@Override
public WebURL entryToObject(TupleInput input) {
WebURL webURL = new WebURL();
webURL.setPrimeKey(input.readString());
webURL.setURL(input.readString());
webURL.setDocid(input.readInt());
webURL.setParentDocid(input.readInt());
webURL.setParentUrl(input.readString());
webURL.setDepth(input.readShort());
webURL.setCookie(input.readString());
webURL.setFormParams(input.readString());
webURL.setMethod(input.readString());
return webURL;
}
@Override
public void objectToEntry(WebURL url, TupleOutput output) {
output.writeString(url.getPrimeKey());
output.writeString(url.getURL());
output.writeInt(url.getDocid());
output.writeInt(url.getParentDocid());
output.writeString(url.getParentUrl());
output.writeShort(url.getDepth());
output.writeString(url.getCookie());
output.writeString(url.getFormParams());
output.writeString(url.getMethod());
}
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 boolean shouldVisit(WebURL url) {
// Don't crawl non-HTML pages
String href = url.getURL().toLowerCase(); // Turns http://www.ics.uci.edu/SomePage.PHP ->
// http://www.ics.uci.edu/somepage.php
if (FILTERS.matcher(href).matches()) // filter using file extension
return false;
// Only crawl within the domain of the seed URL
String currentUrlDomain = URLHelper.getDomain(url.getURL());
String seedUrlDomain = URLHelper.getDomain(this.params.getSeedUrl());
if (currentUrlDomain == null || !currentUrlDomain.endsWith(seedUrlDomain)) return false;
// Don't crawl the same pages too many times (avoid infinite loops)
if (!stats.intendToVisit(url.getURL())) return false;
return true;
}
@Override
public boolean shouldVisit(Page page, WebURL url) {
try {
String href = url.getURL().toLowerCase();
String decodedString = URLDecoder.decode(href, "UTF8");
return filter1.matcher(decodedString).matches() || filter2.matcher(decodedString).matches();
} catch (UnsupportedEncodingException ex) {
ex.printStackTrace();
return false;
}
}
public void InsertItem(String URL, String Text, String HTML) throws SQLException {
WebURL curURL = new WebURL();
curURL.setURL(URL);
Statement stmt = null;
try {
stmt = c.createStatement();
} catch (SQLException e) {
System.out.println("Error, can't create statement in AddLink");
e.printStackTrace();
}
PreparedStatement statement =
c.prepareStatement("INSERT INTO PAGES (URL,SUBDOMAIN,BODY,HTML) values (?, ?, ?, ?)");
statement.setString(1, URL);
statement.setString(2, curURL.getSubDomain());
statement.setString(3, Text);
statement.setString(4, HTML);
statement.executeUpdate();
}
@Override
public boolean shouldVisit(Page referringPage, WebURL url) {
String href = url.getURL().toLowerCase().toString();
// System.out.println("start tag =
// "+href.startsWith("http://estekhdame.ir/blog/tag/")+url);
if (FILTERS.matcher(href).matches()) return false;
if (href.contains("city") || href.contains("study")) {
// System.out.println("hi"+href);
return false;
}
return href.startsWith("http://eshetab.com/state/") || href.contains("/ads/");
}
@Test
public void test() {
String url1 = "http://nba.hupu.com/";
String url2 = "http://www.google.com/";
WebURL a = new WebURL();
a.setURL(url1);
a.setDepth((short) 3);
WebURL b = new WebURL();
b.setURL(url2);
b.setDepth((short) 2);
scheduler.schedule(a);
assertEquals(1, scheduler.getQueueLength());
scheduler.schedule(a);
assertEquals(1, scheduler.getQueueLength());
scheduler.schedule(b);
assertEquals(2, scheduler.getQueueLength());
List<WebURL> l = new ArrayList<WebURL>();
scheduler.getNextURLs(1, l);
assertEquals(url2, l.get(0).getURL());
assertEquals(1, scheduler.getQueueLength());
assertEquals(2, scheduler.getScheduledNum());
}
private Page download(String url) {
WebURL curURL = new WebURL();
curURL.setURL(url);
PageFetchResult fetchResult = null;
try {
fetchResult = pageFetcher.fetchHeader(curURL);
if (fetchResult.getStatusCode() == HttpStatus.SC_OK) {
try {
Page page = new Page(curURL);
fetchResult.fetchContent(page);
if (parser.parse(page, curURL.getURL())) {
return page;
}
} catch (Exception e) {
e.printStackTrace();
}
}
} finally {
fetchResult.discardContentIfNotConsumed();
}
return null;
}
@Override
public boolean shouldVisit(WebURL url) {
String href = url.getURL().toLowerCase();
if (PATTERN_MAIL_FILTERS.matcher(href).matches()) {
return false;
}
for (String crawlDomain : crawlDomains) {
if (href.startsWith(crawlDomain)) {
return true;
}
}
return false;
}
public void downLoadText(String pageText, WebURL webUrl) throws IOException {
int docid = webUrl.getDocid();
File file_output = new File("E:/crawlData/pageText/" + docid + ".txt");
if (!file_output.exists()) {
File parent = new File(file_output.getParent());
if (!parent.exists()) {
parent.mkdirs();
}
}
FileWriter fWriter = new FileWriter(file_output);
fWriter.write(pageText);
fWriter.close();
}
@Override
public boolean shouldVisit(WebURL url) {
String href = url.getURL().toLowerCase();
if (filters.matcher(href).matches()) {
return false;
}
if (imgPatterns.matcher(href).matches()) {
return true;
}
for (String domain : crawlDomains) {
if (href.startsWith(domain)) {
return true;
}
}
return false;
}
/*
* @see
* com.qq.crawler.webcrawler.RailgunCrawler#shouldVisit(edu.uci.ics.crawler4j
* .url.WebURL)
*/
@Override
public boolean shouldVisit(WebURL url) {
String href = url.getURL().toLowerCase();
if (urlPattern.matcher(href).matches()) {
return false;
}
if (null != shouldUnVisitPatterns) {
for (Pattern pattern : shouldUnVisitPatterns) {
if (pattern.matcher(href).matches()) {
return false;
}
}
}
boolean shouldVisit = false;
if (null != shouldVisitPatterns) {
for (Pattern pattern : shouldVisitPatterns) {
if (pattern.matcher(href).matches()) {
shouldVisit = true;
break;
}
}
} else {
shouldVisit = true;
}
if (!shouldVisit) {
return false;
}
if (!CrawlerUtils.FILTERS.matcher(href).matches()) {
for (String host : hosts) {
if (href.startsWith(host)) {
// System.out.println(href + ": fetch");
return true;
}
}
}
return false;
}
/**
* This method receives two parameters. The first parameter is the page in which we have
* discovered this new url and the second parameter is the new url. You should implement this
* function to specify whether the given url should be crawled or not (based on your crawling
* logic). In this example, we are instructing the crawler to ignore urls that have css, js, git,
* ... extensions and to only accept urls that start with "http://www.ics.uci.edu/". In this case,
* we didn't need the referringPage parameter to make the decision.
*/
@Override
public boolean shouldVisit(Page referringPage, WebURL url) {
String dest = url.getURL().toLowerCase();
return FILTERS.matcher(dest).matches() && dest.startsWith(getBaseURL());
}
/**
* This method receives two parameters. The first parameter is the page in which we have
* discovered this new url and the second parameter is the new url. You should implement this
* function to specify whether the given url should be crawled or not (based on your crawling
* logic). In this example, we are instructing the crawler to ignore urls that have css, js, git,
* ... extensions and to only accept urls that start with "http://www.ics.uci.edu/". In this case,
* we didn't need the referringPage parameter to make the decision.
*/
@Override
public boolean shouldVisit(Page referringPage, WebURL url) {
String href = url.getURL().toLowerCase();
return !FILTERS.matcher(href).matches() && href.startsWith("http://www.sanook.com/");
}
@Override
public boolean shouldVisit(WebURL url) {
String href = url.getURL().toLowerCase();
return !filters.matcher(href).matches() && href.startsWith("http://www.lankadeepa.lk/");
}
public boolean shouldVisit(WebURL url) {
String href = url.getURL().toLowerCase();
return !filters.matcher(href).matches() && href.contains("apache.org");
}
/**
* You should implement this function to specify whether the given url should be crawled or not
* (based on your crawling logic).
*/
@Override
public boolean shouldVisit(WebURL url) {
String href = url.getURL().toLowerCase();
return !FILTERS.matcher(href).matches() && href.startsWith("http://www.ics.uci.edu/");
}
@Override
public boolean shouldVisit(WebURL url) {
String href = url.getURL().toLowerCase();
return !Mission.crawlFilters.matcher(href).matches() && href.startsWith(Mission.crawlDomain);
}
