如前例字典,实际是hash和字符的对应,那么经过适当的处理,我们实际可以提取出其hash字库,由于前述之提取方式,可以分字和词2种提取,代码如下:
sector_type_dict = {} # 字典载入...(略)
new_dict1 = {}
new_dict2 = {}
for key, values in sector_type_dict.items():
l = len(values[1].encode('GBK'))
if l > 12:
get_str = values[1].encode('GBK')[-12:].decode('GBK')
elif l < 12:
get_str = ' ' * (12-l) + values[1]
else:
get_str = values[1]
#endif
print (key, get_str, len(get_str.encode('GBK')))
key_str = key.split("-")
new_dict2[key_str[0]] = get_str.encode('GBK')[:4].decode('GBK')
new_dict2[key_str[1]] = get_str.encode('GBK')[4:8].decode('GBK')
new_dict1[key_str[2]] = get_str.encode('GBK')[8:10].decode('GBK')
new_dict1[key_str[3]] = get_str.encode('GBK')[10:12].decode('GBK')
#next
Save_dict(new_dict1, "1-GBK.txt", "0000000000000000", " ")
Save_dict(new_dict2, "2-GBK.txt", "0000000000000000", " ")
如上代码,最后生成1.txt和2.txt分别为:
{
"007f727e7fb6ff00": "服",
"003e7ebdf73eee00": "务",
"0010feffffc3fe00": "白",
"005f7f77337f9300": "酒",
"00cc7f1e5eefd900": "冰",
"004c3eed5ed5f700": "洗",
"007fff66ff18ff00": "空",
"001f3fdf7f7f6300": "调",
"007f7efe7ddf7c00": "部",
"00645ff6fe7f4400": "件",
"007e7e7fe77e7e00": "器",
"0042ff66ee5a6600": "材",
"006aeeea6ffe4200": "料",
"0023ffff7ff93300": "制",
"005e3fde525eff00": "造",
"00726ffa6e72f600": "封",
"00793f7f7ff9ef00": "测",
"005e33df5e6c3f00": "设",
"0076feff7e7e7e00": "备",
"00cc4cff4c6c6c00": "计",
"007ecbfbcbdbee00": "印",
"00797f5f7ff99b00": "刷",
"00207efa7a477f00": "包",
"00247ffeff7e7700": "装",
"007e73deff5e6500": "保",
"00ecfbdef8f69f00": "险",
"007edafedafd1f00": "电",
"00087eda7e18ff00": "生",
"00ff7f7fc0c08000": "产",
"0064ff757fc44400": "种",
"007e5e7ede5e5f00": "植",
"0034fd777634ff00": "业",
"0064ff6cfef74400": "林",
"004fd1eedff79c00": "综",
"001876ff7e667e00": "合",
"00443f7d6ff59f00": "池",
"007eff3c7eff1800": "学",
"007e667effffff00": "品",
"005ef27ad2537300": "机",
"0018db7e1c34e300": "火",
"0018fb7c6cdbb900": "水",
"0048fe7adf73bd00": "热",
"0010fe7f3362ce00": "力",
"0056ff3f365cff00": "发",
"007e7e7e7e7ee300": "其",
"00247ffd5e755f00": "他",
"001866ff7e4a7f00": "金",
"000076fffffeb314": "融",
"0046ff595d5fbf00": "加",
"007f18181818ff00": "工",
"007fff7e7a5a6600": "贸",
"007e7e7e7ef95e00": "易",
"00ff24ff2464c400": "开",
"0044ffff57759f00": "地",
"007ff27e7fb6ff00": "服",
"004eff7ffe5f4600": "棉",
"004cffeaeffbf600": "纺",
"007cde73fb7ec300": "染",
"0046ff4fff7f5700": "辅",
"004edbf1efeaf100": "织",
"00677f76ff0eff00": "整",
"007eff32fcfef900": "家",
"0048fffe5f576600": "饰",
"00247ffeff7ef700": "装",
"007e7e7e7f7e7e00": "普",
"005ffb5ff77b7300": "钢",
"006eec7f7f4a6600": "特",
"005ffb5ff57b5300": "钢",
"007f7e7f7ecef900": "原",
"005e3f1e7e769e00": "港",
"007ec3c3c3ff7e00": "口",
"0064fffefafbb300": "航",
"005e7fde567fff00": "运",
"0047ff65fe7f6b00": "械",
"005ffb4aff5b7f00": "铝",
"005fff5fff5d7300": "铜",
"006efb5ffb7b7f00": "铅",
"0044ffff6eff6400": "锌",
"003c66c3912e7e00": "公",
"006efe6e7b6afe00": "路",
"004effd8ff7f5b00": "输",
"0018ff66ff18e700": "交",
"00ee4cffee6e7f00": "硅",
"00647f7f7c44c400": "片",
"004efbdf7b7bdf00": "组",
"00ff7ec3fe3cff00": "变",
"00ff7e9f1d7f6300": "面",
"004ff87fdb567b00": "板",
"00232323233b3b00": " L",
"009c3fb3b33e9c00": "ED",
"007e00ff2c6dcf00": "元",
"007f7f7e5e7faf00": "属",
"007f7b5b7fc98a00": "用",
"007e7e7f7ee2be00": "居",
"00726cfa757a2c00": "彩",
"007f7e7e7e7d0600": "商",
"005e1ece7fdeb900": "涤",
"004cfef3de79fe00": "纶",
"006467ee7bfb4f00": "粘",
"007feafbfeecfb00": "胶",
"004fc4ffff64e400": "纤",
"004c7fdfdef61f00": "维",
"006afe7efe7bfb00": "氨",
"0044fff5df65e700": "纯",
"00427f7efe7f2700": "碱",
"006afe7e7e7f7f00": "氯",
"002476756c7eff00": "盐",
"0062fbfe6ecb5600": "粉",
"00286bcefc694f00": "化",
"004c3fbf7ffdbf00": "油",
"007e7e7eff7aff00": "墨",
"007c6ff6dffddf00": "酯",
"0021ff77ff57d300": "剂",
"00ff7c7ffb636600": "药",
"004812ff5ff39f00": "治",
"00ff5fff5e6c9f00": "理",
"005eec5f4ff50f00": "场",
"00ff57fe5a7ebb00": "玻",
"007fb3fa7a6def00": "泥",
"007e5f6e3e7e7f00": "建",
"006eff7d7c627e00": "管",
"0062ff66ee5a6600": "材",
"00fffdffefefdb00": "园",
"007e5f6e3e7eff00": "建",
"007fdb7e7f4c5f00": "程",
"00247f7afef66b00": "教",
"00ff7e7e7e7e4600": "育",
"007e0cffff083800": "子",
"003e687e6f7fe700": "兵",
"00247f7eff7e7700": "装",
"006c7fccde7f6d00": "体",
"007eff3c7e7f1800": "零",
"0068ff7e7f7e7e00": "售",
"00487fdc7f4cff00": "连",
"0044fffff57f3b00": "锁",
"005ec6fedb6eff00": "经",
"007fff7f3c7e7e00": "营",
"007e7e7e7f7e7a00": "景",
"001f7f637e7c9d00": "点",
"005f7f37337f9300": "酒",
"007f584f7ef2be00": "店",
"0036f67c7e3e2600": "餐",
"006fffc44c7a7300": "饮",
"007e5a4eff7ecb00": "采",
"002cff6b7eee3b00": "妆",
"00247f7e7f7f7700": "美",
"007ee77a7e7e7e00": "容",
"0044ffee7b7b7f00": "钴",
"005efe5ede7e7f00": "镍",
"005fffdf5f6e7f00": "锂",
"0046ff595ddfbf00": "加",
"007fffff57694700": "饲",
"00187e7e7e7e7600": "食",
"006efefe7effff00": "氮",
"007f777f70b1ff00": "肥",
"007ffb3a6cbf3100": "农",
"007fff5fff446400": "钾",
"007f777ff0b1ff00": "肥",
"007e767c3e7efb00": "系",
"004cfffedff5f700": "统",
"0044fef3ee79ef00": "轮",
"006e79fb7f767f00": "毂",
"00307f7e3eff0800": "车",
"002eff7e7a5a7700": "货",
"005a7f7cff7e7e00": "客",
"005ffffe5de0bf00": "燃",
"007f7efe7e030300": "气",
"0068fff3e47efb00": "软",
"003f7ed672deff00": "疫",
"007f7e5a7e5a7e00": "苗",
"00647ffefefff400": "酵",
"007e6f7f2a7eff00": "塑",
"005bff7bdb7b6600": "树",
"007b7f6e7f9ffb00": "脂",
"00ff7e7e7e7d0600": "商",
"007771ffd8f9df00": "配",
"007e7eff7e7e7e00": "套",
"007e7e7e7effe700": "具",
"00187e7f7ffebe00": "磨",
"002c77dace4c7300": "仪",
"007e7e7f3f6eb300": "表",
"00187f4060c0c000": "广",
"007e5f7fff5fd300": "播",
"00185b7e18dbff00": "出",
"006ff8ff7af6bf00": "版",
"0044ffffff5b7300": "销",
"005bffdefe7ea500": "媒",
"0048ffffef791e00": "物",
"005f1efe42ffef00": "流",
"005b7eff6c5ef300": "炭",
"007e7f7e7f7e8000": "黑",
"006ace797f5f4600": "稀",
"0018187f1818ff00": "土",
"004efa76ff7f6700": "钨",
"005ffb5b7f7b5f00": "钼",
"0046ff7fff5fd700": "捕",
"005eff71de4bd600": "捞",
"007e7e7eff644400": "养",
"006e5effff5b5f00": "殖",
"00665fff7e747f00": "健",
"00647cdeb724c400": "外",
"007f7e6c5e627f00": "医",
"00ecffdeeecc9700": "院",
"006efe6cffe54700": "耗",
"004c7eff5f7e7800": "诊",
"00f7fcfffefa7a00": "断",
"005e1edf7f46ff00": "通",
"005efe5efc567b00": "银",
"007ee07fc6464e00": "行",
"007f7e7e7efd0600": "商",
"004cffffeefc1f00": "啤",
"00427effdf7ce700": "类",
"007cfcfc3cfd6700": "乳",
"004effccffeedf00": "线",
"00563fb37feafe00": "游",
"0066bfec666d9b00": "戏",
"004ff4defe749b00": "纸",
"00df44d656747f00": "证",
"005a7e7f67364c00": "券",
"0018ffdbff181800": "中",
"001818183c66c300": "人",
"0000000000000000": " "
}
{
"000f0f0a0e0e0a00": " IT",
"000f0f070f0f0f00": " 家",
"0067ffe6efff3600": "电零",
"00669ff96716ef00": "分立",
"000f0f0f0f0f0200": " 半",
"00e0f7dafeff2000": "导体",
"0063ffecff6e9f00": "集成",
"006eefefe7ef3f00": "电路",
"00e7fff2fff0f400": "数字",
"0060ff2ffe9a6800": "芯片",
"0070fdf4fe777800": "模拟",
"00fff5f5f7f4ff00": "厨卫",
"00aff2ffffa00400": "种子",
"00e0fffff6f76700": "粮食",
"000f0f0f0f0f0d00": " 机",
"0028ffffff4a7000": "他种",
"00f6ff6fe7f65f00": "农业",
"000f0f0f0f0f0f00": " 股",
"000f0f0f0f0f0700": " 电",
"00a475fb7ecdf300": "池化",
"0076fefffefe7300": "锂电",
"000fffff7f682b00": "专用",
"00f0f76ff7f49700": "其他",
"000f0e0f0f0f0f00": " 新",
"0037e7f7e7eeff00": "能源",
"0063feefefee3f00": "电能",
"0076dffff6ff2f00": "综合",
"00e7fffef6f13100": "电气",
"0062ff85fff2ff00": "自控",
"000b0f0f0f0f0f00": " 输",
"00fe7f9fef6ff300": "变电",
"003f7eeffefffe00": "缆部",
"002ef6e7e7fe8d00": "件及",
"00f427fbfe0d6b00": "子化",
"0067f06ff664cb00": "多元",
"00fa477787df7700": "石油",
"00a776ff7fffff00": "油品",
"00f447fb9ef57300": "石化",
"00267f83ff067300": "住宅",
"00f6ffff8f868f00": "产业",
"00f0f5fff7e69f00": "商业",
"000ff7ff78d87800": "地产",
"00060f0f0f0f0600": " 非",
"002f4fff670ff700": "金属",
"00e6af6f6fff9300": "风电",
"000f0f0f0f0f0900": " 风",
"00fef0f7f4f23d00": "帽及",
"000f4d7f7f7f7d00": "冶钢",
"00ff0f0f0f0af700": "工程",
"00fbf76ff66f3f00": "高速",
"000eefeff7efdf00": "铁路",
"00fc2ffceffff000": "硅料",
"000263fffa4fbd00": "光伏",
"00e8f7f7e7fd3f00": "电池",
"000f070f0f0e0f00": " 逆",
"00bff060f0f0ff00": "加工",
"00076ff6f74fb400": "光学",
"0086eff0eff65f00": "轨交",
"00070f0f0f070f00": " 贵",
"006fff4fe7edcf00": "家居",
"0027ff0c6f6f9d00": "文娱",
"006ef7feff6efc00": "瓷砖",
"0027f6cfffffff00": "成品",
"00e59fff2feff500": "定制",
"00f6fe6ffff80f00": "黑色",
"000f0e0f0f070f00": " 互",
"00effdefffefc100": "联网",
"000f040f060f0b00": " 无",
"00477fa6e75f3400": "化学",
"000a0f0f0e0f0f00": " 钛",
"00070f0f0f0f0f00": " 煤",
"00ac7ffc7fffe000": "涂料",
"00f7dfefe78f9600": "民爆",
"0023ffedffcef500": "纺织",
"000f0f0f0e0f0f00": " 聚",
"00ef2f7f67afd900": "及饲",
"00c7f6c7ffff0600": "料添",
"00040f0f0f0f0f00": " 有",
"00f707ef3fca0d00": "环保",
"0007fffe6f619100": "大气",
"0006feef6fb74b00": "水务",
"00e06f7666ebd400": "及水",
"00f7fff7f7feff00": "固废",
"00f20fef37cf0700": "环境",
"00e7ffe1eff0df00": "航空",
"006af2fffaee7e00": "他计",
"00f2fcfcfcf58500": "算机",
"000efffbfd6dff00": "安防",
"00f77fff67ef7300": "玻璃",
"00d0f8f6f6f6f900": "耐火",
"0000fffeffe7fd00": "装饰",
"006fffff67679700": "房屋",
"00f467fffcfff300": "基础",
"0046ffff77662f00": "专业",
"007765eff7aff300": "咨询",
"0026f7fff6407f00": "他金",
"00fdfe7f7efe7400": "属新",
"00e0ff7ef7c0f700": "磁性",
"00fff0e060f02f00": "军工",
"00eff0eff6f6d900": "航天",
"000ffff737cf3f00": "地面",
"00c6f7e7e7dfdb00": "航海",
"0067f7f7e7ef3f00": "电源",
"00f76ff7f7f7ff00": "百货",
"0004fffffff67f00": "物业",
"0027f7a5f7ecfe00": "旅游",
"006f666666f69f00": "人工",
"0067ff9efffdf300": "自然",
"0070fffff6f23d00": "煤炭",
"0060ffef76668d00": "焦炭",
"006a6ffd2f642c00": "个护",
"00060f0b0e0f0b00": " 化",
"00f7efebf8cafa00": "医疗",
"00f7ff67ef6f0700": "果蔬",
"00e0f7f7f7ff7700": "粮油",
"0027fff6fe4f7400": "他农",
"00fff7ff8f8f8f00": "产品",
"0076ef66f7e76700": "畜禽",
"000fffef68b84800": "水产",
"00e0ffff4f7ff700": "宠物",
"006ffffffcfccf00": "磷肥",
"00e70f7f4fafdc00": "及磷",
"00224fee2fefff00": "运输",
"00f4ffee669f9200": "汽车",
"006cff7eff7ce300": "身附",
"00007f47f7fe3f00": "与发",
"00e67cfe7ced7500": "动机",
"002cefddefcfbf00": "轮胎",
"0067f7fef6c97900": "他汽",
"004fffe66fff2600": "车零",
"00e7f2f7f7f03400": "电子",
"000f0f0f0f0f0b00": " 商",
"00f6fffffe873f00": "用载",
"002766f767e66f00": "垂直",
"006fefcfefa0fb00": "应用",
"0070ffffff7d7900": "横向",
"007777f77fb0f300": "通用",
"0047f7f7e7ebff00": "血液",
"0000efefff07f700": "生物",
"00060f0f0f0f0b00": " 肉",
"00a0fff7f7f60f00": "味发",
"00077ff7a7fd8b00": "休闲",
"000f0f0f0f0b0f00": " 预",
"00f4fefc7f6ef000": "塑料",
"00c07f6fefa0df00": "改性",
"00636ffc6fff7f00": "合成",
"020f0f0f0f0f0f00": " 膜",
"0072f5fe737f7f00": "信运",
"007ff0f0f070ff00": "信工",
"00fef0f7f4a27d00": "程及",
"0077f77f27f77700": "增值",
"0022f5fff7fe3700": "络设",
"006ee0f7f4f27d00": "备及",
"0063fffa7f5b7f00": "信线",
"003ef0e7f4fafd00": "缆及",
"0062fffe7f5e7b00": "信终",
"00aef077f4fadd00": "端及",
"007777fa77b5f700": "通信",
"0062cfeeefdf5800": "机床",
"0066f7f7f6ef7900": "磨具",
"0052fff5f7fe7200": "制冷",
"00e7f79ff70ff100": "空调",
"004f5f87af2f5f00": "仪器",
"0067fdefffe23700": "电视",
"002ffe8f8f8f8f00": "广告",
"002ffcfcff727d00": "橡胶",
"007ffe6ffeff6e00": "零部",
"00676feffefff800": "品牌",
"0086277f77ff9f00": "消费",
"0006060f0f070600": " 小",
"0062f6fffbe27600": "他小",
"00e677f272ffb200": "海洋",
"00603fff7fef7700": "动物",
"000eefe7ef07fb00": "生猪",
"000effffffff9300": "肉鸡",
"00f00ff7e7c64f00": "研发",
"0022feafeff68a00": "体外",
"00ff66ef6d8dfb00": "医药",
"00f0fff6fff7f300": "国有",
"000fff6f61679f00": "大型",
"0065dfff6f4fe700": "份制",
"000b0f0f0f0f0700": " 城",
"000f0f070e0f0500": " 农",
"000e0f0f0e0f0f00": " 软",
"00c7eceeefc2e500": "影视",
"00a77ffe7ef1f100": "油气",
"000f7d7f7fff7f00": "油服",
"000f0f0f0b0f0f00": " 印",
"0016ffffffff5300": "制电",
"0036f3ffe76e7700": "被动",
"00f0cff7ffe6ff00": "服装",
"00ffef6feff85b00": "农用",
"00fe70f774f2fd00": "源及",
"006efffe6166ff00": "重型",
"00eebfcf0fffb700": "印刷",
"0000ffefef3e7f00": "包装",
"0070fff6f6777400": "楼宇",
"00f20f2f0f0aff00": "工控",
"00e0f6f777f4fb00": "激光",
"0026fff9ff4f7f00": "他自",
"00e471fb7eedf300": "动化",
"0000000000000000": " "
}
581

被折叠的 条评论
为什么被折叠?



