foolip

2019/08/15 07:32:58:282  HTTPServer: POST http://127.0.0.1:52985/session
2019/08/15 07:32:58:282  HTTPServer: {"capabilities": {"alwaysMatch": {}}}
2019/08/15 07:32:58:860  AutomationProtocol: SEND {"method":"Automation.createBrowsingContext","params":{"presentationHint":"Window"},"id":1}
2019/08/15 07:32:59:169  AutomationProtocol: RECV {"result":{"handle":"page-BAF6DECF-098E-4B50-9A72-5C1F2A2833C8","presentation":"Window"},"id":1}
2019/08/15 07:32:59:170  AutomationProtocol: SEND {"method":"Automation.switchToBrowsingContext","params":{"browsingContextHandle":"page-BAF6DECF-098E-4B50-9A72-5C1F2A2833C8","frameHandle":""},"id":2}
2019/08/15 07:32:59:233  AutomationProtocol: RECV {"result":{},"id":2}
2019/08/15 07:32:59:233  HTTPServer: --> HTTP 200
2019/08/15 07:32:59:233  HTTPServer: --> {"value":{"sessionId":"B100B732-F397-4147-8428-41C69C57E8EC","capabilities":{"safari:platformVersion":"10.13.6","safari:automaticInspection":false,"webkit:WebRTC":{"DisableICECandidateFiltering":false,"DisableInsecureMediaCa

foolip

const {BigQuery} = require('@google-cloud/bigquery');

const bigquery = new BigQuery();

async function getFeatures() {
  const query = `SELECT DISTINCT feature
    FROM \`httparchive.blink_features.usage\`
    WHERE yyyymmdd >= '20190601'
      AND pct_urls > 1/100 AND pct_urls < 99/100
    ORDER BY feature`;

foolip

page,url,body,truncated
http://www.wetafx.co.nz/,https://www.wetafx.co.nz/themes/weta/js/main_desktop_extended.js,"/*!
 * jQuery JavaScript Library v2.1.4
 * http://jquery.com/
 *
 * Includes Sizzle.js
 * http://sizzlejs.com/
 *
 * Copyright 2005, 2014 jQuery Foundation, Inc. and other contributors
 * Released under the MIT license

foolip

foolip

Use of Accept-Language

Sites were sampled from the Majestic Million, 10 site per order of magnitude. This was done based on the suspicion that use of the header is different in the long tail of sites.

Testing was done in Sweden with different Accept-Language headers based on informed guesses about what languages the sites might support. Between any two attempts using the same site cookies were cleared to avoid previous language being remembered, but it is still possible the server had state based on IP that affected results.

Summary

By rank (buckets of 10):

• 10-99: 2/10 sites fully localized, 2/10 localized GDPR prompts, 2/10 used physical location/IP.

foolip

# output of https://gist.github.com/foolip/d18bd25bd2547c225b4a677dbda31e4b (first revision, with two manual replacements after)

1
	forbes.com
	mit.edu
	godaddy.com
	itunes.apple.com
	t.co
	weebly.com
	live.com

foolip

#!/usr/bin/python3

import csv
import math
import random

rows_by_logrank = {}

with open('majestic_million.csv', 'r') as csvfile:
    majestic = csv.DictReader(csvfile)

foolip

'use strict';

const compareVersions = require('compare-versions');
const fs = require('fs');
const path = require('path');
const uaParser = require('ua-parser-js');

const overrides = require('./overrides').filter(Array.isArray);

function findEntry(bcd, path) {

foolip

'use strict';

const compareVersions = require('compare-versions');
const fs = require('fs');
const path = require('path');
const uaParser = require('ua-parser-js');

const overrides = require('./overrides').filter(Array.isArray);

function findEntry(bcd, path) {

foolip

'use strict';

const compareVersions = require('compare-versions');
const fs = require('fs');
const path = require('path');
const uaParser = require('ua-parser-js');

const overrides = require('./overrides').filter(Array.isArray);

function findEntry(bcd, path) {