{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "0db89081",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_links_from_page(url):\n",
    "    import requests\n",
    "    from bs4 import BeautifulSoup\n",
    "    import re\n",
    "\n",
    "    response = requests.get(url)\n",
    "    soup = BeautifulSoup(response.text, 'html.parser')\n",
    "\n",
    "    # 2. Find all <a> or <button> tags containing the target text\n",
    "    # We use re.IGNORECASE to catch variations like \"ИЗТЕГЛЯНЕ\"\n",
    "    target_text = \"Изтегляне\"\n",
    "    elements = soup.find_all(['a', 'button'], string=re.compile(target_text, re.IGNORECASE))\n",
    "\n",
    "    download_links = []\n",
    "\n",
    "    for tag in elements:\n",
    "        # If the tag is directly an <a>, get its href\n",
    "        if tag.name == 'a' and tag.get('href'):\n",
    "            download_links.append(tag['href'])\n",
    "        \n",
    "        # If it's a <button>, it might be wrapped in an <a> tag\n",
    "        elif tag.name == 'button':\n",
    "            parent_a = tag.find_parent('a')\n",
    "            if parent_a and parent_a.get('href'):\n",
    "                download_links.append(parent_a['href'])\n",
    "\n",
    "    # # Print results\n",
    "    # for link in set(download_links): # 'set' removes duplicates\n",
    "    #     print(f\"Found download link: {link}\")\n",
    "    return download_links"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "1bca41d0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Page:  1\n",
      "Page:  2\n",
      "Page:  3\n",
      "Page:  4\n",
      "Page:  5\n",
      "Page:  6\n",
      "Page:  7\n",
      "Page:  8\n",
      "Page:  9\n",
      "Page:  10\n",
      "Page:  11\n",
      "Page:  12\n",
      "Page:  13\n",
      "Page:  14\n",
      "Page:  15\n",
      "Page:  16\n",
      "Page:  17\n",
      "Page:  18\n",
      "Page:  19\n",
      "Page:  20\n",
      "Page:  21\n",
      "Page:  22\n",
      "Page:  23\n",
      "Page:  24\n",
      "Page:  25\n",
      "Page:  26\n",
      "Page:  27\n",
      "Page:  28\n",
      "Page:  29\n",
      "Page:  30\n",
      "Page:  31\n",
      "Page:  32\n",
      "Page:  33\n",
      "Page:  34\n",
      "Page:  35\n",
      "Page:  36\n",
      "Page:  37\n",
      "Page:  38\n",
      "Page:  39\n",
      "Page:  40\n",
      "Page:  41\n",
      "Page:  42\n",
      "Page:  43\n",
      "Page:  44\n",
      "Page:  45\n",
      "Page:  46\n",
      "Page:  47\n",
      "Page:  48\n",
      "Page:  49\n",
      "Page:  50\n",
      "Page:  51\n",
      "Page:  52\n",
      "Page:  53\n",
      "Page:  54\n",
      "Page:  55\n",
      "Page:  56\n",
      "Page:  57\n",
      "Page:  58\n",
      "Page:  59\n",
      "Page:  60\n",
      "Page:  61\n",
      "Page:  62\n",
      "Page:  63\n",
      "Page:  64\n",
      "Page:  65\n",
      "Page:  66\n",
      "Page:  67\n",
      "Page:  68\n",
      "Page:  69\n",
      "Page:  70\n",
      "Page:  71\n",
      "Page:  72\n",
      "Page:  73\n",
      "Page:  74\n",
      "Page:  75\n",
      "Page:  76\n",
      "Page:  77\n",
      "Page:  78\n",
      "Page:  79\n",
      "Page:  80\n",
      "Page:  81\n",
      "Page:  82\n",
      "Page:  83\n",
      "Page:  84\n",
      "Page:  85\n",
      "Page:  86\n",
      "Page:  87\n",
      "Page:  88\n",
      "Page:  89\n",
      "Page:  90\n",
      "Page:  91\n",
      "Page:  92\n",
      "Page:  93\n",
      "Page:  94\n",
      "Page:  95\n",
      "Page:  96\n",
      "Page:  97\n",
      "Page:  98\n",
      "Page:  99\n",
      "Page:  100\n",
      "Page:  101\n",
      "Page:  102\n",
      "Page:  103\n",
      "Page:  104\n",
      "Page:  105\n",
      "Page:  106\n",
      "Page:  107\n",
      "Page:  108\n",
      "Page:  109\n",
      "Page:  110\n",
      "Page:  111\n",
      "Page:  112\n",
      "Page:  113\n",
      "Page:  114\n",
      "Page:  115\n",
      "Page:  116\n",
      "Page:  117\n",
      "Page:  118\n",
      "Page:  119\n",
      "Page:  120\n",
      "Page:  121\n",
      "Page:  122\n",
      "Page:  123\n",
      "Page:  124\n",
      "Page:  125\n",
      "Page:  126\n",
      "Page:  127\n",
      "Page:  128\n",
      "Page:  129\n",
      "Page:  130\n",
      "Page:  131\n",
      "Page:  132\n",
      "Page:  133\n",
      "Page:  134\n",
      "Page:  135\n",
      "Page:  136\n",
      "Page:  137\n",
      "Page:  138\n",
      "Page:  139\n",
      "Page:  140\n",
      "Page:  141\n",
      "Page:  142\n",
      "Page:  143\n",
      "Page:  144\n",
      "Page:  145\n",
      "Page:  146\n",
      "Page:  147\n",
      "Page:  148\n",
      "Page:  149\n",
      "Page:  150\n",
      "Page:  151\n",
      "Page:  152\n",
      "Page:  153\n",
      "Page:  154\n",
      "Page:  155\n",
      "Page:  156\n",
      "Page:  157\n",
      "Page:  158\n",
      "Page:  159\n",
      "Page:  160\n",
      "Page:  161\n",
      "Page:  162\n",
      "Page:  163\n",
      "Page:  164\n",
      "Page:  165\n",
      "Page:  166\n",
      "Page:  167\n",
      "Page:  168\n",
      "Page:  169\n",
      "Page:  170\n",
      "Page:  171\n",
      "Page:  172\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import sys\n",
    "import time\n",
    "import random\n",
    "\n",
    "start_num = 0 \n",
    "iter_num = 5\n",
    "string_plchldr = \"number_start_placeholder\"\n",
    "\n",
    "link = f\"https://www.bgmountains.org/bg/gps-tracks/cats/all?type=all&start=number_start_placeholder\"\n",
    "lim = 172\n",
    "#take from website\n",
    "list_links = []\n",
    "output_links = []\n",
    "with open(\"out.log\",\"w\") as f:\n",
    "    for i in range(lim):\n",
    "        print(\"Page: \",i+1)\n",
    "        response_links = get_links_from_page(link.replace(string_plchldr,str(iter_num*i)))\n",
    "        output_links.append(response_links)\n",
    "        time.sleep(random.randint(0,6))\n",
    "        f.write(str(response_links) + \"\\n\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "d87c4a49",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[['/bg/gps-tracks/cats/summary/4-belasitsa/1-biloto',\n",
       "  '/bg/gps-tracks/cats/summary/3-osogovo-belasishka/5-dzhama-kadiitsa',\n",
       "  '/bg/gps-tracks/cats/summary/33-pirin/144-sandanski-lilyanovo',\n",
       "  '/bg/gps-tracks/cats/summary/6-osogovo/7-trite-buki-ruen',\n",
       "  '/bg/gps-tracks/cats/summary/8-maleshevska/11-krupnik']]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "output_links"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "3de85cf5",
   "metadata": {},
   "outputs": [],
   "source": [
    "flat = []\n",
    "\n",
    "with open(\"url-final.txt\",\"w\") as f:\n",
    "    for item in output_links:\n",
    "        for entry in item:\n",
    "            flat.append(entry)\n",
    "            f.write(\"https://www.bgmountains.org\"+entry+\"\\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "effc0400",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "858\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "858"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "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": "3.14.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}