Ingestando noticias de mi propia web.ipynb

ingestando-noticias-de-mi-propia-web.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Ingestando noticias de mi propia web.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyN4q7Z8nRJTK+8DwKLR/Bl5",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/ccortezb/d337bc308e6eb804407231140e8655f4/ingestando-noticias-de-mi-propia-web.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "BBWvh-jVtn8J"
      },
      "source": [
        "import requests\n",
        "from bs4 import BeautifulSoup\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import os\n",
        "%matplotlib inline\n",
        "\n",
        "cortezcloud_urls = ['https://www.cortez.cloud/categories/fundamentals',\n",
        "             'https://www.cortez.cloud/categories/serverless',\n",
        "             'https://www.cortez.cloud/categories/awsugperu']\n",
        "\n",
        "def ingestar_noticias(cortezcloud_urls):\n",
        "    cortezcloud_data = []\n",
        "    for url in cortezcloud_urls:\n",
        "        cloud_category = url.split('/')[4]\n",
        "        data = requests.get(url)\n",
        "        soup = BeautifulSoup(data.content, 'html.parser')\n",
        "        \n",
        "        news_blogs = [{'news_headline': headline.find('div', \n",
        "                                                         attrs={\"class\": \"blog-title\"}).string,\n",
        "                          'news_blog': blog.find('div', \n",
        "                                                       attrs={\"class\": \"preview-text\"}).string,\n",
        "                          'cloud_category': cloud_category}\n",
        "                         \n",
        "                            for headline, blog in \n",
        "                             zip(soup.find_all('div', \n",
        "                                               class_=[\"thumbnail-text\"]),\n",
        "                                 soup.find_all('div', \n",
        "                                               class_=[\"thumbnail-text\"]))\n",
        "                        ]\n",
        "        cortezcloud_data.extend(news_blogs)\n",
        "        \n",
        "    df =  pd.DataFrame(cortezcloud_data)\n",
        "    #df = df[['news_headline', 'news_blog', 'cloud_category']]\n",
        "    return df\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 162
        },
        "id": "ERIXIl2ewiwn",
        "outputId": "e6e184cf-1264-4abe-d94f-9ad303cdb51d"
      },
      "source": [
        "ultimos_posts = ingestar_noticias(cortezcloud_urls)\n",
        "ultimos_posts.head(10)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>news_headline</th>\n",
              "      <th>news_blog</th>\n",
              "      <th>cloud_category</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>2 Trabajando con Amazon DocumentDB desde mi local</td>\n",
              "      <td>Seguimos en las series de Docdb, esta vez, 2da...</td>\n",
              "      <td>fundamentals</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>5 cosas que necesitas empezar a aprender para ...</td>\n",
              "      <td>Aún no entiendes bien cómo empezar a migrar tu...</td>\n",
              "      <td>fundamentals</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Primeros pasos con Amazon DocumentDB y AWS CLI</td>\n",
              "      <td>Estas serán unas series donde hablaremos de un...</td>\n",
              "      <td>fundamentals</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Cómo me convierto en un AWS Community Builder ...</td>\n",
              "      <td>Empieza tu travesía para educar AWS en el Perú</td>\n",
              "      <td>awsugperu</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                       news_headline  ... cloud_category\n",
              "0  2 Trabajando con Amazon DocumentDB desde mi local  ...   fundamentals\n",
              "1  5 cosas que necesitas empezar a aprender para ...  ...   fundamentals\n",
              "2     Primeros pasos con Amazon DocumentDB y AWS CLI  ...   fundamentals\n",
              "3  Cómo me convierto en un AWS Community Builder ...  ...      awsugperu\n",
              "\n",
              "[4 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 51
        }
      ]
    }
  ]
}