| 1 | package be.nikiroo.gofetch; |
| 2 | |
| 3 | import java.io.File; |
| 4 | import java.io.FileWriter; |
| 5 | import java.io.FilenameFilter; |
| 6 | import java.io.IOException; |
| 7 | import java.util.Arrays; |
| 8 | import java.util.List; |
| 9 | |
| 10 | import be.nikiroo.gofetch.data.Comment; |
| 11 | import be.nikiroo.gofetch.data.Story; |
| 12 | import be.nikiroo.gofetch.output.Gopher; |
| 13 | import be.nikiroo.gofetch.output.Html; |
| 14 | import be.nikiroo.gofetch.output.Output; |
| 15 | import be.nikiroo.gofetch.support.BasicSupport; |
| 16 | import be.nikiroo.gofetch.support.BasicSupport.Type; |
| 17 | import be.nikiroo.utils.IOUtils; |
| 18 | |
| 19 | /** |
| 20 | * The class that will manage the fetch operations. |
| 21 | * <p> |
| 22 | * It will scrap the required websites and process them to disk. |
| 23 | * |
| 24 | * @author niki |
| 25 | */ |
| 26 | public class Fetcher { |
| 27 | private File dir; |
| 28 | private String preselector; |
| 29 | private int maxStories; |
| 30 | private String hostname; |
| 31 | private int port; |
| 32 | private Type type; |
| 33 | |
| 34 | /** |
| 35 | * Prepare a new {@link Fetcher}. |
| 36 | * |
| 37 | * @param dir |
| 38 | * the target directory where to save the files (won't have |
| 39 | * impact on the files' content) |
| 40 | * @param preselector |
| 41 | * the sub directory and (pre-)selector to use for the resources |
| 42 | * (<b>will</b> have an impact on the files' content) |
| 43 | * @param type |
| 44 | * the type of news to get (or the special keyword ALL to get all |
| 45 | * of the supported sources) |
| 46 | * @param maxStories |
| 47 | * the maximum number of stories to show on the resume page |
| 48 | * @param hostname |
| 49 | * the gopher host to use (<b>will</b> have an impact on the |
| 50 | * files' content) |
| 51 | * @param port |
| 52 | * the gopher port to use (<b>will</b> have an impact on the |
| 53 | * files' content) |
| 54 | */ |
| 55 | public Fetcher(File dir, String preselector, Type type, int maxStories, |
| 56 | String hostname, int port) { |
| 57 | this.dir = dir; |
| 58 | this.preselector = preselector; |
| 59 | this.type = type; |
| 60 | this.maxStories = maxStories; |
| 61 | this.hostname = hostname; |
| 62 | this.port = port; |
| 63 | } |
| 64 | |
| 65 | /** |
| 66 | * Start the fetching operation. |
| 67 | * <p> |
| 68 | * This method will handle the main pages itself, and will call |
| 69 | * {@link Fetcher#list(BasicSupport)} for the stories. |
| 70 | * |
| 71 | * @throws IOException |
| 72 | * in case of I/O error |
| 73 | */ |
| 74 | public void start() throws IOException { |
| 75 | File cache = new File(dir, preselector); |
| 76 | cache.mkdirs(); |
| 77 | File cacheHtml = new File(cache, "index.html"); |
| 78 | cache = new File(cache, ".cache"); |
| 79 | |
| 80 | Output gopher = new Gopher(null, hostname, port); |
| 81 | Output html = new Html(null); |
| 82 | |
| 83 | FileWriter writer = new FileWriter(cache); |
| 84 | try { |
| 85 | FileWriter writerHtml = new FileWriter(cacheHtml); |
| 86 | try { |
| 87 | writer.append(gopher.getIndexHeader()); |
| 88 | writerHtml.append(html.getIndexHeader()); |
| 89 | |
| 90 | Type types[]; |
| 91 | if (type == null) { |
| 92 | types = Type.values(); |
| 93 | } else { |
| 94 | types = new Type[] { type }; |
| 95 | } |
| 96 | |
| 97 | BasicSupport.setPreselector(preselector); |
| 98 | for (Type type : types) { |
| 99 | BasicSupport support = BasicSupport.getSupport(type); |
| 100 | list(support); |
| 101 | |
| 102 | writer.append("1" + support.getDescription()).append("\t") |
| 103 | .append("1" + support.getSelector()) // |
| 104 | .append("\t").append(hostname) // |
| 105 | .append("\t").append(Integer.toString(port)) // |
| 106 | .append("\r\n"); |
| 107 | String ref = support.getSelector(); |
| 108 | while (ref.startsWith("/")) { |
| 109 | ref = ref.substring(1); |
| 110 | } |
| 111 | writerHtml.append("<div class='site'><a href='../" + ref |
| 112 | + "'>" + support.getDescription() + "</a></div>"); |
| 113 | } |
| 114 | |
| 115 | writer.append(gopher.getIndexFooter()); |
| 116 | writerHtml.append(html.getIndexFooter()); |
| 117 | } finally { |
| 118 | writerHtml.close(); |
| 119 | } |
| 120 | } finally { |
| 121 | writer.close(); |
| 122 | } |
| 123 | } |
| 124 | |
| 125 | /** |
| 126 | * Process the stories for the given {@link BasicSupport} to disk. |
| 127 | * |
| 128 | * @param support |
| 129 | * the {@link BasicSupport} to download from |
| 130 | * |
| 131 | * @throws IOException |
| 132 | * in case of I/O error |
| 133 | **/ |
| 134 | private void list(BasicSupport support) throws IOException { |
| 135 | Output gopher = new Gopher(support.getType(), hostname, port); |
| 136 | Output html = new Html(support.getType()); |
| 137 | |
| 138 | new File(dir, support.getSelector()).mkdirs(); |
| 139 | |
| 140 | System.err |
| 141 | .print("Listing recent news for " + support.getType() + "..."); |
| 142 | List<Story> stories = support.list(); |
| 143 | System.err.println(" " + stories.size() + " stories found!"); |
| 144 | int i = 1; |
| 145 | for (Story story : stories) { |
| 146 | IOUtils.writeSmallFile(dir, story.getSelector() + ".header", |
| 147 | gopher.export(story)); |
| 148 | IOUtils.writeSmallFile(dir, story.getSelector() + ".header.html", |
| 149 | html.export(story)); |
| 150 | |
| 151 | System.err.println(String.format("%02d/%02d", i, stories.size()) |
| 152 | + " Fetching comments for story " + story.getId() + "..."); |
| 153 | List<Comment> comments = support.getComments(story); |
| 154 | |
| 155 | IOUtils.writeSmallFile(dir, story.getSelector(), |
| 156 | gopher.export(story, comments)); |
| 157 | IOUtils.writeSmallFile(dir, story.getSelector() + ".html", |
| 158 | html.export(story, comments)); |
| 159 | |
| 160 | i++; |
| 161 | } |
| 162 | |
| 163 | File varDir = new File(dir, support.getSelector()); |
| 164 | String[] headers = varDir.list(new FilenameFilter() { |
| 165 | @Override |
| 166 | public boolean accept(File dir, String name) { |
| 167 | return name.endsWith(".header"); |
| 168 | } |
| 169 | }); |
| 170 | |
| 171 | File cache = new File(varDir, ".cache"); |
| 172 | File cacheHtml = new File(varDir, "index.html"); |
| 173 | FileWriter writer = new FileWriter(cache); |
| 174 | try { |
| 175 | FileWriter writerHtml = new FileWriter(cacheHtml); |
| 176 | try { |
| 177 | if (headers.length > 0) { |
| 178 | Arrays.sort(headers); |
| 179 | int from = headers.length - 1; |
| 180 | int to = headers.length - maxStories; |
| 181 | if (to < 0) { |
| 182 | to = 0; |
| 183 | } |
| 184 | for (i = from; i >= to; i--) { |
| 185 | writer.append(IOUtils.readSmallFile(new File(varDir, |
| 186 | headers[i]))); |
| 187 | |
| 188 | writerHtml.append(IOUtils.readSmallFile(new File( |
| 189 | varDir, headers[i] + ".html"))); |
| 190 | } |
| 191 | } |
| 192 | } finally { |
| 193 | writerHtml.close(); |
| 194 | } |
| 195 | } finally { |
| 196 | writer.close(); |
| 197 | } |
| 198 | } |
| 199 | } |