| 1 | package be.nikiroo.gofetch.support; |
| 2 | |
| 3 | import java.io.IOException; |
| 4 | import java.io.InputStream; |
| 5 | import java.net.URL; |
| 6 | import java.util.ArrayList; |
| 7 | import java.util.List; |
| 8 | |
| 9 | import org.jsoup.helper.DataUtil; |
| 10 | import org.jsoup.nodes.Document; |
| 11 | import org.jsoup.nodes.Element; |
| 12 | import org.jsoup.nodes.Node; |
| 13 | import org.jsoup.select.Elements; |
| 14 | |
| 15 | import be.nikiroo.gofetch.data.Comment; |
| 16 | import be.nikiroo.gofetch.data.Story; |
| 17 | |
| 18 | /** |
| 19 | * Support <a href="http://www.lemonde.fr/">http://www.lemonde.fr/</a>. |
| 20 | * |
| 21 | * @author niki |
| 22 | */ |
| 23 | public class LeMonde extends BasicSupport { |
| 24 | @Override |
| 25 | public String getDescription() { |
| 26 | return "Le Monde: Actualités et Infos en France et dans le monde"; |
| 27 | } |
| 28 | |
| 29 | @Override |
| 30 | public List<Story> list() throws IOException { |
| 31 | List<Story> list = new ArrayList<Story>(); |
| 32 | |
| 33 | for (String topic : new String[] { "international", "politique", |
| 34 | "societe", "sciences" }) { |
| 35 | URL url = new URL("http://www.lemonde.fr/" + topic + "/1.html"); |
| 36 | InputStream in = downloader.open(url); |
| 37 | Document doc = DataUtil.load(in, "UTF-8", url.toString()); |
| 38 | Elements articles = doc.getElementsByTag("article"); |
| 39 | for (Element article : articles) { |
| 40 | Elements times = article.getElementsByTag("time"); |
| 41 | Elements titleElements = article.getElementsByTag("h3"); |
| 42 | Elements contentElements = article.getElementsByClass("txt3"); |
| 43 | if (times.size() > 0 && titleElements.size() > 0 |
| 44 | && contentElements.size() > 0) { |
| 45 | String id = times.get(0).attr("datetime").replace(":", "_") |
| 46 | .replace("+", "_"); |
| 47 | String title = titleElements.get(0).text(); |
| 48 | String date = date(titleElements.get(0).text()); |
| 49 | String content = contentElements.get(0).text(); |
| 50 | String intUrl = ""; |
| 51 | String extUrl = ""; |
| 52 | String author = ""; |
| 53 | String details = ""; |
| 54 | |
| 55 | Elements detailsElements = article |
| 56 | .getElementsByClass("signature"); |
| 57 | if (detailsElements.size() > 0) { |
| 58 | author = detailsElements.get(0).text(); |
| 59 | } |
| 60 | |
| 61 | Elements links = titleElements.get(0).getElementsByTag("a"); |
| 62 | if (links.size() > 0) { |
| 63 | intUrl = links.get(0).absUrl("href"); |
| 64 | list.add(new Story(getType(), id, title, author, date, |
| 65 | topic, details, intUrl, extUrl, content)); |
| 66 | } |
| 67 | } |
| 68 | } |
| 69 | } |
| 70 | |
| 71 | return list; |
| 72 | } |
| 73 | |
| 74 | @Override |
| 75 | public void fetch(Story story) throws IOException { |
| 76 | String fullContent = story.getContent(); |
| 77 | List<Comment> comments = new ArrayList<Comment>(); |
| 78 | |
| 79 | // Note: no comments on this site as far as I can see (or maybe with |
| 80 | // some javascript, I need to check...) |
| 81 | |
| 82 | URL url = new URL(story.getUrlInternal()); |
| 83 | InputStream in = downloader.open(url); |
| 84 | Document doc = DataUtil.load(in, "UTF-8", url.toString()); |
| 85 | Element article = doc.getElementById("articleBody"); |
| 86 | if (article != null) { |
| 87 | for (String line : toLines(article, new BasicElementProcessor() { |
| 88 | @Override |
| 89 | public boolean ignoreNode(Node node) { |
| 90 | if (node instanceof Element) { |
| 91 | Element element = (Element) node; |
| 92 | if (element.hasClass("lire")) { |
| 93 | return true; |
| 94 | } |
| 95 | } |
| 96 | |
| 97 | return false; |
| 98 | } |
| 99 | |
| 100 | @Override |
| 101 | public String isSubtitle(Node node) { |
| 102 | if (node instanceof Element) { |
| 103 | Element element = (Element) node; |
| 104 | if (element.hasClass("intertitre")) { |
| 105 | return element.text(); |
| 106 | } |
| 107 | } |
| 108 | return null; |
| 109 | } |
| 110 | })) { |
| 111 | fullContent += line + "\n"; |
| 112 | } |
| 113 | |
| 114 | // Content is too tight with a single break per line: |
| 115 | fullContent = fullContent.replace("\n", "\n\n") // |
| 116 | .replace("\n\n\n\n", "\n\n") // |
| 117 | .replace("\n\n\n\n", "\n\n") // |
| 118 | .trim(); |
| 119 | } |
| 120 | |
| 121 | story.setFullContent(fullContent); |
| 122 | story.setComments(comments); |
| 123 | } |
| 124 | } |