overcoming-bias-anthology-md.ipynb

overcoming-bias-anthology-md.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "private_outputs": true,
      "provenance": [],
      "authorship_tag": "ABX9TyNc7fKPdBKHKm9MXz/hd0J5",
      "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/intellectronica/e6fcbba87a051f61a1e8c632b9a86983/overcoming-bias-anthology-md.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "m46DdbX1-gVJ"
      },
      "outputs": [],
      "source": [
        "%pip install requests beautifulsoup4 markdown\n",
        "from IPython.display import clear_output ; clear_output()\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import requests\n",
        "from bs4 import BeautifulSoup\n",
        "import time"
      ],
      "metadata": {
        "id": "V-yvwBYaGoU0"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "anthology_html = requests.get('https://overcoming-bias-anthology.com/').text"
      ],
      "metadata": {
        "id": "zZI7cSgO-4Qq"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "anthology_index = []\n",
        "\n",
        "anthology_soup = BeautifulSoup(anthology_html, 'html.parser')\n",
        "for section in anthology_soup.find_all('section'):\n",
        "  idx_subsections = []\n",
        "  for subsection in section.find_all('div'):\n",
        "    idx_items = []\n",
        "    for item in subsection.find_all('li'):\n",
        "      idx_item = {\n",
        "        'title': item.find('a').text,\n",
        "        'url': item.find('a')['href'],\n",
        "        'html': requests.get(item.find('a')['href']).text,\n",
        "      }\n",
        "      idx_items.append(idx_item)\n",
        "      time.sleep(3.45)\n",
        "    idx_subsection = {\n",
        "      'title': subsection.find('h2').text,\n",
        "      'items': idx_items,\n",
        "    }\n",
        "    idx_subsections.append(idx_subsection)\n",
        "  idx_section = {\n",
        "    'title': section.find('h1').text.split(': ')[1],\n",
        "    'subsections': idx_subsections,\n",
        "  }\n",
        "  anthology_index.append(idx_section)"
      ],
      "metadata": {
        "id": "lI_6E9hY_RVn"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from markdown import markdown\n",
        "from IPython.display import display, Markdown\n",
        "\n",
        "anthology_md = '# Overcoming Bias Anthology\\n\\n'\n",
        "\n",
        "for section in anthology_index:\n",
        "  anthology_md += f'## {section[\"title\"]}\\n\\n'\n",
        "  for subsection in section['subsections']:\n",
        "    anthology_md += f'### {subsection[\"title\"]}\\n\\n'\n",
        "    for item in subsection['items']:\n",
        "      anthology_md += f'#### {item[\"title\"]}\\n\\n'\n",
        "      item_soup = BeautifulSoup(item['html'], 'html.parser')\n",
        "      anthology_md += markdown(\n",
        "        item_soup.find('div', class_='available-content').decode_contents()\n",
        "      )\n",
        "      anthology_md += '\\n\\n'\n",
        "\n",
        "with open('overcoming-bias-anthology.md', 'w') as f:\n",
        "  f.write(anthology_md)\n",
        "\n",
        "with open('overcoming-bias-anthology.md', 'r') as f:\n",
        "  anthology_md = f.read()\n",
        "  display(Markdown(anthology_md))"
      ],
      "metadata": {
        "id": "GtNPNl1lACS_"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "hvUVZ3edCfjr"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}