private void crawlForEmailAddresses(String urlSeedToBeScraped) {
// SELECT shopurl FROM shops.shops where placetypes like '%clothing%' and shopurl is not
// null and shopurl <> '';
CrawlConfig config = new CrawlConfig();
config.setCrawlStorageFolder(
"C:\\Users\\janitha\\Documents\\NetBeansProjects\\crawlshopsforcoucou\\target\\interim");
config.setPolitenessDelay(1000);
config.setMaxDepthOfCrawling(1);
config.setIncludeBinaryContentInCrawling(false);
config.setResumableCrawling(false);
PageFetcher pageFetcher = new PageFetcher(config);
RobotstxtConfig robotstxtConfig = new RobotstxtConfig();
RobotstxtServer robotstxtServer = new RobotstxtServer(robotstxtConfig, pageFetcher);
CrawlController controller = null;
String shopUrl = urlSeedToBeScraped;
try {
controller = new CrawlController(config, pageFetcher, robotstxtServer);
controller.addSeed(shopUrl);
EmailScraper.setStartWithDomain(shopUrl);
controller.start(EmailScraper.class, 1);
} catch (Exception ex) {
Logger.getLogger(EmailScraperTest.class.getName())
.log(Level.SEVERE, "Something went wrong" + ex.getMessage());
}
}
public static void main(String[] args) throws Exception {
if (args.length < 3) {
System.out.println("Needed parameters: ");
System.out.println("\t rootFolder (it will contain intermediate crawl data)");
System.out.println("\t numberOfCralwers (number of concurrent threads)");
System.out.println("\t storageFolder (a folder for storing downloaded images)");
return;
}
String rootFolder = args[0];
int numberOfCrawlers = Integer.parseInt(args[1]);
String storageFolder = args[2];
CrawlConfig config = new CrawlConfig();
config.setCrawlStorageFolder(rootFolder);
/*
* Since images are binary content, we need to set this parameter to
* true to make sure they are included in the crawl.
*/
config.setIncludeBinaryContentInCrawling(true);
String[] crawlDomains = new String[] {"http://uci.edu/"};
PageFetcher pageFetcher = new PageFetcher(config);
RobotstxtConfig robotstxtConfig = new RobotstxtConfig();
RobotstxtServer robotstxtServer = new RobotstxtServer(robotstxtConfig, pageFetcher);
CrawlController controller = new CrawlController(config, pageFetcher, robotstxtServer);
for (String domain : crawlDomains) {
controller.addSeed(domain);
}
ImageCrawler.configure(crawlDomains, storageFolder);
controller.start(ImageCrawler.class, numberOfCrawlers);
}
public static void main(String[] args) throws Exception {
if (args.length != 2) {
logger.info("Needed parameters: ");
logger.info("\t rootFolder (it will contain intermediate crawl data)");
logger.info("\t numberOfCralwers (number of concurrent threads)");
return;
}
/*
* crawlStorageFolder is a folder where intermediate crawl data is
* stored.
*/
String crawlStorageFolder = args[0];
/*
* numberOfCrawlers shows the number of concurrent threads that should
* be initiated for crawling.
*/
int numberOfCrawlers = Integer.parseInt(args[1]);
CrawlConfig config = new CrawlConfig();
config.setCrawlStorageFolder(crawlStorageFolder);
/*
* Be polite: Make sure that we don't send more than 1 request per
* second (1000 milliseconds between requests).
*/
config.setPolitenessDelay(1000);
/*
* You can set the maximum crawl depth here. The default value is -1 for
* unlimited depth
*/
config.setMaxDepthOfCrawling(2);
/*
* You can set the maximum number of pages to crawl. The default value
* is -1 for unlimited number of pages
*/
config.setMaxPagesToFetch(1000);
/**
* Do you want crawler4j to crawl also binary data ? example: the contents of pdf, or the
* metadata of images etc
*/
config.setIncludeBinaryContentInCrawling(false);
/*
* Do you need to set a proxy? If so, you can use:
* config.setProxyHost("proxyserver.example.com");
* config.setProxyPort(8080);
*
* If your proxy also needs authentication:
* config.setProxyUsername(username); config.getProxyPassword(password);
*/
/*
* This config parameter can be used to set your crawl to be resumable
* (meaning that you can resume the crawl from a previously
* interrupted/crashed crawl). Note: if you enable resuming feature and
* want to start a fresh crawl, you need to delete the contents of
* rootFolder manually.
*/
config.setResumableCrawling(false);
/*
* Instantiate the controller for this crawl.
*/
PageFetcher pageFetcher = new PageFetcher(config);
RobotstxtConfig robotstxtConfig = new RobotstxtConfig();
RobotstxtServer robotstxtServer = new RobotstxtServer(robotstxtConfig, pageFetcher);
CrawlController controller = new CrawlController(config, pageFetcher, robotstxtServer);
/*
* For each crawl, you need to add some seed urls. These are the first
* URLs that are fetched and then the crawler starts following links
* which are found in these pages
*/
controller.addSeed(UrlStartingSeed.ICS_DOMAIN);
/*
* Start the crawl. This is a blocking operation, meaning that your code
* will reach the line after this only when crawling is finished.
*/
controller.start(BasicCrawler.class, numberOfCrawlers);
}