Fifth Project file

Author: lakshay2k

Extract_Text_from_pdf.ipynb

@@ -0,0 +1,91 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: pyPDF2 in c:\\programdata\\anaconda3\\lib\\site-packages (1.26.0)\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "pip install pyPDF2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The Document details : \n",
+      "\n",
+      "{'/Title': 'Machine Learning', '/Author': 'nazli', '/CreationDate': \"D:20210125212118+05'30'\", '/ModDate': \"D:20210125212118+05'30'\", '/Producer': 'Microsoft® PowerPoint® 2016', '/Creator': 'Microsoft® PowerPoint® 2016'}\n",
+      "The pages are : \n",
+      "69\n"
+     ]
+    }
+   ],
+   "source": [
+    "import PyPDF2\n",
+    "a = PyPDF2.PdfFileReader(\"ML2401.ppt.pdf\")\n",
+    "print(\"The Document details : \\n\")\n",
+    "print(a.documentInfo)\n",
+    "print(\"The pages are : \")\n",
+    "print(a.getNumPages())\n",
+    "str=\"\"\n",
+    "for i in range(1,11):\n",
+    "    str += a.getPage(i).extractText()\n",
+    "    \n",
+    "with open(\"text.txt\",\"w\",encoding ='utf-8') as f:\n",
+    "    f.write(str)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#I created a program that extractes the text from PDF and creates an Text file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}