/** This function is called when a page is fetched and ready to be processed by your program. */
@Override
public void visit(Page page) {
// System.out.println(page.getWebURL().toString().contains("city")+"
// "+page.getWebURL());
// url title date body
if (page.getWebURL().toString().contains("/ads/")
|| page.getWebURL().toString().contains("/view/")) {
if (page.getParseData() instanceof HtmlParseData) {
HtmlParseData htmlParseData = (HtmlParseData) page.getParseData();
String html = htmlParseData.getHtml();
Document doc = Jsoup.parse(html);
String url;
String title;
String body = null;
String date = null;
url = page.getWebURL().getURL();
title = doc.title();
// System.out.println(title);
date = doc.getElementsByClass("nameDiv").get(1).text();
body = doc.getElementsByClass("addsTexts").get(0).text();
System.out.println(date);
System.out.println(body);
// System.out.println(body);
// System.out.println("URL: " + url);
// System.out.println("title: " + title);
// System.out.println("date: " + date);
// System.out.println("body: " + body);
Indexer.add(url, title, body, date);
}
}
}
/** This function is called when a page is fetched and ready to be processed by your program. */
@Override
public void visit(Page page) {
if (page.getParseData() instanceof HtmlParseData) {
ResultSet res = null;
try {
HtmlParseData htmlParseData = (HtmlParseData) page.getParseData();
String html = htmlParseData.getHtml();
Document doc = Jsoup.parse(html);
// check if the page must be crawled
String url = page.getWebURL().getURL();
if (!shouldVisit(url)) {
return;
}
currentPage = getDocumentURL(url.toLowerCase());
// check if the page was already crawled
queryDocumentFind.setString(1, currentPage);
res = queryDocumentFind.executeQuery();
if (res.next()) {
return;
}
logger.debug("Code: " + currentPage);
// insert into DOCUMENT
queryDocumentInsert.setString(1, getSHA256(currentPage));
queryDocumentInsert.setString(2, currentPage);
queryDocumentInsert.setString(3, getDocumentType(url).name());
queryDocumentInsert.setString(4, getDocumentBand(url, doc));
queryDocumentInsert.setString(5, getDocumentAlbum(url, doc));
queryDocumentInsert.setAsciiStream(6, getDocumentContent(url, doc));
queryDocumentInsert.setDate(7, getDocumentCreationDate(url, doc));
queryDocumentInsert.setString(8, getDocumentCover(url, doc));
queryDocumentInsert.setString(9, getDocumentAuthor(url, doc));
queryDocumentInsert.setString(10, getDocumentGenre(url, doc));
queryDocumentInsert.setInt(11, getDocumentYear(url, doc));
queryDocumentInsert.setString(12, getDocumentLabel(url, doc));
queryDocumentInsert.setFloat(13, getDocumentVote(url, doc));
queryDocumentInsert.setBoolean(14, getDocumentMilestone(url, doc));
queryDocumentInsert.executeUpdate();
logger.info("Document " + currentPage + " added into DOCUMENT");
} catch (Throwable t) {
logger.error("Error parsing page " + page.getWebURL().getURL() + ": " + t.getMessage());
} finally {
try {
if (res != null) {
res.close();
}
} catch (Throwable t) {
// do nothing
}
}
}
}
@Override
public void visit(Page page) {
String url = page.getWebURL().getURL();
// We are only interested in processing images
if (!(page.getParseData() instanceof BinaryParseData)) {
return;
}
if (!imgPatterns.matcher(url).matches()) {
return;
}
// Not interested in very small images
if (page.getContentData().length < 10 * 1024) {
return;
}
// get a unique name for storing this image
String extension = url.substring(url.lastIndexOf("."));
String hashedName = Cryptography.MD5(url) + extension;
// store image
IO.writeBytesToFile(page.getContentData(), storageFolder.getAbsolutePath() + "/" + hashedName);
System.out.println("Stored: " + url);
}
/** This function is called when a page is fetched and ready to be processed by your program. */
@Override
public void visit(Page page) {
String url = page.getWebURL().getURL();
System.out.println("URL: " + url);
if (page.getParseData() instanceof HtmlParseData) {
i++;
HtmlParseData htmlParseData = (HtmlParseData) page.getParseData();
String text = htmlParseData.getText();
String html = htmlParseData.getHtml();
Set<WebURL> links = htmlParseData.getOutgoingUrls();
System.out.println("Text: " + text);
System.out.println("Text length: " + text.length());
System.out.println("Html length: " + html.length());
System.out.println("Number of outgoing links: " + links.size());
try {
PrintWriter writer = new PrintWriter(i + ".txt", "UTF-8");
writer.println("Text length: " + text);
writer.println("Html length: " + html);
writer.close();
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (UnsupportedEncodingException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
@Override
public void visit(Page page) {
if (page.getWebURL().getURL().equals("http://www.eshetab.com/")) return;
else if (filter1.matcher(page.getWebURL().getURL()).matches()) {
return;
} else {
System.out.println(page.getWebURL().getURL());
Document doc = Jsoup.parse(((HtmlParseData) page.getParseData()).getHtml());
Elements elements =
doc.select(".addsTexts , .nameDiv:nth-child(3) , .nameDiv:nth-child(2) , .DivTitle span");
String title = elements.get(0).text();
String date =
elements.get(2).text().split(":")[1].substring(1); // it has one space in zero index
date = date.split("-")[2] + "/" + date.split("-")[1] + "/" + date.split("-")[0];
date = CalendarUtility.getEnglishDate(date);
System.out.println(date);
String city = "نامعلوم";
// System.out.println(elements.get(3).text());
city = elements.get(3).text().split(":")[1].substring(1).split("-")[0];
if (city.contains(",")) {
city = city.substring(1, city.length() - 1);
} else {
city = "نامعلوم";
}
System.out.println(date);
String body = elements.get(4).text();
try {
feeds.add(
new Feed(
title, body, city, URLDecoder.decode(page.getWebURL().toString(), "UTF8"), date));
} catch (ParseException e) {
e.printStackTrace();
} catch (UnsupportedEncodingException e) {
e.printStackTrace();
}
}
}
@Override
public void visit(Page page) {
int docid = page.getWebURL().getDocid();
String url = page.getWebURL().getURL();
System.out.println("Docid: " + docid);
// *** Filter urls which need to be processed ************
if (url.startsWith(Mission.crawlDomain + "topic/")
&& page.getParseData() instanceof HtmlParseData) {
// *************************************************
HtmlParseData htmlParseData = (HtmlParseData) page.getParseData();
Document dom = Jsoup.parse(htmlParseData.getHtml());
// *** Scratch elements inside a page **************
Elements titles = dom.select("div.title").select("h2");
/*
* TODO bug: text will also contain title
*/
Elements texts = dom.select("div[class=bd art-content clearfix]");
String title = titles.get(0).text();
String text = texts.get(0).text();
// *************************************************
if (titles.size() == 1 && texts.size() == 1) {
System.out.println("title:" + title);
System.out.println("text:" + text);
String crawlClass = Mission.dbNameMap.get("crawlClass");
String[] crawlFields = Mission.dbNameMap.get("crawlFields").split(",");
// *** Save to database *************************
ODatabaseRecordThreadLocal.INSTANCE.set(Mission.db);
ODocument doc = new ODocument(crawlClass);
doc.field(crawlFields[0], url);
doc.field(crawlFields[1], title);
doc.field(crawlFields[2], text);
doc.save();
// *************************************************
}
}
}
@Override
public void visit(Page page) {
String url = page.getWebURL().getURL();
System.out.println("Visited: " + url);
if (page.getParseData() instanceof HtmlParseData) {
HtmlParseData htmlParseData = (HtmlParseData) page.getParseData();
String text = htmlParseData.getText();
String html = htmlParseData.getHtml();
List<WebURL> links = htmlParseData.getOutgoingUrls();
System.out.println("Text length: " + text.length());
System.out.println("Html length: " + html.length());
System.out.println("Number of outgoing links: " + links.size());
}
}
public void visit(Page page) {
String url = page.getWebURL().getURL();
// standard out contains a single line per URL, with the URL
// followed by all the words found on the page
//
String text = page.getText().replaceAll("[^a-zA-Z]+", " ");
System.out.println(url + "\t" + text);
// standard err contains a line for each outgoing link from the
// page we're crawling
//
for (WebURL link : page.getURLs()) {
System.err.println(url + "\t" + link.getURL());
}
}
@Override
public void visit(Page page) {
// Keep track of visited URLs
String url = page.getWebURL().getURL();
stats.addCrawledUrl(url);
System.out.println("Crawled: " + url);
// Get the page terms and store them locally
if (page.getParseData() instanceof HtmlParseData) { // make sure document has HTML data
HtmlParseData htmlParseData = (HtmlParseData) page.getParseData();
String html = htmlParseData.getHtml();
// Don't keep documents that are too big (bigger than 2MB)
if (html.length() <= 2097152) {
// Store the HTML
this.params.getDocumentStorage().storeDocument(url, html);
}
}
}
@Override
public void visit(Page page) {
String url = page.getWebURL().getURL();
urlQueue.add(new EmailCollectorUrlMessage(url));
logger.info("Scanning URL: " + url);
if (page.getParseData() instanceof HtmlParseData) {
HtmlParseData htmlParseData = (HtmlParseData) page.getParseData();
String html = htmlParseData.getHtml();
try {
addEmail(html);
} catch (InterruptedException e) {
e.printStackTrace();
}
}
logger.info("=============");
}
/** This function is called when a page is fetched and ready to be processed by your program. */
@Override
public void visit(Page page) {
int docid = page.getWebURL().getDocid();
String url = page.getWebURL().getURL();
String domain = page.getWebURL().getDomain();
String path = page.getWebURL().getPath();
String subDomain = page.getWebURL().getSubDomain();
String parentUrl = page.getWebURL().getParentUrl();
String anchor = page.getWebURL().getAnchor();
System.out.println("Docid: " + docid);
System.out.println("URL: " + url);
System.out.println("Domain: '" + domain + "'");
System.out.println("Sub-domain: '" + subDomain + "'");
System.out.println("Path: '" + path + "'");
System.out.println("Parent page: " + parentUrl);
System.out.println("Anchor text: " + anchor);
if (page.getParseData() instanceof HtmlParseData) {
HtmlParseData htmlParseData = (HtmlParseData) page.getParseData();
String text = htmlParseData.getText();
String html = htmlParseData.getHtml();
List<WebURL> links = htmlParseData.getOutgoingUrls();
System.out.println("Text length: " + text.length());
System.out.println("Html length: " + html.length());
System.out.println("Number of outgoing links: " + links.size());
}
Header[] responseHeaders = page.getFetchResponseHeaders();
if (responseHeaders != null) {
System.out.println("Response headers:");
for (Header header : responseHeaders) {
System.out.println("\t" + header.getName() + ": " + header.getValue());
}
}
System.out.println("=============");
}
private void PrintLongestPage() {
String url = longestPage.getWebURL().getURL().toLowerCase();
System.out.println("Longest page is :" + url);
System.out.println("Number of words in the page :" + longestPageWordCount);
}
public ExtractorContext extractContent() {
HtmlParseData htmlParseData = (HtmlParseData) page.getParseData();
ExtractorContext ctx = new ExtractorContext(page, htmlParseData.getHtml());
ctx.setMetaTags(MetadataExtractor.INST.extractMetaTags(ctx.getDoc()));
String language = ctx.getMetaTags().get(MetadataExtractor.CONTENT_LANGUAGE_TAG);
// skip not english pages
if ((language != null && !ENGLISH_US.equals(language.toLowerCase()))) {
LOG.info("Skipping " + ctx.getUrl() + " not ENGLISH");
return null;
}
if (ctx.getUrl().contains(YOUTUBE)) {
String keyWords = ctx.getMetaTags().get(MetadataExtractor.KEYWORDS_TAG);
if (keyWords == null) {
LOG.info("Skipping " + ctx.getUrl() + " no KEYWORDS");
return null;
}
keyWords = keyWords.toLowerCase();
if (!keyWords.contains(SAP)) {
LOG.info("Skipping " + ctx.getUrl() + " no SAP in KEYWORDS");
return null;
}
}
Document clearedHtml = cleanHtml(ctx);
if (clearedHtml.text().length() < MIN_CONTENT_LENGTH) {
LOG.info("Skipping " + ctx.getUrl() + " less then " + MIN_CONTENT_LENGTH + " characters");
return null;
}
// skip pages with not English content
if (!LanguageDetector.INST.isEnglish(clearedHtml.text())) {
LOG.info("Skipping " + ctx.getUrl() + " not ENGLISH");
return null;
}
NavigableSet<ExtractedImage> images = MostRelevantImageExtractor.INST.extract(ctx);
String uniqueFileName = CryptographyUtils.sha1(clearedHtml.text());
PageObject pageObject = new PageObject();
pageObject.setId(uniqueFileName);
pageObject.setTitle(ctx.getTitle());
pageObject.setContent(clearedHtml.html());
pageObject.setUrl(page.getWebURL().getURL());
pageObject.setHtmlCleanerName(ctx.getCleaner().getName());
List<TextBlock> blocks = TextBlocksExtractor.INST.extract(clearedHtml);
if (!blocks.isEmpty()) {
pageObject.setMainBlock(blocks.get(0));
blocks.remove(0);
pageObject.addBlocks(blocks);
}
// set title from First text block if NULL or EMPTY.
if ((pageObject.getTitle() == null || "".equals(pageObject.getTitle().trim()))
&& !pageObject.getBlocks().isEmpty()) {
pageObject.setTitle(pageObject.getBlocks().get(0).getTitle());
}
pageObject.addAllKeywords(BaseClassifier.INST.classify(ctx));
if (!images.isEmpty()) {
pageObject.addImages(images);
}
ctx.setPageObject(pageObject);
return ctx;
}