boxtec
/
yacy_search_server
mirror of https://github.com/yacy/yacy_search_server
4
1
Fork 0
Code Issues Projects Releases Wiki Activity

fix for rss parser: be lazy when rss is not well-formed

Browse Source 
git-svn-id: https://svn.berlios.de/svnroot/repos/yacy/trunk@6552 6c8d7289-2bf4-0310-a012-ef5d649a1542
pull/1/head
orbiter 15 years ago
parent dff4f95c78
commit 3f771d2a16
1 changed files with 105 additions and 90 deletions
Show Stats Download Patch File Download Diff File

195
source/net/yacy/document/parser/rssParser.java
Unescape View File

@ -30,7 +30,9 @@ package net.yacy.document.parser;
import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.UnsupportedEncodingException;
import java.io.Writer;
import java.net.MalformedURLException;
import java.nio.charset.Charset;
import java.util.HashMap;
import java.util.HashSet;
@ -78,109 +80,122 @@ public class rssParser extends AbstractParser implements Idiom {
public Document parse(final DigestURI location, final String mimeType, final String charset, final InputStream source) throws ParserException, InterruptedException {
final LinkedList<String> feedSections = new LinkedList<String>();
final HashMap<DigestURI, String> anchors = new HashMap<DigestURI, String>();
final HashMap<String, ImageEntry> images = new HashMap<String, ImageEntry>();
final ByteBuffer text = new ByteBuffer();
final CharBuffer authors = new CharBuffer();
RSSFeed feed = null;
try {
final LinkedList<String> feedSections = new LinkedList<String>();
final HashMap<DigestURI, String> anchors = new HashMap<DigestURI, String>();
final HashMap<String, ImageEntry> images = new HashMap<String, ImageEntry>();
final ByteBuffer text = new ByteBuffer();
final CharBuffer authors = new CharBuffer();
feed = new RSSReader(source).getFeed();
} catch (IOException e) {
throw new ParserException("reading feed failed: " + e.getMessage(), location);
}
if (feed == null) throw new ParserException("no feed in document", location);
String feedTitle = "";
String feedDescription = "";
if (feed.getChannel() != null) {//throw new ParserException("no channel in document",location);
final RSSFeed feed = new RSSReader(source).getFeed();
if (feed == null) throw new ParserException("no feed in document",location);
// get the rss feed title and description
feedTitle = feed.getChannel().getTitle();
// get feed creator
final String feedCreator = feed.getChannel().getAuthor();
if (feedCreator != null && feedCreator.length() > 0) authors.append(",").append(feedCreator);
String feedTitle = "";
String feedDescription = "";
if (feed.getChannel() != null) {//throw new ParserException("no channel in document",location);
// get the feed description
feedDescription = feed.getChannel().getDescription();
}
if (feed.getImage() != null) {
try {
DigestURI imgURL = new DigestURI(feed.getImage(), null);
images.put(imgURL.hash(), new ImageEntry(imgURL, feedTitle, -1, -1, -1));
} catch (MalformedURLException e) {}
}
// loop through the feed items
for (final RSSMessage item: feed) {
// check for interruption
checkInterruption();
// get the rss feed title and description
feedTitle = feed.getChannel().getTitle();
// get feed creator
final String feedCreator = feed.getChannel().getAuthor();
if (feedCreator != null && feedCreator.length() > 0) authors.append(",").append(feedCreator);
final String itemTitle = item.getTitle();
DigestURI itemURL = null;
try {
itemURL = new DigestURI(item.getLink(), null);
} catch (MalformedURLException e) {
continue;
}
final String itemDescr = item.getDescription();
final String itemCreator = item.getCreator();
if (itemCreator != null && itemCreator.length() > 0) authors.append(",").append(itemCreator);
// get the feed description
feedDescription = feed.getChannel().getDescription();
}
if (feed.getImage() != null) {
final DigestURI imgURL = new DigestURI(feed.getImage(), null);
images.put(imgURL.hash(), new ImageEntry(imgURL, feedTitle, -1, -1, -1));
}
// loop through the feed items
for (final RSSMessage item: feed) {
// check for interruption
checkInterruption();
feedSections.add(itemTitle);
anchors.put(itemURL, itemTitle);
if ((text.length() != 0) && (text.byteAt(text.length() - 1) != 32)) text.append((byte) 32);
text.append(AbstractScraper.stripAll(itemDescr).trim()).append(' ');
final String itemContent = item.getDescription();
if ((itemContent != null) && (itemContent.length() > 0)) {
final ContentScraper scraper = new ContentScraper(itemURL);
final Writer writer = new TransformerWriter(null, null, scraper, null, false);
try {
FileUtils.copy(new ByteArrayInputStream(itemContent.getBytes("UTF-8")), writer, Charset.forName("UTF-8"));
} catch (UnsupportedEncodingException e) {
continue;
} catch (IOException e) {
continue;
}
final String itemTitle = item.getTitle();
final DigestURI itemURL = new DigestURI(item.getLink(), null);
final String itemDescr = item.getDescription();
final String itemCreator = item.getCreator();
if (itemCreator != null && itemCreator.length() > 0) authors.append(",").append(itemCreator);
final String itemHeadline = scraper.getTitle();
if (itemHeadline != null && !itemHeadline.isEmpty()) {
feedSections.add(itemHeadline);
}
feedSections.add(itemTitle);
anchors.put(itemURL, itemTitle);
final Map<DigestURI, String> itemLinks = scraper.getAnchors();
if (itemLinks != null && !itemLinks.isEmpty()) {
anchors.putAll(itemLinks);
}
if ((text.length() != 0) && (text.byteAt(text.length() - 1) != 32)) text.append((byte) 32);
text.append(AbstractScraper.stripAll(itemDescr).trim()).append(' ');
final HashMap<String, ImageEntry> itemImages = scraper.getImages();
if (itemImages != null && !itemImages.isEmpty()) {
ContentScraper.addAllImages(images, itemImages);
}
final String itemContent = item.getDescription();
if ((itemContent != null) && (itemContent.length() > 0)) {
final ContentScraper scraper = new ContentScraper(itemURL);
final Writer writer = new TransformerWriter(null, null, scraper, null, false);
FileUtils.copy(new ByteArrayInputStream(itemContent.getBytes("UTF-8")), writer, Charset.forName("UTF-8"));
final String itemHeadline = scraper.getTitle();
if (itemHeadline != null && !itemHeadline.isEmpty()) {
feedSections.add(itemHeadline);
}
final Map<DigestURI, String> itemLinks = scraper.getAnchors();
if (itemLinks != null && !itemLinks.isEmpty()) {
anchors.putAll(itemLinks);
}
final HashMap<String, ImageEntry> itemImages = scraper.getImages();
if (itemImages != null && !itemImages.isEmpty()) {
ContentScraper.addAllImages(images, itemImages);
}
final byte[] extractedText = scraper.getText();
if ((extractedText != null) && (extractedText.length > 0)) {
if ((text.length() != 0) && (text.byteAt(text.length() - 1) != 32)) text.append((byte) 32);
text.append(scraper.getText());
}
final byte[] extractedText = scraper.getText();
if ((extractedText != null) && (extractedText.length > 0)) {
if ((text.length() != 0) && (text.byteAt(text.length() - 1) != 32)) text.append((byte) 32);
text.append(scraper.getText());
}
}
final Document theDoc = new Document(
location,
mimeType,
"UTF-8",
null,
null,
feedTitle,
(authors.length() > 0)?authors.toString(1,authors.length()):"",
feedSections.toArray(new String[feedSections.size()]),
feedDescription,
text.getBytes(),
anchors,
images);
// close streams
}
}
final Document theDoc = new Document(
location,
mimeType,
"UTF-8",
null,
null,
feedTitle,
(authors.length() > 0)?authors.toString(1,authors.length()):"",
feedSections.toArray(new String[feedSections.size()]),
feedDescription,
text.getBytes(),
anchors,
images);
// close streams
try {
text.close();
authors.close();
return theDoc;
} catch (final InterruptedException e) {
throw e;
} catch (final IOException e) {
throw new ParserException("Unexpected error while parsing rss file." + e.getMessage(),location);
} catch (IOException e) {
}
return theDoc;
}
public Set<String> supportedMimeTypes() {

Write Preview
Loading…
Cancel
Save