Check for URL in a String - 5 algorithms compared. - https://www.geeksforgeeks.org/python-check-url-string/

url-in-string.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [],
   "source": [
    "# for algorithms\n",
    "import re\n",
    "from functools import reduce\n",
    "from urllib.parse import urlparse, ParseResult\n",
    "\n",
    "# for timing\n",
    "from timeit import timeit\n",
    "\n",
    "# types\n",
    "from typing import List, Tuple, Callable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {},
   "outputs": [],
   "source": [
    "string = \"My Profile: https://auth.geeksforgeeks.org/user/Chinmoy%20Lenka/articles in the portal of https://www.geeksforgeeks.org/\"\n",
    "string1 = \"My Profile: https://auth.geeksforgeeks.org/user/Chinmoy%20Lenka/articles in the portal of https://www.geeksforgeeks.org/\"\n",
    "string2 = \"Some more text without URLs\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "metadata": {},
   "outputs": [],
   "source": [
    "def alg1(string: str) -> List[str]:\n",
    "    regex: str = (\n",
    "        r\"(?i)\\b((?:https?://|www\\d{0,3}[.]|[a-z0-9.\\-]+[.][a-z]{2,4}/)(?:[^\\s()<>]+|\\(([^\\s()<>]+|(\\([^\\s()<>]+\\)))*\\))+(?:\\(([^\\s()<>]+|(\\([^\\s()<>]+\\)))*\\)|[^\\s`!()\\[\\]{};:'\\\".,<>?«»“”‘’]))\"\n",
    "    )\n",
    "    url: List[str] = re.findall(regex, string)\n",
    "    return [x[0] for x in url]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [],
   "source": [
    "def alg2(string: str) -> List[str]:\n",
    "    x: List[str] = string.split()\n",
    "    return [i for i in x if i.startswith(\"https:\") or i.startswith(\"http:\")]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "metadata": {},
   "outputs": [],
   "source": [
    "def alg3(string: str) -> List[str]:\n",
    "    x: List[str] = string.split()\n",
    "    return [i for i in x if i.find(\"https:\") == 0 or i.find(\"http:\") == 0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [],
   "source": [
    "def alg4(string: str) -> List[str]:\n",
    "    words: List[str] = string.split()\n",
    "    urls: List[str] = []\n",
    "    for word in words:\n",
    "        parsed: ParseResult = urlparse(word)\n",
    "        if parsed.scheme and parsed.netloc:\n",
    "            urls.append(word)\n",
    "\n",
    "    return urls"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [],
   "source": [
    "def alg5(string1: str, string2: str) -> List[str]:\n",
    "    def merge_url_lists(url_list1: List[str], url_list2: List[str]) -> List[str]:\n",
    "        return url_list1 + url_list2\n",
    "\n",
    "    def find_urls_in_string(string: str) -> List[str]:\n",
    "        x: List[str] = string.split()\n",
    "        return [i for i in x if i.startswith(\"https:\") or i.startswith(\"http:\")]\n",
    "\n",
    "    string_list: List[str] = [string1, string2]\n",
    "    url_list: List[str] = reduce(merge_url_lists, map(find_urls_in_string, string_list))\n",
    "    return url_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [],
   "source": [
    "def time_algorithm(*, algorithm: Callable, number: int = 10000, **kwargs) -> None:\n",
    "    args: Tuple[str, ...] = kwargs.get(\"args\", ())\n",
    "    if algorithm == alg5 and len(args) == 2:\n",
    "        stmt: str = f\"alg5('{args[0]}', '{args[1]}')\"\n",
    "    else:\n",
    "        stmt: str = (\n",
    "            f\"{algorithm.__name__}('{args[0]}')\" if args else f\"{algorithm.__name__}()\"\n",
    "        )\n",
    "\n",
    "    setup: str = f\"from __main__ import {algorithm.__name__}\"\n",
    "    time_taken: float = timeit(stmt=stmt, setup=setup, number=number)\n",
    "    print(f\"{algorithm.__name__}: {time_taken:.5f} seconds\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['https://auth.geeksforgeeks.org/user/Chinmoy%20Lenka/articles', 'https://www.geeksforgeeks.org/']\n",
      "alg1: 0.07131 seconds\n",
      "['https://auth.geeksforgeeks.org/user/Chinmoy%20Lenka/articles', 'https://www.geeksforgeeks.org/']\n",
      "alg2: 0.02130 seconds\n",
      "['https://auth.geeksforgeeks.org/user/Chinmoy%20Lenka/articles', 'https://www.geeksforgeeks.org/']\n",
      "alg3: 0.02427 seconds\n",
      "['https://auth.geeksforgeeks.org/user/Chinmoy%20Lenka/articles', 'https://www.geeksforgeeks.org/']\n",
      "alg4: 0.10071 seconds\n",
      "['https://auth.geeksforgeeks.org/user/Chinmoy%20Lenka/articles', 'https://www.geeksforgeeks.org/']\n",
      "alg5: 0.05229 seconds\n"
     ]
    }
   ],
   "source": [
    "algorithms: List[Tuple[Callable, Tuple]] = [\n",
    "    (alg1, (string,)),\n",
    "    (alg2, (string,)),\n",
    "    (alg3, (string,)),\n",
    "    (alg4, (string,)),\n",
    "    (alg5, (string1, string2)),\n",
    "]\n",
    "\n",
    "for algorithm, args in algorithms:\n",
    "    if len(args) == 1:\n",
    "        print(algorithm(*args))\n",
    "    else:\n",
    "        print(algorithm(args[0], args[1]))\n",
    "    time_algorithm(algorithm=algorithm, args=args)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}