| 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.URL; |
| 7 | import java.util.ArrayList; |
| 8 | import java.util.List; |
| 9 | import java.util.Map; |
| 10 | import java.util.Map.Entry; |
| 11 | import java.util.Scanner; |
| 12 | |
| 13 | import be.nikiroo.fanfix.Instance; |
| 14 | import be.nikiroo.fanfix.data.MetaData; |
| 15 | import be.nikiroo.utils.StringUtils; |
| 16 | |
| 17 | /** |
| 18 | * Support class for <a href="https://sofurry.com/">SoFurry.com</a>, a Furry |
| 19 | * website supporting images and stories (we only retrieve the stories). |
| 20 | * |
| 21 | * @author niki |
| 22 | */ |
| 23 | class YiffStar extends BasicSupport { |
| 24 | |
| 25 | @Override |
| 26 | public String getSourceName() { |
| 27 | return "YiffStar"; |
| 28 | } |
| 29 | |
| 30 | @Override |
| 31 | protected MetaData getMeta(URL source, InputStream in) throws IOException { |
| 32 | MetaData meta = new MetaData(); |
| 33 | |
| 34 | meta.setTitle(getTitle(reset(in))); |
| 35 | meta.setAuthor(getAuthor(source, reset(in))); |
| 36 | meta.setDate(""); |
| 37 | meta.setTags(getTags(reset(in))); |
| 38 | meta.setSource(getSourceName()); |
| 39 | meta.setUrl(source.toString()); |
| 40 | meta.setPublisher(getSourceName()); |
| 41 | meta.setUuid(source.toString()); |
| 42 | meta.setLuid(""); |
| 43 | meta.setLang("EN"); |
| 44 | meta.setSubject("Furry"); |
| 45 | meta.setType(getType().toString()); |
| 46 | meta.setImageDocument(false); |
| 47 | meta.setCover(getCover(source, reset(in))); |
| 48 | |
| 49 | return meta; |
| 50 | } |
| 51 | |
| 52 | @Override |
| 53 | protected boolean supports(URL url) { |
| 54 | String host = url.getHost(); |
| 55 | if (host.startsWith("www.")) { |
| 56 | host = host.substring("www.".length()); |
| 57 | } |
| 58 | |
| 59 | return "sofurry.com".equals(host); |
| 60 | } |
| 61 | |
| 62 | @Override |
| 63 | protected boolean isHtml() { |
| 64 | return true; |
| 65 | } |
| 66 | |
| 67 | @Override |
| 68 | public Map<String, String> getCookies() { |
| 69 | // TODO |
| 70 | // Cookies will actually be retained by the cache manager once logged in |
| 71 | // But we need to connect here and notify the cache manager |
| 72 | |
| 73 | return super.getCookies(); |
| 74 | } |
| 75 | |
| 76 | @Override |
| 77 | public URL getCanonicalUrl(URL source) throws IOException { |
| 78 | if (source.getPath().startsWith("/view")) { |
| 79 | InputStream in = Instance.getCache().open(source, this, false); |
| 80 | String line = getLine(in, "/browse/folder/", 0); |
| 81 | String[] tab = line.split("\""); |
| 82 | if (tab.length > 1) { |
| 83 | String groupUrl = source.getProtocol() + "://" |
| 84 | + source.getHost() + tab[1]; |
| 85 | return new URL(groupUrl); |
| 86 | } |
| 87 | } |
| 88 | |
| 89 | return super.getCanonicalUrl(source); |
| 90 | } |
| 91 | |
| 92 | private List<String> getTags(InputStream in) { |
| 93 | List<String> tags = new ArrayList<String>(); |
| 94 | |
| 95 | String line = getLine(in, "class=\"sf-story-big-tags", 0); |
| 96 | if (line != null) { |
| 97 | String[] tab = StringUtils.unhtml(line).split(","); |
| 98 | for (String possibleTag : tab) { |
| 99 | String tag = possibleTag.trim(); |
| 100 | if (!tag.isEmpty() && !tag.equals("...") && !tags.contains(tag)) { |
| 101 | tags.add(tag); |
| 102 | } |
| 103 | } |
| 104 | } |
| 105 | |
| 106 | return tags; |
| 107 | } |
| 108 | |
| 109 | private BufferedImage getCover(URL source, InputStream in) |
| 110 | throws IOException { |
| 111 | |
| 112 | List<Entry<String, URL>> chaps = getChapters(source, in); |
| 113 | if (!chaps.isEmpty()) { |
| 114 | in = Instance.getCache().open(chaps.get(0).getValue(), this, true); |
| 115 | String line = getLine(in, " name=\"og:image\"", 0); |
| 116 | if (line != null) { |
| 117 | int pos = -1; |
| 118 | for (int i = 0; i < 3; i++) { |
| 119 | pos = line.indexOf('"', pos + 1); |
| 120 | } |
| 121 | |
| 122 | if (pos >= 0) { |
| 123 | line = line.substring(pos + 1); |
| 124 | pos = line.indexOf('"'); |
| 125 | if (pos >= 0) { |
| 126 | line = line.substring(0, pos); |
| 127 | if (line.contains("/thumb?")) { |
| 128 | line = line.replace("/thumb?", |
| 129 | "/auxiliaryContent?type=25&"); |
| 130 | return getImage(this, null, line); |
| 131 | } |
| 132 | } |
| 133 | } |
| 134 | } |
| 135 | } |
| 136 | |
| 137 | return null; |
| 138 | } |
| 139 | |
| 140 | private String getAuthor(URL source, InputStream in) throws IOException { |
| 141 | String author = getLine(in, "class=\"onlinestatus", 0); |
| 142 | if (author != null) { |
| 143 | return StringUtils.unhtml(author).trim(); |
| 144 | } |
| 145 | |
| 146 | return null; |
| 147 | } |
| 148 | |
| 149 | private String getTitle(InputStream in) throws IOException { |
| 150 | String title = getLine(in, "class=\"sflabel pagetitle", 0); |
| 151 | if (title != null) { |
| 152 | if (title.contains("(series)")) { |
| 153 | title = title.replace("(series)", ""); |
| 154 | } |
| 155 | return StringUtils.unhtml(title).trim(); |
| 156 | } |
| 157 | |
| 158 | return null; |
| 159 | } |
| 160 | |
| 161 | @Override |
| 162 | protected String getDesc(URL source, InputStream in) throws IOException { |
| 163 | return null; // TODO: no description at all? Cannot find one... |
| 164 | } |
| 165 | |
| 166 | @Override |
| 167 | protected List<Entry<String, URL>> getChapters(URL source, InputStream in) |
| 168 | throws IOException { |
| 169 | List<Entry<String, URL>> urls = new ArrayList<Entry<String, URL>>(); |
| 170 | |
| 171 | @SuppressWarnings("resource") |
| 172 | Scanner scan = new Scanner(in, "UTF-8"); |
| 173 | scan.useDelimiter("\\n"); |
| 174 | while (scan.hasNext()) { |
| 175 | String line = scan.next(); |
| 176 | if (line.contains("\"/view/") && line.contains("title=")) { |
| 177 | String[] tab = line.split("\""); |
| 178 | if (tab.length > 5) { |
| 179 | String link = tab[5]; |
| 180 | if (link.startsWith("/")) { |
| 181 | link = source.getProtocol() + "://" + source.getHost() |
| 182 | + link; |
| 183 | } |
| 184 | final URL value = new URL(link); |
| 185 | final String key = StringUtils.unhtml(line).trim(); |
| 186 | urls.add(new Entry<String, URL>() { |
| 187 | public URL setValue(URL value) { |
| 188 | return null; |
| 189 | } |
| 190 | |
| 191 | public URL getValue() { |
| 192 | return value; |
| 193 | } |
| 194 | |
| 195 | public String getKey() { |
| 196 | return key; |
| 197 | } |
| 198 | }); |
| 199 | } |
| 200 | } |
| 201 | } |
| 202 | |
| 203 | return urls; |
| 204 | } |
| 205 | |
| 206 | @Override |
| 207 | protected String getChapterContent(URL source, InputStream in, int number) |
| 208 | throws IOException { |
| 209 | StringBuilder builder = new StringBuilder(); |
| 210 | |
| 211 | String startAt = "id=\"sfContentBody"; |
| 212 | String endAt = "id=\"recommendationArea"; |
| 213 | boolean ok = false; |
| 214 | |
| 215 | @SuppressWarnings("resource") |
| 216 | Scanner scan = new Scanner(in, "UTF-8"); |
| 217 | scan.useDelimiter("\\n"); |
| 218 | while (scan.hasNext()) { |
| 219 | String line = scan.next(); |
| 220 | if (!ok && line.contains(startAt)) { |
| 221 | ok = true; |
| 222 | } else if (ok && line.contains(endAt)) { |
| 223 | ok = false; |
| 224 | break; |
| 225 | } |
| 226 | |
| 227 | if (ok) { |
| 228 | builder.append(line); |
| 229 | builder.append('\n'); |
| 230 | } |
| 231 | } |
| 232 | |
| 233 | return builder.toString(); |
| 234 | } |
| 235 | } |