Java HtmlAnchor.getHrefAttribute方法代码示例

import com.gargoylesoftware.htmlunit.html.HtmlAnchor; //导入方法依赖的package包/类
/**
 * 抓取指定城市下的所有电视台
 * 
 * @param htmlPage
 * @param city
 * @return
 */
private List<TvStation> getAllTvStationOfCity(HtmlPage htmlPage, String city) {
	List<TvStation> resultList = new ArrayList<TvStation>();
	List<?> elements = htmlPage
			.getByXPath("//div[@class='chlsnav']//div[@class='plst']/parent::*");
	for (int i = 0, size = elements == null ? 0 : elements.size(); i < size; i++) {
		try {
			HtmlAnchor anchor = (HtmlAnchor) elements.get(i);
			String href = anchor.getHrefAttribute();
			if (!href.startsWith("/program/")) {
				continue;
			}
			logger.debug(anchor.getTextContent()
					+ " program table of tvmao: " + ", url: " + href);
			TimeUnit.MILLISECONDS.sleep(getRandomSleepTime());
			HtmlPage p = (HtmlPage) WebCrawler.crawl(TV_MAO_URL_PREFIX
					+ href);
			resultList.addAll(getTvStations(p, city));
		} catch (Exception e) {
			logger.error("error occur while get all tv station of city: "
					+ city, e);
			continue;
		}
	}
	return resultList;
}
 

import com.gargoylesoftware.htmlunit.html.HtmlAnchor; //导入方法依赖的package包/类
/**
 * Starts the CSV link creation process.
 * 
 * @throws Exception If there was an error while getting the CSV specific information from the forum thread.
 */
public void create() throws Exception{
	java.util.logging.Logger.getLogger("com.gargoylesoftware").setLevel(java.util.logging.Level.OFF);
	
	WebClient webClient = new WebClient(BrowserVersion.CHROME);
    HtmlPage page = (HtmlPage) webClient.getPage(forumThreadLink);
    webClient.waitForBackgroundJavaScriptStartingBefore(waitForJavaScript);
    HtmlAnchor anchor = (HtmlAnchor) page.getByXPath(xPath).get(0);
    csvFileLink = anchor.getHrefAttribute();
    csvFileLink = "http://www.pathofexile.com" + csvFileLink.subSequence(0, csvFileLink.length()-1);
    webClient.close();  
}
 

import com.gargoylesoftware.htmlunit.html.HtmlAnchor; //导入方法依赖的package包/类
private List<ProgramTable> crawlProgramTable(TvMaoCrawlTask task) {
	TvStation station = task.tvStation;
	String queryDate = task.date;
	String stationName = station.getName();

	logger.info("crawl program table of " + stationName + " at "
			+ queryDate);
	HtmlPage htmlPage = (HtmlPage) WebCrawler.crawl(TV_MAO_URL);
	try {
		htmlPage = searchStation(htmlPage, station);
	} catch (Exception e) {
		logger.error("error occur while search station: " + stationName, e);
		return null;
	}

	if (htmlPage == null) {
		logger.debug("cannot get station data from " + TV_MAO_URL + " of "
				+ stationName);
		return null;
	}

	if (!queryDate.equals(DateUtils.today())) {
		Set<String> availableQueryDate = new HashSet<String>();
		String[] dates = DateUtils.getWeek(new Date(), "yyyy-MM-dd");
		for (String d : dates) {
			availableQueryDate.add(d);
		}

		if (availableQueryDate.contains(queryDate)) {
			List<?> dateElements = htmlPage
					.getByXPath("//div[@class='pgnav_wrap']//div[@class='epghdc lt']//dl[@class='commtab clear']/dd/a");
			for (int i = 0, size = dateElements == null ? 0 : dateElements
					.size(); i < size; i++) {
				HtmlAnchor anchor = (HtmlAnchor) dateElements.get(i);
				String value = anchor.getTextContent().trim();
				if (value.endsWith(")")
						&& queryDate.equals(Calendar.getInstance().get(
								Calendar.YEAR)
								+ "-"
								+ value.substring(2, value.length() - 1))) {
					String href = anchor.getHrefAttribute();
					htmlPage = (HtmlPage) WebCrawler
							.crawl(TV_MAO_URL_PREFIX + href);
					break;
				}
			}
		}
	}

	String html = htmlPage.asXml();
	List<ProgramTable> ptList = parseProgramTable(html);
	MyTvUtils.outputCrawlData(queryDate, html, queryDate
			+ Constant.UNDERLINE + getCrawlerName() + Constant.UNDERLINE
			+ stationName);
	for (CrawlEventListener listener : listeners) {
		listener.crawlEnd(new ProgramTableCrawlEndEvent(this, ptList,
				station.getName(), queryDate));
	}
	return ptList;
}