@Nullable public static Element getElementByClass(Element element, String className) { Elements elements = element.getElementsByClass(className); if (elements != null && elements.size() > 0) { return elements.get(0); } else { return null; } }
/** * Parse comments with html parser */ @NonNull public static GalleryComment[] parseComments(Document document) { try { Element cdiv = document.getElementById("cdiv"); Elements c1s = cdiv.getElementsByClass("c1"); List<GalleryComment> list = new ArrayList<>(c1s.size()); for (int i = 0, n = c1s.size(); i < n; i++) { GalleryComment comment = parseComment(c1s.get(i)); if (null != comment) { list.add(comment); } } return list.toArray(new GalleryComment[list.size()]); } catch (Throwable e) { ExceptionUtils.throwIfFatal(e); e.printStackTrace(); return EMPTY_GALLERY_COMMENT_ARRAY; } }
blogPost.put("blog_url", blogURL); articleList_title = article.getElementsByClass("entry-title"); for (Element blogs : articleList_title) { blogPost.put("title", blogs.text().toString()); articleList_dateTime = article.getElementsByClass("posted-on"); for (Element blogs : articleList_dateTime) { blogPost.put("posted_on", blogs.text().toString()); articleList_author = article.getElementsByClass("byline"); for (Element blogs : articleList_author) { String author = blogs.text().toString(); articleList_content = article.getElementsByClass("entry-content"); for (Element blogs : articleList_content) { blogPost.put("content", blogs.text().toString());
@SuppressWarnings("ConstantConditions") public static List<GalleryInfo> parse(String body) throws ParseException { try { List<GalleryInfo> galleryInfoList = new ArrayList<>(15); Document d = Jsoup.parse(body); Element pp = d.getElementById("pp"); Elements id1List = pp.getElementsByClass("id1"); for (int i = 0, n = id1List.size(); i < n; i++) { GalleryInfo galleryInfo = new GalleryInfo(); Element id1 = id1List.get(i); Element id3 = JsoupUtils.getElementByClass(id1, "id3"); Element temp = JsoupUtils.getElementByTag(id3, "a"); String url = temp.attr("href"); GalleryDetailUrlParser.Result result = GalleryDetailUrlParser.parse(url); galleryInfo.gid = result.gid; galleryInfo.token = result.token; temp = JsoupUtils.getElementByTag(temp, "img"); galleryInfo.thumb = EhUtils.handleThumbUrlResolution(temp.attr("src")); galleryInfo.title = temp.attr("title"); galleryInfo.generateSLang(); galleryInfoList.add(galleryInfo); } return galleryInfoList; } catch (Throwable e) { ExceptionUtils.throwIfFatal(e); throw new ParseException("Parse whats hot error", body); } } }
/** * Parse large previews with regular expressions */ private static LargePreviewSet parseLargePreviewSet(Document d, String body) throws ParseException { try { LargePreviewSet largePreviewSet = new LargePreviewSet(); Element gdt = d.getElementById("gdt"); Elements gdtls = gdt.getElementsByClass("gdtl"); int n = gdtls.size(); if (n <= 0) { throw new ParseException("Can't parse large preview", body); } for (int i = 0; i < n; i++) { Element element = gdtls.get(i).child(0); String pageUrl = element.attr("href"); element = element.child(0); String imageUrl = element.attr("src"); if (Settings.getFixThumbUrl()) { imageUrl = EhUrl.getFixedPreviewThumbUrl(imageUrl); } int index = Integer.parseInt(element.attr("alt")) - 1; largePreviewSet.addItem(index, imageUrl, pageUrl); } return largePreviewSet; } catch (Throwable e) { ExceptionUtils.throwIfFatal(e); e.printStackTrace(); throw new ParseException("Can't parse large preview", body); } }
Element ido = JsoupUtils.getElementByClass(d, "ido"); Elements fps = ido.getElementsByClass("fp");
final Elements tableElements = response.parse() .getElementsByClass("info") .select("td"); for (Element element : tableElements) { String string = element.getElementsByClass("infoalt").text().trim() Log.d("Jsoup", string); }
Document element = Jsoup.connect("http://www.ebuyer.com/search?q=" + search ).get(); Elements products = element.body().getElementsByClass("listing-product"); for(Element product : products){ String title = product.getElementsByClass("listing-product-title").text(); String price = product.getElementsByClass("listing-product-price").text(); }
public static Element getFirstElementByClass(Element element, String styleClassName) { if (element == null || styleClassName == null || styleClassName.equals("")) { return null; } Elements elements = element.getElementsByClass(styleClassName); if (elements == null || elements.size() <= 0) { return null; } return elements.get(0); }
for (Element el : myElements) { Element title = el.getElementsByClass("home_title").first(); Element date = el.getElementsByClass("home_date").first(); Element link = el.getElementsByClass("news_list_image").first(); System.out.println(title.text()); System.out.println(date.text()); System.out.println(link.child(0).attr("href")); System.out.println(); }
Document doc = Jsoup.connect("http://dictionary.reference.com/browse/quick").get(); Elements sections = doc.select("div.body div.pbk"); for (Element element : sections) { String elementType = element.getElementsByClass("pg").text(); System.out.println("--------------------"); System.out.println(elementType); for (Element definitions : element.getElementsByClass("luna-Ent")) System.out.println(definitions.text()); }
Document doc = null; try { doc = Jsoup.connect("http://example.com/index.html").get(); } catch (IOException e) { // TODO Throws exception } Element simple = doc.getElementsByClass("simple").first(); Element p = simple.getElementsByClass("name").first(); Element a = p.select("a").first(); String text = a.text(); System.out.println(text);
private static String extractLinesFromTitle(Element title) { Elements lines = title.parent().getElementsByClass("ak-title"); StringBuilder tmp = new StringBuilder(); for (Element line : lines) tmp.append(line.text()).append("\n"); return tmp.toString(); }
private static String extractLinesFromTitle(Element title) { Elements lines = title.parent().getElementsByClass("ak-title"); StringBuilder tmp = new StringBuilder(); for (Element line : lines) tmp.append(line.text()).append("\n"); return tmp.toString(); }
private static String extractStatsFromTitle(Language lg, Element title) { Elements lines = title.parent().getElementsByClass("ak-title"); StringBuilder tmp = new StringBuilder(); for (Element line : lines) tmp.append(EmojiManager.getEmojiForStat(lg, line.text())).append(line.text()).append("\n"); return tmp.toString(); } }
private static String extractStatsFromTitle(Language lg, Element title) { Elements lines = title.parent().getElementsByClass("ak-title"); StringBuilder tmp = new StringBuilder(); for (Element line : lines) tmp.append(EmojiManager.getEmojiForStat(lg, line.text())).append(line.text()).append("\n"); return tmp.toString(); } }
private static FansBean getFans(Element ele) { String data_src = ele.getElementsByTag("img").get(0).absUrl("data-src"); String name = ele.getElementsByClass("name").text(); String num = ele.getElementsByTag("span").get(0).text(); FansBean fans = new FansBean(data_src, name, num); return fans; }
/** * Gets the hCard value of the first descendant element that has the given * CSS class name. * @param cssClass the CSS class name * @return the hCard value or null if not found */ public String firstValue(String cssClass) { Elements elements = element.getElementsByClass(cssClass); return elements.isEmpty() ? null : value(elements.first()); }
@Override public void preprocess(Element body) { body.getElementsByTag("del").remove(); body.getElementsByTag("ins").unwrap(); body.getElementsByClass("rte").remove(); body.select("code[data-annotations]").remove(); } }
private static Almanax gatheringOnlineData(Language lg, String date) throws IOException { LOG.info("connecting to " + Translator.getLabel(lg, "almanax.url") + date + " ..."); Document doc = JSoupManager.getDocument(Translator.getLabel(lg, "almanax.url") + date); String bonus = doc.getElementsByClass("more").first() .clone().getElementsByClass("more-infos").empty().parents().first().text(); String quest = doc.getElementsByClass("more-infos").first().child(0).text(); String ressourceURL = doc.getElementsByClass("more-infos-content").first().children().attr("src"); String offrande = doc.getElementsByClass("fleft").get(3).text(); return new Almanax(bonus, offrande, date, quest, ressourceURL); }