import org.jsoup.helper.DataUtil;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
+import org.jsoup.nodes.Node;
import org.jsoup.select.Elements;
import be.nikiroo.gofetch.data.Comment;
URL url = new URL("https://slashdot.org/");
InputStream in = open(url);
Document doc = DataUtil.load(in, "UTF-8", url.toString());
- Elements stories = doc.getElementsByTag("header");
- for (Element story : stories) {
- Elements titles = story.getElementsByClass("story-title");
+ Elements articles = doc.getElementsByTag("header");
+ for (Element article : articles) {
+ Elements titles = article.getElementsByClass("story-title");
if (titles.size() == 0) {
continue;
}
}
String details = "";
- Elements detailsElements = story.getElementsByClass("details");
+ Elements detailsElements = article.getElementsByClass("details");
if (detailsElements.size() > 0) {
details = detailsElements.get(0).text();
}
private List<Comment> getComments(Element listing) {
List<Comment> comments = new ArrayList<Comment>();
+ Comment lastComment = null;
for (Element commentElement : listing.children()) {
if (commentElement.hasClass("comment")) {
- Comment comment = getComment(commentElement);
- if (!comment.isEmpty()) {
- comments.add(comment);
+ if (!commentElement.hasClass("hidden")) {
+ lastComment = getComment(commentElement);
+ comments.add(lastComment);
+ }
+
+ List<Comment> subComments = new ArrayList<Comment>();
+ for (Element child : commentElement.children()) {
+ if (child.id().contains("commtree_")) {
+ subComments.addAll(getComments(child));
+ }
+ }
+
+ if (lastComment == null) {
+ comments.addAll(subComments);
+ } else {
+ lastComment.addAll(subComments);
}
}
}
+
return comments;
}
+ /**
+ * Get a comment from the given element.
+ *
+ * @param commentElement
+ * the element to get the comment of.
+ *
+ * @return the comment, <b>NOT</b> including sub-comments
+ */
private Comment getComment(Element commentElement) {
- String title = firstOrEmpty(commentElement, "title");
- String author = firstOrEmpty(commentElement, "by");
- String content = firstOrEmpty(commentElement, "commentBody");
- String date = firstOrEmpty(commentElement, "otherdetails");
+ String title = firstOrEmpty(commentElement, "title").text();
+ String author = firstOrEmpty(commentElement, "by").text();
+ String date = firstOrEmpty(commentElement, "otherdetails").text();
+ Element content = firstOrEmpty(commentElement, "commentBody");
+
+ return new Comment(commentElement.id(), author, title, date,
+ toLines(content));
+ }
- Comment comment = new Comment(commentElement.id(), author, title, date,
- content);
+ private List<String> toLines(Element element) {
+ return toLines(element, new QuoteProcessor() {
+ @Override
+ public String processText(String text) {
+ while (text.startsWith(">")) { // comment in one-liners
+ text = text.substring(1).trim();
+ }
- for (Element child : commentElement.children()) {
- if (child.id().contains("commtree_")) {
- comment.addAll(getComments(child));
+ return text;
}
- }
- return comment;
- }
+ @Override
+ public boolean detectQuote(Node node) {
+ if (node instanceof Element) {
+ Element elementNode = (Element) node;
+ if (elementNode.tagName().equals("blockquote")
+ || elementNode.hasClass("quote")
+ || (elementNode.tagName().equals("p")
+ && elementNode.textNodes().size() == 1 && elementNode
+ .textNodes().get(0).getWholeText()
+ .startsWith(">"))) {
+ return true;
+ }
+ }
- private String firstOrEmpty(Element element, String className) {
- Elements subElements = element.getElementsByClass(className);
- if (subElements.size() > 0) {
- return subElements.get(0).text();
- }
+ return false;
+ }
+
+ @Override
+ public boolean ignoreNode(Node node) {
+ return false;
+ }
- return "";
+ @Override
+ public String manualProcessing(Node node) {
+ return null;
+ }
+ });
}
}