How to build an interactive scraper in a Jupyter notebook

scraper.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "4be886d2",
   "metadata": {},
   "source": [
    "# Interactive webpage scraper in Jupyter notebooks\n",
    "\n",
    "How to build an interactive scraper in a Jupyter notebook. This proof-of-concept uses [Outside's search feature](https://www.outsideonline.com/?s=outside)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "1ca5f35f",
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "from bs4 import BeautifulSoup \n",
    "from IPython.display import display, Markdown\n",
    "import ipywidgets as widgets\n",
    "import re\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "68547a37",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "916d7a80aee14e908fd17bf37301c60e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "VBox(children=(Text(value='Bigfoot', description='Search query', placeholder='Bigfoot'), Output()))"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def scrapeSearchResults(query):\n",
    "    articles = []       \n",
    "\n",
    "    url = \"https://www.outsideonline.com/?s={}\".format(query.replace(\" \", \"-\"))    \n",
    "    r = requests.get(url)\n",
    "    soup = BeautifulSoup(r.content)\n",
    "    blocks = soup.find_all(\"div\", {\"class\", \"c-block\"})\n",
    "    for block in blocks:\n",
    "        img = block.find(\"img\", {\"class\": \"o-image\"})\n",
    "        author = block.find(\"span\", {\"class\": \"o-meta__author\"})\n",
    "        heading = block.find(\"a\", {\"class\": \"o-heading__link\"})\n",
    "        dek = block.find(\"div\", {\"class\": \"o-dek\"})\n",
    "        dateOg = block.find(\"span\", {\"class\": \"o-meta__date--original\"})\n",
    "        dateUpdate = block.find(\"span\", {\"class\": \"o-meta__date--updated\"})\n",
    "\n",
    "        articles.append({\n",
    "            \"title\": heading.text.replace(\"  \", \"\").replace(\"\\n\", \"\") if heading else None,\n",
    "            \"dek\": dek.p.text if dek else None,\n",
    "            \"href\":  block.find(\"a\", {\"class\": \"o-heading__link\"})[\"href\"],\n",
    "            \"img\": img[\"data-src\"] if img else None,\n",
    "            \"original-date\":  dateOg.find(\"time\")[\"datetime\"] if dateOg else None,\n",
    "            \"updated-date\": dateUpdate.find(\"time\")[\"datetime\"],\n",
    "            \"author\": author.strong.text if author else None,\n",
    "        })\n",
    "\n",
    "    return articles\n",
    "\n",
    "\n",
    "def displayResults(query):\n",
    "    results = scrapeSearchResults(query)\n",
    "    serializedResults = json.dumps(results, indent=1)\n",
    "    print(serializedResults)\n",
    "    \n",
    "searchWidget = widgets.Text(\n",
    "    value=\"Bigfoot\",\n",
    "    placeholder=\"Bigfoot\",\n",
    "    description=\"Search query\",\n",
    "    disabled=False\n",
    ")\n",
    "\n",
    "out = widgets.interactive_output(displayResults, {\"query\": searchWidget})\n",
    "\n",
    "widgets.VBox([searchWidget, out])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ebb5865b",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}