src/be/nikiroo/fanfix/supported/YiffStar.java

   1 package be.nikiroo.fanfix.supported;
   2
   3 import java.awt.image.BufferedImage;
   4 import java.io.IOException;
   5 import java.io.InputStream;
   6 import java.net.MalformedURLException;
   7 import java.net.URL;
   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.bundles.Config;
  17 import be.nikiroo.fanfix.data.MetaData;
  18 import be.nikiroo.utils.StringUtils;
  19
  20 /**
  21  * Support class for <a href="https://sofurry.com/">SoFurry.com</a>, a Furry
  22  * website supporting images and stories (we only retrieve the stories).
  23  *
  24  * @author niki
  25  */
  26 class YiffStar extends BasicSupport {
  27
  28         @Override
  29         public String getSourceName() {
  30                 return "YiffStar";
  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(source, reset(in)));
  39                 meta.setDate("");
  40                 meta.setTags(getTags(reset(in)));
  41                 meta.setSource(getSourceName());
  42                 meta.setUrl(source.toString());
  43                 meta.setPublisher(getSourceName());
  44                 meta.setUuid(source.toString());
  45                 meta.setLuid("");
  46                 meta.setLang("EN");
  47                 meta.setSubject("Furry");
  48                 meta.setType(getType().toString());
  49                 meta.setImageDocument(false);
  50                 meta.setCover(getCover(source, reset(in)));
  51
  52                 return meta;
  53         }
  54
  55         @Override
  56         protected boolean supports(URL url) {
  57                 String host = url.getHost();
  58                 if (host.startsWith("www.")) {
  59                         host = host.substring("www.".length());
  60                 }
  61
  62                 return "sofurry.com".equals(host);
  63         }
  64
  65         @Override
  66         protected boolean isHtml() {
  67                 return true;
  68         }
  69
  70         @Override
  71         public void login() throws IOException {
  72                 // Note: this should not be necessary anymore
  73                 // (the "/guest" trick is enough)
  74                 String login = Instance.getConfig().getString(
  75                                 Config.LOGIN_YIFFSTAR_USER);
  76                 String password = Instance.getConfig().getString(
  77                                 Config.LOGIN_YIFFSTAR_PASS);
  78
  79                 if (login != null && !login.isEmpty() && password != null
  80                                 && !password.isEmpty()) {
  81                         Map<String, String> post = new HashMap<String, String>();
  82                         post.put("sfLoginUsername", login);
  83                         post.put("sfLoginPassword", password);
  84                         post.put("YII_CSRF_TOKEN", "");
  85
  86                         // Cookies will actually be retained by the cache manager once
  87                         // logged in
  88                         Instance.getCache()
  89                                         .openNoCache(new URL("https://www.sofurry.com/user/login"),
  90                                                         this, post).close();
  91                 }
  92         }
  93
  94         @Override
  95         public URL getCanonicalUrl(URL source) throws IOException {
  96                 if (source.getPath().startsWith("/view")) {
  97                         source = new URL(source.toString() + "/guest");
  98                         InputStream in = Instance.getCache().open(source, this, false);
  99                         String line = getLine(in, "/browse/folder/", 0);
 100                         if (line != null) {
 101                                 String[] tab = line.split("\"");
 102                                 if (tab.length > 1) {
 103                                         String groupUrl = source.getProtocol() + "://"
 104                                                         + source.getHost() + tab[1];
 105                                         return guest(groupUrl);
 106                                 }
 107                         }
 108                 }
 109
 110                 return super.getCanonicalUrl(source);
 111         }
 112
 113         private List<String> getTags(InputStream in) {
 114                 List<String> tags = new ArrayList<String>();
 115
 116                 String line = getLine(in, "class=\"sf-story-big-tags", 0);
 117                 if (line != null) {
 118                         String[] tab = StringUtils.unhtml(line).split(",");
 119                         for (String possibleTag : tab) {
 120                                 String tag = possibleTag.trim();
 121                                 if (!tag.isEmpty() && !tag.equals("...") && !tags.contains(tag)) {
 122                                         tags.add(tag);
 123                                 }
 124                         }
 125                 }
 126
 127                 return tags;
 128         }
 129
 130         private BufferedImage getCover(URL source, InputStream in)
 131                         throws IOException {
 132
 133                 List<Entry<String, URL>> chaps = getChapters(source, in);
 134                 if (!chaps.isEmpty()) {
 135                         in = Instance.getCache().open(chaps.get(0).getValue(), this, true);
 136                         String line = getLine(in, " name=\"og:image\"", 0);
 137                         if (line != null) {
 138                                 int pos = -1;
 139                                 for (int i = 0; i < 3; i++) {
 140                                         pos = line.indexOf('"', pos + 1);
 141                                 }
 142
 143                                 if (pos >= 0) {
 144                                         line = line.substring(pos + 1);
 145                                         pos = line.indexOf('"');
 146                                         if (pos >= 0) {
 147                                                 line = line.substring(0, pos);
 148                                                 if (line.contains("/thumb?")) {
 149                                                         line = line.replace("/thumb?",
 150                                                                         "/auxiliaryContent?type=25&");
 151                                                         return getImage(this, null, line);
 152                                                 }
 153                                         }
 154                                 }
 155                         }
 156                 }
 157
 158                 return null;
 159         }
 160
 161         private String getAuthor(URL source, InputStream in) throws IOException {
 162                 String author = getLine(in, "class=\"onlinestatus", 0);
 163                 if (author != null) {
 164                         return StringUtils.unhtml(author).trim();
 165                 }
 166
 167                 return null;
 168         }
 169
 170         private String getTitle(InputStream in) throws IOException {
 171                 String title = getLine(in, "class=\"sflabel pagetitle", 0);
 172                 if (title != null) {
 173                         if (title.contains("(series)")) {
 174                                 title = title.replace("(series)", "");
 175                         }
 176                         return StringUtils.unhtml(title).trim();
 177                 }
 178
 179                 return null;
 180         }
 181
 182         @Override
 183         protected String getDesc(URL source, InputStream in) throws IOException {
 184                 return null; // TODO: no description at all? Cannot find one...
 185         }
 186
 187         @Override
 188         protected List<Entry<String, URL>> getChapters(URL source, InputStream in)
 189                         throws IOException {
 190                 List<Entry<String, URL>> urls = new ArrayList<Entry<String, URL>>();
 191
 192                 @SuppressWarnings("resource")
 193                 Scanner scan = new Scanner(in, "UTF-8");
 194                 scan.useDelimiter("\\n");
 195                 while (scan.hasNext()) {
 196                         String line = scan.next();
 197                         if (line.contains("\"/view/") && line.contains("title=")) {
 198                                 String[] tab = line.split("\"");
 199                                 if (tab.length > 5) {
 200                                         String link = tab[5];
 201                                         if (link.startsWith("/")) {
 202                                                 link = source.getProtocol() + "://" + source.getHost()
 203                                                                 + link;
 204                                         }
 205                                         final URL value = guest(link);
 206                                         final String key = StringUtils.unhtml(line).trim();
 207                                         urls.add(new Entry<String, URL>() {
 208                                                 public URL setValue(URL value) {
 209                                                         return null;
 210                                                 }
 211
 212                                                 public URL getValue() {
 213                                                         return value;
 214                                                 }
 215
 216                                                 public String getKey() {
 217                                                         return key;
 218                                                 }
 219                                         });
 220                                 }
 221                         }
 222                 }
 223
 224                 return urls;
 225         }
 226
 227         @Override
 228         protected String getChapterContent(URL source, InputStream in, int number)
 229                         throws IOException {
 230                 StringBuilder builder = new StringBuilder();
 231
 232                 String startAt = "id=\"sfContentBody";
 233                 String endAt = "id=\"recommendationArea";
 234                 boolean ok = false;
 235
 236                 @SuppressWarnings("resource")
 237                 Scanner scan = new Scanner(in, "UTF-8");
 238                 scan.useDelimiter("\\n");
 239                 while (scan.hasNext()) {
 240                         String line = scan.next();
 241                         if (!ok && line.contains(startAt)) {
 242                                 ok = true;
 243                         } else if (ok && line.contains(endAt)) {
 244                                 ok = false;
 245                                 break;
 246                         }
 247
 248                         if (ok) {
 249                                 builder.append(line);
 250                                 builder.append(' ');
 251                         }
 252                 }
 253
 254                 return builder.toString();
 255         }
 256
 257         /**
 258          * Return a {@link URL} from the given link, but add the "/guest" part to it
 259          * to make sure we don't need to be logged-in to see it.
 260          *
 261          * @param link
 262          *            the link
 263          *
 264          * @return the {@link URL}
 265          *
 266          * @throws MalformedURLException
 267          */
 268         private URL guest(String link) throws MalformedURLException {
 269                 if (link.contains("?")) {
 270                         if (link.contains("/?")) {
 271                                 return new URL(link.replace("?", "guest?"));
 272                         } else {
 273                                 return new URL(link.replace("?", "/guest?"));
 274                         }
 275                 } else {
 276                         return new URL(link + "/guest");
 277                 }
 278         }
 279 }