Java Element.text方法代码示例

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
private String extractContent(String url) {
    String summary = "";
    try {
        Document doc = Jsoup.connect(url).get();
        Element element = doc.getElementById("intro").child(1);
        if (element.childNodeSize() == 2) {
            Element target = element.getElementsByClass("hidden").get(0);
            summary = target.text();
        } else {
            summary = element.text();
        }
    } catch (Exception e) {
        e.printStackTrace();
    }
    return summary;
}
 

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
@Override
public List doAnalysis(String html) {
	List<Major> list = new ArrayList<Major>();
	Element element = null;
	Elements options = null;
	element=HTMLUtil.getSelectorByName(html, Constants.HTML_ELEMENT_NAME.SELECT_NAME_MAJOR.getValue());
	if (element != null) {
		options = element.children();
		Major major = null;
		for (Element e : options) {
			if (e.val().equals("")||e.text()==null||e.text().trim().equals("")||e.val().equals("Nothing"))
				continue;
			major = new Major();
			major.setName(HTMLUtil.cutName(e.text()));
			major.setNo(e.attr("value"));
			Academy academy=new Academy();
			academy.setNo(academyNo);
			major.setAcademy(academy);
			list.add(major);
		}
	}
	return list;
}
 

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
/**
 * 抽取元素数据
 *
 * @param fieldElement
 * @param selectType
 * @param selectVal
 * @return
 */
public static String parseElement(Element fieldElement, XxlCrawlerConf.SelectType selectType, String selectVal) {
    String fieldElementOrigin = null;
    if (XxlCrawlerConf.SelectType.HTML == selectType) {
        fieldElementOrigin = fieldElement.html();
    } else if (XxlCrawlerConf.SelectType.VAL == selectType) {
        fieldElementOrigin = fieldElement.val();
    } else if (XxlCrawlerConf.SelectType.TEXT == selectType) {
        fieldElementOrigin = fieldElement.text();
    } else if (XxlCrawlerConf.SelectType.ATTR == selectType) {
        fieldElementOrigin = fieldElement.attr(selectVal);
    }  else if (XxlCrawlerConf.SelectType.HAS_CLASS == selectType) {
        fieldElementOrigin = String.valueOf(fieldElement.hasClass(selectVal));
    }  else {
        fieldElementOrigin = fieldElement.toString();
    }
    return fieldElementOrigin;
}
 

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
public static UpdateInfo check (Market market, String packageName) throws IOException{
    Document document;
    UpdateInfo info = new UpdateInfo();
    info.mMarket = market;
    info.mPackageName = packageName;
    switch (market) {
        case MARKET_COOLAPK:
            document = Jsoup.connect("http://coolapk.com/apk/" + packageName).get();
            info.mVersionName = document.select("dl.dl-horizontal").get(0).select("dd").get(2).text();
            info.mChangeLog = document.select("div.ex-card-wrapper").get(3).html();
            return info;
        case MARKET_GOOGLEPLAY:
            document = Jsoup.connect("https://play.google.com/store/apps/details?id=" + packageName).get();
            info.mVersionName = document.select("div[itemprop=softwareVersion]").get(0).html();
            Elements elements = document.select("div.recent-change");
            String changeLog = "";
            for (Element element : elements) {
                changeLog += element.text();
            }
            info.mChangeLog = changeLog;
            return info;
        case MARKET_WANDOUJIA :
            document = Jsoup.connect("http://www.wandoujia.com/apps/" + packageName).get();
            info.mVersionName = document.select("div[class=con]").get(0).text().substring(3);
            info.mChangeLog = document.select("div[class=con]").get(1).html();
            return info;
    }
    return null;
}
 

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
public void getData(String link,TreeMap<String, Integer> frequencyData)
{
	int count = 0;
	try
	{
		Trie myTrie = new Trie();
		Document document = Jsoup.connect(link).get();
		Elements paragraph = document.select("p");
		
		for(Element para : paragraph)
		{
			String p = para.text();
			p = p.replaceAll("[,.!?:;()-]", "\\s");
			
			for (String word : p.split(" ")) {
				if (StopWord.is(word.toLowerCase())) continue;
				myTrie.insert(word.toLowerCase());
				count = PageRanking.getCount(word, frequencyData) + 1 ;
				frequencyData.put(word, count);
			}
		}
	}
	catch(Exception e)
	{
		e.printStackTrace();
	}	
}
 

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
private TorrentDetail collectDetail(String body) {
    TorrentDetail detail = new TorrentDetail();
    Map<String, String> info = new HashMap<>();

    //获取种子信息
    Document doc = Jsoup.parse(body);

    if(doc.select("dl").size() < 1) {
        return null;
    }

    Elements dtEles = doc.getElementsByTag("dt");
    Elements ddEles = doc.getElementsByTag("dd");
    if(dtEles.size() == ddEles.size()) {
        for(int i = 0; i < dtEles.size() - 1; i++) {
            String key = dtEles.get(i).text().trim();
            key = key.substring(0, key.length() - 1);
            String value = ddEles.get(i).text().trim();
            info.put(key, value);
        }
    }
    detail.setInfo(info);

    //获取种子的磁力链接
    Element linkEle = doc.select("div.download a").first();
    String link = linkEle.attr("href");
    detail.setLink(link);

    //获取种子的介绍
    Element introEle = doc.select("div.nfo pre").first();
    String intro = introEle.text();
    detail.setIntro(intro);

    return detail;
}
 

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
private static HtmlCssTheme themeFromElement(Element element) {
    Element titleElement = element.select(".title a").first();
    String title = titleElement.text();
    String url = HttpUrl.parse(HOST + titleElement.attr("href"))
                        .newBuilder()
                        .addQueryParameter("ref", affilaiteCode)
                        .build().toString();
    String imageUrl = HOST + element.select(".imgWrap img").attr("src");
    int downloads = Optional.of(element.select(".sales").text())
                            .filter(val -> !Strings.isNullOrEmpty(val))
                            .map(val -> val.replace(" sales", ""))
                            .map(Integer::parseInt)
                            .orElse(0);
    return new HtmlCssTheme(title, url, imageUrl, downloads);
}
 

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
@Override
public Weather convert(Element node, Selector selector) {
    String text = node.text();
    int offset = text.indexOf("Weather");
    offset += "Weather is ".length();
    text = text.substring(offset);

    return new Weather(text);
}
 

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
@Override
public List<InfoItem> parseInfoItems(String body) {
    Elements items = Jsoup.parseBodyFragment(body).getElementsByClass("list-art").get(0).children();
    ArrayList<InfoItem> infoItems = new ArrayList<>(items.size());
    for (Element item : items) {
        Element a = item.getElementsByTag("a").get(0);
        InfoItem infoItem = new InfoItem(a.text(),
                item.getElementsByTag("span").get(0).text()
                , SITE + a.attr("href"));
        infoItems.add(infoItem);
    }

    return infoItems;
}
 

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
public Link parse() throws IOException {
    Link parent = null;

    do {
        visited.add(startUrl);

        Connection con = Jsoup.connect(startUrl).userAgent("Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0");
        Document doc = con.get();

        Element head = doc.getElementById("firstHeading");
        Link current = new Link(startUrl, head.text());

        current.parent = parent;
        parent = current;

        Elements links = doc.getElementById("bodyContent").select("a[href]");

        for(Element link : links) {
            String url = link.absUrl("href");

            if(url.startsWith("https://en.wikipedia.org/wiki/") && url.lastIndexOf(":") == 5 && !url.contains("#")) {
                if(url.equals("https://en.wikipedia.org/wiki/Philosophy")) {
                    Link phil = new Link("https://en.wikipedia.org/wiki/Philosophy", "Philosophy");
                    phil.parent = parent;

                    return phil;
                }

                if(!visited.contains(url))
                    toVisit.add(url);
            }
        }

        startUrl = toVisit.poll();
    } while(!toVisit.isEmpty());

    return null;
}
 

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
@Override
public String getDescription() throws ParsingException {
    Element desEl = el.select("div[class*=\"yt-lockup-description\"]").first();
    if (desEl == null) {
        return "";
    } else {
        return desEl.text();
    }
}
 

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
private String getValue(Element element, String attrName) {
	if (attrName == null) {
		return element.outerHtml();
	} else if ("innerHtml".equalsIgnoreCase(attrName)) {
		return element.html();
	} else if ("text".equalsIgnoreCase(attrName)) {
		return getText(element);
	} else if ("allText".equalsIgnoreCase(attrName)) {
		return element.text();
	} else {
		return element.attr(attrName);
	}
}
 

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
private Incident(Element message) {
    String timestamp = message.getElementsByTag("small").first().text();
    String description = message.text();
    this.timestamp = parseTimestamp(timestamp);
    this.status = ServerStatus.get(message.getElementsByTag("strong").first().text());
    this.description = description.replace(new StringBuilder(timestamp).append(" ").append(status).append(" - "), "");
}
 

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
private String getValue(Element element) {
    if (attrName == null) {
        return element.outerHtml();
    } else if ("innerHtml".equalsIgnoreCase(attrName)) {
        return element.html();
    } else if ("text".equalsIgnoreCase(attrName)) {
        return getText(element);
    } else if ("allText".equalsIgnoreCase(attrName)) {
        return element.text();
    } else {
        return element.attr(attrName);
    }
}
 

import org.jsoup.nodes.Element; //导入方法依赖的package包/类
public List<MagneticModel> getList() {
    List<MagneticModel> listModels = new ArrayList<>();
    MagneticModel magneticModel;
    Elements a = document.select("div.list").select("a[href]:not(.desc):not(.asc)");
    for (Element element : a) {
        if (!TextUtils.equals("点击搜索", element.text())) {
            magneticModel = new MagneticModel();
            magneticModel.title = element.text();
            magneticModel.url = element.select("a[href]").attr("abs:href");
            listModels.add(magneticModel);
        }
    }
    return listModels;
}