private void outputVolumeIndex(
String tagName,
String titleName,
String titleIntroduction,
List<String> volumeTitleList,
List<String> snsSysIDList) {
String outputDirectory = getBaseOutputDirectory();
String text = "";
int count = volumeTitleList.size();
text += "TITLE_NAME = '" + getOutputText(titleName) + "';\n";
text += "TITLE_INTRODUCTION = '" + getOutputText(titleIntroduction) + "';\n";
text += "VOLUME_LIST = new Array( ";
for (int i = 0; i < count; i++) {
if (i > 0) text += ", ";
text +=
"'"
+ getOutputText(volumeTitleList.get(i))
+ "', "
+ "'"
+ getVolumeID(snsSysIDList.get(i))
+ "'";
}
text += "\n);\n";
Common.outputFile(text, outputDirectory, tagName + ".js");
}
private void buildIndexFile(String tagName) {
String dirPath = getBaseOutputDirectory() + tagName + Common.getSlash();
String path = "";
String text = "";
List<String> volumeTagList = new ArrayList<String>();
File dir = new File(dirPath); // 你的log檔路徑
File fileList[] = dir.listFiles(); // 得出檔案清單
String volumeTitle = "";
// 取得代號清單
for (int i = 0; i < fileList.length; i++) {
if (fileList[i].isFile()) { // 過濾檔案
String[] temps = fileList[i].toString().split("\\\\");
String volumeTag = temps[temps.length - 1].split("\\.")[0];
if (!volumeTag.matches("comment")) volumeTagList.add(volumeTag);
// print(i + " TAG : " + volumeTag);
}
}
for (int i = 0; i < volumeTagList.size(); i++) {
path = dirPath + volumeTagList.get(i) + ".js";
text = Common.getFileString(path);
if (text.split("'").length <= 1) continue;
volumeTitle = text.split("'")[1];
}
System.exit(0);
}
private void handleAllUpdatePage() {
for (int i = 0; i < 10; i++) {
String listURL = "http://manhua.dmzj.com/update_" + (i + 1) + ".shtml";
List<String> tagNameList = getTagNameList(listURL);
for (int j = 0; j < tagNameList.size(); j++) {
String tagName = tagNameList.get(j);
handleSingleTitle(tagName);
}
}
}
private boolean needUpdate(String tagName, List<String> volumeTitleList) {
if (volumeTitleList.size() == 0) return false;
String text = Common.getFileString(getBaseOutputDirectory(), tagName + ".js");
int lastVolumeIndex = volumeTitleList.size() - 1;
String lastVolumeTitle = volumeTitleList.get(lastVolumeIndex);
// 如果目錄裡面找不到最後一集，代表需要更新
return (text.indexOf(lastVolumeTitle) < 0);
}
private List<String> getTagNameList(String url) {
int beginIndex = 0;
int endIndex = 0;
int index = 0;
List<String> urlList = new ArrayList<String>();
String temp = "";
String dummyTagName = "ghdxj";
Common.deleteFile(getBaseOutputDirectory(), dummyTagName + ".js");
Common.deleteFolder(getBaseOutputDirectory() + dummyTagName);
urlList.add(dummyTagName); // 因為第一個都會取得錯誤的評論資料，所以想把錯都推給東方
String allPageString = getAllPageString(url);
while (true) {
beginIndex = allPageString.indexOf(" href=", beginIndex);
if (beginIndex < 0) break;
beginIndex = allPageString.indexOf("=", beginIndex) + 2;
if (beginIndex < 0) break;
temp = allPageString.substring(beginIndex, beginIndex + 30);
if (temp.indexOf(baseURL) >= 0) {
// print("with BASE");
// ex. href='http://manhua.dmzj.com/lianaibaojun/
beginIndex = allPageString.indexOf(".com", beginIndex);
if (beginIndex < 0) break;
beginIndex = allPageString.indexOf("/", beginIndex);
if (beginIndex < 0) break;
}
beginIndex++; // 從"/"之後開始
endIndex = allPageString.indexOf("/", beginIndex);
if (endIndex < 0) break;
temp = allPageString.substring(beginIndex, endIndex);
boolean existed = false;
for (int i = 0; i < urlList.size(); i++) {
if (urlList.get(i).equals(temp)) {
existed = true;
break;
}
}
if (existed || isIllegalPage(temp)) {
continue;
}
urlList.add(temp);
// print("" + index + " : " + temp);
index++;
beginIndex = endIndex;
}
return urlList;
}
private void handleAllRankPage() {
String[] urlList =
new String[] {
"http://manhua.dmzj.com/rank/total-list-",
"http://manhua.dmzj.com/rank/yiwanjie/total-list-",
"http://manhua.dmzj.com/rank/gaoxiao/total-list-",
"http://manhua.dmzj.com/rank/shaonian/total-list-"
};
for (int k = 0; k < urlList.length; k++) {
String baseListURL = urlList[k];
for (int i = 0; i < 5; i++) {
String listURL = baseListURL + (i + 1) + ".shtml";
List<String> tagNameList = getTagNameList(listURL);
for (int j = 0; j < tagNameList.size(); j++) {
String tagName = tagNameList.get(j);
handleSingleTitle(tagName);
}
}
}
}
private void outputVolumeComment(
String tagName,
String volumeTitle,
String fileName,
String siteName,
List<String> commentList) {
String text = "";
text += "VOLUME_TITLE = '" + volumeTitle + "';\n";
text += siteName + " = new Array( \n";
for (int i = 0; i < commentList.size(); i++) {
if (i > 0) {
text += ", ";
}
text += "'" + commentList.get(i) + "'";
}
text += "\n);";
String outputDirectory = getBaseOutputDirectory() + tagName + Common.getSlash();
Common.outputFile(text, outputDirectory, fileName + ".js");
}
@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
}
private void outputMainListFile(boolean stepByStepMode) {
List<String> tagList = new ArrayList<String>();
List<String> nameList = new ArrayList<String>();
List<String> lastVolumeTitleList = new ArrayList<String>();
List<String> lastVolumeIDList = new ArrayList<String>();
String name = "";
String path = "";
String text = "";
File dir = new File(getBaseOutputDirectory()); // 你的log檔路徑
File fileList[] = dir.listFiles(); // 得出檔案清單
// 取得代號清單
for (int i = 0; i < fileList.length; i++) {
if (fileList[i].isDirectory()) { // 過濾檔案
String[] temps = fileList[i].toString().split("\\\\");
name = temps[temps.length - 1];
tagList.add(name);
// print(i + " TAG : " + name);
}
}
// 取得名稱清單
for (int i = 0; i < tagList.size(); i++) {
path = getBaseOutputDirectory() + tagList.get(i) + ".js";
text = Common.getFileString(path);
// print("------------" + text + "------------end");
String[] temps = text.split("'");
if (temps.length <= 1) {
// buildIndexFile(tagList.get(i));
continue;
}
name = temps[1]; // 取第一個''資料字串
nameList.add(name);
// print(i + " NAME : " + name);
int beginIndex = 0;
int endIndex = 0;
String temp = "";
if (stepByStepMode) // 新的放後面
{
beginIndex = text.indexOf(");", beginIndex) - 2;
endIndex = text.lastIndexOf("'", beginIndex);
beginIndex = text.lastIndexOf("'", endIndex - 2) + 1;
temp = text.substring(beginIndex, endIndex);
lastVolumeTitleList.add(temp);
print("文件中最新一集: " + temp);
beginIndex = text.indexOf(");", endIndex + 1) + 1;
endIndex = text.lastIndexOf("'", beginIndex);
beginIndex = text.lastIndexOf("'", endIndex - 2) + 1;
temp = text.substring(beginIndex, endIndex);
lastVolumeIDList.add(temp);
} else // 新的放前面
{
beginIndex = text.indexOf("new Array(", beginIndex);
beginIndex = text.indexOf("'", beginIndex) + 1;
endIndex = text.indexOf("'", beginIndex);
temp = text.substring(beginIndex, endIndex);
lastVolumeTitleList.add(temp);
beginIndex = text.indexOf("'", endIndex + 1) + 1;
endIndex = text.indexOf("'", beginIndex);
temp = text.substring(beginIndex, endIndex);
lastVolumeIDList.add(temp);
}
// print(i + " VOLUME : " + temp);
}
List<List<String>> combinationList = new ArrayList<List<String>>();
combinationList.add(nameList);
combinationList.add(tagList);
combinationList.add(lastVolumeTitleList);
combinationList.add(lastVolumeIDList);
outputListFile(combinationList, "MAIN_LIST", mainListFileName);
}
private void handleSingleTitle(String tagName) {
int beginIndex = 0;
int endIndex = 0;
String titleURL = Common.getRegularURL(baseURL + "/" + tagName);
String titleText = getAllPageString(titleURL);
// 取得標題列表和網址列表
tsukkomiMode = false;
String titleName = getTitleOnMainPage(titleURL, titleText);
if (titleName == null) {
print("無效的作品主頁網址: " + titleURL);
return;
}
List<List<String>> combinationList = getVolumeTitleAndUrlOnMainPage(titleURL, titleText);
List<String> volumeTitleList = combinationList.get(0);
List<String> volumeUrlList = combinationList.get(1);
tsukkomiMode = true;
// List<String> snsSysIDList = new ArrayList<String>(); // sns_sys_id
// List<String> snsViewPointTokenList = new ArrayList<String>(); // sns_view_point_token
String snsSysID = "";
String snsViewPointToken = "";
boolean stepByStepMode = false;
String lastVolumeID = getLastVolumeID(titleText);
String lastVolumeTitle = getLastVolumeTitle(titleText);
// 用於main_list.js
newTitleList.add(titleName);
newTagList.add(tagName);
newVolumeTitleList.add(lastVolumeTitle);
newVolumeDirList.add(lastVolumeID);
// 如果不需要更新，就跳過往下個去做
if (!needUpdate(tagName, volumeTitleList)) {
int lastIndex = volumeTitleList.size() - 1;
if (lastIndex < 0 && titleText.indexOf("g_last_chapter_id") > 0) {
print("集數列表因為版權而拿掉 , 需要一集一集慢慢爬");
stepByStepMode = true;
} else if (lastIndex < 0) {
print("跳過 , 因為 " + titleName + "[" + tagName + "] 沒有任何集數 ");
return;
} else {
print(
"跳過 , 因為 " + titleName + "[" + tagName + "] 已有最新集數: " + volumeTitleList.get(lastIndex));
return;
}
}
String titleIntroduction = getTitleIntroduction(titleText);
handleTitlePic(tagName, titleText);
if (!stepByStepMode
|| !new File(getBaseOutputDirectory() + tagName + Common.getSlash() + "comment.js")
.exists()) {
handleTitleComment(tagName, titleText);
}
int volumeCount = volumeUrlList.size();
int existedVolumeCount = getExistedVolumeCount(tagName);
// print("" + tagName + ":" + volumeCount + "," + existedVolumeCount);
// System.exit(0);
// 取得每個集數的評論列表
for (int j = existedVolumeCount; j < volumeCount && !stepByStepMode; j++) // 某個作品的集數列表
{
String volumeURL = volumeUrlList.get(j);
String volumeText = getAllPageString(volumeURL);
String volumeTitle = volumeTitleList.get(j);
snsSysID = handleSingleVolume(tagName, titleName, titleIntroduction, volumeTitle, volumeText);
}
String nowVolumeID = lastVolumeID;
while (stepByStepMode) {
String volumeURL = baseURL + "/" + tagName + "/" + nowVolumeID + ".shtml";
String volumeText = getAllPageString(volumeURL);
beginIndex = volumeText.indexOf("g_chapter_name");
beginIndex = volumeText.indexOf("\"", beginIndex) + 1;
endIndex = volumeText.indexOf("\"", beginIndex);
String volumeTitle = volumeText.substring(beginIndex, endIndex);
print("正要處理的集數: " + volumeTitle + " : " + volumeURL);
snsSysID = handleSingleVolume(tagName, titleName, titleIntroduction, volumeTitle, volumeText);
nowVolumeID = getPreviousVolumeID(volumeText);
if (nowVolumeID == null) break;
}
// outputMainListFile(stepByStepMode);
}
