@Override
public void parseComicURL() { // parse URL and save all URLs in comicURL //
// 先取得前面的下載伺服器網址
String allPageString = Common.getFileString(SetUp.getTempDirectory(), indexName);
Common.debugPrint("開始解析這一集有幾頁 : ");
int beginIndex = allPageString.indexOf("name=\"selectb\"");
beginIndex = allPageString.indexOf(">", beginIndex) + 1;
int endIndex = allPageString.indexOf("</select>", beginIndex);
String tempString = allPageString.substring(beginIndex, endIndex);
totalPage = tempString.split("<option").length - 1;
Common.debugPrintln("共 " + totalPage + " 頁");
comicURL = new String[totalPage];
String[] comicPageURL = new String[totalPage];
beginIndex = endIndex = 0;
for (int i = 0; i < totalPage && Run.isAlive; i++) {
beginIndex = allPageString.indexOf("value=", beginIndex);
beginIndex = allPageString.indexOf("\"", beginIndex) + 1;
endIndex = allPageString.indexOf("\"", beginIndex);
comicPageURL[i] = baseURL + allPageString.substring(beginIndex, endIndex);
}
String picURL = "";
for (int p = 0; p < totalPage; p++) {
if (!Common.existPicFile(getDownloadDirectory(), p + 1)
|| !Common.existPicFile(getDownloadDirectory(), p + 2)) {
allPageString = getAllPageString(comicPageURL[p]);
beginIndex = allPageString.indexOf("id=picwin");
beginIndex = allPageString.indexOf("src=", beginIndex);
beginIndex = allPageString.indexOf("\"", beginIndex) + 1;
endIndex = allPageString.indexOf("\"", beginIndex);
comicURL[p] = Common.getFixedChineseURL(allPageString.substring(beginIndex, endIndex));
// Common.debugPrintln( ( p + 1 ) + " " + comicURL[p] ); // debug
// 每解析一個網址就下載一張圖
singlePageDownload(getTitle(), getWholeTitle(), comicURL[p], totalPage, p + 1, 0);
}
}
// System.exit( 0 ); // debug
}
@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
}
@Override
public void parseComicURL() { // parse URL and save all URLs in comicURL //
// 先取得前面的下載伺服器網址
initNewData();
String allPageString = Common.getFileString(SetUp.getTempDirectory(), indexName);
Common.debugPrint("開始解析這一集有幾頁 : ");
if (tsukkomiMode) {
int beginIndex = 0;
int endIndex = 0;
String listURL = webSite;
List<String> tagNameList = new ArrayList<String>();
if (webSite.matches(".*/")) {
listURL = webSite.substring(0, webSite.length() - 1);
}
if (isRssPage()) {
print("is RSS page : " + listURL);
outputNewListFile(listURL);
tagNameList = getTagNameList(listURL);
for (int i = 0; i < tagNameList.size(); i++) // 作品列表
{
String tagName = tagNameList.get(i);
handleSingleTitle(tagName);
}
} else // ex.
// http://manhua.dmzj.com/tags/category_search/0-0-0-all-0-0-1-447.shtml#category_nav_anchor
{
print("is Normal List Page : " + webSite);
if (webSite.indexOf("/update_") > 0) {
handleAllUpdatePage();
} else if (webSite.indexOf("/rank/") > 0) {
handleAllRankPage();
}
}
System.exit(0);
}
// 取得所有位址編碼代號
int beginIndex = allPageString.indexOf("'[") + 2;
int endIndex = allPageString.indexOf("\"]", beginIndex) + 1;
String allCodeString = allPageString.substring(beginIndex, endIndex);
totalPage = allCodeString.split("\",\"").length;
Common.debugPrintln("共 " + totalPage + " 頁");
comicURL = new String[totalPage];
refers = new String[totalPage];
// 取得位址編碼代號的替換字元
beginIndex = allPageString.indexOf(",'", endIndex) + 2;
endIndex = allPageString.indexOf("'.", beginIndex);
String allVarString = allPageString.substring(beginIndex, endIndex);
String[] varTokens = allVarString.split("\\|");
for (int i = 0; i < varTokens.length; i++) {
Common.debugPrintln(i + " " + varTokens[i]); // test
}
// System.exit( 0 );
String basePicURL = "http://images.dmzj.com/"; // "http://images.manhua.178.com/";
String[] codeTokens = allCodeString.split("\",\"");
codeTokens = getRealCodeTokens(codeTokens, varTokens);
String firstCode = codeTokens[0].replaceAll("\"", "");
String firstPicURL = "";
Common.debugPrintln("第一張編碼：" + firstCode);
firstPicURL = basePicURL + Common.getFixedChineseURL(getDecodeURL(firstCode));
firstPicURL = firstPicURL.replaceAll("\\\\", "");
Common.debugPrintln("第一張圖片網址：" + firstPicURL);
// System.exit( 0 );
String[] picNames = new String[totalPage];
for (int i = 0; i < picNames.length; i++) {
codeTokens[i] = codeTokens[i].replaceAll("\"", "");
beginIndex = codeTokens[i].lastIndexOf("/") + 1;
endIndex = codeTokens[i].length(); // .lastIndexOf( "\"" );
// Common.debugPrintln( codeTokens[i] + " " + beginIndex + " " + endIndex );
picNames[i] =
Common.getFixedChineseURL(getDecodeURL(codeTokens[i].substring(beginIndex, endIndex)));
// System.exit( 0 ); // debug
}
endIndex = firstPicURL.lastIndexOf("/") + 1;
String parentPicURL = firstPicURL.substring(0, endIndex);
for (int i = 0; i < codeTokens.length && Run.isAlive; i++) {
comicURL[i] = parentPicURL + picNames[i]; // 存入每一頁的網頁網址
refers[i] = webSite;
// Common.debugPrintln( ( i + 1 ) + " " + comicURL[i] ); // debug
}
// System.exit( 0 ); // debug
}
