@Override public synchronized void setParameters() { Common.downloadFile(webSite, SetUp.getTempDirectory(), indexName, false, ""); Common.newEncodeFile(SetUp.getTempDirectory(), indexName, indexEncodeName, Encoding.GBK); String tempStr = Common.getFileString(SetUp.getTempDirectory(), indexEncodeName); String[] lines = tempStr.split("\n"); for (int i = 0; i < lines.length; i++) { String line = Common.getTraditionalChinese(lines[i]); // ".": contain all characters except "\r" and "\n" // "(?s).": contain all characters if (line.matches("(?s).*title(?s).*")) { // get title ex.<title>尸錄 4話</title> String[] temp = line.split("<|>"); if (getWholeTitle() == null || getWholeTitle().equals("")) setWholeTitle(Common.getStringRemovedIllegalChar(temp[2])); } else if (line.matches("(?s).*page(?s).*")) { // get total page ex. | 共34頁 | int beginIndex = line.indexOf(Common.getStringUsingDefaultLanguage("共", "共")); int endIndex = line.indexOf(Common.getStringUsingDefaultLanguage("頁", "頁")); String temp = line.substring(beginIndex + 1, endIndex); totalPage = Integer.parseInt(temp); break; } } comicURL = new String[totalPage]; // totalPage = amount of comic pic SetUp.setWholeTitle(wholeTitle); }
@Override public String getAllPageString(String urlString) { String indexName = Common.getStoredFileName(SetUp.getTempDirectory(), "index_KUKU_", "html"); String indexEncodeName = Common.getStoredFileName(SetUp.getTempDirectory(), "index_KUKU_encode_", "html"); Common.downloadFile(urlString, SetUp.getTempDirectory(), indexName, false, ""); Common.newEncodeFile(SetUp.getTempDirectory(), indexName, indexEncodeName, Encoding.GBK); return Common.getFileString(SetUp.getTempDirectory(), indexEncodeName); }
/** @author user */ public ParseKUKU() { enumName = "KUKU"; regexs = new String[] { "(?s).*kukudm.com(?s).*", "(?s).*socomic.com(?s).*", "(?s).*socomic.net(?s).*" }; parserName = this.getClass().getName(); downloadBefore = true; siteID = Site.formString("KUKU"); siteName = "kuku"; indexName = Common.getStoredFileName(SetUp.getTempDirectory(), "index_kuku_parse_", "html"); indexEncodeName = Common.getStoredFileName(SetUp.getTempDirectory(), "index_kuku_encode_parse_", "html"); baseURL = "http://n.kukudm.com/"; }
@Override public synchronized void parseComicURL() { System.out.print("parse the pic URL:"); for (int i = 0; i < totalPage && Run.isAlive; i++) { // 檢查下一張圖是否存在同個資料夾,若存在就跳下一張 if (!Common.existPicFile(getDownloadDirectory(), i + 2) || !Common.existPicFile(getDownloadDirectory(), i + 1)) { int endIndex = webSite.lastIndexOf("/"); String tempWebSite = webSite.substring(0, endIndex + 1) + (i + 1) + ".htm"; Common.downloadFile(tempWebSite, SetUp.getTempDirectory(), indexName, false, ""); Common.newEncodeFile(SetUp.getTempDirectory(), indexName, indexEncodeName, Encoding.GBK); String tempStr = Common.getFileString(SetUp.getTempDirectory(), indexEncodeName); String[] lines = tempStr.split("\n"); for (int count = 0; count < lines.length && Run.isAlive; count++) { String line = lines[count]; if (line.matches("(?s).*document.write(?s).*")) { String[] temp = line.split("'\"|\"|'|>"); System.out.println(baseURL + temp[3]); // replace %20 from white space in URL String frontURL = temp[3].replaceAll("\\s", "%20"); comicURL[i] = Common.getFixedChineseURL(baseURL + frontURL); // Common.debugPrintln( i + " " + comicURL[i] ); // debug // 每解析一個網址就下載一張圖 singlePageDownload(getTitle(), getWholeTitle(), comicURL[i], totalPage, i + 1, 0); break; } } } } // System.exit( 0 ); // debug }