| 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 | import be.nikiroo.utils.StringUtils; |
| 18 | |
| 19 | public class TooLinux extends BasicSupport { |
| 20 | @Override |
| 21 | public String getDescription() { |
| 22 | return "TooLinux: Premier quotidien francophone d'actualité généraliste sur Linux, les logiciels libres et l'interopérabilité, depuis mars 2000."; |
| 23 | } |
| 24 | |
| 25 | @Override |
| 26 | public List<Story> list() throws IOException { |
| 27 | List<Story> list = new ArrayList<Story>(); |
| 28 | |
| 29 | URL url = new URL("https://www.toolinux.com/"); |
| 30 | InputStream in = downloader.open(url); |
| 31 | Document doc = DataUtil.load(in, "UTF-8", url.toString()); |
| 32 | Elements articles = doc.getElementsByClass("hentry"); |
| 33 | for (Element article : articles) { |
| 34 | String id = ""; |
| 35 | String intUrl = ""; |
| 36 | String extUrl = ""; // nope |
| 37 | String title = ""; |
| 38 | String date = ""; |
| 39 | String details = ""; |
| 40 | String body = ""; |
| 41 | |
| 42 | Element urlElement = article.getElementsByTag("a").first(); |
| 43 | if (urlElement != null) { |
| 44 | intUrl = urlElement.absUrl("href"); |
| 45 | } |
| 46 | |
| 47 | Element titleElement = article.getElementsByClass("entry-title") |
| 48 | .first(); |
| 49 | if (titleElement != null) { |
| 50 | title = StringUtils.unhtml(titleElement.text()).trim(); |
| 51 | } |
| 52 | |
| 53 | Element dateElement = article.getElementsByClass("published") |
| 54 | .first(); |
| 55 | if (dateElement != null) { |
| 56 | date = StringUtils.unhtml(dateElement.text()).trim(); |
| 57 | id = dateElement.attr("title").trim(); |
| 58 | } |
| 59 | |
| 60 | if (id.isEmpty()) { |
| 61 | // fallback |
| 62 | id = intUrl.replace("/", "_"); |
| 63 | } |
| 64 | |
| 65 | Element detailsElement = article.getElementsByClass("introduction") |
| 66 | .first(); |
| 67 | details = "(" + date + ") "; |
| 68 | if (detailsElement != null) { |
| 69 | details += StringUtils.unhtml(detailsElement.text()).trim(); |
| 70 | } |
| 71 | |
| 72 | list.add(new Story(getType(), id, title, details, intUrl, extUrl, |
| 73 | body)); |
| 74 | } |
| 75 | |
| 76 | return list; |
| 77 | } |
| 78 | |
| 79 | @Override |
| 80 | public void fetch(Story story) throws IOException { |
| 81 | String fullContent = story.getContent(); |
| 82 | List<Comment> comments = new ArrayList<Comment>(); |
| 83 | story.setComments(comments); |
| 84 | |
| 85 | URL url = new URL(story.getUrlInternal()); |
| 86 | InputStream in = downloader.open(url); |
| 87 | try { |
| 88 | Document doc = DataUtil.load(in, "UTF-8", url.toString()); |
| 89 | Element article = doc.getElementById("content"); |
| 90 | if (article != null) { |
| 91 | for (String line : toLines(article, |
| 92 | new BasicElementProcessor() { |
| 93 | @Override |
| 94 | public boolean ignoreNode(Node node) { |
| 95 | if ("notes".equals(node.attr("class"))) { |
| 96 | return true; |
| 97 | } |
| 98 | return false; |
| 99 | } |
| 100 | })) { |
| 101 | fullContent += line + "\n"; |
| 102 | } |
| 103 | |
| 104 | // Content is too tight with a single break per line: |
| 105 | fullContent = fullContent.replace("\n", "\n\n") // |
| 106 | .replace("\n\n\n\n", "\n\n") // |
| 107 | .replace("\n\n\n\n", "\n\n") // |
| 108 | .trim(); |
| 109 | } |
| 110 | |
| 111 | story.setFullContent(fullContent); |
| 112 | } finally { |
| 113 | if (in != null) { |
| 114 | in.close(); |
| 115 | } |
| 116 | } |
| 117 | } |
| 118 | } |