摘要：故事的起因是上周六看中國(guó)好聲音一個(gè)周杰倫戰(zhàn)隊(duì)的學(xué)員用人工智能寫的歌詞，于是乎，我也有了這個(gè)想法，代碼的主題思路是看先生的文章，雖然最后不能寫出一首歌，但是押韻腳這事情分分鐘搞定了主題的思路，就是先抓取很多首歌曲的歌詞，利用分詞后，將分好的詞

故事的起因是上周六看《中國(guó)好聲音》,一個(gè)周杰倫戰(zhàn)隊(duì)的學(xué)員用人工智能寫的歌詞，于是乎，我也有了這個(gè)想法，代碼的主題思路是看Crossin先生的文章，雖然最后不能寫出一首歌，但是押韻腳這事情分分鐘搞定了

主題的思路，就是先抓取很多首歌曲的歌詞，利用jieba分詞后，將分好的詞按照押韻表進(jìn)行分類，最后匹配查詢就可以了

這個(gè)地方可以去網(wǎng)上搜押韻表

#引用各種需要的庫
import requests
import jieba
import re
from xpinyin import Pinyin
p = Pinyin()

RhymeIndex = [("1", ["a", "ia", "ua"]), ("2", ["ai", "uai"]), ("3", ["an", "ian", "uan"]),
              ("4", ["ang", "iang", "uang"]), ("5", ["ao", "iao"]), ("6", ["e", "o", "uo"]), ("7", ["ei", "ui"]),
              ("8", ["en", "in", "un"]), ("9", ["eng", "ing", "ong", "iong"]), ("10", ["er"]), ("11", ["i"]),
              ("12", ["ie", "ye"]), ("13", ["ou", "iu"]), ("14", ["u"]), ("16", ["ue"]), ("15", ["qu", "xu", "yu"])]

RhymeDct = {"ui": "7", "uan": "3", "ian": "3", "iu": "13", "en": "8", "ue": "16", "ing": "9", "a": "1", "ei": "7",
            "eng": "9", "uo": "6", "ye": "12", "in": "8", "ou": "13", "ao": "5", "uang": "4", "ong": "9", "ang": "4",
            "ai": "2", "ua": "1", "uai": "2", "an": "3", "iao": "5", "ia": "1", "ie": "12", "iong": "9", "i": "11",
            "er": "10", "e": "6", "u": "14", "un": "8", "iang": "4", "o": "6", "qu": "15", "xu": "15", "yu": "15"}

分好的詞與押韻表對(duì)應(yīng)起來，舉個(gè)栗子，比如“沒有”對(duì)應(yīng)的是“7-13”，就等于你給每個(gè)詞都貼了一個(gè)標(biāo)簽，這樣你以后想搜索的時(shí)候，就可以根據(jù)標(biāo)簽找到這些詞了

def _analysis_words(words):
        word_py =p.get_pinyin((u"{}".format(words)))
        lst_words = word_py.split("-")
        r = []
        for i in lst_words:
            while True:
                if not i:
                    break
                token = RhymeDct.get(i, None)
                if token:
                    r.append(token)
                    break
                i = i[1:]
        if len(r) == len(words):
            return "-".join(r)
# print(_analysis_words("兄弟"))

這個(gè)地方數(shù)據(jù)爬取的越多，肯定你的詞庫就越壯大，后面分詞也越高，我這里只爬取了3首歌曲的歌詞，并且最后是存儲(chǔ)到txt中，當(dāng)然，放數(shù)據(jù)庫里就更好了

def GetKeyword():
    #歌曲列表
    # url = "http://music.163.com/api/playlist/detail?id=808976784"
    # req = requests.get(url)
    # data = req.json()
    # print(data["result"]["tracks"] )
    # tracks =data["result"]["tracks"]  #歌曲列表
    tracks=["431795900","33850315","430053482"]
    #寫入記事本文件
    with open("keyword.txt","a") as f:
        f.write("[")
        for i in tracks:
            print(111)
            #歌詞
            # lrcurl = "http://music.163.com/api/song/lyric?os=pc&id="+str(i["id"])+"&lv=-1&kv=-1&tv=-1"
            lrcurl = "http://music.163.com/api/song/lyric?os=pc&id="+str(i)+"&lv=-1&kv=-1&tv=-1"
            lrcreq = requests.get(lrcurl)
            dt = lrcreq.json()
            lrc=re.sub(u"[.*?]", "", dt["lrc"]["lyric"])
            #jieba分詞
            seg_list = list(jieba.cut(lrc, cut_all=True))
            for i in seg_list:
                #加入判斷，只寫入2個(gè)字組成的詞
                if len(i)==2:
                    #寫入格式：{"7-13":"追求"}
                    if _analysis_words(i)!=None:
                        f.write("{""+_analysis_words(i)+"":""+i+""},")
        f.write("]")
        f.close()
       

GetKeyword()

def Findkey(str):
    result={}
    with open("keyword.txt", "r") as f:
        # print(f.readlines())
        list=eval(f.readlines()[0])
        for item in list:
            if item.get(str):
                key=item.get(str)
                number=result.get(key)
                #如果一個(gè)詞出現(xiàn)多次，進(jìn)行次數(shù)累加，用來表示頻次
                if number !=None and number>=1:
                    result[key]=number+1
                else:
                    result.update({key:1})
        f.close()
        print(result) 

key=input("請(qǐng)輸入關(guān)鍵詞:")
str=_analysis_words(key)
print("匹配押韻的詞：")
Findkey(str)

# hello 大家好，我的名字叫離島
# 沒事愛在博客寫寫，這感覺讓我愜愜
# 寫代碼不是男生的事，女生不是只能做測(cè)試
# 熱愛編碼，沒有辦法
# 他們都叫我是熱愛編碼的Coding女生