jieba分割热词，统计频率，以及停用词

import jieba
from collections import Counter

if __name__ == '__main__':
    filehandle = open("boke.txt", "r", encoding='utf-8',errors='ignore');
    mystr = filehandle.read()
    seg_list = jieba.cut(mystr)  # 默认是精确模式
    print(seg_list)
    # all_words = cut_words.split()
    # print(all_words)
    stopwords = {}.fromkeys([line.rstrip() for line in open("stop.txt", "r", encoding='utf-8',errors='ignore')])
    c = Counter()
    for x in seg_list:
        if x not in stopwords:
            if len(x) > 1 and x != '
':
                c[x] += 1
    print('
词频统计结果：')
    for (k, v) in c.most_common(50):  # 输出词频最高的前两个词
        print("%s:%d" % (k, v))

    # print(mystr)
    filehandle.close();
    # seg2 = jieba.cut("好好学学python，有用。", cut_all=False)
    # print("精确模式（也是默认模式）：", ' '.join(seg2))

　　参考了龙哥的代码。自己代码总是出现转码问题