import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;
+import java.util.ArrayList;
import java.util.List;
import java.util.zip.GZIPInputStream;
-import be.nikiroo.gofetch.data.Comment;
+import org.jsoup.helper.StringUtil;
+import org.jsoup.nodes.Element;
+import org.jsoup.nodes.Node;
+import org.jsoup.nodes.TextNode;
+import org.jsoup.select.Elements;
+import org.jsoup.select.NodeTraversor;
+import org.jsoup.select.NodeVisitor;
+
import be.nikiroo.gofetch.data.Story;
public abstract class BasicSupport {
public enum Type {
- SLASHDOT, PIPEDOT, LWN,
+ SLASHDOT, PIPEDOT, LWN, LEMONDE,
+ }
+
+ public interface QuoteProcessor {
+ public boolean detectQuote(Node node);
+
+ public String processText(String text);
+
+ public boolean ignoreNode(Node node);
+
+ /**
+ * Manually process this node if so desired.
+ *
+ * @param node
+ * the node to optionally process
+ *
+ * @return NULL if not processed, a {@link String} (may be empty) if we
+ * must not process it any further
+ */
+ public String manualProcessing(Node node);
}
static private String preselector;
private Type type;
+ /**
+ * List all the recent items, but only assure the ID and internal URL to
+ * fetch it later on (until it has been fetched, the rest of the
+ * {@link Story} is not confirmed).
+ *
+ * @return the list of new stories
+ *
+ * @throws IOException
+ * in case of I/O
+ */
abstract public List<Story> list() throws IOException;
- abstract public List<Comment> getComments(Story story) throws IOException;
+ /**
+ * Fetch the full article content as well as all the comments associated to
+ * this {@link Story}, if any (can be empty, but not NULL).
+ *
+ * @param story
+ * the story to fetch the comments of
+ *
+ * @throws IOException
+ * in case of I/O error
+ */
+ abstract public void fetch(Story story) throws IOException;
abstract public String getDescription();
case LWN:
support = new LWN();
break;
+ case LEMONDE:
+ support = new LeMonde();
+ break;
}
if (support != null) {
return in;
}
+
+ /**
+ * Get the first {@link Element} of the given class, or an empty span
+ * {@link Element} if none found.
+ *
+ * @param element
+ * the element to look in
+ * @param className
+ * the class to look for
+ *
+ * @return the value or an empty span {@link Element}
+ */
+ static protected Element firstOrEmpty(Element element, String className) {
+ Elements subElements = element.getElementsByClass(className);
+ if (subElements.size() > 0) {
+ return subElements.get(0);
+ }
+
+ return new Element("span");
+ }
+
+ /**
+ * Get the first {@link Element} of the given tag, or an empty span
+ * {@link Element} if none found.
+ *
+ * @param element
+ * the element to look in
+ * @param tagName
+ * the tag to look for
+ *
+ * @return the value or an empty span {@link Element}
+ */
+ static protected Element firstOrEmptyTag(Element element, String tagName) {
+ Elements subElements = element.getElementsByTag(tagName);
+ if (subElements.size() > 0) {
+ return subElements.get(0);
+ }
+
+ return new Element("span");
+ }
+
+ static protected List<String> toLines(Element element,
+ final QuoteProcessor quoteProcessor) {
+ final List<String> lines = new ArrayList<String>();
+ final StringBuilder currentLine = new StringBuilder();
+ final List<Integer> quoted = new ArrayList<Integer>();
+ final List<Node> ignoredNodes = new ArrayList<Node>();
+
+ if (element != null) {
+ new NodeTraversor(new NodeVisitor() {
+ @Override
+ public void head(Node node, int depth) {
+ String manual = null;
+ boolean ignore = quoteProcessor.ignoreNode(node)
+ || ignoredNodes.contains(node.parentNode());
+ if (!ignore) {
+ manual = quoteProcessor.manualProcessing(node);
+ if (manual != null) {
+ currentLine.append(manual);
+ ignore = true;
+ }
+ }
+
+ if (ignore) {
+ ignoredNodes.add(node);
+ return;
+ }
+
+ String prep = "";
+ for (int i = 0; i < quoted.size(); i++) {
+ prep += ">";
+ }
+ prep += " ";
+
+ boolean enterQuote = quoteProcessor.detectQuote(node);
+ boolean leaveQuote = quoted.contains(depth);
+
+ if (enterQuote) {
+ quoted.add(depth);
+ }
+
+ if (leaveQuote) {
+ quoted.remove(Integer.valueOf(depth));
+ }
+
+ if (enterQuote || leaveQuote) {
+ if (currentLine.length() > 0) {
+ if (currentLine.charAt(currentLine.length() - 1) == '\n') {
+ currentLine.setLength(currentLine.length() - 1);
+ }
+ for (String l : currentLine.toString().split("\n")) {
+ lines.add(prep + l);
+ }
+ }
+ currentLine.setLength(0);
+ }
+
+ if (node instanceof Element) {
+ Element element = (Element) node;
+ boolean block = element.isBlock()
+ || element.tagName().equalsIgnoreCase("br");
+ if (block && currentLine.length() > 0) {
+ currentLine.append("\n");
+ }
+ } else if (node instanceof TextNode) {
+ TextNode textNode = (TextNode) node;
+ String line = StringUtil.normaliseWhitespace(textNode
+ .getWholeText());
+
+ currentLine.append(quoteProcessor.processText(line));
+ currentLine.append(" ");
+ }
+ }
+
+ @Override
+ public void tail(Node node, int depth) {
+ }
+ }).traverse(element);
+ }
+
+ if (currentLine.length() > 0) {
+ String prep = "";
+ for (int i = 0; i < quoted.size(); i++) {
+ prep += ">";
+ }
+ prep += " ";
+ if (currentLine.length() > 0) {
+ if (currentLine.charAt(currentLine.length() - 1) == '\n') {
+ currentLine.setLength(currentLine.length() - 1);
+ }
+ for (String l : currentLine.toString().split("\n")) {
+ lines.add(prep + l);
+ }
+ }
+ }
+
+ for (int i = 0; i < lines.size(); i++) {
+ lines.set(i, lines.get(i).replace(" ", " ").trim());
+ }
+
+ return lines;
+ }
}