Notebooks with basic for metadat usage

notebooks/BasicMetadata_Class.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The autoreload extension is already loaded. To reload it, use:\n",
+      "  %reload_ext autoreload\n"
+     ]
+    }
+   ],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2\n",
+    "\n",
+    "import os, sys\n",
+    "\n",
+    "sys.path.append('../src/python/')\n",
+    "\n",
+    "import def_classes as defc\n",
+    "import numpy as np\n",
+    "from pdf2image import convert_from_path, convert_from_bytes\n",
+    "import utils_proc\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "year = 1978\n",
+    "folder_database = '../data/AB/'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## List the files inside the tar"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1011\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "array([['./1978/20006356.pdf', '20006356'],\n",
+       "       ['./1978/20006357.pdf', '20006357'],\n",
+       "       ['./1978/20006358.pdf', '20006358'],\n",
+       "       ...,\n",
+       "       ['./1978/20007364.pdf', '20007364'],\n",
+       "       ['./1978/20007365.pdf', '20007365'],\n",
+       "       ['./1978/20007366.pdf', '20007366']], dtype='<U19')"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "name_tar = '00_rawpdfs'\n",
+    "list_docs = utils_proc.get_list(year, folder_database, name_tar)\n",
+    "print(len(list_docs[0]))\n",
+    "np.transpose(list_docs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# From the ones above\n",
+    "iddoc = '20026449'\n",
+    "input_file = './' + str(year) +'/' + iddoc +'.pdf'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "d1 = defc.Document(input_file, folder_database)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "d1."
+   ]
+  }
+ ],
+ "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": "3.6.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}