n-kb

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
import csv, time
import os.path

browser = webdriver.Chrome()

for year in range(2013, 2020):
    for month in range(1,13):

n-kb

{
  "log": {
    "comment": "",
    "creator": {
      "comment": "",
      "name": "BrowserMob Proxy",
      "version": "2.1.4"
    },
    "entries": [
      {

xeoncross

http://www.youtube.com/watch?v=-wtIMTCHWuI

http://www.youtube.com/v/-wtIMTCHWuI?version=3&autohide=1

http://youtu.be/-wtIMTCHWuI

http://www.youtube.com/oembed?url=http%3A//www.youtube.com/watch?v%3D-wtIMTCHWuI&format=json

http://www.youtube.com/attribution_link?a=JdfC0C9V6ZI&u=%2Fwatch%3Fv%3DEhxJLojIE_o%26feature%3Dshare

marcus-at-localhost

<?php
  
$filters = "1,2,4,(5,6,7),8;9";
var_dump(preg_split("~[,|;](?![^(]*\\))~", $filters));

/*
array (size=6)
  0 => string '1' (length=1)
  1 => string '2' (length=1)
  2 => string '4' (length=1)

rocketgeek

<?php 

// Extraction utility for getting attributes from HTML tag.
function extract_html_atts( $string, $prefix = "data-" ) {
	$start = 0;
	$end = 0;

	while( strpos( $string, $prefix, $end ) ) {
		$start = strpos( $string, $prefix, $start )+strlen( $prefix );
		$end   = strpos( $string, '"', $start )-1;

xeoncross

These weights are often combined into a tf-idf value, simply by multiplying them together. The best scoring words under tf-idf are uncommon ones which are repeated many times in the text, which lead early web search engines to be vulnerable to pages being stuffed with repeated terms to trick the search engines into ranking them highly for those keywords. For that reason, more complex weighting schemes are generally used, but tf-idf is still a good first step, especially for systems where no one is trying to game the system.

There are a lot of variations on the basic tf-idf idea, but a straightforward implementation might look like:

    <?php
    $tfidf = $term_frequency *  // tf
        log( $total_document_count / $documents_with_term, 2); // idf
    ?>

It's worth repeating that the IDF is the total document count over the count of the ones containing the term. So, if there were 50 documents in the collection, and two of them contained the term in question, the IDF would be 50/2 = 25. To be accurate, we s

rocketgeek

<?php

// https://stackoverflow.com/questions/23062537/how-to-convert-html-to-json-using-php
function html_to_obj( $html ) {
    $dom = new DOMDocument();
    $dom->loadHTML( $html );
    return element_to_obj( $dom->documentElement );
}

function element_to_obj( $element ) {

nicklasos

<?php

function multiple_download(array $urls, $save_path = '/tmp')
{
    $multi_handle = curl_multi_init();
    $file_pointers = [];
    $curl_handles = [];

    // Add curl multi handles, one per file we don't already have
    foreach ($urls as $key => $url) {

nima-rahbar

// ==UserScript==
// @name         Linkvertise Bypass
// @namespace    https://github.com/nima-rahbar/
// @version      1.0
// @description  Bypass links that cannot be bypassed by Universal Bypass
// @author       Nima Rahbar
// @match        *://*.linkvertise.com/*
// @match        *://*.linkvertise.net/*
// @match        *://*.link-to.net/*
// @icon         https://nimarahbar.com/wp-content/uploads/2017/07/favicon.png

eusonlito

<?php

function folderSize ($dir)
{
    $size = 0;

    foreach (glob(rtrim($dir, '/').'/*', GLOB_NOSORT) as $each) {
        $size += is_file($each) ? filesize($each) : folderSize($each);
    }