHݮ6R9rA"vD}N@9!Ϫa•84 Tq] k9n3skS6F%L7Ex>둞n< +mFi5pzNXЈI ~|畒 P^YU+l3Ѫ= ncw}y!hD,0x_OYg2r5Z +r2c]^N,]tw?e~ 3=b +˚fZ +PYûQжY_}Ox񯌂a/N@xWAn0h@,3FpY WiCJcI{hJNВ,vށ$~7Y|8UoaU$Dd/Ct/kHT"hRoWΖtkF/*n#~9xԭ>PW6z{U7?=sg ׫~l Z9͇Z2?:P},-;K d+j6|1n5QWVK2Ia!4W}Jںdq@s枷Oxo-z6{}NMQc=  }V=R>RN^"$gH|w?~F}wi8u`DMl 3>,֧8?7>xiVo0V(m"$@W\Հ@P \-K 7萝)BCɿtMNrnD}G50,FS+8%܇p/S~fuHPY`e j  IC})]V-2>ɓXp8L/6X,`ڙl絛 G i OZD}^zFN'O'F,Ƀc2ZY_pp1"T-+t*~.\("Fr4 ip'cv؛#̆ +?qTlɘFc`}F  @1TPo]ԳĠYMe0C7b:f!d-v@Im}az3 C`Hh +Ow@^G/c牖"~/jlSVJFɓL:KlcdIORA/9;Ʌ#aZSHk>o:T»k\w)Aq"'T82<4}YH"||FE hʌ, \OX%g?aߋWdyHCS_g;qT.d'jn;ͣD3W8@(a4]/ppv[Md>2L]<0I?C|Z9eU@S.OO3cgn$3Ťz62ݍ !ŤTm-!$jnJ,IwSjJ҆Tz1&Hm|in)`^\kFp74lw8}}_M"#&,QնƳ$ڳmm?s A7i{@:ۅk;"vUCZD"sY2A@lAl˄ujG,T͒DFB9* )X5gfɞEi֓_x<R1Dҵ8R&r/ +ibjM-K9|EcP 9@ G  +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 251 + +GET /images/logo520.png HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Referer: http://dyomedea.com/ +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dyomedea.com + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dyomedea.com/images/logo520.png +WARC-Date: 2012-04-23T10:05:43Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 216 + +via: http://dyomedea.com/ +hopsFromSeed: E +fetchTimeMs: 81 +outlink: whois:dyomedea.com I =INFERRED_MISC +outlink: http://dyomedea.com/favicon.ico I =INFERRED_MISC +outlink: whois:95.142.167.137 I =INFERRED_MISC + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://dyomedea.com/styles/screen.css +WARC-Date: 2012-04-23T10:05:46Z +WARC-Payload-Digest: sha1:MCLYBLAE464FBGQ24UFIUOCCFSI7SPVM +WARC-IP-Address: 95.142.167.137 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 1063 + +HTTP/1.1 200 OK +Date: Mon, 23 Apr 2012 10:05:46 GMT +Server: Apache-Coyote/1.1 +Last-Modified: Mon, 27 Apr 2009 21:16:19 GMT +Expires: Fri, 10 Aug 2012 13:46:42 GMT +Cache-Control: public +Pragma: +Content-Type: text/css +Content-Length: 751 +Via: 1.0 dyomedea.com +Vary: Accept-Encoding +Connection: close + +/* CSS Dyomeda.com */ + +/* version ecran */ + + +body, html { + background: #5782a1; +} + +#divTetiere h1 a{ + background: repeat-x url(../images/fd-tetiere.png); +} + +#divTetiere img { + background: #5782a1; +} + +#divMenu ul { + background: #30467d url(../images/fd-menu.png) repeat; +} + + +#divMenu li, #divMenu li a, #divMenu a:visited { + color: #ffffff; +} + +#divMenu li.on a, #divMenu li.on a:visited { + color: #ffc42e; +} + +#divContenant { + width: 70%; + margin-right: 15%; + margin-left: 15%; +} + +#divContenu { + width: 98%; +} + +#divPiedPage { + width: 99%; + background: #688FAB; +} + +.mentions { + color: #e6e6e6; +} + +pre { + border: thin dotted #646464; + background: #f2f2f2; + overflow:auto; + font-size: 0.75em; + width: 98%; +} + + + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://dyomedea.com/styles/screen.css +WARC-Date: 2012-04-23T10:05:46Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 250 + +GET /styles/screen.css HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Referer: http://dyomedea.com/ +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dyomedea.com + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dyomedea.com/styles/screen.css +WARC-Date: 2012-04-23T10:05:46Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 345 + +via: http://dyomedea.com/ +hopsFromSeed: E +fetchTimeMs: 57 +outlink: whois:95.142.167.137 I =INFERRED_MISC +outlink: http://dyomedea.com/images/fd-menu.png E =EMBED_MISC +outlink: http://dyomedea.com/favicon.ico I =INFERRED_MISC +outlink: whois:dyomedea.com I =INFERRED_MISC +outlink: http://dyomedea.com/images/fd-tetiere.png E =EMBED_MISC + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://purl.org/favicon.ico +WARC-Date: 2012-04-23T10:05:47Z +WARC-Payload-Digest: sha1:6TRHDMHIOSVJ3GLUQ3OJRISRMTVQ5LJ6 +WARC-IP-Address: 132.174.1.35 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 1970 + +HTTP/1.1 404 Not Found +Date: Mon, 23 Apr 2012 10:05:46 GMT +Server: 1060 NetKernel v3.3 - Powered by Jetty +Connection: close +Expires: Thu, 01 Jan 1970 00:00:00 GMT +Content-Type: text/html;charset=UTF-8 +Content-Length: 1739 + + + + + + + PURL not found + + + + + + + +

+ + + + + + + +
+ Suggestion: +
+ Go To purl.org +
+ + + + + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://purl.org/favicon.ico +WARC-Date: 2012-04-23T10:05:47Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 252 + +GET /favicon.ico HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Referer: http://purl.org/dc/elements/1.1/ +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: purl.org + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://purl.org/favicon.ico +WARC-Date: 2012-04-23T10:05:47Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 521 + +via: http://purl.org/dc/elements/1.1/ +hopsFromSeed: EI +fetchTimeMs: 272 +outlink: http://purl.org/docs/images/zepheiralogo.png E img/@src +outlink: http://www.oclc.org/ L a/@href +outlink: http://zepheira.com/ L a/@href +outlink: http://purl.org/docs/images/oclclogo.png E img/@src +outlink: whois:132.174.1.35 I =INFERRED_MISC +outlink: http://purl.org/favicon.ico I =INFERRED_MISC +outlink: whois:purl.org I =INFERRED_MISC +outlink: http://purl.org/ L a/@href +outlink: http://purl.org/docs/style.css E link/@href + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://dublincore.org/2010/10/11/dcelements.rdf +WARC-Date: 2012-04-23T10:05:47Z +WARC-Payload-Digest: sha1:Z7QXOBMD4MQMJBXGZN4IMBDOZBO3VE7Z +WARC-IP-Address: 211.185.62.34 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 17731 + +HTTP/1.1 200 OK +Date: Mon, 23 Apr 2012 08:51:23 GMT +Server: Apache/2.0.59 (Unix) DAV/2 mod_ssl/2.0.59 OpenSSL/0.9.8g SVN/1.4.3 +Last-Modified: Wed, 29 Sep 2010 14:31:58 GMT +ETag: "7cc3b-4411-d2e8b380" +Accept-Ranges: bytes +Content-Length: 17425 +Content-Type: application/rdf+xml +Connection: close + + + + + + + + + +]> + + +Dublin Core Metadata Element Set, Version 1.1 + +2010-10-11 + + +Title +A name given to the resource. + +1999-07-02 +2008-01-14 + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + +Creator +An entity primarily responsible for making the resource. +Examples of a Creator include a person, an organization, or a service. Typically, the name of a Creator should be used to indicate the entity. + +1999-07-02 +2008-01-14 + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + +Subject +The topic of the resource. +Typically, the subject will be represented using keywords, key phrases, or classification codes. Recommended best practice is to use a controlled vocabulary. To describe the spatial or temporal topic of the resource, use the Coverage element. + +1999-07-02 +2008-01-14 + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + +Description +An account of the resource. +Description may include but is not limited to: an abstract, a table of contents, a graphical representation, or a free-text account of the resource. + +1999-07-02 +2008-01-14 + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + +Publisher +An entity responsible for making the resource available. +Examples of a Publisher include a person, an organization, or a service. Typically, the name of a Publisher should be used to indicate the entity. + +1999-07-02 +2008-01-14 + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + +Contributor +An entity responsible for making contributions to the resource. +Examples of a Contributor include a person, an organization, or a service. Typically, the name of a Contributor should be used to indicate the entity. + +1999-07-02 +2008-01-14 + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + +Date +A point or period of time associated with an event in the lifecycle of the resource. +Date may be used to express temporal information at any level of granularity. Recommended best practice is to use an encoding scheme, such as the W3CDTF profile of ISO 8601 [W3CDTF]. + +1999-07-02 +2008-01-14 + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + +Type +The nature or genre of the resource. +Recommended best practice is to use a controlled vocabulary such as the DCMI Type Vocabulary [DCMITYPE]. To describe the file format, physical medium, or dimensions of the resource, use the Format element. + +1999-07-02 +2008-01-14 + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + +Format +The file format, physical medium, or dimensions of the resource. +Examples of dimensions include size and duration. Recommended best practice is to use a controlled vocabulary such as the list of Internet Media Types [MIME]. + +1999-07-02 +2008-01-14 + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + +Identifier +An unambiguous reference to the resource within a given context. +Recommended best practice is to identify the resource by means of a string conforming to a formal identification system. + +1999-07-02 +2008-01-14 + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + +Source +A related resource from which the described resource is derived. +The described resource may be derived from the related resource in whole or in part. Recommended best practice is to identify the related resource by means of a string conforming to a formal identification system. + +1999-07-02 +2008-01-14 + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + +Language +A language of the resource. +Recommended best practice is to use a controlled vocabulary such as RFC 4646 [RFC4646]. + +1999-07-02 +2008-01-14 + + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + +Relation +A related resource. +Recommended best practice is to identify the related resource by means of a string conforming to a formal identification system. + +1999-07-02 +2008-01-14 + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + +Coverage +The spatial or temporal topic of the resource, the spatial applicability of the resource, or the jurisdiction under which the resource is relevant. +Spatial topic and spatial applicability may be a named place or a location specified by its geographic coordinates. Temporal topic may be a named period, date, or date range. A jurisdiction may be a named administrative entity or a geographic place to which the resource applies. Recommended best practice is to use a controlled vocabulary such as the Thesaurus of Geographic Names [TGN]. Where appropriate, named places or time periods can be used in preference to numeric identifiers such as sets of coordinates or date ranges. + +1999-07-02 +2008-01-14 + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + +Rights +Information about rights held in and over the resource. +Typically, rights information includes a statement about various property rights associated with the resource, including intellectual property rights. + +1999-07-02 +2008-01-14 + + +A second property with the same name as this property has been declared in the dcterms: namespace (http://purl.org/dc/terms/). See the Introduction to the document "DCMI Metadata Terms" (http://dublincore.org/documents/dcmi-terms/) for an explanation. + + + + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://dublincore.org/2010/10/11/dcelements.rdf +WARC-Date: 2012-04-23T10:05:47Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 272 + +GET /2010/10/11/dcelements.rdf HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Referer: http://purl.org/dc/elements/1.1/ +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dublincore.org + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dublincore.org/2010/10/11/dcelements.rdf +WARC-Date: 2012-04-23T10:05:47Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 234 + +via: http://purl.org/dc/elements/1.1/ +hopsFromSeed: ER +fetchTimeMs: 1719 +outlink: http://dublincore.org/favicon.ico I =INFERRED_MISC +outlink: whois:dublincore.org I =INFERRED_MISC +outlink: whois:211.185.62.34 I =INFERRED_MISC + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: whois://whois.pir.org/dublincore.org +WARC-Date: 2012-04-23T10:05:48Z +WARC-Record-ID: +Content-Type: text/plain +Content-Length: 2719 + +Access to .ORG WHOIS information is provided to assist persons in +determining the contents of a domain name registration record in the +Public Interest Registry registry database. The data in this record is provided by +Public Interest Registry for informational purposes only, and Public Interest Registry does not +guarantee its accuracy. This service is intended only for query-based +access. You agree that you will use this data only for lawful purposes +and that, under no circumstances will you use this data to: (a) allow, +enable, or otherwise support the transmission by e-mail, telephone, or +facsimile of mass unsolicited, commercial advertising or solicitations +to entities other than the data recipient's own existing customers; or +(b) enable high volume, automated, electronic processes that send +queries or data to the systems of Registry Operator, a Registrar, or +Afilias except as reasonably necessary to register domain names or +modify existing registrations. All rights reserved. Public Interest Registry reserves +the right to modify these terms at any time. By submitting this query, +you agree to abide by this policy. + +Domain ID:D9251392-LROR +Domain Name:DUBLINCORE.ORG +Created On:19-Aug-1999 13:23:09 UTC +Last Updated On:12-Jan-2012 18:33:36 UTC +Expiration Date:19-Aug-2014 13:23:09 UTC +Sponsoring Registrar:Network Solutions LLC (R63-LROR) +Status:CLIENT TRANSFER PROHIBITED +Registrant ID:43612149-NSI +Registrant Name:Stuart Sutton +Registrant Street1:4 Shenton Way +Registrant Street2:SGX Centre 2, #17-01 +Registrant Street3: +Registrant City:Singapore +Registrant State/Province: +Registrant Postal Code:068807 +Registrant Country:SG +Registrant Phone:+65.68466733 +Registrant Phone Ext.: +Registrant FAX: +Registrant FAX Ext.: +Registrant Email:sasutton@dublincore.net +Admin ID:43612149-NSI +Admin Name:Stuart Sutton +Admin Street1:4 Shenton Way +Admin Street2:SGX Centre 2, #17-01 +Admin Street3: +Admin City:Singapore +Admin State/Province: +Admin Postal Code:068807 +Admin Country:SG +Admin Phone:+65.68466733 +Admin Phone Ext.: +Admin FAX: +Admin FAX Ext.: +Admin Email:sasutton@dublincore.net +Tech ID:43612149-NSI +Tech Name:Stuart Sutton +Tech Street1:4 Shenton Way +Tech Street2:SGX Centre 2, #17-01 +Tech Street3: +Tech City:Singapore +Tech State/Province: +Tech Postal Code:068807 +Tech Country:SG +Tech Phone:+65.68466733 +Tech Phone Ext.: +Tech FAX: +Tech FAX Ext.: +Tech Email:sasutton@dublincore.net +Name Server:NS.PUBNET.NE.KR +Name Server:MAIL.NL.GO.KR +Name Server: +Name Server: +Name Server: +Name Server: +Name Server: +Name Server: +Name Server: +Name Server: +Name Server: +Name Server: +Name Server: +DNSSEC:Unsigned + + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: whois://whois.arin.net/z+%2B+211.185.62.34 +WARC-Date: 2012-04-23T10:05:49Z +WARC-Record-ID: +Content-Type: text/plain +Content-Length: 1939 + +# +# The following results may also be obtained via: +# http://whois.arin.net/rest/nets;q=211.185.62.34?showDetails=true&showARIN=false&ext=netref2 +# + +NetRange: 211.0.0.0 - 211.255.255.255 +CIDR: 211.0.0.0/8 +OriginAS: +NetName: NET-211 +NetHandle: NET-211-0-0-0-1 +Parent: +NetType: Allocated to APNIC +Comment: This IP address range is not registered in the ARIN database. +Comment: For details, refer to the APNIC Whois Database via +Comment: WHOIS.APNIC.NET or http://wq.apnic.net/apnic-bin/whois.pl +Comment: ** IMPORTANT NOTE: APNIC is the Regional Internet Registry +Comment: for the Asia Pacific region. APNIC does not operate networks +Comment: using this IP address range and is not able to investigate +Comment: spam or abuse reports relating to these addresses. For more +Comment: help, refer to http://www.apnic.net/apnic-info/whois_search2/abuse-and-spamming +RegDate: 1996-07-01 +Updated: 2010-08-02 +Ref: http://whois.arin.net/rest/net/NET-211-0-0-0-1 + +OrgName: Asia Pacific Network Information Centre +OrgId: APNIC +Address: PO Box 3646 +City: South Brisbane +StateProv: QLD +PostalCode: 4101 +Country: AU +RegDate: +Updated: 2012-01-24 +Ref: http://whois.arin.net/rest/org/APNIC + +ReferralServer: whois://whois.apnic.net + +OrgTechHandle: AWC12-ARIN +OrgTechName: APNIC Whois Contact +OrgTechPhone: +61 7 3858 3188 +OrgTechEmail: search-apnic-not-arin@apnic.net +OrgTechRef: http://whois.arin.net/rest/poc/AWC12-ARIN + +OrgAbuseHandle: AWC12-ARIN +OrgAbuseName: APNIC Whois Contact +OrgAbusePhone: +61 7 3858 3188 +OrgAbuseEmail: search-apnic-not-arin@apnic.net +OrgAbuseRef: http://whois.arin.net/rest/poc/AWC12-ARIN + +# +# ARIN WHOIS data and services are subject to the Terms of Use +# available at: https://www.arin.net/whois_tou.html +# + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://dyomedea.com/favicon.ico +WARC-Date: 2012-04-23T10:05:49Z +WARC-Payload-Digest: sha1:F6G7ZFWRBV6NT7ATRZNMXPBY7CI3PEDT +WARC-IP-Address: 95.142.167.137 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 4181 + +HTTP/1.1 404 Introuvable +Date: Mon, 23 Apr 2012 10:05:49 GMT +Server: Apache-Coyote/1.1 +Last-Modified: Mon, 23 Apr 2012 10:05:49 GMT +Expires: Mon, 23 Apr 2012 10:05:49 GMT +Cache-Control: post-check=0, pre-check=0 +Pragma: +Content-Type: application/xhtml+xml;charset=utf-8 +Content-Length: 3836 +Via: 1.0 dyomedea.com +Connection: close + + + + + + + + Dyomedea : Guide de haute technologie XML + + + + + + + + + + + + + +
+
+

DYOMEDEA : Guide de haute technologie...

+
+ +
+
+

Dyomedea : Guide de haute technologie XML

+
 
+
+ +

Page inexistante (erreur 404)

+ +

La page que vous avez demandé n'existe pas sur le site http://dyomedea.com

+ +

Si vous pensez qu'il s'agit d'une erreur liée au site http://dyomedea.com, merci de + la signaler à Eric van der Vlist. +

+ +

Sinon, si vous obtenez cette erreur après avoir suivi un lien, merci de la signaler à + l'auteur de la page contenant le lien erroné. +

+ +
+
+
à propos planxhtml 1.1 +  css 2.0

Mentions Légales

+
Dyomedea et XMLfr sont des marques + déposées. Tous droits réservés. © Dyomedea, 1999-2010
Dyomedea, SARL au + capital de 10 000 € - RCS: Paris B 422 260 208 - 75, rue de Lourmel 75015 + Paris.

 
+ + + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://dyomedea.com/favicon.ico +WARC-Date: 2012-04-23T10:05:49Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 244 + +GET /favicon.ico HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Referer: http://dyomedea.com/ +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dyomedea.com + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dyomedea.com/favicon.ico +WARC-Date: 2012-04-23T10:05:49Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 1190 + +via: http://dyomedea.com/ +hopsFromSeed: I +fetchTimeMs: 82 +outlink: http://dyomedea.com/styles/print.css E link/@href +outlink: mailto:vdv@dyomedea.com L a/@href +outlink: http://dyomedea.com/projets/ L a/@href +outlink: http://dyomedea.com/ L a/@href +outlink: http://dyomedea.com/help/ L a/@href +outlink: http://dyomedea.com/communication/ L a/@href +outlink: http://dyomedea.com/images/logo520.png E img/@src +outlink: http://dyomedea.com/map/ L a/@href +outlink: whois:95.142.167.137 I =INFERRED_MISC +outlink: http://dyomedea.com/styles/standard.css E link/@href +outlink: http://dyomedea.com/formation/ L a/@href +outlink: http://validator.w3.org/check/referer L a/@href +outlink: http://dyomedea.com/english/favicon.ico L a/@href +outlink: http://purl.org/dc/elements/1.1/ E link/@href +outlink: whois:dyomedea.com I =INFERRED_MISC +outlink: http://dyomedea.com/styles/screen.css E link/@href +outlink: http://dyomedea.com/favicon.ico I =INFERRED_MISC +outlink: http://dyomedea.com/images/bout.png E img/@src +outlink: http://jigsaw.w3.org/css-validator/check/referer L a/@href +outlink: http://dyomedea.com/conseil/ L a/@href +outlink: http://dyomedea.com/dyomedea/ L a/@href + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: whois://whois.apnic.net/211.185.62.34 +WARC-Date: 2012-04-23T10:05:49Z +WARC-Record-ID: +Content-Type: text/plain +Content-Length: 1820 + +% [whois.apnic.net node-5] +% Whois data copyright terms http://www.apnic.net/db/dbcopyright.html + +inetnum: 211.172.0.0 - 211.199.255.255 +netname: KRNIC-KR +descr: KRNIC +descr: Korea Network Information Center +country: KR +admin-c: HM127-AP +tech-c: HM127-AP +remarks: ****************************************** +remarks: KRNIC is the National Internet Registry +remarks: in Korea under APNIC. If you would like to +remarks: find assignment information in detail +remarks: please refer to the KRNIC Whois DB +remarks: http://whois.nic.or.kr/english/index.html +remarks: ****************************************** +mnt-by: APNIC-HM +mnt-lower: MNT-KRNIC-AP +changed: hostmaster@apnic.net 20000607 +changed: hostmaster@apnic.net 20010606 +status: ALLOCATED PORTABLE +source: APNIC + +person: Host Master +address: 11F, KTF B/D, 1321-11, Seocho2-Dong, Seocho-Gu, +address: Seoul, Korea, 137-857 +country: KR +phone: +82-2-2186-4500 +fax-no: +82-2-2186-4496 +e-mail: hostmaster@nic.or.kr +nic-hdl: HM127-AP +mnt-by: MNT-KRNIC-AP +changed: hostmaster@nic.or.kr 20020507 +source: APNIC + +inetnum: 211.184.0.0 - 211.185.255.255 +netname: PUBNET-KR +descr: Korea Telecom-PUBNET +country: KR +admin-c: IA30-KR +tech-c: IM30-KR +status: ALLOCATED PORTABLE +mnt-by: MNT-KRNIC-AP +mnt-irt: IRT-KRNIC-KR +remarks: This information has been partially mirrored by APNIC from +remarks: KRNIC. To obtain more specific information, please use the +remarks: KRNIC whois server at whois.krnic.net. +changed: hostmaster@nic.or.kr +source: KRNIC + + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://dyomedea.com/images/bout.png +WARC-Date: 2012-04-23T10:05:52Z +WARC-Payload-Digest: sha1:GSXQTUF5CX2FQDSYWYXBENCD47RJDXP2 +WARC-IP-Address: 95.142.167.137 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 524 + +HTTP/1.1 200 OK +Date: Mon, 23 Apr 2012 10:05:52 GMT +Server: Apache-Coyote/1.1 +Last-Modified: Mon, 27 Apr 2009 21:16:21 GMT +Expires: Fri, 10 Aug 2012 13:46:49 GMT +Cache-Control: public +Pragma: +Content-Type: image/png +Content-Length: 234 +Via: 1.0 dyomedea.com +Connection: close + +PNG + + IHDR-i ZgAMAOX2tEXtSoftwareAdobe ImageReadyqe< PLTE0F}W(YtRNS@*TIDATxԱ YB4Τ$omDbh4Fh4F[?r5ktIKt sW?F?U@1wIENDB` + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://dyomedea.com/images/bout.png +WARC-Date: 2012-04-23T10:05:52Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 248 + +GET /images/bout.png HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Referer: http://dyomedea.com/ +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dyomedea.com + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dyomedea.com/images/bout.png +WARC-Date: 2012-04-23T10:05:52Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 216 + +via: http://dyomedea.com/ +hopsFromSeed: E +fetchTimeMs: 54 +outlink: whois:dyomedea.com I =INFERRED_MISC +outlink: http://dyomedea.com/favicon.ico I =INFERRED_MISC +outlink: whois:95.142.167.137 I =INFERRED_MISC + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://dyomedea.com/images/puce.png +WARC-Date: 2012-04-23T10:05:55Z +WARC-Payload-Digest: sha1:OBN6LKMHMTVMIM2F4NGXCLGW46RL7WG5 +WARC-IP-Address: 95.142.167.137 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 447 + +HTTP/1.1 200 OK +Date: Mon, 23 Apr 2012 10:05:55 GMT +Server: Apache-Coyote/1.1 +Last-Modified: Mon, 27 Apr 2009 21:16:21 GMT +Expires: Fri, 10 Aug 2012 13:46:52 GMT +Cache-Control: public +Pragma: +Content-Type: image/png +Content-Length: 157 +Via: 1.0 dyomedea.com +Connection: close + +PNG + + IHDRNgAMAOX2tEXtSoftwareAdobe ImageReadyqe<PLTE.IDATxb```ddd4# ȊPi#>BIENDB` + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://dyomedea.com/images/puce.png +WARC-Date: 2012-04-23T10:05:55Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 267 + +GET /images/puce.png HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Referer: http://dyomedea.com/styles/standard.css +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dyomedea.com + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dyomedea.com/images/puce.png +WARC-Date: 2012-04-23T10:05:55Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 236 + +via: http://dyomedea.com/styles/standard.css +hopsFromSeed: EE +fetchTimeMs: 63 +outlink: whois:95.142.167.137 I =INFERRED_MISC +outlink: http://dyomedea.com/favicon.ico I =INFERRED_MISC +outlink: whois:dyomedea.com I =INFERRED_MISC + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://dyomedea.com/images/fd-menu.png +WARC-Date: 2012-04-23T10:05:58Z +WARC-Payload-Digest: sha1:XHSKLTIZIED73A767LG5T73MDWNML4TY +WARC-IP-Address: 95.142.167.137 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 437 + +HTTP/1.1 200 OK +Date: Mon, 23 Apr 2012 10:05:58 GMT +Server: Apache-Coyote/1.1 +Last-Modified: Mon, 27 Apr 2009 21:16:21 GMT +Expires: Fri, 10 Aug 2012 13:46:56 GMT +Cache-Control: public +Pragma: +Content-Type: image/png +Content-Length: 147 +Via: 1.0 dyomedea.com +Connection: close + +PNG + + IHDR(-SgAMAOX2tEXtSoftwareAdobe ImageReadyqe<PLTEio}0F}WIDATxb`D `D0IPI,IENDB` + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://dyomedea.com/images/fd-menu.png +WARC-Date: 2012-04-23T10:05:58Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 268 + +GET /images/fd-menu.png HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Referer: http://dyomedea.com/styles/screen.css +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dyomedea.com + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dyomedea.com/images/fd-menu.png +WARC-Date: 2012-04-23T10:05:58Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 234 + +via: http://dyomedea.com/styles/screen.css +hopsFromSeed: EE +fetchTimeMs: 59 +outlink: whois:dyomedea.com I =INFERRED_MISC +outlink: whois:95.142.167.137 I =INFERRED_MISC +outlink: http://dyomedea.com/favicon.ico I =INFERRED_MISC + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://dublincore.org/favicon.ico +WARC-Date: 2012-04-23T10:05:57Z +WARC-Payload-Digest: sha1:HYZOZGARLB7ATJSLRIGZN2UEORPIZXJH +WARC-IP-Address: 211.185.62.34 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 4448 + +HTTP/1.1 200 OK +Date: Mon, 23 Apr 2012 08:51:33 GMT +Server: Apache/2.0.59 (Unix) DAV/2 mod_ssl/2.0.59 OpenSSL/0.9.8g SVN/1.4.3 +Last-Modified: Mon, 30 Jun 2008 03:54:54 GMT +ETag: "7f1df-1036-38dddf80" +Accept-Ranges: bytes +Content-Length: 4150 +Content-Type: image/x-icon +Connection: close + +  &h ( @ fffffffffeefefeeefefeefffffffffffffffffffeee3TjffjT4fefffffffffffffffffffffsjefitefffffffffffffffffx"zff mFfeE mff!zxfffffffffffff&|-efkqfeefqjff,'}efffffffffff)~1efe l mgfm kffe1,efffffefffeef-0ffeq98qfee/.ffeeefffffp%{gfeevF${WW$|Evfffg%|peffee n\eff m@WijW@ nfff[ mffeepneh +kFgfpuuoggG lhelpfffff%|Ijh1jf&|&|fj0hjI&|feeeffffeqseJLetpffeeffefjfffgXp+-pWfffejeeel{fhNUihhiUOhfznefi1GttF1jfe${,fv'}"z"z'|vf+${fefefefoqf y yfpoeeeeefefffefpNnnMqffefffefUn +ljgxzfj +knTfff"z]fG-f l lf,Ge[$|fe l/eegb,rs,bfef- meeegjffeqfg9:gfqfeeiheefffeehggn4E xfhgfxE3mghhfeffffffeu jfeirqife jveefffffeT/eefIFBJfee,Veefffffeo}heeefie m lfheeeeh|pfffffffeeffef77efffeefe68efefffffffffeefffeefhYYhfeffffeffffffffffeeebcefAAffadeffffffffffffffffffifff!y"yeefifffffffffffffffffffefffffhhfefffffffffffffffffffffffffeefefeeeefefffffffff( ffffee"zgg"zeffffffffjk k,+ kkjfffffff khg kfefffh +k lq3zz2q l +lhfemf7r"z#zr7fmff krjrrjr kfvZf?'}'}?fZv5r)*~r5eefXxxXfef kv55v kgh li4uv4h lhgff4,IW//WI,5effe|ke"zIsqI"zej}effeef=etsf=fffffffetOffNufffffffffffffeffffff + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://dublincore.org/favicon.ico +WARC-Date: 2012-04-23T10:05:57Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 273 + +GET /favicon.ico HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Referer: http://dublincore.org/2010/10/11/dcelements.rdf +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dublincore.org + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dublincore.org/favicon.ico +WARC-Date: 2012-04-23T10:05:57Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 250 + +via: http://dublincore.org/2010/10/11/dcelements.rdf +hopsFromSeed: ERI +fetchTimeMs: 1265 +outlink: whois:211.185.62.34 I =INFERRED_MISC +outlink: whois:dublincore.org I =INFERRED_MISC +outlink: http://dublincore.org/favicon.ico I =INFERRED_MISC + + + +WARC/1.0 +WARC-Type: response +WARC-Target-URI: http://dyomedea.com/images/fd-tetiere.png +WARC-Date: 2012-04-23T10:06:01Z +WARC-Payload-Digest: sha1:HLIXQNEZC6SVR57GUKHOYCPDZ6I3A46S +WARC-IP-Address: 95.142.167.137 +WARC-Record-ID: +Content-Type: application/http; msgtype=response +Content-Length: 488 + +HTTP/1.1 200 OK +Date: Mon, 23 Apr 2012 10:06:01 GMT +Server: Apache-Coyote/1.1 +Last-Modified: Mon, 27 Apr 2009 21:16:21 GMT +Expires: Fri, 10 Aug 2012 13:46:59 GMT +Cache-Control: public +Pragma: +Content-Type: image/png +Content-Length: 198 +Via: 1.0 dyomedea.com +Connection: close + +PNG + + IHDRiSZgAMAOX2tEXtSoftwareAdobe ImageReadyqe< PLTE0F}W(YtRNS@*0IDATxb`F D +`&400BJ 2QqHwmIENDB` + +WARC/1.0 +WARC-Type: request +WARC-Target-URI: http://dyomedea.com/images/fd-tetiere.png +WARC-Date: 2012-04-23T10:06:01Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/http; msgtype=request +Content-Length: 271 + +GET /images/fd-tetiere.png HTTP/1.0 +User-Agent: Mozilla/5.0 (compatible; heritrix/3.1.0 +http://owark.org) +Connection: close +Referer: http://dyomedea.com/styles/screen.css +Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 +Host: dyomedea.com + + + +WARC/1.0 +WARC-Type: metadata +WARC-Target-URI: http://dyomedea.com/images/fd-tetiere.png +WARC-Date: 2012-04-23T10:06:01Z +WARC-Concurrent-To: +WARC-Record-ID: +Content-Type: application/warc-fields +Content-Length: 234 + +via: http://dyomedea.com/styles/screen.css +hopsFromSeed: EE +fetchTimeMs: 60 +outlink: http://dyomedea.com/favicon.ico I =INFERRED_MISC +outlink: whois:95.142.167.137 I =INFERRED_MISC +outlink: whois:dyomedea.com I =INFERRED_MISC + + + diff --git a/archiver/pipelines/actions/package-heritrix-warc.xpl b/archiver/pipelines/actions/package-heritrix-warc.xpl index c2204a7..b9a11e4 100644 --- a/archiver/pipelines/actions/package-heritrix-warc.xpl +++ b/archiver/pipelines/actions/package-heritrix-warc.xpl @@ -7,7 +7,7 @@ + xmlns:pipeline="java:org.orbeon.oxf.processor.pipeline.PipelineFunctionLibrary" xmlns:owk="http://owark.org/orbeon/processors"> @@ -33,6 +33,15 @@ + + + + + + + + + diff --git a/archiver/pipelines/config/processors-local.xml b/archiver/pipelines/config/processors-local.xml new file mode 100644 index 0000000..0efa933 --- /dev/null +++ b/archiver/pipelines/config/processors-local.xml @@ -0,0 +1,6 @@ + + + + + +