Python_PDF_Utils.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from pyPdf import PdfFileReader\n",
    "import shutil"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "pdf_dir = r'/home/user/Desktop/finance_2016_17/'\n",
    "missed_files = []\n",
    "pdf_files = []\n",
    "for doc in os.listdir(pdf_dir):\n",
    "    if doc.endswith(\".pdf\"):\n",
    "        try:\n",
    "            pdf = PdfFileReader(open(os.path.join(pdf_dir, doc)))\n",
    "            pdf_files.append([doc, pdf.getNumPages()])\n",
    "        except:\n",
    "            missed_files.append(doc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['PSI_G&A_16-17_655.pdf',\n",
       " 'PSI_G&A_16-17_1401-1.pdf',\n",
       " 'PSI_G&A_16-17_861.pdf',\n",
       " 'PSI_G&A_16-17_1596-1.pdf',\n",
       " 'PSI_G&A_16-17_441.pdf',\n",
       " 'PSI_G&A_16-17_1491-1.pdf']"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "missed_files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = sorted(pdf_files, key=lambda x: (x[1], x[0]), reverse=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "mv = [val for idx, val in enumerate(a) if val[1]> 100]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "big_dir = r'/home/user/Desktop/big_documents/'\n",
    "for idx,val in enumerate(mv):\n",
    "    try:\n",
    "        shutil.move(os.path.join(pdf_dir, val[0]), os.path.join(big_dir, val[0]))\n",
    "    except:\n",
    "        print val"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "24"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(mv)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}