python-tika-server.ipnb

python-tika-server.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:388fb5be2fc1d54eed3c94abfce3c816b8f2abe8ab8b2384323a15b22ad2de0a"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Install Tika server docker image:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "$ sudo docker pull logicalspark/docker-tikaserver\n",
      "$ sudo docker run -d -p 9998:9998 logicalspark/docker-tikaserver"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Check to see if server is up:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "$ curl -X GET http://localhost:9998/tika"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "> This is Tika Server. Please PUT"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Use curl..."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "$ curl -T foo.doc http://localhost:9998/rmeta"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "[\n",
      " {\"Application-Name\":\"Microsoft Office Word\",\n",
      "  \"Application-Version\":\"15.0000\",\n",
      "  \"X-Parsed-By\":[\"org.apache.tika.parser.DefaultParser\",\"org.apache.tika.parser.microsoft.ooxml.OOXMLParser\"],\n",
      "  \"X-TIKA:content\":\"embed_0 \"\n",
      "  ...\n",
      " },\n",
      " {\"Content-Encoding\":\"ISO-8859-1\",\n",
      "  \"Content-Length\":\"8\",\n",
      "  \"Content-Type\":\"text/plain; charset=ISO-8859-1\"\n",
      "  \"X-TIKA:content\": ...\n",
      " }\n",
      " ...\n",
      "]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "... or your favourite REST python client:"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import requests\n",
      "import json\n",
      "\n",
      "url = \"http://localhost:9998/rmeta\"\n",
      "filepath = 'foo.doc'\n",
      "\n",
      "with open(filepath) as fh:\n",
      "    filedata = fh.read()\n",
      "    response = requests.put(url, data=filedata, params={'file': filepath})"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "docjson = json.loads(response.text)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 16
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Document Text is in X-TIKA:content"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print docjson[0]['X-TIKA:content']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "foo doc body"
     ]
    }
   ],
   "metadata": {}
  }
 ]
}