读取bdict格式文件并转化为txt

bdict格式是百度输入法的词库文件，那么怎么看里面的内容呢？ 这就需要用到bdict到txt的转化。

下载：百度输入法-词库列表-餐饮

比如下载“菜名大全” 文件名：dict_file_734_20111227170031_1.0.0.bdict

文件大小134924字节

转换代码参考这篇文档：【搜狗&百度词库】.bdict文件与.scel转txt_scel文件在线-CSDN博客

import struct
import binascii
 
class Baidu(object):
    def __init__(self, originfile):
        self.originfile = originfile
        self.lefile = originfile + '.le'
        self.txtfile = originfile[0:(originfile.__len__()-5)] + 'txt'
        self.buf = [b'0' for x in range(0,2)]
        self.listwords = [] 
    # 字节流大端转小端
    def be2le(self):
        of = open(self.originfile,'rb')
        lef = open(self.lefile, 'wb')
        contents = of.read()
        contents_size = contents.__len__()
        mo_size = (contents_size % 2)
        # 保证是偶数
        if mo_size > 0:
            contents_size += (2-mo_size)
            contents += contents + b'0000'
        # 大小端交换
        for i in range(0, contents_size, 2):
            self.buf[1] = contents[i]
            self.buf[0] = contents[i+1]
            le_bytes = struct.pack('2B', self.buf[0], self.buf[1])
            lef.write(le_bytes)
        print('写入成功转为小端的字节流')
        of.close()
        lef.close()
    def le2txt(self):
        lef = open(self.lefile, 'rb')
        txtf = open(self.txtfile, 'w')
        # 以字符串形式读取转成小端后的字节流，百度词典的起始位置为0x350
        le_bytes = lef.read().hex()[0x350:]
        i = 0
        while i<len(le_bytes):
            result = le_bytes[i:i+4]
            i+=4
            # 将所有字符解码成汉字，拼音或字符
            content = binascii.a2b_hex(result).decode('utf-16-be')
            # 判断汉字
            if '\u4e00' <= content <= '\u9fff':
                self.listwords.append(content)
            else:
                if self.listwords:
                    word = ''.join(self.listwords)
                    txtf.write(word + '\n')
                self.listwords = []
        print('写入txt成功')
        lef.close()
        txtf.close()
if __name__ == '__main__':
    path = '你的.bdict文件'
    bd = Baidu(path)
    bd.be2le()
    bd.le2txt()

略微修改了，提高了效率，降低了磁盘写操作频率，可以在命令行执行时跟需要转换的文件名：

import struct
import binascii
import sys

class Baidu(object):
    def __init__(self, originfile):
        self.originfile = originfile
        self.lefile = originfile + '.le'
        self.txtfile = originfile[0:(originfile.__len__()-5)] + 'txt'
        self.buf = [b'0' for x in range(0,2)]
        self.listwords = [] 
    # 字节流大端转小端
    def be2le(self):
        of = open(self.originfile,'rb')
        lef = open(self.lefile, 'wb')
        contents = of.read()
        contents_size = contents.__len__()
        mo_size = (contents_size % 2)
#         print("====mozie", mo_size)
        # 保证是偶数
        if mo_size > 0:
            contents_size += (2-mo_size)
            contents += contents + b'0000'
        mo_size = (contents_size % 2)
#         print("====mozie", mo_size)
        # 大小端交换
        tmp = b""
        for i in range(0, contents_size, 2):
            self.buf[1] = contents[i]
            self.buf[0] = contents[i+1]
            le_bytes = struct.pack('2B', self.buf[0], self.buf[1])
            tmp = tmp + le_bytes
        lef.write(tmp)
        print('写入成功转为小端的字节流')
        of.close()
        lef.close()
    def le2txt(self):
        lef = open(self.lefile, 'rb')
        txtf = open(self.txtfile, 'w')
        # 以字符串形式读取转成小端后的字节流，百度词典的起始位置为0x350
        le_bytes = lef.read().hex()[0x350:]
  
        print(f'====len bytes of lefile:{len(le_bytes)}')
        i = 0
        tmpword = ""
        while i<len(le_bytes):
            result = le_bytes[i:i+4]
            i+=4
            # 将所有字符解码成汉字，拼音或字符
            content = binascii.a2b_hex(result).decode('utf-16-be')
#             print(content)
            # 判断汉字
            if '\u4e00' <= content <= '\u9fff':
                self.listwords.append(content)
            else:
                if self.listwords:
                    word = ''.join(self.listwords)
                    # txtf.write(word + '\n')
                    word = word + '\n'
                    tmpword = tmpword + word
                self.listwords = []
        # print(tmpword)
        txtf.write(tmpword)
        print('写入txt成功')
        lef.close()
        txtf.close()
if __name__ == '__main__':
    try:
        file_path = sys.argv[1]
        path = file_path
    except  :
        path = '8food.bdict'
    bd = Baidu(path)
    bd.be2le()
    bd.le2txt()

存盘为bd.py文件 

执行转换

python bd.py

程序会自动读取8food.bdict文件，并转为8food.txt文件

也可以跟文件名，比如下载的8大菜系文件是 dict_file_734_20111227170031_1.0.0.bdict：

python bd.py dict_file_734_20111227170031_1.0.0.bdict

生成文件为dict_file_734_20111227170031_1.0.0.txt，内容为菜名：

阿胶炖肉

阿胶牛肉汤

阿胶养阴粥

阿胶养阴粥

安阳三熏

鹌鹑蛋烧稚

鹌鹑枸杞粥

鹌鹑枸杞粥

熬黄花鱼

八宝菠菜

这样百度输入法词库就转换为txt文件了！