Create UTF-8 Dictionary

utf-8-scraper.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "5dced423-9ff4-4343-85b4-4efaae87a53a",
   "metadata": {},
   "outputs": [],
   "source": [
    "%%capture\n",
    "!pip install lxml pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "97c8de8f-eb6f-4847-adad-3e155e0e9e58",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "bc83a338-bcd3-4ea2-8474-45d9ada3cc6c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Specify the URL of the website containing the table\n",
    "url = 'https://www.utf8-chartable.de/unicode-utf8-table.pl?number=1024&names=-'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "f97f0582-efe1-4db5-bdfd-ad88bbaabef2",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Use pandas to read the table from the specified URL\n",
    "tables = pd.read_html(url)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "9ba697b4-70f0-41c4-b81d-c8cdda895818",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# How many tables?\n",
    "len(tables)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "134902fe-9cba-4cc3-948e-936c5c31278e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unicode code point</th>\n",
       "      <th>Char</th>\n",
       "      <th>UTF-8</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>U+0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>U+0001</td>\n",
       "      <td>NaN</td>\n",
       "      <td>01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>U+0002</td>\n",
       "      <td>NaN</td>\n",
       "      <td>02</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>U+0003</td>\n",
       "      <td>NaN</td>\n",
       "      <td>03</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>U+0004</td>\n",
       "      <td>NaN</td>\n",
       "      <td>04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1019</th>\n",
       "      <td>U+03FB</td>\n",
       "      <td>ϻ</td>\n",
       "      <td>cf bb</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1020</th>\n",
       "      <td>U+03FC</td>\n",
       "      <td>ϼ</td>\n",
       "      <td>cf bc</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1021</th>\n",
       "      <td>U+03FD</td>\n",
       "      <td>Ͻ</td>\n",
       "      <td>cf bd</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1022</th>\n",
       "      <td>U+03FE</td>\n",
       "      <td>Ͼ</td>\n",
       "      <td>cf be</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1023</th>\n",
       "      <td>U+03FF</td>\n",
       "      <td>Ͽ</td>\n",
       "      <td>cf bf</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1024 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Unicode code point Char  UTF-8\n",
       "0                U+0000  NaN     00\n",
       "1                U+0001  NaN     01\n",
       "2                U+0002  NaN     02\n",
       "3                U+0003  NaN     03\n",
       "4                U+0004  NaN     04\n",
       "...                 ...  ...    ...\n",
       "1019             U+03FB    ϻ  cf bb\n",
       "1020             U+03FC    ϼ  cf bc\n",
       "1021             U+03FD    Ͻ  cf bd\n",
       "1022             U+03FE    Ͼ  cf be\n",
       "1023             U+03FF    Ͽ  cf bf\n",
       "\n",
       "[1024 rows x 3 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Work with the third table\n",
    "df = tables[2]\n",
    "df.columns = ['Unicode code point', 'Char', 'UTF-8']\n",
    "df\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "49517050-ed7e-4516-8858-cfba3fd0d8a8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create dictionary\n",
    "filter = df[\"UTF-8\"].str.contains(r'^c[3-9a-f]')\n",
    "utf8_char_dict = df[ filter ].set_index('UTF-8')['Char'].to_dict()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d2eeab76-8ffd-4dc9-babf-ddcd6bb9d763",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'c3 80': 'À',\n",
       " 'c3 81': 'Á',\n",
       " 'c3 82': 'Â',\n",
       " 'c3 83': 'Ã',\n",
       " 'c3 84': 'Ä',\n",
       " 'c3 85': 'Å',\n",
       " 'c3 86': 'Æ',\n",
       " 'c3 87': 'Ç',\n",
       " 'c3 88': 'È',\n",
       " 'c3 89': 'É'}"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display first few items of dictionary\n",
    "dict(list(utf8_char_dict.items())[:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "aeabd281-c08c-4635-9222-19c511e6234d",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}