import jieba
from jieba.analyse import extract_tags
from sklearn.feature_extraction.text import TfidfVectorizer

jieba.load_userdict('extraDict.txt')  # 導(dǎo)入自己建立詞典

def stopwordlist():
    stopwords = [line.strip() for line in open('chinesestopwords.txt', encoding='UTF-8').readlines()]
    # ---停用詞補(bǔ)充,視具體情況而定---
    i = 0
    for i in range(19):
        stopwords.append(str(10 + i))
    # ----------------------
 
    return stopwords

def seg_word(line):
    # seg=jieba.cut_for_search(line.strip())
    seg = jieba.cut(line.strip())
    temp = ""
    counts = {}
    wordstop = stopwordlist()
    for word in seg:
        if word not in wordstop:
            if word != ' ':
                temp += word
                temp += '\n'
                counts[word] = counts.get(word, 0) + 1#統(tǒng)計(jì)每個(gè)詞出現(xiàn)的次數(shù)
    return  temp #顯示分詞結(jié)果
    #return str(sorted(counts.items(), key=lambda x: x[1], reverse=True)[:20])  # 統(tǒng)計(jì)出現(xiàn)前二十最多的詞及次數(shù)

def output(inputfilename, outputfilename):
    inputfile = open(inputfilename, encoding='UTF-8', mode='r')
    outputfile = open(outputfilename, encoding='UTF-8', mode='w')
    for line in inputfile.readlines():
        line_seg = seg_word(line)
        outputfile.write(line_seg)
    inputfile.close()
    outputfile.close()
    return outputfile

if __name__ == '__main__':
    print("__name__", __name__)
    inputfilename = 'abstract.txt'
    outputfilename = 'a1.txt'
    output(inputfilename, outputfilename)

#定義字符串
sentences = """           # 字符串很長(zhǎng)時(shí)用三個(gè)引號(hào)
Love is more than a word
it says so much.
When I see these four letters,
I almost feel your touch.
This is only happened since
I fell in love with you.
Why this word does this,
I haven't got a clue.
"""
#具體實(shí)現(xiàn)
#  將句子里面的逗號(hào)去掉,去掉多種符號(hào)時(shí)請(qǐng)用循環(huán)，這里我就這樣吧
sentences=sentences.replace(',','')   
sentences=sentences.replace('.','')   #  將句子里面的.去掉
sentences = sentences.split()         # 將句子分開(kāi)為單個(gè)的單詞，分開(kāi)后產(chǎn)生的是一個(gè)列表sentences
# print(sentences)
count_dict = {}
for sentence in sentences:
    if sentence not in count_dict:    # 判斷是否不在統(tǒng)計(jì)的字典中
        count_dict[sentence] = 1
    else:                              # 判斷是否不在統(tǒng)計(jì)的字典中
        count_dict[sentence] += 1
for key,value in count_dict.items():
    print(f"{key}出現(xiàn)了{(lán)value}次")