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