show all additions in wikipedia page history

skibadee.js

// show all additions in wikipedia page history
//
// get the XML file from
//   https://en.wikipedia.org/wiki/Special:Export
//
//   Add pages manually:
//     Skibadee
//
//   [ ] Include only the current revision, not the full history
//    ^ uncheck this
//
// set filename in variable
//   wikipedia_xml_file
//
// install dependencies
//   npm i xml2js diff
//
// run script
//   node skibadee.js
//
// comment the line
//     if (ip == 1) { break }
//   to see all pages
//
// license = CC0-1.0

const fs = require('fs')
const xml2js = require('xml2js')
const jsdiff = require('diff')



// edit this
const wikipedia_xml_file = 'Wikipedia-20200119163602.xml'



const src = fs.readFileSync(wikipedia_xml_file).toString('utf-8')

xml2js.parseString(src, function (err, result) {
  
  let text_last = ''

  for (let [ip, page] of result.mediawiki.page.entries()) {
    
    // comment the next line to see all pages
    if (ip == 1) { break } // flood limit
    
    for (let [ir, revision] of page.revision.entries()) {
      
      //if (ir == 20) { break } // flood limit
      
      console.log(`# revision ${revision.id}`)
      const text = revision.text[0]._

      if (!text) { continue }

      // find changed words
      const diff = jsdiff.diffWords(text_last, text)

      for (let d of diff) {

        // print added words
        if (d.added) {
          console.log(d.value)
        }

      }

      text_last = text
    }
  }

})