mirror of
https://github.com/ada-dmitry/CourseWork_IRFM.git
synced 2026-09-24 01:10:18 +00:00
- Implemented loader in `modules/loader.py` to download HTML pages using curl and urllib. - Created processor in `modules/processor.py` for processing the text of the Russian Criminal Code (УК РФ). - Added README files for both loader and processor explaining their functionality and usage. - Generated output files including original text, prepared text, and subject index in CSV and JSON formats.
702 lines
13 KiB
JSON
702 lines
13 KiB
JSON
[
|
|
{
|
|
"word": "срок",
|
|
"count": 3342,
|
|
"line": 34,
|
|
"char": 151,
|
|
"source_word": "срок"
|
|
},
|
|
{
|
|
"word": "размер",
|
|
"count": 2024,
|
|
"line": 136,
|
|
"char": 25,
|
|
"source_word": "размере"
|
|
},
|
|
{
|
|
"word": "лишение",
|
|
"count": 1843,
|
|
"line": 31,
|
|
"char": 183,
|
|
"source_word": "лишения"
|
|
},
|
|
{
|
|
"word": "свобода",
|
|
"count": 1563,
|
|
"line": 3,
|
|
"char": 53,
|
|
"source_word": "свобод"
|
|
},
|
|
{
|
|
"word": "определенный",
|
|
"count": 1399,
|
|
"line": 120,
|
|
"char": 24,
|
|
"source_word": "определенные"
|
|
},
|
|
{
|
|
"word": "иной",
|
|
"count": 1267,
|
|
"line": 4,
|
|
"char": 241,
|
|
"source_word": "иные"
|
|
},
|
|
{
|
|
"word": "лицо",
|
|
"count": 1224,
|
|
"line": 7,
|
|
"char": 1,
|
|
"source_word": "Лица"
|
|
},
|
|
{
|
|
"word": "наказываться",
|
|
"count": 1084,
|
|
"line": 493,
|
|
"char": 1,
|
|
"source_word": "наказывается"
|
|
},
|
|
{
|
|
"word": "работа",
|
|
"count": 1080,
|
|
"line": 122,
|
|
"char": 14,
|
|
"source_word": "работы"
|
|
},
|
|
{
|
|
"word": "осудить",
|
|
"count": 973,
|
|
"line": 25,
|
|
"char": 746,
|
|
"source_word": "осуждены"
|
|
},
|
|
{
|
|
"word": "таковой",
|
|
"count": 942,
|
|
"line": 409,
|
|
"char": 174,
|
|
"source_word": "таковых"
|
|
},
|
|
{
|
|
"word": "штраф",
|
|
"count": 899,
|
|
"line": 119,
|
|
"char": 1,
|
|
"source_word": "штраф"
|
|
},
|
|
{
|
|
"word": "период",
|
|
"count": 873,
|
|
"line": 136,
|
|
"char": 135,
|
|
"source_word": "период"
|
|
},
|
|
{
|
|
"word": "доход",
|
|
"count": 864,
|
|
"line": 136,
|
|
"char": 113,
|
|
"source_word": "дохода"
|
|
},
|
|
{
|
|
"word": "деятельность",
|
|
"count": 824,
|
|
"line": 53,
|
|
"char": 752,
|
|
"source_word": "деятельности"
|
|
},
|
|
{
|
|
"word": "заработный",
|
|
"count": 808,
|
|
"line": 136,
|
|
"char": 86,
|
|
"source_word": "заработной"
|
|
},
|
|
{
|
|
"word": "плата",
|
|
"count": 808,
|
|
"line": 136,
|
|
"char": 97,
|
|
"source_word": "платы"
|
|
},
|
|
{
|
|
"word": "право",
|
|
"count": 797,
|
|
"line": 2,
|
|
"char": 118,
|
|
"source_word": "права"
|
|
},
|
|
{
|
|
"word": "должность",
|
|
"count": 704,
|
|
"line": 120,
|
|
"char": 37,
|
|
"source_word": "должности"
|
|
},
|
|
{
|
|
"word": "преступление",
|
|
"count": 696,
|
|
"line": 3,
|
|
"char": 309,
|
|
"source_word": "преступлений"
|
|
},
|
|
{
|
|
"word": "занимать",
|
|
"count": 694,
|
|
"line": 120,
|
|
"char": 15,
|
|
"source_word": "занимать"
|
|
},
|
|
{
|
|
"word": "заниматься",
|
|
"count": 682,
|
|
"line": 120,
|
|
"char": 51,
|
|
"source_word": "заниматься"
|
|
},
|
|
{
|
|
"word": "принудительный",
|
|
"count": 659,
|
|
"line": 56,
|
|
"char": 135,
|
|
"source_word": "принудительные"
|
|
},
|
|
{
|
|
"word": "деяние",
|
|
"count": 657,
|
|
"line": 4,
|
|
"char": 174,
|
|
"source_word": "деяния"
|
|
},
|
|
{
|
|
"word": "совершенный",
|
|
"count": 578,
|
|
"line": 20,
|
|
"char": 15,
|
|
"source_word": "совершенные"
|
|
},
|
|
{
|
|
"word": "предусмотренный",
|
|
"count": 474,
|
|
"line": 14,
|
|
"char": 113,
|
|
"source_word": "предусмотренного"
|
|
},
|
|
{
|
|
"word": "ограничение",
|
|
"count": 447,
|
|
"line": 116,
|
|
"char": 223,
|
|
"source_word": "ограничении"
|
|
},
|
|
{
|
|
"word": "группа",
|
|
"count": 410,
|
|
"line": 85,
|
|
"char": 144,
|
|
"source_word": "группу"
|
|
},
|
|
{
|
|
"word": "наказание",
|
|
"count": 406,
|
|
"line": 4,
|
|
"char": 229,
|
|
"source_word": "наказаний"
|
|
},
|
|
{
|
|
"word": "средство",
|
|
"count": 353,
|
|
"line": 53,
|
|
"char": 541,
|
|
"source_word": "средством"
|
|
},
|
|
{
|
|
"word": "крупный",
|
|
"count": 338,
|
|
"line": 848,
|
|
"char": 122,
|
|
"source_word": "крупных"
|
|
},
|
|
{
|
|
"word": "совершение",
|
|
"count": 329,
|
|
"line": 4,
|
|
"char": 283,
|
|
"source_word": "совершение"
|
|
},
|
|
{
|
|
"word": "обязательный",
|
|
"count": 261,
|
|
"line": 114,
|
|
"char": 116,
|
|
"source_word": "обязательных"
|
|
},
|
|
{
|
|
"word": "организация",
|
|
"count": 250,
|
|
"line": 53,
|
|
"char": 870,
|
|
"source_word": "организацию"
|
|
},
|
|
{
|
|
"word": "повлечь",
|
|
"count": 248,
|
|
"line": 546,
|
|
"char": 68,
|
|
"source_word": "повлекшие"
|
|
},
|
|
{
|
|
"word": "тяжкий",
|
|
"count": 237,
|
|
"line": 30,
|
|
"char": 185,
|
|
"source_word": "тяжкие"
|
|
},
|
|
{
|
|
"word": "использование",
|
|
"count": 234,
|
|
"line": 84,
|
|
"char": 221,
|
|
"source_word": "использования"
|
|
},
|
|
{
|
|
"word": "исправительный",
|
|
"count": 229,
|
|
"line": 123,
|
|
"char": 1,
|
|
"source_word": "исправительные"
|
|
},
|
|
{
|
|
"word": "совершить",
|
|
"count": 228,
|
|
"line": 7,
|
|
"char": 7,
|
|
"source_word": "совершившие"
|
|
},
|
|
{
|
|
"word": "отношение",
|
|
"count": 213,
|
|
"line": 7,
|
|
"char": 213,
|
|
"source_word": "отношения"
|
|
},
|
|
{
|
|
"word": "действие",
|
|
"count": 206,
|
|
"line": 8,
|
|
"char": 74,
|
|
"source_word": "действия"
|
|
},
|
|
{
|
|
"word": "цель",
|
|
"count": 204,
|
|
"line": 13,
|
|
"char": 121,
|
|
"source_word": "целью"
|
|
},
|
|
{
|
|
"word": "государственный",
|
|
"count": 188,
|
|
"line": 53,
|
|
"char": 2031,
|
|
"source_word": "государственного"
|
|
},
|
|
{
|
|
"word": "равно",
|
|
"count": 187,
|
|
"line": 85,
|
|
"char": 107,
|
|
"source_word": "равно"
|
|
},
|
|
{
|
|
"word": "сумма",
|
|
"count": 185,
|
|
"line": 136,
|
|
"char": 229,
|
|
"source_word": "сумме"
|
|
},
|
|
{
|
|
"word": "применение",
|
|
"count": 184,
|
|
"line": 6,
|
|
"char": 1,
|
|
"source_word": "Применение"
|
|
},
|
|
{
|
|
"word": "предусмотреть",
|
|
"count": 184,
|
|
"line": 18,
|
|
"char": 133,
|
|
"source_word": "предусмотренных"
|
|
},
|
|
{
|
|
"word": "организовать",
|
|
"count": 183,
|
|
"line": 85,
|
|
"char": 32,
|
|
"source_word": "организовавшее"
|
|
},
|
|
{
|
|
"word": "уголовный",
|
|
"count": 180,
|
|
"line": 1,
|
|
"char": 1,
|
|
"source_word": "Уголовное"
|
|
},
|
|
{
|
|
"word": "особо",
|
|
"count": 178,
|
|
"line": 30,
|
|
"char": 207,
|
|
"source_word": "особо"
|
|
},
|
|
{
|
|
"word": "суд",
|
|
"count": 175,
|
|
"line": 23,
|
|
"char": 349,
|
|
"source_word": "суда"
|
|
},
|
|
{
|
|
"word": "предварительный",
|
|
"count": 165,
|
|
"line": 93,
|
|
"char": 124,
|
|
"source_word": "предварительного"
|
|
},
|
|
{
|
|
"word": "военный",
|
|
"count": 163,
|
|
"line": 21,
|
|
"char": 401,
|
|
"source_word": "военном"
|
|
},
|
|
{
|
|
"word": "незаконный",
|
|
"count": 162,
|
|
"line": 53,
|
|
"char": 1199,
|
|
"source_word": "незаконном"
|
|
},
|
|
{
|
|
"word": "случай",
|
|
"count": 161,
|
|
"line": 22,
|
|
"char": 141,
|
|
"source_word": "случае"
|
|
},
|
|
{
|
|
"word": "сговор",
|
|
"count": 161,
|
|
"line": 74,
|
|
"char": 174,
|
|
"source_word": "сговор"
|
|
},
|
|
{
|
|
"word": "примечание",
|
|
"count": 159,
|
|
"line": 296,
|
|
"char": 1,
|
|
"source_word": "Примечание"
|
|
},
|
|
{
|
|
"word": "ответственность",
|
|
"count": 156,
|
|
"line": 1,
|
|
"char": 122,
|
|
"source_word": "ответственность"
|
|
},
|
|
{
|
|
"word": "арест",
|
|
"count": 156,
|
|
"line": 127,
|
|
"char": 1,
|
|
"source_word": "арест"
|
|
},
|
|
{
|
|
"word": "причинение",
|
|
"count": 151,
|
|
"line": 9,
|
|
"char": 71,
|
|
"source_word": "причинение"
|
|
},
|
|
{
|
|
"word": "неосторожность",
|
|
"count": 143,
|
|
"line": 60,
|
|
"char": 78,
|
|
"source_word": "неосторожности"
|
|
},
|
|
{
|
|
"word": "ущерб",
|
|
"count": 142,
|
|
"line": 204,
|
|
"char": 135,
|
|
"source_word": "ущерба"
|
|
},
|
|
{
|
|
"word": "признаваться",
|
|
"count": 141,
|
|
"line": 4,
|
|
"char": 181,
|
|
"source_word": "признаются"
|
|
},
|
|
{
|
|
"word": "заведомо",
|
|
"count": 141,
|
|
"line": 53,
|
|
"char": 1130,
|
|
"source_word": "заведомо"
|
|
},
|
|
{
|
|
"word": "другой",
|
|
"count": 138,
|
|
"line": 7,
|
|
"char": 297,
|
|
"source_word": "других"
|
|
},
|
|
{
|
|
"word": "несовершеннолетний",
|
|
"count": 138,
|
|
"line": 54,
|
|
"char": 6,
|
|
"source_word": "несовершеннолетний"
|
|
},
|
|
{
|
|
"word": "вред",
|
|
"count": 137,
|
|
"line": 9,
|
|
"char": 82,
|
|
"source_word": "вреда"
|
|
},
|
|
{
|
|
"word": "положение",
|
|
"count": 134,
|
|
"line": 7,
|
|
"char": 184,
|
|
"source_word": "положения"
|
|
},
|
|
{
|
|
"word": "орган",
|
|
"count": 133,
|
|
"line": 80,
|
|
"char": 135,
|
|
"source_word": "органам"
|
|
},
|
|
{
|
|
"word": "имущество",
|
|
"count": 131,
|
|
"line": 53,
|
|
"char": 621,
|
|
"source_word": "имущества"
|
|
},
|
|
{
|
|
"word": "вещество",
|
|
"count": 131,
|
|
"line": 53,
|
|
"char": 1607,
|
|
"source_word": "веществ"
|
|
},
|
|
{
|
|
"word": "вид",
|
|
"count": 127,
|
|
"line": 4,
|
|
"char": 224,
|
|
"source_word": "виды"
|
|
},
|
|
{
|
|
"word": "служба",
|
|
"count": 126,
|
|
"line": 124,
|
|
"char": 24,
|
|
"source_word": "службе"
|
|
},
|
|
{
|
|
"word": "информация",
|
|
"count": 125,
|
|
"line": 87,
|
|
"char": 107,
|
|
"source_word": "информации"
|
|
},
|
|
{
|
|
"word": "здоровье",
|
|
"count": 124,
|
|
"line": 53,
|
|
"char": 179,
|
|
"source_word": "здоровью"
|
|
},
|
|
{
|
|
"word": "указанный",
|
|
"count": 118,
|
|
"line": 35,
|
|
"char": 337,
|
|
"source_word": "указанного"
|
|
},
|
|
{
|
|
"word": "нарушение",
|
|
"count": 118,
|
|
"line": 201,
|
|
"char": 29,
|
|
"source_word": "нарушении"
|
|
},
|
|
{
|
|
"word": "сеть",
|
|
"count": 117,
|
|
"line": 230,
|
|
"char": 147,
|
|
"source_word": "сетях"
|
|
},
|
|
{
|
|
"word": "человек",
|
|
"count": 116,
|
|
"line": 3,
|
|
"char": 60,
|
|
"source_word": "человека"
|
|
},
|
|
{
|
|
"word": "последствие",
|
|
"count": 112,
|
|
"line": 5,
|
|
"char": 72,
|
|
"source_word": "последствия"
|
|
},
|
|
{
|
|
"word": "служебный",
|
|
"count": 110,
|
|
"line": 104,
|
|
"char": 139,
|
|
"source_word": "служебного"
|
|
},
|
|
{
|
|
"word": "административный",
|
|
"count": 107,
|
|
"line": 298,
|
|
"char": 288,
|
|
"source_word": "административной"
|
|
},
|
|
{
|
|
"word": "гражданин",
|
|
"count": 106,
|
|
"line": 3,
|
|
"char": 71,
|
|
"source_word": "гражданина"
|
|
},
|
|
{
|
|
"word": "подкуп",
|
|
"count": 106,
|
|
"line": 86,
|
|
"char": 97,
|
|
"source_word": "подкупа"
|
|
},
|
|
{
|
|
"word": "превышать",
|
|
"count": 105,
|
|
"line": 31,
|
|
"char": 164,
|
|
"source_word": "превышает"
|
|
},
|
|
{
|
|
"word": "денежный",
|
|
"count": 105,
|
|
"line": 135,
|
|
"char": 12,
|
|
"source_word": "денежное"
|
|
},
|
|
{
|
|
"word": "смерть",
|
|
"count": 104,
|
|
"line": 492,
|
|
"char": 41,
|
|
"source_word": "смерти"
|
|
},
|
|
{
|
|
"word": "законодательство",
|
|
"count": 101,
|
|
"line": 1,
|
|
"char": 11,
|
|
"source_word": "законодательство"
|
|
},
|
|
{
|
|
"word": "число",
|
|
"count": 101,
|
|
"line": 17,
|
|
"char": 274,
|
|
"source_word": "числе"
|
|
},
|
|
{
|
|
"word": "насилие",
|
|
"count": 101,
|
|
"line": 101,
|
|
"char": 295,
|
|
"source_word": "насилием"
|
|
},
|
|
{
|
|
"word": "иностранный",
|
|
"count": 98,
|
|
"line": 22,
|
|
"char": 68,
|
|
"source_word": "иностранных"
|
|
},
|
|
{
|
|
"word": "характер",
|
|
"count": 94,
|
|
"line": 4,
|
|
"char": 270,
|
|
"source_word": "характера"
|
|
},
|
|
{
|
|
"word": "соответствие",
|
|
"count": 92,
|
|
"line": 22,
|
|
"char": 234,
|
|
"source_word": "соответствии"
|
|
},
|
|
{
|
|
"word": "отбывание",
|
|
"count": 92,
|
|
"line": 27,
|
|
"char": 246,
|
|
"source_word": "отбывания"
|
|
},
|
|
{
|
|
"word": "угроза",
|
|
"count": 92,
|
|
"line": 28,
|
|
"char": 109,
|
|
"source_word": "угрозой"
|
|
},
|
|
{
|
|
"word": "возраст",
|
|
"count": 89,
|
|
"line": 48,
|
|
"char": 48,
|
|
"source_word": "возрасте"
|
|
},
|
|
{
|
|
"word": "медицинский",
|
|
"count": 87,
|
|
"line": 56,
|
|
"char": 155,
|
|
"source_word": "медицинского"
|
|
},
|
|
{
|
|
"word": "должностной",
|
|
"count": 86,
|
|
"line": 7,
|
|
"char": 171,
|
|
"source_word": "должностного"
|
|
},
|
|
{
|
|
"word": "условие",
|
|
"count": 86,
|
|
"line": 35,
|
|
"char": 296,
|
|
"source_word": "условии"
|
|
},
|
|
{
|
|
"word": "оружие",
|
|
"count": 86,
|
|
"line": 53,
|
|
"char": 1764,
|
|
"source_word": "оружия"
|
|
}
|
|
] |