/** * Parse HTML file and extract the relevant content, and send it to be downloaded. */
@Override
public void run() {
Log.d(String.format("AnalyzerTask is running on %s", currUrl));
HashMap<String, ArrayList<String>> exts = new HashMap<>();
// Put the extensions from config.ini in a hash-map, for passing it to the HtmlParser.
exts.put("imageExtensions", WebCrawler.imageExtensions);
exts.put("videoExtensions", WebCrawler.videoExtensions);
exts.put("documentExtensions", WebCrawler.documentExtensions);
// Extracting the relevant URLs from the given HTML.
HtmlParser parser = new HtmlParser(currUrl, currHtml, exts);
parser.parse();
// Filling the URL lists with downloadable data
ArrayList<String> imgUrls = parser.getImagesUrls();
ArrayList<String> videoUrls = parser.getVideosUrls();
ArrayList<String> docUrls = parser.getDocsUrls();
ArrayList<String> hrefUrls = parser.getHrefUrls();
Log.d("Sending images to downloads");
sendToDownload(imgUrls, DownloaderTask.RESOURCE_TYPE_IMG);
Log.d("Sending videos to downloads");
sendToDownload(videoUrls, DownloaderTask.RESOURCE_TYPE_VIDEO);
Log.d("Sending documents to downloads");
sendToDownload(docUrls, DownloaderTask.RESOURCE_TYPE_DOC);
Log.d("Sending HREFs to downloads");
sendToDownload(hrefUrls, DownloaderTask.RESOURCE_TYPE_HREF);
decreaseNumOfAnalyzersAlive();
}
