{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "d792e3b7-4590-4545-a343-2c9ee606f50e", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Requirement already satisfied: natasha in c:\\programdata\\anaconda3\\lib\\site-packages (1.6.0)\n", "Requirement already satisfied: pymorphy2 in c:\\programdata\\anaconda3\\lib\\site-packages (from natasha) (0.9.1)\n", "Requirement already satisfied: razdel>=0.5.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from natasha) (0.5.0)\n", "Requirement already satisfied: navec>=0.9.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from natasha) (0.10.0)\n", "Requirement already satisfied: slovnet>=0.6.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from natasha) (0.6.0)\n", "Requirement already satisfied: yargy>=0.16.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from natasha) (0.16.0)\n", "Requirement already satisfied: ipymarkup>=0.8.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from natasha) (0.9.0)\n", "Requirement already satisfied: intervaltree>=3 in c:\\programdata\\anaconda3\\lib\\site-packages (from ipymarkup>=0.8.0->natasha) (3.1.0)\n", "Requirement already satisfied: numpy in c:\\programdata\\anaconda3\\lib\\site-packages (from navec>=0.9.0->natasha) (1.26.4)\n", "Requirement already satisfied: dawg-python>=0.7.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from pymorphy2->natasha) (0.7.2)\n", "Requirement already satisfied: pymorphy2-dicts-ru<3.0,>=2.4 in c:\\programdata\\anaconda3\\lib\\site-packages (from pymorphy2->natasha) (2.4.417127.4579844)\n", "Requirement already satisfied: docopt>=0.6 in c:\\programdata\\anaconda3\\lib\\site-packages (from pymorphy2->natasha) (0.6.2)\n", "Requirement already satisfied: sortedcontainers<3.0,>=2.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from intervaltree>=3->ipymarkup>=0.8.0->natasha) (2.4.0)\n", "Note: you may need to restart the kernel to use updated packages.\n" ] } ], "source": [ "# устанавливаем библиотеку natasha для дальнейших работ\n", "pip install natasha" ] }, { "cell_type": "code", "execution_count": 3, "id": "c6a64528-8064-41aa-83f1-591096e03080", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Requirement already satisfied: bs4 in c:\\programdata\\anaconda3\\lib\\site-packages (0.0.2)\n", "Requirement already satisfied: beautifulsoup4 in c:\\programdata\\anaconda3\\lib\\site-packages (from bs4) (4.12.3)\n", "Requirement already satisfied: soupsieve>1.2 in c:\\programdata\\anaconda3\\lib\\site-packages (from beautifulsoup4->bs4) (2.5)\n", "Note: you may need to restart the kernel to use updated packages.\n" ] } ], "source": [ "# устанавливаем библиотеку bs4 (Beautiful Soup 4) для дальнейших работ\n", "pip install bs4" ] }, { "cell_type": "code", "execution_count": 1, "id": "407b9639-427f-4e2d-98a0-bafc0bba45f6", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | recommendationid | \n", "language | \n", "review | \n", "timestamp_created | \n", "timestamp_updated | \n", "voted_up | \n", "votes_up | \n", "votes_funny | \n", "weighted_vote_score | \n", "written_during_early_access | \n", "comment_count | \n", "steam_purchase | \n", "received_for_free | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "149400957 | \n", "english | \n", "Apparently, my favorite colour is red. Astario... | \n", "1698960336 | \n", "1698960336 | \n", "True | \n", "1 | \n", "0 | \n", "0.00000 | \n", "False | \n", "0 | \n", "True | \n", "False | \n", "
1 | \n", "150084129 | \n", "english | \n", "I literally got a new 1TB SSD to play this aft... | \n", "1699913072 | \n", "1699913072 | \n", "True | \n", "1 | \n", "0 | \n", "0.00000 | \n", "False | \n", "0 | \n", "True | \n", "False | \n", "
2 | \n", "148459881 | \n", "english | \n", "An incredible game, Bg3 has incredible graphic... | \n", "1697668891 | \n", "1697668891 | \n", "True | \n", "0 | \n", "0 | \n", "0.00000 | \n", "False | \n", "0 | \n", "False | \n", "False | \n", "
3 | \n", "79014545 | \n", "english | \n", "good | \n", "1604953762 | \n", "1691397976 | \n", "True | \n", "0 | \n", "0 | \n", "0.00000 | \n", "True | \n", "0 | \n", "True | \n", "False | \n", "
4 | \n", "144059171 | \n", "english | \n", "I havent been this invested into a game since ... | \n", "1691902245 | \n", "1691902245 | \n", "True | \n", "0 | \n", "0 | \n", "0.00000 | \n", "False | \n", "0 | \n", "True | \n", "False | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
1995 | \n", "77854487 | \n", "english | \n", "The graphics, game play, and voice acting are ... | \n", "1603168676 | \n", "1634929644 | \n", "True | \n", "0 | \n", "0 | \n", "0.00000 | \n", "True | \n", "0 | \n", "True | \n", "False | \n", "
1996 | \n", "148174826 | \n", "english | \n", "I,m very new to a game like this but i already... | \n", "1697253758 | \n", "1697253758 | \n", "True | \n", "0 | \n", "0 | \n", "0.00000 | \n", "False | \n", "0 | \n", "True | \n", "False | \n", "
1997 | \n", "149257034 | \n", "english | \n", "A real work of art, tremendous amounts of deta... | \n", "1698765718 | \n", "1698765718 | \n", "True | \n", "0 | \n", "0 | \n", "0.00000 | \n", "False | \n", "0 | \n", "True | \n", "False | \n", "
1998 | \n", "121727958 | \n", "english | \n", "Game is still in flux, but I trust the develop... | \n", "1662289547 | \n", "1662289547 | \n", "True | \n", "0 | \n", "0 | \n", "0.00000 | \n", "True | \n", "0 | \n", "True | \n", "False | \n", "
1999 | \n", "144358746 | \n", "english | \n", "⣿⣿⣿⣿⣿⣿⣿⣿⡿⠿⠛⠛⠛⠋⠉⠈⠉⠉⠉⠉⠛⠻⢿⣿⣿⣿⣿⣿⣿⣿\\n⣿⣿⣿⣿⣿⡿⠋⠁⠀⠀⠀⠀⠀⠀... | \n", "1692216013 | \n", "1692216013 | \n", "True | \n", "1 | \n", "0 | \n", "0.52381 | \n", "False | \n", "0 | \n", "True | \n", "False | \n", "
2000 rows × 13 columns
\n", "\n", " | language | \n", "review | \n", "
---|---|---|
0 | \n", "english | \n", "Apparently, my favorite colour is red. Astario... | \n", "
1 | \n", "english | \n", "I literally got a new 1TB SSD to play this aft... | \n", "
2 | \n", "english | \n", "An incredible game, Bg3 has incredible graphic... | \n", "
3 | \n", "english | \n", "good | \n", "
4 | \n", "english | \n", "I havent been this invested into a game since ... | \n", "
... | \n", "... | \n", "... | \n", "
1995 | \n", "english | \n", "The graphics, game play, and voice acting are ... | \n", "
1996 | \n", "english | \n", "I,m very new to a game like this but i already... | \n", "
1997 | \n", "english | \n", "A real work of art, tremendous amounts of deta... | \n", "
1998 | \n", "english | \n", "Game is still in flux, but I trust the develop... | \n", "
1999 | \n", "english | \n", "⣿⣿⣿⣿⣿⣿⣿⣿⡿⠿⠛⠛⠛⠋⠉⠈⠉⠉⠉⠉⠛⠻⢿⣿⣿⣿⣿⣿⣿⣿\\n⣿⣿⣿⣿⣿⡿⠋⠁⠀⠀⠀⠀⠀⠀... | \n", "
2000 rows × 2 columns
\n", "\n", " | recommendationid | \n", "language | \n", "review | \n", "timestamp_created | \n", "timestamp_updated | \n", "voted_up | \n", "votes_up | \n", "votes_funny | \n", "weighted_vote_score | \n", "written_during_early_access | \n", "comment_count | \n", "steam_purchase | \n", "received_for_free | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "149400957 | \n", "english | \n", "apparently, my favorite colour is red. astario... | \n", "1698960336 | \n", "1698960336 | \n", "True | \n", "1 | \n", "0 | \n", "0.00000 | \n", "False | \n", "0 | \n", "True | \n", "False | \n", "
1 | \n", "150084129 | \n", "english | \n", "i literally got a new 1tb ssd to play this aft... | \n", "1699913072 | \n", "1699913072 | \n", "True | \n", "1 | \n", "0 | \n", "0.00000 | \n", "False | \n", "0 | \n", "True | \n", "False | \n", "
2 | \n", "148459881 | \n", "english | \n", "an incredible game, bg3 has incredible graphic... | \n", "1697668891 | \n", "1697668891 | \n", "True | \n", "0 | \n", "0 | \n", "0.00000 | \n", "False | \n", "0 | \n", "False | \n", "False | \n", "
3 | \n", "79014545 | \n", "english | \n", "good | \n", "1604953762 | \n", "1691397976 | \n", "True | \n", "0 | \n", "0 | \n", "0.00000 | \n", "True | \n", "0 | \n", "True | \n", "False | \n", "
4 | \n", "144059171 | \n", "english | \n", "i havent been this invested into a game since ... | \n", "1691902245 | \n", "1691902245 | \n", "True | \n", "0 | \n", "0 | \n", "0.00000 | \n", "False | \n", "0 | \n", "True | \n", "False | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
1995 | \n", "77854487 | \n", "english | \n", "the graphics, game play, and voice acting are ... | \n", "1603168676 | \n", "1634929644 | \n", "True | \n", "0 | \n", "0 | \n", "0.00000 | \n", "True | \n", "0 | \n", "True | \n", "False | \n", "
1996 | \n", "148174826 | \n", "english | \n", "i,m very new to a game like this but i already... | \n", "1697253758 | \n", "1697253758 | \n", "True | \n", "0 | \n", "0 | \n", "0.00000 | \n", "False | \n", "0 | \n", "True | \n", "False | \n", "
1997 | \n", "149257034 | \n", "english | \n", "a real work of art, tremendous amounts of deta... | \n", "1698765718 | \n", "1698765718 | \n", "True | \n", "0 | \n", "0 | \n", "0.00000 | \n", "False | \n", "0 | \n", "True | \n", "False | \n", "
1998 | \n", "121727958 | \n", "english | \n", "game is still in flux, but i trust the develop... | \n", "1662289547 | \n", "1662289547 | \n", "True | \n", "0 | \n", "0 | \n", "0.00000 | \n", "True | \n", "0 | \n", "True | \n", "False | \n", "
1999 | \n", "144358746 | \n", "english | \n", "⣿⣿⣿⣿⣿⣿⣿⣿⡿⠿⠛⠛⠛⠋⠉⠈⠉⠉⠉⠉⠛⠻⢿⣿⣿⣿⣿⣿⣿⣿\\n⣿⣿⣿⣿⣿⡿⠋⠁⠀⠀⠀⠀⠀⠀... | \n", "1692216013 | \n", "1692216013 | \n", "True | \n", "1 | \n", "0 | \n", "0.52381 | \n", "False | \n", "0 | \n", "True | \n", "False | \n", "
2000 rows × 13 columns
\n", "