From bbb7960d5174658f70d56383bd563503edfcdd32 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=9E=AB=E8=B0=B7=E5=89=91=E4=BB=99?= <mapaler@163.com>
Date: Sun, 16 Jun 2019 16:34:45 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BF=AE=E6=94=B9=E6=80=AA=E7=89=A9=E4=BF=A1?=
 =?UTF-8?q?=E6=81=AF=E5=86=85=E6=96=87=E4=BB=B6=E4=BD=8D=E7=BD=AE?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .gitignore                                 |  3 +-
 monsters-info/extractByNode.js             | 67 ++++++++++------------
 monsters-info/extract_CHT.js               | 48 ++++++++++++++++
 monsters-info/{ => official-API}/test.html |  0
 monsters-info/提取中文数据.bat       |  7 +++
 5 files changed, 86 insertions(+), 39 deletions(-)
 create mode 100644 monsters-info/extract_CHT.js
 rename monsters-info/{ => official-API}/test.html (100%)
 create mode 100644 monsters-info/提取中文数据.bat

diff --git a/.gitignore b/.gitignore
index 629b2932..412af3b1 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1 +1,2 @@
-monsters-info/Download-pad.skyozora.com
\ No newline at end of file
+/monsters-info/Download-pad.skyozora.com
+/monsters-info/opencc
diff --git a/monsters-info/extractByNode.js b/monsters-info/extractByNode.js
index 8b12350b..621a60c4 100644
--- a/monsters-info/extractByNode.js
+++ b/monsters-info/extractByNode.js
@@ -1,40 +1,31 @@
 var fs = require('fs');
+var officialAPI = ["ja","en","ko"]; //来源于官方API
+var custom = ["cht","chs"]; //来源于自定义文件
 
-console.log('正在读取日文怪物信息');
-var ja_json = fs.readFileSync("./ja.json", 'utf-8'); //使用同步读取
-var ja = JSON.parse(ja_json);//将字符串转换为json对象
-var msja = ja.card;
-console.log('正在读取英文怪物信息');
-var en_json = fs.readFileSync("./en.json", 'utf-8'); //使用同步读取
-var en = JSON.parse(en_json);//将字符串转换为json对象
-var msen = en.card;
-console.log('正在读取韩文怪物信息');
-var ko_json = fs.readFileSync("./ko.json", 'utf-8'); //使用同步读取
-var ko = JSON.parse(ko_json);//将字符串转换为json对象
-var msko = ko.card;
-var mArr = [];
+var cards = officialAPI.map(function(code){
+	console.log("正在读取官方 " + code + " 信息");
+	var json = fs.readFileSync("official-API/" + code +".json", 'utf-8'); //使用同步读取
+	var card = JSON.parse(json).card;//将字符串转换为json对象
+	return card;
+})
 
-for (var mi=0;mi<msja.length;mi++)
+var mainCard = cards[0]; //数据的主要card
+var mArr = []; //储存输出内容
+for (var mi=0;mi<mainCard.length;mi++)
 {
-	var m = msja[mi],m2 = msen[mi],m3 = msko[mi];
+	var m = mainCard[mi];
 	if (m[0] != mi) //id超了，都是些怪物了
 	{
 		break;
 	}else
 	{
-		if (m2[0] != m[0]){m2 = null;} //ID不一致时则没有内容
-		if (m3[0] != m[0]){m3 = null;} //ID不一致时则没有内容
-
 		//名字
-		var nameObj = {
-			ja:m[1],
-			//en:((m2 && !/^\*+/.test(m2[1]))?m2[1]:""), //没有数据，或者名字是星号都为空
-			//ko:((m3 && !/^\*+/.test(m3[1]))?m3[1]:""),
-		}
-		if (m2 && !/^\*+/.test(m2[1]))
-			nameObj["en"] = m2[1];
-		if (m3 && !/^\*+/.test(m3[1]))
-			nameObj["ko"] = m3[1];
+		var nameObj = {};
+		officialAPI.forEach(function(code,idx){
+			var _m = cards[idx][mi];
+			if (_m && !/^\*+/.test(_m[1])) //没有数据，或者名字是星号，则为空
+				nameObj[code] = _m[1];
+		})
 
 		//类型
 		var type = [m[5]];
@@ -65,18 +56,18 @@ for (var mi=0;mi<msja.length;mi++)
 	}
 }
 
+var cards_c = custom.map(function(code){
+	console.log("正在读取自定义 " + code + " 信息");
+	var json = fs.readFileSync("custom/" + code +".json", 'utf-8'); //使用同步读取
+	var card = JSON.parse(json);//将字符串转换为json对象
+	return card;
+})
 
-console.log('正在读取繁体中文怪物信息');
-var CHTtext = fs.readFileSync("CHT.json", 'utf-8'); //使用同步读取
-console.log('正在读取简体中文怪物信息');
-var CHStext = fs.readFileSync("CHS.json", 'utf-8'); //使用同步读取
-var CHT = JSON.parse(CHTtext);//将字符串转换为json对象
-var CHS = JSON.parse(CHStext);//将字符串转换为json对象
-
-CHT.forEach(function(cm,idx){
-	var m = mArr[cm.id];
-	m.name["cht"] = cm.name;
-	m.name["chs"] = CHS[idx].name;
+cards_c.forEach(function(card,cidx){ //每个文件循环
+	card.forEach(function(cm,idx){ //每个文件内的名字循环
+		var m = mArr[cm.id];
+		m.name[custom[cidx]] = cm.name;
+	});
 });
 
 var str = JSON.stringify(mArr);
diff --git a/monsters-info/extract_CHT.js b/monsters-info/extract_CHT.js
new file mode 100644
index 00000000..dfd7a314
--- /dev/null
+++ b/monsters-info/extract_CHT.js
@@ -0,0 +1,48 @@
+var fs = require('fs');
+var sourceFolder = "Download-pad.skyozora.com/pad.skyozora.com";
+var outJSON = "custom/CHT.json";
+var path = require('path');//解析需要遍历的文件夹
+
+//根据文件路径读取文件，返回文件列表
+fs.readdir(sourceFolder,function(err,files){
+	if(err){
+		console.warn(err);
+	}else{
+		//遍历读取到的文件列表
+		var monArr = [];
+		files.forEach(function(filename){
+			var searchID = /^(\d+)\.html$/i.exec(filename);
+			if (searchID)
+			{
+				var filepath = path.join(sourceFolder, filename);//合并当前文件的路径
+				var htmlText = fs.readFileSync(filepath, 'utf-8'); //使用同步读取
+				var searchName = /<h2 .+>\s*?([\s\S]+)\s*?<\/h2>/igm.exec(htmlText);
+				try
+				{
+					var m = {
+						id:searchID[1],
+						name:searchName[1].replace("\n",""),
+					}
+					monArr.push(m);
+					if (monArr.length % 100 == 0)
+					{
+						console.log("已读取 " + monArr.length + " 个网页");
+					}
+				}catch(e)
+				{
+					console.log(filename,e)
+				}
+			}
+		});
+		monArr.sort(function(a,b){
+			return a.id - b.id;
+		})
+		var str = JSON.stringify(monArr);
+		fs.writeFile(outJSON,str,function(err){
+			if(err){
+				console.error(err);
+			}
+			console.log("---繁体中文导出成功，共 " + monArr.length + " 个名称---");
+		})
+	}
+});
\ No newline at end of file
diff --git a/monsters-info/test.html b/monsters-info/official-API/test.html
similarity index 100%
rename from monsters-info/test.html
rename to monsters-info/official-API/test.html
diff --git a/monsters-info/提取中文数据.bat b/monsters-info/提取中文数据.bat
new file mode 100644
index 00000000..b5706603
--- /dev/null
+++ b/monsters-info/提取中文数据.bat
@@ -0,0 +1,7 @@
+@echo off
+echo ��ʼ��ȡ��ҳ����
+node.exe extract_CHT.js
+echo ���ڽ���������ת��Ϊ��������
+opencc\opencc.exe -i custom\CHT.json -o custom\CHS.json -c opencc\t2s.json
+echo ת�����
+pause
\ No newline at end of file