medium-backup-script.ipynb

medium-backup-script.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "medium-backup-script.ipynb",
      "version": "0.3.2",
      "provenance": [],
      "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/gist/btahir/af1c57771fc4318792689a11122e6388/medium-backup-script.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ffvp_f9fbYNV",
        "colab_type": "text"
      },
      "source": [
        "# Backup Your Medium Articles\n",
        "\n",
        "This script is a quick and dirty way to backup the contents of your medium stories. "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jG9TcDStrhLe",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# import stuff\n",
        "import requests\n",
        "import bs4\n",
        "import os\n",
        "import shutil\n",
        "from PIL import Image"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fjsF_K5lronE",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "#@title Make A Folder\n",
        "FOLDER_NAME = 'medium' #@param {type:\"string\"}\n",
        "os.mkdir(FOLDER_NAME)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pRVDffnZro9O",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# cd into that directory\n",
        "os.chdir(FOLDER_NAME)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "BnLdQjrirpD9",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "#@title Enter Medium Story URL\n",
        "MEDIUM_URL = 'https://medium.com/@btahir/using-python-to-backup-your-medium-articles-6f581a0c0d90' #@param {type:\"string\"}\n",
        "\n",
        "response = requests.get(MEDIUM_URL)\n",
        "soup = bs4.BeautifulSoup(response.text,'lxml')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CqQZrN00sJxz",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "3984c200-0053-43cf-8f51-5eba645f449e"
      },
      "source": [
        "# get title\n",
        "title = soup.find('h1').get_text()\n",
        "print(title)"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Using Python to Backup your Medium Articles\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-7_fFpO8sZm1",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# get text\n",
        "paragraphs = soup.find_all('p')\n",
        "\n",
        "with open('content.txt', 'w') as f:\n",
        "  f.write(title + '\\n\\n')\n",
        "  for p in paragraphs:\n",
        "    f.write( p.get_text() )\n",
        "    f.write('\\n\\n')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LMUAvCklsmD0",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 119
        },
        "outputId": "51266a5a-f3da-4e6e-a4c7-ebedf5364a75"
      },
      "source": [
        "# get images\n",
        "images = soup.find('body').find_all('img')\n",
        "i = 0\n",
        "\n",
        "for im in images:\n",
        "  i+=1\n",
        "  url = im.get('src')\n",
        "  print('Downloading: ', url) \n",
        "  try:\n",
        "    response = requests.get(url, stream=True)\n",
        "    with open(str(i) + '.jpg', 'wb') as out_file:\n",
        "        shutil.copyfileobj(response.raw, out_file)\n",
        "    del response\n",
        "  except:\n",
        "    print('Could not download: ', url)"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Downloading:  https://miro.medium.com/fit/c/96/96/1*r5v9ysUAacoGCpxgMkjLiQ.jpeg\n",
            "Downloading:  https://miro.medium.com/max/60/1*2qHXJ3-C6-RGphhlak9X5Q.jpeg?q=20\n",
            "Downloading:  None\n",
            "Could not download:  None\n",
            "Downloading:  https://miro.medium.com/max/1400/1*2qHXJ3-C6-RGphhlak9X5Q.jpeg\n",
            "Downloading:  https://miro.medium.com/fit/c/160/160/1*r5v9ysUAacoGCpxgMkjLiQ.jpeg\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Y7jaY3SJ_jkn",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# delete smaller thumbnail photos - let's say any images below 500 height + width\n",
        "for file in os.listdir('.'):\n",
        "  if file.endswith(\".jpg\"):\n",
        "    im = Image.open(file)\n",
        "    size = im.height + im.width\n",
        "    if size < 500:\n",
        "      os.remove(file)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Z42OPGS9ukHW",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "videos = soup.find_all('iframe')\n",
        "\n",
        "youtubeStarterURL = 'https://www.youtube.com/watch?v='\n",
        "vlist = []\n",
        "\n",
        "for v in videos:\n",
        "  try:\n",
        "    src = v.get('src')\n",
        "    start = src.index('watch%3Fv%3D')\n",
        "    end = src.index('&image')\n",
        "    vlist.append(youtubeStarterURL + src[start+12:end])\n",
        "  except:\n",
        "    continue\n",
        "\n",
        "if len(vlist) > 0:\n",
        "  with open('video-links.txt', 'w') as f:\n",
        "    for vid in vlist:\n",
        "      f.write( str(vid) )\n",
        "      f.write('\\n\\n')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "OY5Tb6SI4aSe",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "4fe6fc49-ed1a-4b47-cd2f-7641b4074b09"
      },
      "source": [
        "cd .."
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/content\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "J-MJqeeuvMJw",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "dfd8e1f7-7097-48c0-b415-03b5ed7f8f27"
      },
      "source": [
        "#@title ZIP Folder\n",
        "ZIP_FILE = 'medium-zipped' #@param {type:\"string\"}\n",
        "shutil.make_archive(ZIP_FILE, 'zip', FOLDER_NAME)"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'/content/medium-zipped.zip'"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "HwY2ISxhaoYu",
        "colab_type": "text"
      },
      "source": [
        "You can download the final zipped file manually form the left or send to dropbox/google drive/ other storage place."
      ]
    }
  ]
}