Instagram Web Scraper

<?php
//returns a big old hunk of JSON from a non-private IG account page.
function scrape_insta($username) {
    $insta_source = file_get_contents('http://instagram.com/'.$username);
    $shards = explode('window._sharedData = ', $insta_source);
    $insta_json = explode(';</script>', $shards[1]);
    $insta_array = json_decode($insta_json[0], TRUE);
    return $insta_array;
}
//Supply a username
$my_account = 'cosmocatalano';
//Do the deed
$results_array = scrape_insta($my_account);
//An example of where to go from there
$latest_array = $results_array['entry_data']['ProfilePage'][0]['user']['media']['nodes'][0];
echo 'Latest Photo:<br/>';
echo '<a href="http://instagram.com/p/'.$latest_array['code'].'"><img src="'.$latest_array['display_src'].'"></a></br>';
echo 'Likes: '.$latest_array['likes']['count'].' - Comments: '.$latest_array['comments']['count'].'<br/>';
/* BAH! An Instagram site redesign in June 2015 broke quick retrieval of captions, locations and some other stuff.
echo 'Taken at '.$latest_array['location']['name'].'<br/>';
//Heck, lets compare it to a useful API, just for kicks.
echo '<img src="http://maps.googleapis.com/maps/api/staticmap?markers=color:red%7Clabel:X%7C'.$latest_array['location']['latitude'].','.$latest_array['location']['longitude'].'&zoom=13&size=300x150&sensor=false">';
?>
*/

<?php

class InstagramScraper
{
    protected $content;
    function __construct($url)
    {
        $this->content = @file_get_contents($url);
    }

    public function image(){
        preg_match('#<meta +property=\\"og:image\\" +content=\\"(http.+?\.jpg)\\"#', $this->content, $result);
        return $result[1];
    }
}
?>

 for($cnt=0; $cnt < 20; $cnt++)
{
 $latest_array = $results_array['entry_data']['ProfilePage'][0]['user']['media']['nodes'][$cnt];

 echo 'Latest Photo:<br/>';
 echo '<a href="http://instagram.com/p/'.$latest_array['code'].'"><img src="'.$latest_array['display_src'].'"></a></br>';
 echo 'Likes: '.$latest_array['likes']['count'].' - Comments: '.$latest_array['comments']['count'].'<br/>';
}

/**
 *
 * Instagram Follower Web Scrapper
 *
 * Steps to use.
 * 1. Open instagram user's profile in browser https://www.instagram.com/tvfpitchers/
 * 2. Open console ( press F12 in chrome ) and paste all the code below
 * 3. Click on followers button and load all the followers
 * 4. Call function downloadAsCsv() by writing "downloadAsCsv()" in console to download csv file containing user's all the followers .
 *
 * @author : Hardik Sondagar <[email protected]>
 *
 */

var followers = [];

(function(XHR) {
    "use strict";

    var stats = [];
    var timeoutId = null;

    var open = XHR.prototype.open;
    var send = XHR.prototype.send;

    XHR.prototype.open = function(method, url, async, user, pass) {
        this._url = url;
        open.call(this, method, url, async, user, pass);
    };

    XHR.prototype.send = function(data) {
        var self = this;
        var start;
        var oldOnReadyStateChange;
        var url = this._url;

        function onReadyStateChange() {
            if(self.readyState == 4 && url == 'https://www.instagram.com/query/') {

              var response = JSON.parse(self.response);
              followers = followers.concat(response.followed_by.nodes);

            }

            if(oldOnReadyStateChange) {
                oldOnReadyStateChange();
            }
        }

        if(!this.noIntercept) {
            start = new Date();

            if(this.addEventListener) {
                this.addEventListener("readystatechange", onReadyStateChange, false);
            } else {
                oldOnReadyStateChange = this.onreadystatechange;
                this.onreadystatechange = onReadyStateChange;
            }
        }

        send.call(this, data);
    }
})(XMLHttpRequest);

function downloadAsCsv() {



    var csvContent = "data:text/csv;charset=utf-8,";

    var header = "Username,Requested_by_viewer,Followed_by_viewer,Profile_pic_url,Full Name,is_verified,Id\n";
    csvContent += header;

    followers.forEach(function(infoArray, index){

        var data = $.map(infoArray, function(value) {
        return [value];
        });

        dataString = data.join(",");
        csvContent += index < followers.length ? dataString+ "\n" : dataString;

    });

    var encodedUri = encodeURI(csvContent);
    var link = document.createElement("a");
    link.setAttribute("href", encodedUri);

    var pathArray = window.location.pathname.split('/');

    var milliseconds = (new Date).getTime();
    var filename = 'followers.'+ milliseconds +'.csv';

    if(pathArray && pathArray.length > 1) {
        filename = pathArray[1] + '.' + milliseconds +'.csv';
    }
    link.setAttribute("download",filename);
    document.body.appendChild(link); // Required for FF

    link.click(); // This will download the data file named "my_data.csv".

https://gist.github.com/cosmocatalano

https://gist.github.com/aboustayyef

https://gist.github.com/lmj0011

https://gist.github.com/hardiksondagar