python 题目处理题目处理

import random
import string
from sparkdesk_web.core import SparkWeb
from pyhandytools.file import FileUtils
import csv
import random
import time
from nltk.corpus import wordnet as wn


def generate_synonyms(word):
    synsets = wn.synsets(word)
    synonyms = [synset.name() for synset in synsets]
    return synonyms
if __name__ == '__main__':
    conf_data = FileUtils.load_json('./conf/keys.json')

    sparkWeb = SparkWeb(
        cookie=conf_data['Cookie'],
        fd=conf_data['fd'],
        GtToken=conf_data['GtToken']
    )

    #single chat
wordlist = [ ]
quote = '用'
questionlist =[
    '白日依山尽，黄河入海流',
    '飞流直下三千尺，疑是银河落九天'
 ]
#'给我三个嫦的形近字，答案给我三个字用逗号隔开，不要陈述问题，不要解析，答案之间不能重复'
# '云母屏风烛影深，长河渐落晓星沉',
# '嫦娥应悔偷灵药，碧海青天夜夜心'
import random
import string
import re
from pypinyin import pinyin, lazy_pinyin, Style
import os
import pickle


def get_all_char_pinyin():
    path = "output2.txt"
    pinyin_dict = {}
    with open(path, "r", encoding="utf-8") as f:
        for line in f.readlines():
            ch = line.strip()
            ch_pinyin = pinyin(ch, style=Style.TONE3, heteronym=False)
            # heteronym 是否启用多音字模式
            for p_li in ch_pinyin:
                for p in p_li:
                    if p not in pinyin_dict:
                        pinyin_dict[p] = [ch]
                    else:
                        pinyin_dict[p].append(ch)
    return pinyin_dict

pinyin_dict = get_all_char_pinyin()

def getsamesoundword(s):
        # 获取同音汉字
        similarity_dict = {}
        match_char = s
        ch_pinyin = pinyin(match_char, style=Style.TONE3, heteronym=False)
        res = []
        for p_li in ch_pinyin:
            for p in p_li:
                #print(p)
                if match_char in pinyin_dict[p]:
                    pinyin_dict[p].remove(match_char)
                res.extend(pinyin_dict[p])
        #print(res)
        return res

def extract_and_replace(s):
    # 随机选择2-6个字符的索引范围
    start = random.randint(0,len(s))
    end = start + random.randint(0, len(s))
    # 提取字符串中的子串
    substring = s[start:end]
    # 用空括号替换子串
    s = s[:start] + '()' * len(substring) + s[end:]
    return [s,substring]

def replace_random_char(s):

    # 排除中英文标点符号

    exclude = set(string.punctuation + string.digits)
    # 从剩余字符中随机选取一个字符
    char = random.choice(list(set(s) - exclude))
    # 用括号替换原有位置
    s = s.replace(char, '()', 1)
    #多个字符
    # chars = [random.choice(list(set(s) - exclude)) for _ in range(2)]
    #
    # # 用括号替换原有位置
    #
    # s = ''.join(f'({char})' if chars in chars else char for char in s)
    #
    return [s,char]
def replace_duplicates(lst):#去除掉重复选项
    seen = set()
    result = []
    for item in lst:
        if item not in seen:
            seen.add(item)
            result.append(item)
        else:
            result.append('-')
    return result


import random


def random_split_string(s):
    # 随机选择一个切割点
    split_point = random.randint(1, len(s) - 1)
    # 切割字符串
    first_part = s[:split_point]
    second_part = s[split_point:]
    return first_part, second_part


def addlist2(s):
    data2 = []
    for w in questionlist:

                a1 = re.split(r'[.,、， !?]+', w)#两个句子 循环一下

                for q in a1:
                    data = []
                    answerlist = []

                    word =extract_and_replace(q)#从句子中抽取扣空 ['嫦娥应悔偷灵()', '药']
                    #print(q,word,'抽空的句子')
                    if word[1] == '':#如果抽到空的 过滤掉
                        break
                    if len(word[1]) > s:#控制题目
                        break
                    data.append(word[0])
                    for w in range(3):
                        newword = ''
                        for x in word[1]: #生成答案的相思答案
                            list = getsamesoundword(x)
                            if list:
                                #print(list,'这是list')
                                if len(list) > 0:
                                    choose =random.choice(list)
                                    #print(choose,'choose')
                                else:
                                    choose = list[0]
                            else:
                                choose='无'
                            newword+=str(choose)
                        answerlist.append(newword)
                    answerlist.append(word[1])
                    #print(answerlist,'answerlist')
                    random.shuffle(answerlist)  # 重新排列ANSWERLIST
                    answerlist = replace_duplicates(answerlist)
                    index = answerlist.index(word[1])  # 列表中找到某个元素
                    for qw in answerlist:
                        data.append(qw)
                    # 生成正确选项
                    if index == 0:
                        asd = 'a'
                    elif index == 1:
                        asd = 'b'
                    elif index == 2:
                        asd = 'c'
                    elif index == 3:
                        asd = 'd'
                    else:
                        asd = '无'
                    data.append(asd)
                    data.append(word[1])
                    #print(data,'组的题')

                    if data:
                        #print(data,'data')
                        data2.append(data)
    return data2
                    # with open("new.csv", "a", encoding='utf-8') as csvfile:
                    #     writer = csv.writer(csvfile, lineterminator='\n')
                    #     writer.writerows([data])

def addlist3(s):
    data2 = []
    for w in questionlist:
        a1 = re.split(r'[.,、， !?]+', w)  # 两个句子 循环一下
        data1 = []
        for q in a1:


            while True:
                answerlist = []
                data = []
                s1, s2 = random_split_string(q)#将一个诗句分成两段
                #print(s1, s2, 'newword')
                index = random.randint(0, len(s1) - 1)#获取第一段的一个随机汉字
                newword = getsamesoundword(s1[index])#创造一个同声字
                if len(newword) >0:
                    b1 = s1[:index] + newword[0] + s1[index + 1:]#制造一个被替换同声字的混淆答案
                else:
                    pass
                index2 = random.randint(0, len(s2) - 1)
                newword2 = getsamesoundword(s2[index2])
                if len(newword2) > 0:
                    b2 = s2[:index2] + newword2[0] + s2[index2 + 1:]
                else:
                    pass
                #print(newword, 'newword')
                if len(newword) >0 and s1[index]!=newword[0]:
                    answerlist.append(s1)
                    answerlist.append(b1)
                    answerlist.append(s2)
                    answerlist.append(b2)
                    random.shuffle(answerlist)
                    data.append('请选择两个能连成正确的诗句')
                    for x in answerlist:
                        data.append(x)
                    index_s1 = data.index(s1)
                    index_s2 = data.index(s2)
                    if index_s1 == 1:
                        asd = 'a'
                    elif index_s1 == 2:
                        asd = 'b'
                    elif index_s1 == 3:
                        asd = 'c'
                    elif index_s1 == 4:
                        asd = 'd'
                    else:
                        asd2 = '无'
                    if index_s2 == 1:
                        asd2 = 'a'
                    elif index_s2 == 2:
                        asd2 = 'b'
                    elif index_s2 == 3:
                        asd2 = 'c'
                    elif index_s2 == 4:
                        asd2 = 'd'
                    else:
                        asd2 = '无'
                    data.append(asd)
                    data.append(asd2)
                    data.append(s1+s2)

                    data2.append(data)
                    #print(data2,'打印的')

                    break

    return data2
            #print(data, 'datalist')




def addlist():

    for w in questionlist:
                data = []
                answerlist = []
                #print(replace_random_char(w))
                word =replace_random_char(w)
                print(word[1]+'的形近字，答案最多3个汉字,用逗号隔开，必须不是词语，不要陈述问题，不要解析，答案之间不能重复')
                answer = sparkWeb.chat(word[1]+'的形近字，答案只给我3个字,用逗号隔开，不可以是词语，不要陈述问题，不要解析，答案之间不能重复')
                list =  re.split(r'[.,、， !?]+', answer)
                print(list,'这是list')
                #data.append('选择对应的汉字填入古诗' + word[1])

                if answer:
                    for x in list:
                        answerlist.append(x)
                else:
                    data.append('无答案')
                answerlist.append(word[1])
                random.shuffle(answerlist)#重新排列ANSWERLIST

                index = answerlist.index(word[1])#列表中找到某个元素
                 #生成正确选项
                if index == 0:
                    choose = 'a'
                if index == 1:
                    choose = 'b'
                if index == 2:
                    choose = 'c'
                if index == 3:
                    choose = 'd'
                data.append('选择对应的汉字填入古诗中，'+word[0])
                for x in answerlist:
                    data.append(x)
                data.append(choose)
                data.append(word[1])

                with open("new.csv", "a", encoding='utf-8') as csvfile:
                    writer = csv.writer(csvfile, lineterminator='\n')
                    writer.writerows([data])


tempdata=[]
data=[]
findaldata = []


def checklist2(word): #查询是否重复
    for x in tempdata:
        #print(findaldata, word[0], x[0], '对比')
        if word[0] == x[0]:



            return 1
def checklist(word): #查询是否重复
    for x in findaldata:
        if word == x[1]:
            return 1
def getquestions():
    for i in range(2):
        item = addlist3(1)
        for x in item:
            if checklist(x) !=1:
                findaldata.append(x)

    # print(findaldata)
    while True:

        new = addlist2(1)
        if new:
            if checklist2(new[0]) == 1:
                #print('pass addlist(1)')
                pass
            else:
                #print(new,'new',len(tempdata))
                #print(new[0], 'new')
                tempdata.append(new[0])
        #print(tempdata,'tempdata')
        if len(tempdata) > 11:
            random_elements = random.sample(tempdata, 8)
            #print(random_elements,'random_elements')
            break


    for x in random_elements:
        findaldata.append(x)

    while True:
        new = addlist2(3)
        #print(new)
        if new:
            if checklist2(new[0]) != 1:
                pass
            else:
                findaldata.append(new)
        if len(findaldata) > 28:
            break

    print(findaldata,len(findaldata))