| 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 | /** |
| 20 | * Support <a |
| 21 | * href="https://www.theregister.co.uk/">https://www.theregister.co.uk/</a>. |
| 22 | * |
| 23 | * @author niki |
| 24 | */ |
| 25 | public class TheRegister extends BasicSupport { |
| 26 | @Override |
| 27 | public String getDescription() { |
| 28 | return "The Register: Biting the hand that feeds IT"; |
| 29 | } |
| 30 | |
| 31 | @Override |
| 32 | public List<Story> list() throws IOException { |
| 33 | List<Story> list = new ArrayList<Story>(); |
| 34 | |
| 35 | URL url = new URL("https://www.theregister.co.uk/"); |
| 36 | InputStream in = downloader.open(url); |
| 37 | Document doc = DataUtil.load(in, "UTF-8", url.toString()); |
| 38 | Elements articles = doc.getElementsByClass("story_link"); |
| 39 | for (Element article : articles) { |
| 40 | if (article.getElementsByClass("time_stamp").isEmpty()) { |
| 41 | // Some articles are doubled, |
| 42 | // but the second copy without the time info |
| 43 | continue; |
| 44 | } |
| 45 | |
| 46 | String id = ""; |
| 47 | String intUrl = article.absUrl("href"); |
| 48 | String extUrl = ""; // nope |
| 49 | String title = ""; |
| 50 | String date = ""; |
| 51 | String details = ""; |
| 52 | String body = ""; |
| 53 | String categ = ""; |
| 54 | String author = ""; // nope |
| 55 | |
| 56 | Element categElement = article.previousElementSibling(); |
| 57 | if (categElement != null) { |
| 58 | categ = categElement.text().trim(); |
| 59 | } |
| 60 | |
| 61 | Element titleElement = article.getElementsByTag("h4").first(); |
| 62 | if (titleElement != null) { |
| 63 | title = StringUtils.unhtml(titleElement.text()).trim(); |
| 64 | } |
| 65 | |
| 66 | Element dateElement = article.getElementsByClass("time_stamp") |
| 67 | .first(); |
| 68 | if (dateElement != null) { |
| 69 | String epochS = dateElement.attr("data-epoch"); |
| 70 | if (epochS != null && !epochS.isEmpty()) { |
| 71 | id = epochS; |
| 72 | date = date(epochS); |
| 73 | } |
| 74 | } |
| 75 | |
| 76 | if (id.isEmpty()) { |
| 77 | // fallback |
| 78 | id = article.attr("href").replace("/", "_"); |
| 79 | } |
| 80 | |
| 81 | Element detailsElement = article.getElementsByClass("standfirst") |
| 82 | .first(); |
| 83 | details = "(" + date + ") "; |
| 84 | if (detailsElement != null) { |
| 85 | details += StringUtils.unhtml(detailsElement.text()).trim(); |
| 86 | } |
| 87 | |
| 88 | // We have some "details" but no content, so we switch them: |
| 89 | body = details; |
| 90 | details = ""; |
| 91 | list.add(new Story(getType(), id, title, author, date, categ, |
| 92 | details, intUrl, extUrl, body)); |
| 93 | } |
| 94 | |
| 95 | return list; |
| 96 | } |
| 97 | |
| 98 | @Override |
| 99 | public void fetch(Story story) throws IOException { |
| 100 | String fullContent = story.getContent(); |
| 101 | List<Comment> comments = new ArrayList<Comment>(); |
| 102 | story.setComments(comments); |
| 103 | |
| 104 | URL url = new URL(story.getUrlInternal()); |
| 105 | InputStream in = downloader.open(url); |
| 106 | try { |
| 107 | Document doc = DataUtil.load(in, "UTF-8", url.toString()); |
| 108 | Element article = doc.getElementById("body"); |
| 109 | if (article != null) { |
| 110 | for (String line : toLines(article, |
| 111 | new BasicElementProcessor() { |
| 112 | // TODO: ignore headlines/pub |
| 113 | })) { |
| 114 | fullContent += line + "\n"; |
| 115 | } |
| 116 | |
| 117 | // Content is too tight with a single break per line: |
| 118 | fullContent = fullContent.replace("\n", "\n\n") // |
| 119 | .replace("\n\n\n\n", "\n\n") // |
| 120 | .replace("\n\n\n\n", "\n\n") // |
| 121 | .trim(); |
| 122 | } |
| 123 | |
| 124 | story.setFullContent(fullContent); |
| 125 | |
| 126 | // Get comments URL then parse it |
| 127 | in.close(); |
| 128 | in = null; |
| 129 | in = downloader |
| 130 | .open(new URL("https://forums.theregister.co.uk/forum/1" |
| 131 | + url.getPath())); |
| 132 | doc = DataUtil.load(in, "UTF-8", url.toString()); |
| 133 | Element posts = doc.getElementById("forum_posts"); |
| 134 | if (posts != null) { |
| 135 | for (Element post : posts.getElementsByClass("post")) { |
| 136 | String id = ""; |
| 137 | String author = ""; |
| 138 | String title = ""; |
| 139 | String date = ""; |
| 140 | List<String> content = new ArrayList<String>(); |
| 141 | |
| 142 | Element idE = post.getElementsByTag("a").first(); |
| 143 | if (idE != null) { |
| 144 | id = idE.attr("id"); |
| 145 | if (id.startsWith("c_")) { |
| 146 | id = id.substring(2); |
| 147 | } |
| 148 | |
| 149 | Element dateE = idE.getElementsByTag("span").first(); |
| 150 | if (dateE != null) { |
| 151 | date = date(dateE.attr("data-epoch")); |
| 152 | } |
| 153 | } |
| 154 | |
| 155 | Element authorE = post.getElementsByClass("author").first(); |
| 156 | if (authorE != null) { |
| 157 | author = StringUtils.unhtml(authorE.text()).trim(); |
| 158 | } |
| 159 | |
| 160 | Element titleE = post.getElementsByTag("h4").first(); |
| 161 | if (titleE != null) { |
| 162 | title = StringUtils.unhtml(titleE.text()).trim(); |
| 163 | } |
| 164 | |
| 165 | Element contentE = post.getElementsByClass("body").first(); |
| 166 | if (contentE != null) { |
| 167 | for (String line : toLines(contentE, |
| 168 | new BasicElementProcessor() { |
| 169 | @Override |
| 170 | public boolean ignoreNode(Node node) { |
| 171 | // TODO: ignore headlines/pub |
| 172 | |
| 173 | // Remove the comment title (which has |
| 174 | // already been processed earlier) |
| 175 | if (node instanceof Element) { |
| 176 | Element el = (Element) node; |
| 177 | if ("h4".equals(el.tagName())) { |
| 178 | return true; |
| 179 | } |
| 180 | } |
| 181 | |
| 182 | return false; |
| 183 | } |
| 184 | })) { |
| 185 | content.add(line); |
| 186 | } |
| 187 | } |
| 188 | |
| 189 | Comment comment = new Comment(id, author, title, date, |
| 190 | content); |
| 191 | Comment parent = null; |
| 192 | |
| 193 | Element inReplyTo = post.getElementsByClass("in-reply-to") |
| 194 | .first(); |
| 195 | if (inReplyTo != null) { |
| 196 | String parentId = inReplyTo.absUrl("href"); |
| 197 | if (parentId != null && parentId.contains("/")) { |
| 198 | int i = parentId.lastIndexOf('/'); |
| 199 | parentId = parentId.substring(i + 1); |
| 200 | parent = story.getCommentById(parentId); |
| 201 | } |
| 202 | } |
| 203 | |
| 204 | if (parent == null) { |
| 205 | comments.add(comment); |
| 206 | } else { |
| 207 | parent.add(comment); |
| 208 | } |
| 209 | } |
| 210 | } |
| 211 | } finally { |
| 212 | if (in != null) { |
| 213 | in.close(); |
| 214 | } |
| 215 | } |
| 216 | } |
| 217 | } |