Extracts XHR from HAR files

har-stream-processor

// How will this work

// 1. Stream read the json
// https://www.npmjs.com/package/stream-json

// 2. Extract valuable information
// 3. Rewrite/Rewire request urls

// 4. Put Request/Response pairs in the cache
// https://developer.mozilla.org/en-US/docs/Web/API/Cache/put

// 5. Visualize some of the extracted data

const fs = require('fs');
const path = require('path');
const { chain } = require('stream-chain');
const { parser } = require('stream-json');
const { streamArray } = require('stream-json/streamers/StreamArray');
const { pick } = require('stream-json/filters/Pick');

const HAR_FILE = path.join(__dirname, '../', 'resources', 'www.facebook.com.har');

const xhrFilter = (data) => data.value._resourceType === 'xhr' ? data.value : undefined

const pipeline = chain([
  fs.createReadStream(HAR_FILE),
  parser(),
  pick({ filter: 'log.entries' }),
  streamArray(),
  xhrFilter,
  data => {
    console.log(data.request.url);
    return data;
  }
]);

let counter = 0;
pipeline.on('data', () => counter++);
pipeline.on('end', () =>
  console.log(`Found ${counter} XHR requests.`));