package.json

{
  "name": "wiki",
  "version": "1.0.0",
  "description": "",
  "main": "scan.js",
  "scripts": {
    "test": "echo \"Error: no test specified\" && exit 1"
  },
  "author": "",
  "license": "ISC",
  "dependencies": {
    "node-fetch": "^2.6.1",
    "wikijs": "^6.0.1"
  }
}

scan.js

const fetch = require("node-fetch");
const fs = require('fs');

// Search query string
const SEARCH_QUERY = "hastemplate:Infobox_officeholder incategory:living_people";

// Suspicious revision keywords
const SUSPICIOUS_WORDS = ["award", "charity", "controversies"]

// File name is current timestamp
var stream = fs.createWriteStream(Date.now() + ".txt");

stream.once('open', function(fd) {

  // Start at page 1 of API search results
  var previous_offset = 0;
  var previous_continue = "-||";

  // Write header to .txt export file
  stream.write("id | title | wordcount | pageviews | revisions | flagged\n");

  async function startScan() {

    for (var i = 0; i < 100; i++) {

      var search_url = "https://en.wikipedia.org/w/api.php?action=query&list=search&srsearch=" + encodeURI(SEARCH_QUERY) + "&srlimit=50&format=json";

      if (previous_offset) {
        search_url = search_url + "&sroffset=" + previous_offset;
        search_url = search_url + "&continue=" + previous_continue;
      }

      var response = await fetch(search_url);
      var data = await response.json();

      if (data.continue) {
        previous_offset = data.continue.sroffset;
        previous_continue = data.continue.continue;
      }

      for (var j = 0; j < 50; j++) {

        // Pause for 1 second to avoid API rate limit
        await new Promise(r => setTimeout(r, 1000));

        var page_id = data.query.search[j].pageid;
        var page_url = "https://en.wikipedia.org/w/api.php?action=query&format=json&prop=pageviews|revisions&pageids=" + page_id + "&rvlimit=100";

        var page_response = await fetch(page_url);
        var page_data = await page_response.json();

        // Get page title
        var title = page_data.query.pages[page_id].title;

        // Get page wordcount
        var wordcount = data.query.search[j].wordcount;

        // Get number of pageviews in the last month
        var pageviews = Object.values(page_data.query.pages[page_id].pageviews).reverse();
        var month_pageviews = 0;
        for (var p = 0; p < 30; p++) {
          month_pageviews += pageviews[p];
        }

        // Get number of revisions in the last month
        var recent_revisions = 0;
        for (var r = 0; r < page_data.query.pages[page_id].revisions.length; r++) {
          var revision_date = new Date(page_data.query.pages[page_id].revisions[r].timestamp);
          if (daysBetween(new Date(), revision_date) < 30) {
            recent_revisions += 1;
          }
        }

        // Get number of revisions that mention keywords
        var suspicious_revisions = 0;
        for (var r = 0; r < page_data.query.pages[page_id].revisions.length; r++) {
          var revision_date = new Date(page_data.query.pages[page_id].revisions[r].timestamp);
          let revision_comment = page_data.query.pages[page_id].revisions[r].comment;
          if (revision_comment) {
            revision_comment = revision_comment.toLowerCase();
            if (daysBetween(new Date(), revision_date) < 30) {
              for (var x = 0; x < SUSPICIOUS_WORDS.length; x++) {
                if (revision_comment.includes(SUSPICIOUS_WORDS[x])) {
                  suspicious_revisions += 1;
                }
              }
            }
          }
        }

        console.log("(" + page_id + ") " + title + " | " + wordcount + " | " + month_pageviews + " | " + recent_revisions + " | " + suspicious_revisions)

        // Write data to file
        stream.write(page_id + " | " + title + " | " + wordcount + " | " + month_pageviews + " | " + recent_revisions + " | " + suspicious_revisions + "\n");

      }
    }

  }

  function daysBetween(d1, d2) {
    var diff = Math.abs(d1.getTime() - d2.getTime());
    return diff / (1000 * 60 * 60 * 24);
  };

  startScan();

});