Wikipedia User Name Validator

User Name Validator.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "import mwapi\n",
    "\n",
    "def validate_username(user_name, lang):\n",
    "    \"\"\"\n",
    "    Normalize a single user name via the wikimedia API\n",
    "    :param user_name: the user-name to normalize\n",
    "    :param lang: the language to make an api session if none supplied\n",
    "    :return: dict like {'user_id': 123, 'name': 'canonical username'}\n",
    "    \"\"\"\n",
    "    mwapi_session = mwapi.Session(f'https://{lang}.wikipedia.org', user_agent=\"CivilServant Username Normalizer <operations@civilservant.io>\")\n",
    "    user_name_resp = mwapi_session.get(action='query', list='users', ususers=user_name)\n",
    "    try:\n",
    "        name_id = user_name_resp['query']['users'][0]\n",
    "        return {\"valid\":True, \"user_id\": name_id['userid'], \"canonical_user_name\": name_id['name']}\n",
    "    except Exception as e:\n",
    "        e = \"User name not found\" if isinstance(e, KeyError) else e\n",
    "        return {\"valid\":False, \"error\":e}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "you can provide a string, and the canonical name might be different, wikimedia capitlizes the first letter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'valid': True, 'user_id': 13023703, 'canonical_user_name': 'Maximilianklein'}"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validate_username('maximilianklein', 'en')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "of course exact matches work"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'valid': True, 'user_id': 13023703, 'canonical_user_name': 'Maximilianklein'}"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validate_username('Maximilianklein', 'en')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "so to does the convention \"User:\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'valid': True, 'user_id': 13023703, 'canonical_user_name': 'Maximilianklein'}"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validate_username('User:Maximilianklein', 'en')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Note that the language is important for user_ids"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'valid': True, 'user_id': 33564818, 'canonical_user_name': 'Juliakamin'}"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validate_username('User:Juliakamin', 'en')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "in french it's different"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'valid': True, 'user_id': 3113092, 'canonical_user_name': 'Juliakamin'}"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validate_username('User:Juliakamin', 'fr')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Spaces or underscores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'valid': True, 'user_id': 7723863, 'canonical_user_name': 'Piano non troppo'}"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validate_username('Piano non troppo', 'en')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Should return the same"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'valid': True, 'user_id': 7723863, 'canonical_user_name': 'Piano non troppo'}"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validate_username('Piano_non_troppo', 'en')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "Invalid user names should return with \"valid:False\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'valid': False, 'error': 'User name not found'}"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "validate_username('doesnt exist user name', 'en')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}