Social Media data - Twitter use case

Author: nathalyAlarconT

Unstructured_SocialMedia_Twitter.ipynb

@@ -0,0 +1,137 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "Unstructured_SocialMedia_Twitter.ipynb",
+      "provenance": [],
+      "collapsed_sections": [],
+      "include_colab_link": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "view-in-github",
+        "colab_type": "text"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/nathalyAlarconT/mod_datasources/blob/master/Unstructured_SocialMedia_Twitter.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "HJtCq5TYaEFE",
+        "colab_type": "text"
+      },
+      "source": [
+        "\n",
+        "Inicialmente, debes recabar el token de tu cuenta de twitter, en la sección de aplicaciones:\n",
+        "\n",
+        "https://developer.twitter.com/\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "kgOfWD5eLq1Y",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "import tweepy\n",
+        "import csv\n",
+        "# import pandas as pd\n",
+        "####input your credentials here\n",
+        "\n",
+        "consumer_key = 'WvOxM9QWOGUjdw5YzfsnuDaRc'\n",
+        "consumer_secret = '6HPusgb4zGMbQkJ2NtC3wdVRuZytyQvZuQfJiZhbcSxYkN2NR0'\n",
+        "access_token = ''\n",
+        "access_token_secret = ''\n",
+        "\n",
+        "auth = tweepy.OAuthHandler(consumer_key, consumer_secret)\n",
+        "auth.set_access_token(access_token, access_token_secret)\n",
+        "api = tweepy.API(auth,wait_on_rate_limit=True)"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "BDj4Cft_L1EM",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "# Vamos a  guardar los tweets en un archivo .csv\n",
+        "csvFile = open('tweets.csv', 'a+')\n",
+        "#Usamos csv Writer\n",
+        "csvWriter = csv.writer(csvFile)\n",
+        "\n",
+        "# Configuramos los términos de nuestra búsqueda.\n",
+        "texto_a_buscar = '@elonmusk'\n",
+        "cantidad_resultados = 10\n",
+        "fechas_inicial = \"2020-02-01\"\n",
+        "idioma = \"es\"\n",
+        "\n",
+        "\n",
+        "i = 0\n",
+        "for tweet in tweepy.Cursor(api.search,q=texto_a_buscar,\n",
+        "                           lang=idioma,\n",
+        "                           since=fechas_inicial).items(cantidad_resultados):\n",
+        "    i = i + 1\n",
+        "    print(\"\\n \", i,\".------------------------------------------------\")\n",
+        "    print (tweet.created_at, '[', tweet.user.screen_name, ']', '\\n', tweet.text)\n",
+        "\n",
+        "    # Vamos a guardar el resultado de los tuits obtenidos en un archivo\n",
+        "    csvWriter.writerow([tweet.created_at,tweet.user.screen_name, tweet.text.encode('utf-8')])\n",
+        "csvFile.close()"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "gGW7vcMD3yvp",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "!head tweets.csv"
+      ],
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "vu0-7wuvMGm-",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "# Analizamos ahora el contenido de un tuit\n",
+        "\n",
+        "import json\n",
+        "# convert to string\n",
+        "json_str = json.dumps(tweet._json)\n",
+        "\n",
+        "#deserialise string into python object\n",
+        "parsed = json.loads(json_str)\n",
+        "\n",
+        "print(json.dumps(parsed, indent=4, sort_keys=True))"
+      ],
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}