python将bin文件转为txt文件编码问题的解决

刚开始使用以下代码，发现报错：UnicodeDecodeError: 'utf-8' codec can't decode byte 0xa6 in position 0: invalid start byte

import gensim
import codecs


def main():
    path_to_model = 'file.bin'
    output_file = 'file.txt'
    bin2txt(path_to_model, output_file)


def bin2txt(path_to_model, output_file):
    output = codecs.open(output_file, 'w', 'utf-8')
    model = gensim.models.KeyedVectors.load_word2vec_format(path_to_model, binary=True)
    print('Done loading Word2Vec!')
    vocab = model.vocab
    for item in vocab:
        vector = list()
        for dimension in model[item]:
            vector.append(str(dimension))
        vector_str = ",".join(vector)
        line = item + "\t" + vector_str
        output.writelines(line + "\n") 
    output.close()


if __name__ == "__main__":
    main()

后来调试发现是这一句报错了：

model = gensim.models.KeyedVectors.load_word2vec_format(path_to_model, binary=True)

将这一句改为如下，成功运行：

model = gensim.models.KeyedVectors.load_word2vec_format(path_to_model, binary=False)