@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 = 0, endIndex = 0;
totalPage = allPageString.split("<option ").length;
Common.debugPrintln("共 " + totalPage + " 頁");
comicURL = new String[totalPage];
String picURL = "";
int p = 0; // 目前頁數
for (int i = 0; i < totalPage && Run.isAlive; i++) {
beginIndex = allPageString.indexOf("<img id");
beginIndex = allPageString.indexOf("\"", beginIndex) + 1;
endIndex = allPageString.indexOf("\"", beginIndex);
String tempURL = allPageString.substring(beginIndex, endIndex);
if (Common.isLegalURL(tempURL)) {
comicURL[p++] = tempURL;
Common.debugPrintln(p + " " + comicURL[p - 1]); // debug
// 每解析一個網址就下載一張圖
singlePageDownload(getTitle(), getWholeTitle(), comicURL[p - 1], totalPage, p, 0);
} else {
totalPage--;
}
// Common.downloadFile( comicURL[p - 1], "", p + ".jpg", false, "" );
if (p < totalPage) {
beginIndex = allPageString.indexOf("</select>");
beginIndex = allPageString.indexOf("\"", beginIndex) + 1;
endIndex = allPageString.indexOf("\"", beginIndex);
tempURL = allPageString.substring(beginIndex, endIndex);
if ("#".equals(tempURL)) {
Common.debugPrintln("THE LAST PAGE !!");
break;
}
String nextPageURL = "http://comic101.com" + tempURL;
Common.downloadFile(nextPageURL, SetUp.getTempDirectory(), indexName, false, "");
allPageString = Common.getFileString(SetUp.getTempDirectory(), indexName);
}
}
// System.exit( 0 ); // debug
}
// 將代號轉為實際字串
private String[] getRealCodeTokens(String[] codeTokens, String[] varTokens) {
String[] realCodeTokens = new String[codeTokens.length];
String tempChar = "";
for (int i = 0; i < codeTokens.length; i++) {
realCodeTokens[i] = "";
Common.debugPrintln("這次要分解的code : " + codeTokens[i]);
for (int j = codeTokens[i].length() - 1; j >= 0; j--) {
int index = -1;
// 兩個數字字元組合在一起
index = getVarIndex(codeTokens[i].charAt(j));
if (j > 0 && index >= 0) {
char c = codeTokens[i].charAt(j - 1);
if (c >= '1' && c <= '9') {
int num = Integer.parseInt(String.valueOf(c));
index += ((26 + 26 + 10) * num);
// 若之後找不到此index對應的token , 可直接用此數字字串
tempChar = "" + codeTokens[i].charAt(j);
j--;
} else {
tempChar = "";
}
} else {
tempChar = "";
}
if (index >= 0 && index < varTokens.length && !varTokens[index].equals("")) {
realCodeTokens[i] = varTokens[index] + realCodeTokens[i];
} else {
realCodeTokens[i] = "" + codeTokens[i].charAt(j) + tempChar + realCodeTokens[i];
}
// Common.debugPrintln( realCodeTokens[i] );
}
Common.debugPrintln("分解結果: " + realCodeTokens[i]);
}
// System.exit( 0 );
return realCodeTokens;
}
@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 = getAllPageString(webSite);
Common.debugPrint("開始解析這一集有幾頁 : ");
String baseURL = "http://mh2.xindm.cn";
int beginIndex = allPageString.indexOf("Array(");
beginIndex = allPageString.indexOf("\"", beginIndex);
int endIndex = allPageString.indexOf(");", beginIndex);
String tempPicString = allPageString.substring(beginIndex, endIndex);
String[] picURLs = tempPicString.split(",");
totalPage = picURLs.length;
Common.debugPrintln("共 " + totalPage + " 頁");
comicURL = new String[totalPage];
for (int i = 0; i < picURLs.length; i++) {
comicURL[i] = baseURL + picURLs[i].replaceAll("\"", "");
Common.debugPrintln("第" + (i + 1) + "頁網址：" + comicURL[i]);
}
// 須取得cookie才能下載圖片（防盜連專家....）
String[] cookies = Common.getCookieStrings(webSite, null);
String cookieString = "";
int cookieCount = 0; // 取得前兩組cookie就可以了
if (cookies[0] != null) {
cookieString =
"Hm_lvt_016bf6f495d44a067f569423ad894560=1337210178886; " + cookies[0].split(";")[0];
}
Common.debugPrintln("取得cookies：" + cookieString);
for (int p = 1; p <= totalPage && Run.isAlive; p++) {
String referURL = webSite + "?p=" + p;
// 每解析一個網址就下載一張圖
singlePageDownloadUsingSimple(
getTitle(), getWholeTitle(), comicURL[p - 1], totalPage, p, cookieString, referURL);
Common.debugPrintln((p) + " " + comicURL[p - 1] + " " + referURL); // debug
}
// System.exit(1); // debug
}
@Override
public void setParameters() {
Common.debugPrintln("開始解析各參數 :");
Common.debugPrintln("開始解析title和wholeTitle :");
if (getWholeTitle() == null || getWholeTitle().equals("")) {
String allPageString = getAllPageString(webSite);
int beginIndex = Common.getIndexOfOrderKeyword(allPageString, ">>", 4) + 2;
int endIndex = allPageString.indexOf("<", beginIndex);
String title = allPageString.substring(beginIndex, endIndex).trim();
setWholeTitle(Common.getStringRemovedIllegalChar(Common.getTraditionalChinese(title)));
}
Common.debugPrintln("作品名稱(title) : " + getTitle());
Common.debugPrintln("章節名稱(wholeTitle) : " + getWholeTitle());
}
@Override
public List<List<String>> getVolumeTitleAndUrlOnMainPage(String urlString, String allPageString) {
// combine volumeList and urlList into combinationList, return it.
List<List<String>> combinationList = new ArrayList<List<String>>();
List<String> urlList = new ArrayList<String>();
List<String> volumeList = new ArrayList<String>();
if (tsukkomiMode) {
urlList.add(urlString);
volumeList.add("tsukkomi");
combinationList.add(volumeList);
combinationList.add(urlList);
return combinationList;
}
int beginIndex = allPageString.indexOf("class=\"cartoon_online_border\"");
int endIndex = allPageString.indexOf("document.write", beginIndex);
if (urlString.indexOf("mh.") > 0) {
beginIndex = allPageString.indexOf("chapter_list");
endIndex = allPageString.indexOf("</script>", beginIndex);
}
String tempString = allPageString.substring(beginIndex, endIndex);
int volumeCount = tempString.split("href=\"").length - 1;
String volumeTitle = "";
beginIndex = endIndex = 0;
for (int i = 0; i < volumeCount; i++) {
// 取得單集位址
beginIndex = tempString.indexOf("href=\"", beginIndex) + 6;
endIndex = tempString.indexOf("\"", beginIndex);
urlList.add(baseURL + tempString.substring(beginIndex, endIndex));
// 取得單集名稱
beginIndex = tempString.indexOf(">", beginIndex) + 1;
endIndex = tempString.indexOf("<", beginIndex);
volumeTitle = tempString.substring(beginIndex, endIndex);
volumeList.add(
getVolumeWithFormatNumber(
Common.getStringRemovedIllegalChar(
Common.getTraditionalChinese(volumeTitle.trim()))));
}
totalVolume = volumeCount;
Common.debugPrintln("共有" + totalVolume + "集");
combinationList.add(volumeList);
combinationList.add(urlList);
return combinationList;
}
@Override
public List<List<String>> getVolumeTitleAndUrlOnMainPage(String urlString, String allPageString) {
// combine volumeList and urlList into combinationList, return it.
List<List<String>> combinationList = new ArrayList<List<String>>();
List<String> urlList = new ArrayList<String>();
List<String> volumeList = new ArrayList<String>();
String[] lines = allPageString.split("\n");
int beginIndex = 0;
int endIndex = 0;
String volumeURL = "";
beginIndex = allPageString.indexOf("id='comiclistn'");
endIndex = allPageString.indexOf("</table>", beginIndex);
String tempString = allPageString.substring(beginIndex, endIndex);
int volumeCount = tempString.split("<dd>").length - 1;
// 單集位址的網域名稱（有四組，可置換）
String baseVolumeURL = "http://comic.kukudm.com";
beginIndex = endIndex = 0;
for (int i = 0; i < volumeCount; i++) {
// 取得單集位址
beginIndex = tempString.indexOf("<dd>", beginIndex) + 1;
beginIndex = tempString.indexOf("'", beginIndex) + 1;
endIndex = tempString.indexOf("'", beginIndex);
volumeURL = tempString.substring(beginIndex, endIndex);
if (volumeURL.matches("http.*")) {
urlList.add(tempString.substring(beginIndex, endIndex));
} else {
urlList.add(baseVolumeURL + tempString.substring(beginIndex, endIndex));
}
// 取得單集名稱
beginIndex = tempString.indexOf(">", beginIndex) + 1;
endIndex = tempString.indexOf("<", beginIndex);
volumeList.add(
getVolumeWithFormatNumber(
Common.getStringRemovedIllegalChar(
Common.getTraditionalChinese(
tempString.substring(beginIndex, endIndex).trim()))));
}
totalVolume = volumeCount;
Common.debugPrintln("共有" + totalVolume + "集");
combinationList.add(volumeList);
combinationList.add(urlList);
return combinationList;
}
@Override
public void setParameters() {
Common.debugPrintln("開始解析各參數 :");
Common.downloadFile(webSite, SetUp.getTempDirectory(), indexName, false, "");
if (getWholeTitle() == null || getWholeTitle().equals("")) {
Common.debugPrintln("開始解析title和wholeTitle :");
String allPageString = Common.getFileString(SetUp.getTempDirectory(), indexEncodeName);
int beginIndex = allPageString.indexOf("alt=");
beginIndex = allPageString.indexOf("\"", beginIndex) + 1;
int endIndex = allPageString.indexOf("\"", beginIndex);
String tempTitleString = allPageString.substring(beginIndex, endIndex).trim();
setWholeTitle(
getVolumeWithFormatNumber(
Common.getStringRemovedIllegalChar(
Common.getTraditionalChinese(tempTitleString.trim()))));
}
Common.debugPrintln("作品名稱(title) : " + getTitle());
Common.debugPrintln("章節名稱(wholeTitle) : " + getWholeTitle());
}
public String getMainUrlFromSingleVolumeUrl(String volumeURL) {
// ex. http://www.178.com/mh/kongjuzhiyuan/16381-2.shtml轉為
// http://manhua.178.com/kongjuzhiyuan/
String allPageString = getAllPageString(volumeURL);
int beginIndex = allPageString.indexOf("g_comic_url");
beginIndex = allPageString.indexOf("\"", beginIndex) + 1;
int endIndex = allPageString.indexOf("\"", beginIndex);
String mainPageURL = baseURL + "/" + allPageString.substring(beginIndex, endIndex);
Common.debugPrintln("MAIN_URL: " + mainPageURL);
return mainPageURL;
}
@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 List<List<String>> getVolumeTitleAndUrlOnMainPage(String urlString, String allPageString) {
// combine volumeList and urlList into combinationList, return it.
List<List<String>> combinationList = new ArrayList<List<String>>();
List<String> urlList = new ArrayList<String>();
List<String> volumeList = new ArrayList<String>();
String tempString = "";
int beginIndex, endIndex;
beginIndex = allPageString.indexOf("class=\"plie\"");
endIndex = allPageString.indexOf("</ul>", beginIndex);
// 存放集數頁面資訊的字串
tempString = allPageString.substring(beginIndex, endIndex);
int volumeCount = tempString.split("href=").length - 1;
String volumeTitle = "";
beginIndex = endIndex = 0;
for (int i = 0; i < volumeCount; i++) {
// 取得單集位址
beginIndex = tempString.indexOf("href=", beginIndex);
beginIndex = tempString.indexOf("\"", beginIndex) + 1;
endIndex = tempString.indexOf("\"", beginIndex);
urlList.add(baseURL + tempString.substring(beginIndex, endIndex));
// 取得單集名稱
beginIndex = tempString.indexOf(">", beginIndex) + 1;
endIndex = tempString.indexOf("</a>", beginIndex);
volumeTitle = tempString.substring(beginIndex, endIndex);
volumeTitle = volumeTitle.replaceFirst("<br\\s+/{0,1}>", "");
volumeList.add(
getVolumeWithFormatNumber(
Common.getStringRemovedIllegalChar(
Common.getTraditionalChinese(volumeTitle.trim()))));
}
totalVolume = volumeCount;
Common.debugPrintln("共有" + totalVolume + "集");
combinationList.add(volumeList);
combinationList.add(urlList);
return combinationList;
}
public String getMainUrlFromSingleVolumeUrl(String volumeURL) {
// ex. http://comic.ck101.com/page/1749372轉為
// http://comic.ck101.com/comic/7039
String allPageString = getAllPageString(volumeURL);
int beginIndex = allPageString.lastIndexOf("class=\"page_title\"");
beginIndex = allPageString.lastIndexOf("href=", beginIndex);
beginIndex = allPageString.lastIndexOf("\"", beginIndex) + 1;
int endIndex = allPageString.lastIndexOf("\"", beginIndex);
String mainPageURL = baseURL + volumeURL.substring(beginIndex, endIndex).trim();
Common.debugPrintln("MAIN_URL: " + mainPageURL);
return mainPageURL;
}
public String getMainUrlFromSingleVolumeUrl(String volumeURL) {
// ex. http://dm.game.mop.com/primary/45489.html#pic或
// http://dm.game.mop.com/primary/45489/1.html#pic轉為
// http://dm.game.mop.com/fengmian/4827.html
int beginIndex = volumeURL.indexOf("primary");
beginIndex = volumeURL.indexOf("/", beginIndex) + 1;
int endIndex = volumeURL.indexOf("/", beginIndex);
if (endIndex < 0) {
endIndex = volumeURL.indexOf("/", beginIndex);
}
String mainPageURL = volumeURL.substring(0, endIndex) + ".html";
Common.debugPrintln("MAIN_URL: " + mainPageURL);
return mainPageURL;
}
@Override
public List<List<String>> getVolumeTitleAndUrlOnMainPage(String urlString, String allPageString) {
// combine volumeList and urlList into combinationList, return it.
List<List<String>> combinationList = new ArrayList<List<String>>();
List<String> urlList = new ArrayList<String>();
List<String> volumeList = new ArrayList<String>();
int beginIndex = allPageString.indexOf("<li><a href=\"http://www") - 1;
int endIndex = allPageString.indexOf("</table>", beginIndex);
String listString = allPageString.substring(beginIndex, endIndex);
totalVolume = allPageString.split("<li><a href=\"http://www").length - 1;
beginIndex = endIndex = 0;
for (int i = 0; i < totalVolume; i++) {
// 取得單集位址
beginIndex = listString.indexOf("http://www", beginIndex);
endIndex = listString.indexOf("\"", beginIndex);
urlList.add(listString.substring(beginIndex, endIndex));
// 取得單集名稱
beginIndex = listString.indexOf("<span", beginIndex) + 1;
beginIndex = listString.indexOf(">", beginIndex) + 1;
endIndex = listString.indexOf("<", beginIndex);
String volumeTitle = listString.substring(beginIndex, endIndex);
volumeList.add(
getVolumeWithFormatNumber(
Common.getStringRemovedIllegalChar(
Common.getTraditionalChinese(volumeTitle.trim()))));
}
Common.debugPrintln("共有" + totalVolume + "集");
combinationList.add(volumeList);
combinationList.add(urlList);
return combinationList;
}
public void print(String message) {
Common.debugPrintln(message);
}
public void showParameters() { // for debug
Common.debugPrintln("----------");
Common.debugPrintln("totalPage = " + totalPage);
Common.debugPrintln("webSite = " + webSite);
Common.debugPrintln("----------");
}
@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
}
@Override
public List<List<String>> getVolumeTitleAndUrlOnMainPage(String urlString, String allPageString) {
// combine volumeList and urlList into combinationList, return it.
List<List<String>> combinationList = new ArrayList<List<String>>();
List<String> urlList = new ArrayList<String>();
List<String> volumeList = new ArrayList<String>();
String tempString = "";
int lastPage = 0;
int beginIndex, endIndex;
urlString = urlString.split("0/0/")[0];
// 接著在迴圈內下載每一頁, 取得每一集資訊
int totalVolumeCount = 0;
String pageURL = urlString;
while (true) {
if (lastPage++ > 0) {
pageURL = urlString + "0/0/" + lastPage;
}
allPageString = getAllPageString(pageURL);
beginIndex = allPageString.indexOf("class=\"comicBox\"");
endIndex = allPageString.indexOf("class=\"fbComment\"", beginIndex);
tempString = allPageString.substring(beginIndex, endIndex);
// 代表此頁已經沒有集數了。
if (tempString.indexOf("class=\"recTitle\"") < 0) break;
// 取得存放一整頁面集數資訊
beginIndex = allPageString.indexOf("class=\"comicBox\"");
beginIndex = allPageString.indexOf("class=\"relativeRec", beginIndex);
endIndex = allPageString.indexOf("</div>", beginIndex);
tempString = allPageString.substring(beginIndex, endIndex);
int volumeCount = tempString.split("<h3").length - 1; // 單一頁面的集數
totalVolumeCount += volumeCount;
String volumeURL = "";
String volumeTitle = "";
beginIndex = endIndex = 0;
for (int j = 0; j < volumeCount; j++) {
// 取得單集位址
beginIndex = tempString.indexOf("<h3", beginIndex);
beginIndex = tempString.indexOf("href=", beginIndex);
beginIndex = tempString.indexOf("\"", beginIndex) + 1;
endIndex = tempString.indexOf("\"", beginIndex);
volumeURL = baseURL + tempString.substring(beginIndex, endIndex);
urlList.add(baseURL + tempString.substring(beginIndex, endIndex));
// 取得單集名稱
beginIndex = tempString.indexOf("title=", beginIndex);
beginIndex = tempString.indexOf("\"", beginIndex) + 1;
endIndex = tempString.indexOf("\"", beginIndex);
volumeTitle = tempString.substring(beginIndex, endIndex);
volumeList.add(
getVolumeWithFormatNumber(
Common.getStringRemovedIllegalChar(
Common.getTraditionalChinese(volumeTitle.trim()))));
Common.debugPrintln(volumeURL + " : " + volumeTitle);
}
}
Common.debugPrintln(" 共有 " + (lastPage - 1) + " 張目錄頁");
totalVolume = totalVolumeCount;
Common.debugPrintln("共有" + totalVolume + "集");
combinationList.add(volumeList);
combinationList.add(urlList);
return combinationList;
}
