Java Elements.first方法代码示例

import org.jsoup.select.Elements; //导入方法依赖的package包/类
private void fetchImage() {
    try {
        Document doc = Http.url(url)
                           .retries(3)
                           .get();
        // Find image
        Elements images = doc.select("a > img");
        if (images.size() == 0) {
            logger.warn("Image not found at " + this.url);
            return;
        }
        Element image = images.first();
        String imgsrc = image.attr("src");
        imgsrc = "http://" + this.url.getHost() + "/" + imgsrc;
        // Provide prefix and let the AbstractRipper "guess" the filename
        String prefix = "";
        if (Utils.getConfigBoolean("download.save_order", true)) {
            prefix = String.format("%03d_", index);
        }
        addURLToDownload(new URL(imgsrc), prefix);
    } catch (IOException e) {
        logger.error("[!] Exception while loading/parsing " + this.url, e);
    }
}
 

import org.jsoup.select.Elements; //导入方法依赖的package包/类
private void fetchImage() {
    try {
        Document doc = Http.url(url).get();
        // Find image
        Elements images = doc.select(".image-container img");
        if (images.size() == 0) {
            logger.warn("Image not found at " + this.url);
            return;
        }
        Element image = images.first();
        String imgsrc = image.attr("src");
        logger.info("Found URL " + imgsrc);
        // Provide prefix and let the AbstractRipper "guess" the filename
        String prefix = "";
        if (Utils.getConfigBoolean("download.save_order", true)) {
            prefix = String.format("%03d_", index);
        }
        addURLToDownload(new URL(imgsrc), prefix);
    } catch (IOException e) {
        logger.error("[!] Exception while loading/parsing " + this.url, e);
    }
}
 

import org.jsoup.select.Elements; //导入方法依赖的package包/类
@Override
public Document getNextPage(Document page) throws IOException {
    if (isThisATest()) {
        return null;
    }
    Elements nextButtons = page.select("link[rel=\"next\"]");
    if (nextButtons.size() == 0) {
        if (page.select("link[rel=\"prev\"]").size() == 0) {
            throw new IOException("No next page found");
        } else {
            throw new IOException("Hit end of pages");
        }
    }
    Element a = nextButtons.first();
    String nextPage = a.attr("href");
    if (nextPage.startsWith("/")) {
        nextPage = "http://" + this.url.getHost() + nextPage;
    }
    if (!sleep(PAGE_SLEEP_TIME)) {
        throw new IOException("Interrupted while waiting to load next page: " + nextPage);
    }
    logger.info("Found next page: " + nextPage);
    return Http.url(nextPage)
               .cookies(cookies)
               .get();
}
 

import org.jsoup.select.Elements; //导入方法依赖的package包/类
private void fetchImage() {
    try {
        Document doc = Http.url(this.url)
                           .referrer(this.url)
                           .get();

        // Find image
        Elements images = doc.select("#photoImageSection img");
        Element image = images.first();
        String imgsrc = image.attr("src");
        logger.info("Found URL " + imgsrc + " via " + images.get(0));

        // Provide prefix and let the AbstractRipper "guess" the filename
        String prefix = "";
        if (Utils.getConfigBoolean("download.save_order", true)) {
            prefix = String.format("%03d_", index);
        }

        URL imgurl = new URL(url, imgsrc);
        addURLToDownload(imgurl, prefix);

    } catch (IOException e) {
        logger.error("[!] Exception while loading/parsing " + this.url, e);
    }
}
 

import org.jsoup.select.Elements; //导入方法依赖的package包/类
/**
 * 对与页面 的 一些动态通过js填充内容的select 的内容进行 提取，并封装成Doc 元素
 * @param html
 * @return
 */
public static Element getSelectorByName(String html,String selectName){
	if(html==null) return null;
	Document doc = Jsoup.parse(html);
	Elements selectors =null;
	//先去页面拿 ,如果拿不到，或者拿到的是空的 列表，则在js拿
	selectors=doc.select("select[name="+selectName+"]");
	if(selectors!=null&&selectors.select("option").size()>0&&selectors.text()!=null&&!selectors.text().trim().equals("")){
		return selectors.first();
	} 
	//首先去js里面拿,拿不到再去页面拿
	selectors=doc.select("script");
	if(selectors!=null&&selectors.size()>0){
		String seletorHtml=selectors.html().replaceAll("[\\s\\S]*(<select[\\w\\W]*>[\\w\\W]+</select>)", "$1");
		Document docTemp = Jsoup.parse("<html>"+seletorHtml+"</html>");
		return docTemp.select("select[name="+selectName+"]").first();
	}
	
	return null;
}
 

import org.jsoup.select.Elements; //导入方法依赖的package包/类
/**
 * 下载图片到临时路径
 */
public void downLoadPict(String songId) {
	String downUrl = "http://music.163.com/song/29802464";
	if (songId != null) {
		downUrl = songId;
	}
	int i = 0;
	Elements select = null;
	try {
		select = Jsoup.connect(downUrl)
				.header("Referer", "http://music.163.com/")
				.header("Host", "music.163.com").get().select("img[src]");
		Element first = select.first();
		String attr = first.attr("abs:src");
		i = HttpClientUtil.doDownload(attr, FILE_PATH);
		LOGGER.info("图片下载成功" + i);
	} catch (IOException e) {
		LOGGER.error("图片下载失败", e);
	}
}
 

import org.jsoup.select.Elements; //导入方法依赖的package包/类
private void fetchImage() {
    try {
        Document doc = getPageWithRetries(this.url);

        // Find image
        Elements images = doc.select(".sni > a > img");
        if (images.size() == 0) {
            // Attempt to find image elsewise (Issue #41)
            images = doc.select("img#img");
            if (images.size() == 0) {
                logger.warn("Image not found at " + this.url);
                return;
            }
        }
        Element image = images.first();
        String imgsrc = image.attr("src");
        logger.info("Found URL " + imgsrc + " via " + images.get(0));
        Pattern p = Pattern.compile("^http://.*/ehg/image.php.*&n=([^&]+).*$");
        Matcher m = p.matcher(imgsrc);
        if (m.matches()) {
            // Manually discover filename from URL
            String savePath = this.workingDir + File.separator;
            if (Utils.getConfigBoolean("download.save_order", true)) {
                savePath += String.format("%03d_", index);
            }
            savePath += m.group(1);
            addURLToDownload(new URL(imgsrc), new File(savePath));
        }
        else {
            // Provide prefix and let the AbstractRipper "guess" the filename
            String prefix = "";
            if (Utils.getConfigBoolean("download.save_order", true)) {
                prefix = String.format("%03d_", index);
            }
            addURLToDownload(new URL(imgsrc), prefix);
        }
    } catch (IOException e) {
        logger.error("[!] Exception while loading/parsing " + this.url, e);
    }
}
 

import org.jsoup.select.Elements; //导入方法依赖的package包/类
@Override
public Document getNextPage(Document doc) throws IOException {
    if (doc.select("li.next.hidden").size() != 0) {
        // Last page
        throw new IOException("No more pages");
    }
    Elements els = doc.select("li.next > a");
    Element first = els.first();
    String nextURL = first.attr("href");
    nextURL = "http://www.hentai-foundry.com" + nextURL;
    return Http.url(nextURL)
               .referrer(url)
               .cookies(cookies)
               .get();
}
 

import org.jsoup.select.Elements; //导入方法依赖的package包/类
/**
 * Extract first element according to a query
 */
private static Element element(Element container, String query) {

    Elements select = container.select(query);

    if (select.size() == 0) {
        throw new ElementNotFoundException(query);
    }

    return select.first();
}
 

import org.jsoup.select.Elements; //导入方法依赖的package包/类
private static List<FlowerCategory> getCategoryList() {

		List<FlowerCategory> categories = new ArrayList<FlowerCategory>();

		try {
			Document doc = Jsoup.connect("http://www.aihuhua.com/baike/").get();
			Elements catelist = doc.getElementsByClass("catelist");
			Element cates = catelist.first();
			List<Node> childNodes = cates.childNodes();
			for (int i = 0; i < childNodes.size(); i++) {
				Node node = childNodes.get(i);
				List<Node> childs = node.childNodes();
				if (childs != null && childs.size() > 0) {
					FlowerCategory category = new FlowerCategory();
					for (int j = 0; j < childs.size(); j++) {
						Node child = childs.get(j);
						if ("a".equals(child.nodeName())) {
							category.setUrl(child.attr("href"));
							category.setImgPath(child.childNode(1).attr("src"));
						} else if ("h2".equals(child.nodeName())) {
							category.setName(child.attr("title"));
						}
					}
					categories.add(category);
				}
			}
		} catch (IOException e) {
			e.printStackTrace();
		}

		return categories;
	}
 

import org.jsoup.select.Elements; //导入方法依赖的package包/类
@Override
public void run() {
    try {
        if (!TextUtils.isEmpty(AuthInfoManager.getInstance().getUsername()) &&
                !TextUtils.isEmpty(AuthInfoManager.getInstance().getAvatar())) {
            successOnUI("succeed");
            return;
        }

        Document doc = get(ConstantUtil.BASE_URL);
        Elements elements = doc.select("div.usercard");
        if (!elements.isEmpty()) {
            Element usercardElement = elements.first();

            AuthInfoManager.getInstance().setUsername(usercardElement.select("div.username").first().text());
            AuthInfoManager.getInstance().setAvatar(usercardElement.select("img.avatar").first().attr("src"));
            successOnUI("succeed");
            return;
        }
    } catch (IOException e) {
        e.printStackTrace();
    }

    AuthInfoManager.getInstance().setUsername(null);
    AuthInfoManager.getInstance().setAvatar(null);
    failedOnUI("auth failed");
}
 

import org.jsoup.select.Elements; //导入方法依赖的package包/类
/**
 * Extract and parse a standard article. A standard article is published on the main page and by definition,
 * is not: from a hosted blog, nor a video, nor a special multimedia content. It has some standardized fields like
 * one (or multiple) author(s), a date, a description, an headline, a description and a list of paragraphs.
 * Each paragraph is a block of text (comments included) or an image or an embedded tweet.
 *
 * @param articles article to analyze
 * @return a list of formatted content that can be nicely displayed in the recycler view.
 */
@NonNull
private List<Model> extractStandardArticle(@NonNull Elements articles) {
    TextView headLine = new TextView(this);
    TextView authors = new TextView(this);
    TextView dates = new TextView(this);
    TextView description = new TextView(this);

    int defaultText = ThemeUtils.getStyleableColor(this, R.styleable.CustomTheme_defaultText);
    int authorDateText = ThemeUtils.getStyleableColor(this, R.styleable.CustomTheme_authorDateText);

    headLine.setTextColor(defaultText);
    description.setTextColor(defaultText);
    authors.setTextColor(authorDateText);
    dates.setTextColor(authorDateText);

    headLine.setTextSize(TypedValue.COMPLEX_UNIT_SP, getResources().getDimension(R.dimen.article_headline));
    authors.setTextSize(TypedValue.COMPLEX_UNIT_SP, getResources().getDimension(R.dimen.article_authors));
    dates.setTextSize(TypedValue.COMPLEX_UNIT_SP, getResources().getDimension(R.dimen.article_authors));
    description.setTextSize(TypedValue.COMPLEX_UNIT_SP, getResources().getDimension(R.dimen.article_description));

    Element article = articles.first();
    headLine.setText(extractAttr(article, ATTR_HEADLINE));
    authors.setText(extractAttr(article, ATTR_AUTHOR));
    dates.setText(extractDates(article));
    shareText = extractAttr(article, ATTR_DESCRIPTION);
    description.setText(shareText);

    List<Model> views = new ArrayList<>();
    views.add(new Model(headLine));
    views.add(new Model(authors));
    views.add(new Model(dates));
    views.add(new Model(description));
    views.addAll(extractParagraphs(article));
    return views;
}
 

import org.jsoup.select.Elements; //导入方法依赖的package包/类
private void fetchImage() {
    try {
        //Document doc = getPageWithRetries(this.url);
        Document doc = Http.url(this.url).get();

        // Find image
        Elements images = doc.select("#image-container > a > img");
        if (images.size() == 0) {
            // Attempt to find image elsewise (Issue #41)
            images = doc.select("img#img");
            if (images.size() == 0) {
                logger.warn("Image not found at " + this.url);
                return;
            }
        }
        Element image = images.first();
        String imgsrc = image.attr("src");
        logger.info("Found URL " + imgsrc + " via " + images.get(0));

        Pattern p = Pattern.compile("^https?://i.nhentai.net/galleries/\\d+/(.+)$");
        Matcher m = p.matcher(imgsrc);
        if (m.matches()) {
            // Manually discover filename from URL
            String savePath = this.workingDir + File.separator;
            if (Utils.getConfigBoolean("download.save_order", true)) {
                savePath += String.format("%03d_", index);
            }
            savePath += m.group(1);
            addURLToDownload(new URL(imgsrc), new File(savePath));
        } else {
            // Provide prefix and let the AbstractRipper "guess" the filename
            String prefix = "";
            if (Utils.getConfigBoolean("download.save_order", true)) {
                prefix = String.format("%03d_", index);
            }
            addURLToDownload(new URL(imgsrc), prefix);
        }
    } catch (IOException e) {
        logger.error("[!] Exception while loading/parsing " + this.url, e);
    }
}
 

import org.jsoup.select.Elements; //导入方法依赖的package包/类
public PublicCourseOption doAnalysis(String html){
	if (html == null)
		return null;
	PublicCourseOption option = new PublicCourseOption();
	Document doc = null;
	doc = Jsoup.parse(html);
	Elements elements = doc.select("#dataListDiv");
	Element dataListDiv = elements.first();
	if(dataListDiv==null) {
		System.out.println(cNo);
		return null;
	}
	/*
	 * 去掉 上课班级的那一列
	 */
	//
	// 去掉title
	Elements titleNodes = dataListDiv.select(".T");

	if (titleNodes.size() == 0) {
		return null;
	}
	for (int i = 0; i < titleNodes.size(); i = i + 2) {
		titleNodes.get(i).childNode(3).remove();
	}
	// 去掉class =B 的 第四个节点
	Elements classBNodes = dataListDiv.select(".B");
	Elements classHNodes = dataListDiv.select(".H");

	for (Element classBNode : classBNodes) {
		classBNode.childNode(3).remove();
	}

	for (Element classHNode : classHNodes) {
		classHNode.childNode(2).remove();
	}

	// System.out.println(dataListDiv);
	option.setcNo(getcNo());
	option.setCampus(getCampusArea());
	option.setTermNo(getTermNo());
	String optionHtml = dataListDiv.toString().replaceAll(
			"<=\\\"\\\" d=\\\"\\\"", "").replaceAll("disabled", " ");
	option.setOptionHtml(optionHtml);
	return option;
}
 

import org.jsoup.select.Elements; //导入方法依赖的package包/类
/**
 * This method is not functionnal at this moment.
 *
 * @param doc the document to analyze
 * @return a list of formatted content that can be nicely displayed in the recycler view.
 */
@NonNull
private List<Model> extractVideo(@NonNull Document doc) {
    Elements elements = doc.select("section.video");
    if (elements.isEmpty()) {
        return new ArrayList<>();
    }

    TextView headLine = new TextView(this);
    TextView authors = new TextView(this);
    TextView dates = new TextView(this);
    TextView content = new TextView(this);

    int defaultText = ThemeUtils.getStyleableColor(this, R.styleable.CustomTheme_defaultText);
    int authorDateText = ThemeUtils.getStyleableColor(this, R.styleable.CustomTheme_authorDateText);

    headLine.setTextColor(defaultText);
    content.setTextColor(defaultText);
    authors.setTextColor(authorDateText);
    dates.setTextColor(authorDateText);

    headLine.setTextSize(TypedValue.COMPLEX_UNIT_SP, getResources().getDimension(R.dimen.article_headline));
    authors.setTextSize(TypedValue.COMPLEX_UNIT_SP, getResources().getDimension(R.dimen.article_authors));
    dates.setTextSize(TypedValue.COMPLEX_UNIT_SP, getResources().getDimension(R.dimen.article_authors));
    content.setTextSize(TypedValue.COMPLEX_UNIT_SP, getResources().getDimension(R.dimen.article_body));

    Element video = elements.first();
    headLine.setText(extractAttr(video, ATTR_HEADLINE));
    authors.setText(extractAttr(video, ATTR_AUTHOR));
    dates.setText(extractDates(video));
    Elements els = video.select("div.grid_12.alpha");
    if (atLeastOneChild(els)) {
        for (Element e : els) {
            Log.d(TAG, e.html());
        }
        els.select("h2").remove();
        els.select("span.txt_gris_soutenu").remove();
        els.select("#recos_videos_outbrain").remove();
        fromHtml(content, els.html());
    }
    List<Model> views = new ArrayList<>();
    views.add(new Model(headLine));
    views.add(new Model(authors));
    views.add(new Model(dates));
    views.add(new Model(content));


    return views;
}