Notebook for scraping reviews from Trustpilot

trustpilot-scraping.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Trustpilot Scraping Script\n",
    "Notebook created Jan, 2022 by <a href=\"https://www.linkedin.com/in/andy-clarke-media/\" target=\"_blank\">Andy Clarke - Data Journalist @ Graphext</a>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Imports\n",
    "import math\n",
    "import csv\n",
    "import time\n",
    "import json\n",
    "import requests\n",
    "from lxml import html"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Scraper set for http://www.trustpilot.com/review/n26.com - saving result to test_n26.csv\n"
     ]
    }
   ],
   "source": [
    "## Configurations\n",
    "\n",
    "# Trustpilot review page\n",
    "basePage = 'http://www.trustpilot.com/review/'\n",
    "\n",
    "# Change the name of your \n",
    "reviewSite = 'n26.com'\n",
    "reviewPage = basePage + reviewSite\n",
    "\n",
    "# Data file to save to | will save data row by row\n",
    "datafile = 'test_n26.csv'\n",
    "\n",
    "# Trustpilot default \n",
    "resultsPerPage = 20 \n",
    "\n",
    "print('Scraper set for ' + reviewPage + ' - saving result to ' + datafile)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/anaconda3/lib/python3.7/site-packages/urllib3/connectionpool.py:847: InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings\n",
      "  InsecureRequestWarning)\n"
     ]
    }
   ],
   "source": [
    "## Count amount of pages to scrape\n",
    "\n",
    "# Get page, skipping HTTPS as it gives certificate errors\n",
    "page = requests.get(reviewPage, verify=False)\n",
    "tree = html.fromstring(page.content)\n",
    "\n",
    "# Amount of chunks to consider for displaying processing output \n",
    "# For ex. 10 means output progress for every 10th of the data\n",
    "tot_chunks = 20\n",
    "\n",
    "# Throttling to avoid spamming page with requests\n",
    "# With sleepTime seconds between every page request\n",
    "throttle = True\n",
    "sleepTime = 1\n",
    "\n",
    "# Adjust number of pages to scrape (use the number inside the last pagination element)\n",
    "pages = 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processing..\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-39-a024e3f3794e>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     10\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     11\u001b[0m         \u001b[0;31m# Sleep if throttle enabled\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 12\u001b[0;31m         \u001b[0;32mif\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mthrottle\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mtime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msleep\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msleepTime\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     13\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     14\u001b[0m         \u001b[0mpage\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrequests\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mreviewPage\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;34m'?page='\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "## Main scraping section\n",
    "\n",
    "with open(datafile, 'w', newline='', encoding='utf8') as csvfile:\n",
    "    \n",
    "    # Tab delimited to allow for special characters\n",
    "    datawriter = csv.writer(csvfile, delimiter=',')\n",
    "    datawriter.writerow(['published_date', 'country_code', 'title', 'body', 'rating'])\n",
    "    print('Processing..')\n",
    "    for i in range(1,pages+1):\n",
    "        \n",
    "        # Sleep if throttle enabled\n",
    "        if(throttle): time.sleep(sleepTime)\n",
    "\n",
    "        page = requests.get(reviewPage + '?page=' + str(i))\n",
    "        tree = html.fromstring(page.content)\n",
    "        \n",
    "        # Each item below scrapes a pages review titles, bodies and ratings\n",
    "        \n",
    "        # This element selector will update\n",
    "        script_bodies = tree.xpath(\"//script[starts-with(@id, '__NEXT_DATA__')]\")\n",
    "        for idx,elem in enumerate(script_bodies):\n",
    "            curr_item = json.loads(elem.text_content())\n",
    "            \n",
    "            reviews_list = curr_item['props']['pageProps']['reviews']\n",
    "            \n",
    "            # Capture Data\n",
    "            for rev in reviews_list:\n",
    "                country_code = rev['consumer']['countryCode']\n",
    "                published_date = rev['dates']['publishedDate']\n",
    "                title = rev['title']\n",
    "                body = rev['text']\n",
    "                rating = rev['rating']\n",
    "                \n",
    "                #print(published_date, country_code, title, body, rating)\n",
    "                \n",
    "                datawriter.writerow([published_date, country_code, title, body, rating])\n",
    "            \n",
    "    print('Processed ratings.. Finished!')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}