{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: PyPDF2 in c:\\users\\franz\\.conda\\envs\\tensorflow\\lib\\site-packages (1.26.0)\n",
      "Requirement already satisfied: tika in c:\\users\\franz\\.conda\\envs\\tensorflow\\lib\\site-packages (1.24)\n",
      "Requirement already satisfied: requests in c:\\users\\franz\\.conda\\envs\\tensorflow\\lib\\site-packages (from tika) (2.27.1)\n",
      "Requirement already satisfied: setuptools in c:\\users\\franz\\.conda\\envs\\tensorflow\\lib\\site-packages (from tika) (58.0.4)\n",
      "Requirement already satisfied: charset-normalizer~=2.0.0 in c:\\users\\franz\\.conda\\envs\\tensorflow\\lib\\site-packages (from requests->tika) (2.0.4)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\franz\\.conda\\envs\\tensorflow\\lib\\site-packages (from requests->tika) (2021.10.8)\n",
      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\franz\\.conda\\envs\\tensorflow\\lib\\site-packages (from requests->tika) (3.3)\n",
      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\franz\\.conda\\envs\\tensorflow\\lib\\site-packages (from requests->tika) (1.26.8)\n"
     ]
    }
   ],
   "source": [
    "! pip install PyPDF2\n",
    "! pip install tika"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from tika import parser\n",
    "import codecs\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def obtener_texto(file_path,store_path):\n",
    "    file_data = parser.from_file(file_path)\n",
    "    output = file_data['content']\n",
    "    output = output.strip()   \n",
    "    output= output.split('\\n')\n",
    "    with codecs.open(store_path+'.txt', 'w','utf-8') as the_file: \n",
    "        for line in output:\n",
    "            #print(line)\n",
    "            if len(line)>4:       \n",
    "                the_file.write(str(line)+'\\n')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-03-17 17:02:20,018 [MainThread  ] [WARNI]  Failed to see startup log message; retrying...\n"
     ]
    }
   ],
   "source": [
    "PDF_PATH = 'PDF'\n",
    "TXT_PATH= 'TXT'\n",
    "files  = os.listdir(PDF_PATH)\n",
    "for  file in  files:\n",
    "    obtener_texto(PDF_PATH+'/'+file,TXT_PATH+'/'+file)\n",
    " "
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "3f7e9d73c32ad96f75174922c475a50b168aad887cbaa14717912a88f31d3802"
  },
  "kernelspec": {
   "display_name": "Python 3.9.7 ('tf-gpu')",
   "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": "3.9.7"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}