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

   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.bundles.Config;
  17 import be.nikiroo.fanfix.data.MetaData;
  18 import be.nikiroo.utils.Image;
  19 import be.nikiroo.utils.Progress;
  20 import be.nikiroo.utils.StringUtils;
  21
  22 /**
  23  * Support class for <a href="https://sofurry.com/">SoFurry.com</a>, a Furry
  24  * website supporting images and stories (we only retrieve the stories).
  25  *
  26  * @author niki
  27  */
  28 class YiffStar extends BasicSupport_Deprecated {
  29
  30         @Override
  31         public String getSourceName() {
  32                 return "YiffStar";
  33         }
  34
  35         @Override
  36         protected MetaData getMeta(URL source, InputStream in) throws IOException {
  37                 MetaData meta = new MetaData();
  38
  39                 meta.setTitle(getTitle(reset(in)));
  40                 meta.setAuthor(getAuthor(reset(in)));
  41                 meta.setDate("");
  42                 meta.setTags(getTags(reset(in)));
  43                 meta.setSource(getSourceName());
  44                 meta.setUrl(source.toString());
  45                 meta.setPublisher(getSourceName());
  46                 meta.setUuid(source.toString());
  47                 meta.setLuid("");
  48                 meta.setLang("en");
  49                 meta.setSubject("Furry");
  50                 meta.setType(getType().toString());
  51                 meta.setImageDocument(false);
  52                 meta.setCover(getCover(source, reset(in)));
  53
  54                 return meta;
  55         }
  56
  57         @Override
  58         protected boolean supports(URL url) {
  59                 String host = url.getHost();
  60                 if (host.startsWith("www.")) {
  61                         host = host.substring("www.".length());
  62                 }
  63
  64                 return "sofurry.com".equals(host);
  65         }
  66
  67         @Override
  68         protected boolean isHtml() {
  69                 return true;
  70         }
  71
  72         @Override
  73         public void login() throws IOException {
  74                 // Note: this should not be necessary anymore
  75                 // (the "/guest" trick is enough)
  76                 String login = Instance.getConfig().getString(
  77                                 Config.LOGIN_YIFFSTAR_USER);
  78                 String password = Instance.getConfig().getString(
  79                                 Config.LOGIN_YIFFSTAR_PASS);
  80
  81                 if (login != null && !login.isEmpty() && password != null
  82                                 && !password.isEmpty()) {
  83                         Map<String, String> post = new HashMap<String, String>();
  84                         post.put("sfLoginUsername", login);
  85                         post.put("sfLoginPassword", password);
  86                         post.put("YII_CSRF_TOKEN", "");
  87
  88                         // Cookies will actually be retained by the cache manager once
  89                         // logged in
  90                         Instance.getCache()
  91                                         .openNoCache(new URL("https://www.sofurry.com/user/login"),
  92                                                         this, post, null, null).close();
  93                 }
  94         }
  95
  96         @Override
  97         public URL getCanonicalUrl(URL source) {
  98                 try {
  99                         if (source.getPath().startsWith("/view")) {
 100                                 source = new URL(source.toString() + "/guest");
 101                                 InputStream in = Instance.getCache().open(source, this, false);
 102                                 String line = getLine(in, "/browse/folder/", 0);
 103                                 if (line != null) {
 104                                         String[] tab = line.split("\"");
 105                                         if (tab.length > 1) {
 106                                                 String groupUrl = source.getProtocol() + "://"
 107                                                                 + source.getHost() + tab[1];
 108                                                 return guest(groupUrl);
 109                                         }
 110                                 }
 111                         }
 112                 } catch (Exception e) {
 113                         Instance.getTraceHandler().error(e);
 114                 }
 115
 116                 return super.getCanonicalUrl(source);
 117         }
 118
 119         private List<String> getTags(InputStream in) {
 120                 List<String> tags = new ArrayList<String>();
 121
 122                 String line = getLine(in, "class=\"sf-story-big-tags", 0);
 123                 if (line != null) {
 124                         String[] tab = StringUtils.unhtml(line).split(",");
 125                         for (String possibleTag : tab) {
 126                                 String tag = possibleTag.trim();
 127                                 if (!tag.isEmpty() && !tag.equals("...") && !tags.contains(tag)) {
 128                                         tags.add(tag);
 129                                 }
 130                         }
 131                 }
 132
 133                 return tags;
 134         }
 135
 136         private Image getCover(URL source, InputStream in) throws IOException {
 137
 138                 List<Entry<String, URL>> chaps = getChapters(source, in, null);
 139                 if (!chaps.isEmpty()) {
 140                         in = Instance.getCache().open(chaps.get(0).getValue(), this, true);
 141                         String line = getLine(in, " name=\"og:image\"", 0);
 142                         if (line != null) {
 143                                 int pos = -1;
 144                                 for (int i = 0; i < 3; i++) {
 145                                         pos = line.indexOf('"', pos + 1);
 146                                 }
 147
 148                                 if (pos >= 0) {
 149                                         line = line.substring(pos + 1);
 150                                         pos = line.indexOf('"');
 151                                         if (pos >= 0) {
 152                                                 line = line.substring(0, pos);
 153                                                 if (line.contains("/thumb?")) {
 154                                                         line = line.replace("/thumb?",
 155                                                                         "/auxiliaryContent?type=25&");
 156                                                         return getImage(this, null, line);
 157                                                 }
 158                                         }
 159                                 }
 160                         }
 161                 }
 162
 163                 return null;
 164         }
 165
 166         private String getAuthor(InputStream in) {
 167                 String author = getLine(in, "class=\"onlinestatus", 0);
 168                 if (author != null) {
 169                         return StringUtils.unhtml(author).trim();
 170                 }
 171
 172                 return null;
 173         }
 174
 175         private String getTitle(InputStream in) {
 176                 String title = getLine(in, "class=\"sflabel pagetitle", 0);
 177                 if (title != null) {
 178                         if (title.contains("(series)")) {
 179                                 title = title.replace("(series)", "");
 180                         }
 181                         return StringUtils.unhtml(title).trim();
 182                 }
 183
 184                 return null;
 185         }
 186
 187         @Override
 188         protected String getDesc(URL source, InputStream in) throws IOException {
 189                 return null; // TODO: no description at all? Cannot find one...
 190         }
 191
 192         @Override
 193         protected List<Entry<String, URL>> getChapters(URL source, InputStream in,
 194                         Progress pg) throws IOException {
 195                 List<Entry<String, URL>> urls = new ArrayList<Entry<String, URL>>();
 196
 197                 @SuppressWarnings("resource")
 198                 Scanner scan = new Scanner(in, "UTF-8");
 199                 scan.useDelimiter("\\n");
 200                 while (scan.hasNext()) {
 201                         String line = scan.next();
 202                         if (line.contains("\"/view/") && line.contains("title=")) {
 203                                 String[] tab = line.split("\"");
 204                                 if (tab.length > 5) {
 205                                         String link = tab[5];
 206                                         if (link.startsWith("/")) {
 207                                                 link = source.getProtocol() + "://" + source.getHost()
 208                                                                 + link;
 209                                         }
 210                                         urls.add(new AbstractMap.SimpleEntry<String, URL>(
 211                                                         StringUtils.unhtml(line).trim(), guest(link)));
 212                                 }
 213                         }
 214                 }
 215
 216                 return urls;
 217         }
 218
 219         @Override
 220         protected String getChapterContent(URL source, InputStream in, int number,
 221                         Progress pg) throws IOException {
 222                 StringBuilder builder = new StringBuilder();
 223
 224                 String startAt = "id=\"sfContentBody";
 225                 String endAt = "id=\"recommendationArea";
 226                 boolean ok = false;
 227
 228                 @SuppressWarnings("resource")
 229                 Scanner scan = new Scanner(in, "UTF-8");
 230                 scan.useDelimiter("\\n");
 231                 while (scan.hasNext()) {
 232                         String line = scan.next();
 233                         if (!ok && line.contains(startAt)) {
 234                                 ok = true;
 235                         } else if (ok && line.contains(endAt)) {
 236                                 ok = false;
 237                                 break;
 238                         }
 239
 240                         if (ok) {
 241                                 builder.append(line);
 242                                 builder.append(' ');
 243                         }
 244                 }
 245
 246                 return builder.toString();
 247         }
 248
 249         /**
 250          * Return a {@link URL} from the given link, but add the "/guest" part to it
 251          * to make sure we don't need to be logged-in to see it.
 252          *
 253          * @param link
 254          *            the link
 255          *
 256          * @return the {@link URL}
 257          *
 258          * @throws MalformedURLException
 259          *             in case of data error
 260          */
 261         private URL guest(String link) throws MalformedURLException {
 262                 if (link.contains("?")) {
 263                         if (link.contains("/?")) {
 264                                 return new URL(link.replace("?", "guest?"));
 265                         }
 266
 267                         return new URL(link.replace("?", "/guest?"));
 268                 }
 269
 270                 return new URL(link + "/guest");
 271         }
 272 }