| 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='https://pipedot.org/'>https://pipedot.org/</a>. |
| 20 | * |
| 21 | * @author niki |
| 22 | */ |
| 23 | public class Pipedot extends BasicSupport { |
| 24 | @Override |
| 25 | public String getDescription() { |
| 26 | return "Pipedot: News for nerds, without the corporate slant"; |
| 27 | } |
| 28 | |
| 29 | @Override |
| 30 | public List<Story> list() throws IOException { |
| 31 | List<Story> list = new ArrayList<Story>(); |
| 32 | |
| 33 | URL url = new URL("https://pipedot.org/"); |
| 34 | InputStream in = open(url); |
| 35 | Document doc = DataUtil.load(in, "UTF-8", url.toString()); |
| 36 | Elements articles = doc.getElementsByClass("story"); |
| 37 | for (Element article : articles) { |
| 38 | Elements titles = article.getElementsByTag("h1"); |
| 39 | if (titles.size() == 0) { |
| 40 | continue; |
| 41 | } |
| 42 | |
| 43 | Element title = titles.get(0); |
| 44 | |
| 45 | String id = ""; |
| 46 | for (Element idElem : article.getElementsByTag("a")) { |
| 47 | if (idElem.attr("href").startsWith("/pipe/")) { |
| 48 | id = idElem.attr("href").substring("/pipe/".length()); |
| 49 | break; |
| 50 | } |
| 51 | } |
| 52 | |
| 53 | String intUrl = null; |
| 54 | String extUrl = null; |
| 55 | |
| 56 | Elements links = article.getElementsByTag("a"); |
| 57 | if (links.size() > 0) { |
| 58 | intUrl = links.get(0).absUrl("href"); |
| 59 | } |
| 60 | |
| 61 | // Take first ext URL as original source |
| 62 | for (Element link : links) { |
| 63 | String uuu = link.absUrl("href"); |
| 64 | if (!uuu.isEmpty() && !uuu.contains("pipedot.org/")) { |
| 65 | extUrl = uuu; |
| 66 | break; |
| 67 | } |
| 68 | } |
| 69 | |
| 70 | String details = ""; |
| 71 | Elements detailsElements = article.getElementsByTag("div"); |
| 72 | if (detailsElements.size() > 0) { |
| 73 | details = detailsElements.get(0).text(); |
| 74 | } |
| 75 | |
| 76 | String body = ""; |
| 77 | for (Element elem : article.children()) { |
| 78 | String tag = elem.tag().toString(); |
| 79 | if (!tag.equals("header") && !tag.equals("footer")) { |
| 80 | body = elem.text(); |
| 81 | break; |
| 82 | } |
| 83 | } |
| 84 | |
| 85 | list.add(new Story(getType(), id, title.text(), details, intUrl, |
| 86 | extUrl, body)); |
| 87 | } |
| 88 | |
| 89 | return list; |
| 90 | } |
| 91 | |
| 92 | @Override |
| 93 | public void fetch(Story story) throws IOException { |
| 94 | List<Comment> comments = new ArrayList<Comment>(); |
| 95 | |
| 96 | URL url = new URL(story.getUrlInternal()); |
| 97 | InputStream in = open(url); |
| 98 | Document doc = DataUtil.load(in, "UTF-8", url.toString()); |
| 99 | Elements listing = doc.getElementsByTag("main"); |
| 100 | if (listing.size() > 0) { |
| 101 | comments.addAll(getComments(listing.get(0))); |
| 102 | } |
| 103 | |
| 104 | story.setComments(comments); |
| 105 | } |
| 106 | |
| 107 | private List<Comment> getComments(Element listing) { |
| 108 | List<Comment> comments = new ArrayList<Comment>(); |
| 109 | for (Element commentElement : listing.children()) { |
| 110 | if (commentElement.hasClass("comment")) { |
| 111 | Comment comment = getComment(commentElement); |
| 112 | if (!comment.isEmpty()) { |
| 113 | comments.add(comment); |
| 114 | } |
| 115 | } |
| 116 | } |
| 117 | return comments; |
| 118 | } |
| 119 | |
| 120 | private Comment getComment(Element commentElement) { |
| 121 | String title = firstOrEmptyTag(commentElement, "h3").text(); |
| 122 | String author = firstOrEmpty(commentElement, "h4").text(); |
| 123 | Element content = firstOrEmpty(commentElement, "comment-body"); |
| 124 | |
| 125 | String date = ""; |
| 126 | int pos = author.lastIndexOf(" on "); |
| 127 | if (pos >= 0) { |
| 128 | date = author.substring(pos + " on ".length()).trim(); |
| 129 | author = author.substring(0, pos).trim(); |
| 130 | } |
| 131 | |
| 132 | Comment comment = new Comment(commentElement.id(), author, title, date, |
| 133 | toLines(content)); |
| 134 | |
| 135 | Elements commentOutline = commentElement |
| 136 | .getElementsByClass("comment-outline"); |
| 137 | if (commentOutline.size() > 0) { |
| 138 | comment.addAll(getComments(commentOutline.get(0))); |
| 139 | } |
| 140 | |
| 141 | return comment; |
| 142 | } |
| 143 | |
| 144 | private List<String> toLines(Element element) { |
| 145 | return toLines(element, new QuoteProcessor() { |
| 146 | @Override |
| 147 | public String processText(String text) { |
| 148 | return text; |
| 149 | } |
| 150 | |
| 151 | @Override |
| 152 | public boolean detectQuote(Node node) { |
| 153 | if (node instanceof Element) { |
| 154 | Element elementNode = (Element) node; |
| 155 | if (elementNode.tagName().equals("blockquote") |
| 156 | || elementNode.hasClass("quote")) { |
| 157 | return true; |
| 158 | } |
| 159 | } |
| 160 | |
| 161 | return false; |
| 162 | } |
| 163 | |
| 164 | @Override |
| 165 | public boolean ignoreNode(Node node) { |
| 166 | return false; |
| 167 | } |
| 168 | |
| 169 | @Override |
| 170 | public String manualProcessing(Node node) { |
| 171 | return null; |
| 172 | } |
| 173 | }); |
| 174 | } |
| 175 | } |