| 1 | package be.nikiroo.fanfix.supported; |
| 2 | |
| 3 | import java.io.IOException; |
| 4 | import java.io.InputStream; |
| 5 | import java.net.MalformedURLException; |
| 6 | import java.net.URL; |
| 7 | import java.text.SimpleDateFormat; |
| 8 | import java.util.ArrayList; |
| 9 | import java.util.Date; |
| 10 | import java.util.List; |
| 11 | import java.util.Map.Entry; |
| 12 | import java.util.Scanner; |
| 13 | |
| 14 | import be.nikiroo.fanfix.Instance; |
| 15 | import be.nikiroo.utils.StringUtils; |
| 16 | |
| 17 | /** |
| 18 | * Support class for <a href="http://www.fanfiction.net/">Faniction.net</a> |
| 19 | * stories, a website dedicated to fanfictions of many, many different |
| 20 | * universes, from TV shows to novels to games. |
| 21 | * |
| 22 | * @author niki |
| 23 | */ |
| 24 | class Fanfiction extends BasicSupport { |
| 25 | @Override |
| 26 | protected boolean isHtml() { |
| 27 | return true; |
| 28 | } |
| 29 | |
| 30 | @Override |
| 31 | public String getSourceName() { |
| 32 | return "Fanfiction.net"; |
| 33 | } |
| 34 | |
| 35 | @Override |
| 36 | protected String getSubject(URL source, InputStream in) { |
| 37 | String line = getLine(in, "id=pre_story_links", 0); |
| 38 | if (line != null) { |
| 39 | int pos = line.lastIndexOf('"'); |
| 40 | if (pos >= 1) { |
| 41 | line = line.substring(pos + 1); |
| 42 | pos = line.indexOf('<'); |
| 43 | if (pos >= 0) { |
| 44 | return line.substring(0, pos); |
| 45 | } |
| 46 | } |
| 47 | } |
| 48 | |
| 49 | return null; |
| 50 | } |
| 51 | |
| 52 | @Override |
| 53 | protected List<String> getTags(URL source, InputStream in) |
| 54 | throws IOException { |
| 55 | List<String> tags = super.getTags(source, in); |
| 56 | |
| 57 | String key = "title=\"Send Private Message\""; |
| 58 | String line = getLine(in, key, 2); |
| 59 | if (line != null) { |
| 60 | key = "Rated:"; |
| 61 | int pos = line.indexOf(key); |
| 62 | if (pos >= 0) { |
| 63 | line = line.substring(pos + key.length()); |
| 64 | key = "Chapters:"; |
| 65 | pos = line.indexOf(key); |
| 66 | if (pos >= 0) { |
| 67 | line = line.substring(0, pos); |
| 68 | line = StringUtils.unhtml(line).trim(); |
| 69 | if (line.endsWith("-")) { |
| 70 | line = line.substring(0, line.length() - 1); |
| 71 | } |
| 72 | |
| 73 | for (String tag : line.split("-")) { |
| 74 | tags.add(tag.trim()); |
| 75 | } |
| 76 | } |
| 77 | } |
| 78 | } |
| 79 | |
| 80 | return tags; |
| 81 | } |
| 82 | |
| 83 | @Override |
| 84 | protected String getTitle(URL source, InputStream in) { |
| 85 | int i = 0; |
| 86 | @SuppressWarnings("resource") |
| 87 | Scanner scan = new Scanner(in, "UTF-8"); |
| 88 | scan.useDelimiter("\\n"); |
| 89 | while (scan.hasNext()) { |
| 90 | String line = scan.next(); |
| 91 | if (line.contains("xcontrast_txt")) { |
| 92 | if ((++i) == 2) { |
| 93 | line = StringUtils.unhtml(line).trim(); |
| 94 | if (line.startsWith("Follow/Fav")) { |
| 95 | line = line.substring("Follow/Fav".length()).trim(); |
| 96 | } |
| 97 | |
| 98 | return line; |
| 99 | } |
| 100 | } |
| 101 | } |
| 102 | |
| 103 | return null; |
| 104 | } |
| 105 | |
| 106 | @Override |
| 107 | protected String getAuthor(URL source, InputStream in) { |
| 108 | int i = 0; |
| 109 | @SuppressWarnings("resource") |
| 110 | Scanner scan = new Scanner(in, "UTF-8"); |
| 111 | scan.useDelimiter("\\n"); |
| 112 | while (scan.hasNext()) { |
| 113 | String line = scan.next(); |
| 114 | if (line.contains("xcontrast_txt")) { |
| 115 | if ((++i) == 3) { |
| 116 | return StringUtils.unhtml(line).trim(); |
| 117 | } |
| 118 | } |
| 119 | } |
| 120 | |
| 121 | return null; |
| 122 | } |
| 123 | |
| 124 | @Override |
| 125 | protected String getDate(URL source, InputStream in) { |
| 126 | String key = "Published: <span data-xutime='"; |
| 127 | String line = getLine(in, key, 0); |
| 128 | if (line != null) { |
| 129 | int pos = line.indexOf(key); |
| 130 | if (pos >= 0) { |
| 131 | line = line.substring(pos + key.length()); |
| 132 | pos = line.indexOf('\''); |
| 133 | if (pos >= 0) { |
| 134 | line = line.substring(0, pos).trim(); |
| 135 | try { |
| 136 | SimpleDateFormat sdf = new SimpleDateFormat( |
| 137 | "YYYY-MM-dd"); |
| 138 | return sdf |
| 139 | .format(new Date(1000 * Long.parseLong(line))); |
| 140 | } catch (NumberFormatException e) { |
| 141 | Instance.syserr(new IOException( |
| 142 | "Cannot convert publication date: " + line, e)); |
| 143 | } |
| 144 | } |
| 145 | } |
| 146 | } |
| 147 | |
| 148 | return null; |
| 149 | } |
| 150 | |
| 151 | @Override |
| 152 | protected String getDesc(URL source, InputStream in) { |
| 153 | return getLine(in, "title=\"Send Private Message\"", 1); |
| 154 | } |
| 155 | |
| 156 | @Override |
| 157 | protected URL getCover(URL url, InputStream in) { |
| 158 | String key = "class='cimage"; |
| 159 | String line = getLine(in, key, 0); |
| 160 | if (line != null) { |
| 161 | int pos = line.indexOf(key); |
| 162 | if (pos >= 0) { |
| 163 | line = line.substring(pos + key.length()); |
| 164 | key = "src='"; |
| 165 | pos = line.indexOf(key); |
| 166 | if (pos >= 0) { |
| 167 | line = line.substring(pos + key.length()); |
| 168 | pos = line.indexOf('\''); |
| 169 | if (pos >= 0) { |
| 170 | line = line.substring(0, pos); |
| 171 | if (line.startsWith("//")) { |
| 172 | line = url.getProtocol() + "://" |
| 173 | + line.substring(2); |
| 174 | } else if (line.startsWith("//")) { |
| 175 | line = url.getProtocol() + "://" + url.getHost() |
| 176 | + "/" + line.substring(1); |
| 177 | } else { |
| 178 | line = url.getProtocol() + "://" + url.getHost() |
| 179 | + "/" + url.getPath() + "/" + line; |
| 180 | } |
| 181 | |
| 182 | try { |
| 183 | return new URL(line); |
| 184 | } catch (MalformedURLException e) { |
| 185 | Instance.syserr(e); |
| 186 | } |
| 187 | } |
| 188 | } |
| 189 | } |
| 190 | } |
| 191 | |
| 192 | return null; |
| 193 | } |
| 194 | |
| 195 | @Override |
| 196 | protected List<Entry<String, URL>> getChapters(URL source, InputStream in) { |
| 197 | List<Entry<String, URL>> urls = new ArrayList<Entry<String, URL>>(); |
| 198 | |
| 199 | String base = source.toString(); |
| 200 | int pos = base.lastIndexOf('/'); |
| 201 | String suffix = base.substring(pos); // including '/' at start |
| 202 | base = base.substring(0, pos); |
| 203 | if (base.endsWith("/1")) { |
| 204 | base = base.substring(0, base.length() - 1); // including '/' at end |
| 205 | } |
| 206 | |
| 207 | String line = getLine(in, "id=chap_select", 0); |
| 208 | String key = "<option value="; |
| 209 | int i = 1; |
| 210 | for (pos = line.indexOf(key); pos >= 0; pos = line.indexOf(key, pos), i++) { |
| 211 | pos = line.indexOf('>', pos); |
| 212 | if (pos >= 0) { |
| 213 | int endOfName = line.indexOf('<', pos); |
| 214 | if (endOfName >= 0) { |
| 215 | String name = line.substring(pos + 1, endOfName); |
| 216 | String chapNum = i + "."; |
| 217 | if (name.startsWith(chapNum)) { |
| 218 | name = name.substring(chapNum.length(), name.length()); |
| 219 | } |
| 220 | |
| 221 | try { |
| 222 | final String chapName = name.trim(); |
| 223 | final URL chapURL = new URL(base + i + suffix); |
| 224 | urls.add(new Entry<String, URL>() { |
| 225 | public URL setValue(URL value) { |
| 226 | return null; |
| 227 | } |
| 228 | |
| 229 | public URL getValue() { |
| 230 | return chapURL; |
| 231 | } |
| 232 | |
| 233 | public String getKey() { |
| 234 | return chapName; |
| 235 | } |
| 236 | }); |
| 237 | } catch (MalformedURLException e) { |
| 238 | Instance.syserr(new IOException("Cannot parse chapter " |
| 239 | + i + " url: " + (base + i + suffix), e)); |
| 240 | } |
| 241 | } |
| 242 | } |
| 243 | } |
| 244 | |
| 245 | return urls; |
| 246 | } |
| 247 | |
| 248 | @Override |
| 249 | protected String getChapterContent(URL source, InputStream in, int number) { |
| 250 | StringBuilder builder = new StringBuilder(); |
| 251 | String startAt = "class='storytext "; |
| 252 | String endAt1 = "function review_init"; |
| 253 | String endAt2 = "id=chap_select"; |
| 254 | boolean ok = false; |
| 255 | |
| 256 | @SuppressWarnings("resource") |
| 257 | Scanner scan = new Scanner(in, "UTF-8"); |
| 258 | scan.useDelimiter("\\n"); |
| 259 | while (scan.hasNext()) { |
| 260 | String line = scan.next(); |
| 261 | if (!ok && line.contains(startAt)) { |
| 262 | ok = true; |
| 263 | } else if (ok && (line.contains(endAt1) || line.contains(endAt2))) { |
| 264 | ok = false; |
| 265 | break; |
| 266 | } |
| 267 | |
| 268 | if (ok) { |
| 269 | // First line may contain the title and chap name again |
| 270 | if (builder.length() == 0) { |
| 271 | int pos = line.indexOf("<hr"); |
| 272 | if (pos >= 0) { |
| 273 | line = line.substring(pos); |
| 274 | } |
| 275 | } |
| 276 | |
| 277 | builder.append(line); |
| 278 | } |
| 279 | } |
| 280 | |
| 281 | return builder.toString(); |
| 282 | } |
| 283 | |
| 284 | @Override |
| 285 | protected boolean supports(URL url) { |
| 286 | return "fanfiction.net".equals(url.getHost()) |
| 287 | || "www.fanfiction.net".equals(url.getHost()); |
| 288 | } |
| 289 | } |