fbd2XML

#include
using namespace std;
int main() {
    //原始字符串|〖 为+ | 〗为-| 【】都删除
    string uts="+HT5SS-+JP3-+CX2-+CT-阿鼻地狱+CX-+HT-+WTXT-+JP-+KG2-+CT(-ā+CT)- ｂí ｄì ｙù+KG2-+HT8.25,8.5SS-+JP5-+ZK(*2#-+HT8.5，8.75K-+CS%100,0,0,0-阿鼻：梵语译音，意为“无间”，即痛苦没有间断的意思。“阿鼻地狱”为佛教传说中八大地狱里最下层、最痛苦的地狱。+CS-+HT8.25,8.5SS-《敦煌变文集·目连缘起》：“七日之间，母身将死，堕阿鼻地狱，受无间之余殃。”元·无名氏《来生债》四折：“若不是点化真言，险堕了阿鼻地狱。”柯灵《从〈秋瑾传〉说到〈赛金花〉》：“八国联军铁蹄下的故都，烧杀淫掠，如阿鼻地狱，尽人皆知。”+HT8.5，8.75K-+CS%100,0,0,0-也比喻无法摆脱、难以忍受的痛苦境地。+CS-+HT8.25,8.5SS-冯雪峰《上饶集中营·炼狱杂记》：“但也有少数意志薄弱的……逐步上当，终至堕入阿鼻地狱。”+CS-+HT8.25,8.5SS-";
    //string uts = "+HT5SS-+JP3-+CX2-+CT-哀兵必胜+CX-+HT-+WTXT-+JP-+KG*2-+CT(-āｉ+CT)- ｂīｎɡ ｂì ｓｈèｎɡ+KG*2-+HT8.25,8.5SS-+JP5- +HT8.5，8.75K-+CS%100,0,0,0-哀兵：由于受压或遭受危难而处在悲愤中的军队。+HT8.5，8.75K-+CS%100,0,0,0-指受压迫而悲愤地奋起反抗的军队一定能胜利。常用以鼓励处于劣势的一方要建立必胜的信心和勇气。+CS-+HT8.25,8.5SS-语本《老子·六十九章》：“故抗兵相加，哀者胜矣。”+CS-+HT8.25,8.5SS-宗璞《南渡记》三章：“我们让人欺负够了，全国百姓谁不愿打！岂不闻哀兵必胜啊！”+CS-+HT8.25,8.5SS-";
    //变量
    string fins;
    string word;
    string chapter = "3-1";
    string header = " + chapter + "\" role=\"汉语辞书条目库\">"+"";
    //提取拼音
    for (int i = 0; i < uts.length(); i++) {
        if (uts[i] == '(' && uts[i + 1] == '-') {
            for (int j = i; j < i + 50; j++) {
                if (uts[j] == '+' && uts[j + 1] == 'K') {
                    pinyin = uts.substr(i + 2, j - 1 - i - 1);
                }
            }
        }
    }
    //删除废物
    pinyin.erase(std::remove(pinyin.begin(), pinyin.end(), 'C'));
    pinyin.erase(std::remove(pinyin.begin(), pinyin.end(), 'T'));
    pinyin.erase(std::remove(pinyin.begin(), pinyin.end(), '+'));
    pinyin.erase(std::remove(pinyin.begin(), pinyin.end(), '-'));
    pinyin.erase(std::remove(pinyin.begin(), pinyin.end(), ')'));
    fins = fins + pinyin + "新华成语词典";
    //提取解释
    for (int i = 0; i < uts.length(); i++) {
        if (uts[i] == 'S' && uts[i + 1] == '%' && CS100count == 0) {
            CS100count++;
            for (int j = i; j < uts.length(); j++) {
                if (countsecond == 0 && uts[j] == '+' && uts[j + 1] == 'C' && uts[j + 2] == 'S' && uts[j + 3] == '-') {
                    countsecond++;
                    text1 = uts.substr(i + 12, j - 1 - i - 11);
                }
            }
        }
    }
    fins = fins + text1+ "";  
    //提取废话，倒数第三段
    for (int i = 0; i < uts.length(); i++) {
        if (uts[i] == 'S' && uts[i + 1] == 'S') {
            countthird++;
            if (countthird == 3) {
                for (int j = i; j < uts.length(); j++) {
                    if (uts[j] == '+' && uts[j + 1] == 'H' && uts[j + 2] == 'T' && uts[j + 3] == '8' && uts[j + 4] == '.' && uts[j + 5] == '5')
                       text2 = uts.substr(i+3 , j - 1 - i - 2);
                }
            }
        }
    }
    fins = fins + text2 + "";
    //提取倒数第二段
    for (int i = 0; i < uts.length(); i++) {
        if (uts[i] == '+' && uts[i + 1] == 'C' && uts[i + 2] == 'S' && uts[i + 3] == '%' && uts[i + 4] == '1' && uts[i + 5] == '0') {
            countfourth++;
            if (countfourth == 2) {
                for (int j = i; j < uts.length(); j++) {
                    if (uts[j] == '+' && uts[j + 1] == 'C' && uts[j + 2] == 'S' && uts[j + 3] == '-') {
                        countfivth++;
                        if (countfivth == 1) {
                            text3 = uts.substr(i + 14, j - i - 14);
                        }
                    }
                }
            }
        }
    }
    fins = fins + text3 + "";
    //最后一段
    for (int i = 0; i < uts.length(); i++) {
        if (uts[i] == '+' && uts[i + 1] == 'C' && uts[i + 2] == 'S' && uts[i + 3] == '-') {
            countsixth++;
            if (countsixth == 2) {
                for (int j = i+1; j < uts.length(); j++) {
                    if (uts[j] == '+' && uts[j + 1] == 'C' && uts[j + 2] == 'S' && uts[j + 3] == '-') {
                        text4 = uts.substr(i + 18, j - i - 18);
                    }
                }
            }
        }
    }
    fins = fins + text4 + "";
    cout << fins << endl;
    return 0;
}