| 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.util.AbstractMap; |
| 8 | import java.util.ArrayList; |
| 9 | import java.util.HashMap; |
| 10 | import java.util.List; |
| 11 | import java.util.Map; |
| 12 | import java.util.Map.Entry; |
| 13 | import java.util.Scanner; |
| 14 | |
| 15 | import be.nikiroo.fanfix.Instance; |
| 16 | import be.nikiroo.fanfix.data.MetaData; |
| 17 | import be.nikiroo.utils.Image; |
| 18 | import be.nikiroo.utils.Progress; |
| 19 | import be.nikiroo.utils.StringUtils; |
| 20 | |
| 21 | /** |
| 22 | * Support class for <a href="http://www.fimfiction.net/">FimFiction.net</a> |
| 23 | * stories, a website dedicated to My Little Pony. |
| 24 | * |
| 25 | * @author niki |
| 26 | */ |
| 27 | class Fimfiction extends BasicSupport_Deprecated { |
| 28 | @Override |
| 29 | protected boolean isHtml() { |
| 30 | return true; |
| 31 | } |
| 32 | |
| 33 | @Override |
| 34 | protected MetaData getMeta(URL source, InputStream in) throws IOException { |
| 35 | MetaData meta = new MetaData(); |
| 36 | |
| 37 | meta.setTitle(getTitle(reset(in))); |
| 38 | meta.setAuthor(getAuthor(reset(in))); |
| 39 | meta.setDate(getDate(reset(in))); |
| 40 | meta.setTags(getTags(reset(in))); |
| 41 | meta.setSource(getType().getSourceName()); |
| 42 | meta.setUrl(source.toString()); |
| 43 | meta.setPublisher(getType().getSourceName()); |
| 44 | meta.setUuid(source.toString()); |
| 45 | meta.setLuid(""); |
| 46 | meta.setLang("en"); |
| 47 | meta.setSubject("MLP"); |
| 48 | meta.setType(getType().toString()); |
| 49 | meta.setImageDocument(false); |
| 50 | meta.setCover(getCover(reset(in))); |
| 51 | |
| 52 | return meta; |
| 53 | } |
| 54 | |
| 55 | @Override |
| 56 | public Map<String, String> getCookies() { |
| 57 | Map<String, String> cookies = new HashMap<String, String>(); |
| 58 | cookies.put("view_mature", "true"); |
| 59 | return cookies; |
| 60 | } |
| 61 | |
| 62 | private List<String> getTags(InputStream in) { |
| 63 | List<String> tags = new ArrayList<String>(); |
| 64 | tags.add("MLP"); |
| 65 | |
| 66 | @SuppressWarnings("resource") |
| 67 | Scanner scan = new Scanner(in, "UTF-8"); |
| 68 | scan.useDelimiter("\\n"); |
| 69 | boolean started = false; |
| 70 | while (scan.hasNext()) { |
| 71 | String line = scan.next(); |
| 72 | |
| 73 | if (!started) { |
| 74 | started = line.contains("\"story_container\""); |
| 75 | } |
| 76 | |
| 77 | if (started && line.contains("class=\"tag-")) { |
| 78 | if (line.contains("index.php")) { |
| 79 | break; // end of *this story* tags |
| 80 | } |
| 81 | |
| 82 | String keyword = "title=\""; |
| 83 | Scanner tagScanner = new Scanner(line); |
| 84 | tagScanner.useDelimiter(keyword); |
| 85 | if (tagScanner.hasNext()) { |
| 86 | tagScanner.next();// Ignore first one |
| 87 | } |
| 88 | while (tagScanner.hasNext()) { |
| 89 | String tag = tagScanner.next(); |
| 90 | if (tag.contains("\"")) { |
| 91 | tag = tag.split("\"")[0]; |
| 92 | tag = StringUtils.unhtml(tag).trim(); |
| 93 | if (!tag.isEmpty() && !tags.contains(tag)) { |
| 94 | tags.add(tag); |
| 95 | } |
| 96 | } |
| 97 | } |
| 98 | tagScanner.close(); |
| 99 | } |
| 100 | } |
| 101 | |
| 102 | return tags; |
| 103 | } |
| 104 | |
| 105 | private String getTitle(InputStream in) { |
| 106 | String line = getLine(in, " property=\"og:title\"", 0); |
| 107 | if (line != null) { |
| 108 | int pos = -1; |
| 109 | for (int i = 0; i < 3; i++) { |
| 110 | pos = line.indexOf('"', pos + 1); |
| 111 | } |
| 112 | |
| 113 | if (pos >= 0) { |
| 114 | line = line.substring(pos + 1); |
| 115 | pos = line.indexOf('"'); |
| 116 | if (pos >= 0) { |
| 117 | return StringUtils.unhtml(line.substring(0, pos)).trim(); |
| 118 | } |
| 119 | } |
| 120 | } |
| 121 | |
| 122 | return null; |
| 123 | } |
| 124 | |
| 125 | private String getAuthor(InputStream in) { |
| 126 | String line = getLine(in, " href=\"/user/", 0); |
| 127 | if (line != null) { |
| 128 | int pos = line.indexOf('"'); |
| 129 | if (pos >= 0) { |
| 130 | line = line.substring(pos + 1); |
| 131 | pos = line.indexOf('"'); |
| 132 | if (pos >= 0) { |
| 133 | line = line.substring(0, pos); |
| 134 | pos = line.lastIndexOf('/'); |
| 135 | if (pos >= 0) { |
| 136 | line = line.substring(pos + 1); |
| 137 | return line.replace('+', ' '); |
| 138 | } |
| 139 | } |
| 140 | } |
| 141 | } |
| 142 | |
| 143 | return null; |
| 144 | } |
| 145 | |
| 146 | private String getDate(InputStream in) { |
| 147 | String line = getLine(in, "<span class=\"date\">", 0); |
| 148 | if (line != null) { |
| 149 | int pos = -1; |
| 150 | for (int i = 0; i < 3; i++) { |
| 151 | pos = line.indexOf('>', pos + 1); |
| 152 | } |
| 153 | |
| 154 | if (pos >= 0) { |
| 155 | line = line.substring(pos + 1); |
| 156 | pos = line.indexOf('<'); |
| 157 | if (pos >= 0) { |
| 158 | return line.substring(0, pos).trim(); |
| 159 | } |
| 160 | } |
| 161 | } |
| 162 | |
| 163 | return null; |
| 164 | } |
| 165 | |
| 166 | @Override |
| 167 | protected String getDesc(URL source, InputStream in) { |
| 168 | // the og: meta version is the SHORT resume, this is the LONG resume |
| 169 | return getLine(in, "class=\"description-text bbcode\"", 1); |
| 170 | } |
| 171 | |
| 172 | private Image getCover(InputStream in) { |
| 173 | // Note: the 'og:image' is the SMALL cover, not the full version |
| 174 | String cover = getLine(in, "class=\"story_container__story_image\"", 1); |
| 175 | if (cover != null) { |
| 176 | int pos = cover.indexOf('"'); |
| 177 | if (pos >= 0) { |
| 178 | cover = cover.substring(pos + 1); |
| 179 | pos = cover.indexOf('"'); |
| 180 | if (pos >= 0) { |
| 181 | cover = cover.substring(0, pos); |
| 182 | } |
| 183 | } |
| 184 | } |
| 185 | |
| 186 | return getImage(this, null, cover); |
| 187 | } |
| 188 | |
| 189 | @Override |
| 190 | protected List<Entry<String, URL>> getChapters(URL source, InputStream in, |
| 191 | Progress pg) { |
| 192 | List<Entry<String, URL>> urls = new ArrayList<Entry<String, URL>>(); |
| 193 | @SuppressWarnings("resource") |
| 194 | Scanner scan = new Scanner(in, "UTF-8"); |
| 195 | scan.useDelimiter("\\n"); |
| 196 | boolean started = false; |
| 197 | while (scan.hasNext()) { |
| 198 | String line = scan.next().trim(); |
| 199 | |
| 200 | if (!started) { |
| 201 | started = line.equals("<!--Chapters-->"); |
| 202 | } else { |
| 203 | if (line.equals("</form>")) { |
| 204 | break; |
| 205 | } |
| 206 | |
| 207 | if (line.startsWith("<a href=") |
| 208 | || line.contains("class=\"chapter-title\"")) { |
| 209 | // Chapter name |
| 210 | String name = line; |
| 211 | int pos = name.indexOf('>'); |
| 212 | if (pos >= 0) { |
| 213 | name = name.substring(pos + 1); |
| 214 | pos = name.indexOf('<'); |
| 215 | if (pos >= 0) { |
| 216 | name = name.substring(0, pos); |
| 217 | } |
| 218 | } |
| 219 | // Chapter content |
| 220 | pos = line.indexOf('/'); |
| 221 | if (pos >= 0) { |
| 222 | line = line.substring(pos); // we take the /, not +1 |
| 223 | pos = line.indexOf('"'); |
| 224 | if (pos >= 0) { |
| 225 | line = line.substring(0, pos); |
| 226 | } |
| 227 | } |
| 228 | |
| 229 | try { |
| 230 | urls.add(new AbstractMap.SimpleEntry<String, URL>(name, |
| 231 | new URL("http://www.fimfiction.net" + line))); |
| 232 | } catch (MalformedURLException e) { |
| 233 | Instance.getInstance().getTraceHandler().error(e); |
| 234 | } |
| 235 | } |
| 236 | } |
| 237 | } |
| 238 | |
| 239 | return urls; |
| 240 | } |
| 241 | |
| 242 | @Override |
| 243 | protected String getChapterContent(URL source, InputStream in, int number, |
| 244 | Progress pg) { |
| 245 | return getLine(in, "<div class=\"bbcode\">", 1); |
| 246 | } |
| 247 | |
| 248 | @Override |
| 249 | protected boolean supports(URL url) { |
| 250 | return "fimfiction.net".equals(url.getHost()) |
| 251 | || "www.fimfiction.net".equals(url.getHost()); |
| 252 | } |
| 253 | } |