I am using the elasticsearch module in my nodejs app to query my index using fuzzy completion. The text I'm trying to search is Rome–Fiumicino Leonardo da Vinci International Airport. when searching this term I get no results, but if I cut the term to 50 characters it does find it and return results.
const result = await elasticsearch.search({
index: 'myIndex',
body: {
suggest: {
fuzzinessZero: {
text,
completion: {
field: 'name_suggest',
fuzzy: {
fuzziness: 0,
},
contexts,
},
},
fuzzinessOne: {
text,
completion: {
field: 'name_suggest',
fuzzy: {
fuzziness: 1,
},
contexts,
},
},
fuzzinessTwo: {
text,
completion: {
field: 'name_suggest',
fuzzy: {
fuzziness: 2,
},
contexts,
},
},
},
}
})
This is the result I get in fuzzinessOne
As you can see, the result in the text field is cut to 50 characters (maybe that's the issue). And inside the _source I get back all the inputs which is used for the search, and one of them is the full exact term which I tried to search, as well with all the other available combinations available.
It is worth mentioning that I'm using AWS openSearch.
And this is the settings which I use to create the index:
settings: {
analysis: {
filter: {
autocomplete_filter: {
type: 'edge_ngram',
min_gram: 2,
max_gram: 20,
},
shingle_filter: {
type: 'shingle',
max_shingle_size: 3,
},
},
analyzer: {
autocomplete: {
type: 'custom',
tokenizer: 'standard',
filter: ['lowercase', 'shingle_filter', 'asciifolding'],
},
},
},
}
You are facing this issue because of default value of max_input_length parameter is set to 50.
Below is description given for this parameter in documentation:
Limits the length of a single input, defaults to 50 UTF-16 code
points. This limit is only used at index time to reduce the total
number of characters per input string in order to prevent massive
inputs from bloating the underlying datastructure. Most use cases
won’t be influenced by the default value since prefix completions
seldom grow beyond prefixes longer than a handful of characters.
You can use this default behaviour or you can updated your index mapping with increase value of max_input_length parameter and reindex your data.
{
"mappings": {
"dynamic": "false",
"properties": {
"namesuggest": {
"type": "completion",
"analyzer": "keyword_lowercase_analyzer",
"preserve_separators": true,
"preserve_position_increments": true,
"max_input_length": 100,
"contexts": [
{
"name": "searchable",
"type": "CATEGORY"
}
]
}
}
},
"settings": {
"index": {
"mapping": {
"ignore_malformed": "true"
},
"refresh_interval": "5s",
"analysis": {
"analyzer": {
"keyword_lowercase_analyzer": {
"filter": [
"lowercase"
],
"type": "custom",
"tokenizer": "keyword"
}
}
},
"number_of_replicas": "0",
"number_of_shards": "1"
}
}
}
I am trying to get count of unseen messages from object in lodash.
below is my object
[
"conversation_id": "5a88779b2321141f2864e484"
"messages": [
{
"message_id": "5a88779b2321141f2864e483",
"sender_uid": 2,
"receiver_uid": 1,
"created": "2018-02-17T18:42:35.252Z",
"status": 1,
"delivered": false,
"seen": true,
}
]
]
I want to get count of seen: false messages
You can use filter to get all see = false messages and then can check length
var users = {
"conversation_id": "5a88779b2321141f2864e484",
"messages": [
{ "message_id": "5a88779b2321141f2864e483","sender_uid": 2,"receiver_uid": 1,"created": "2018-02-17T18:42:35.252Z","status": 1,"delivered": false,"seen": true,},
{ "message_id": "5a88779b2321141f2864e483","sender_uid": 2,"receiver_uid": 1,"created": "2018-02-17T18:42:35.252Z","status": 1,"delivered": false,"seen": false },
{ "message_id": "5b88779b2321141f2864e483","sender_uid": 2, "receiver_uid": 1, "created": "2018-02-17T18:42:35.252Z", "status": 1,"delivered": false,"seen": false,}
]
}
var unseen_messages = _.filter(users.messages, message => { return !message.seen; }).length;
console.log(unseen_messages);
<script src="https://cdn.jsdelivr.net/lodash/4.13.1/lodash.min.js"></script>
Without lodash you can use reduce
var users = {
"conversation_id": "5a88779b2321141f2864e484",
"messages": [
{ "message_id": "5a88779b2321141f2864e483","sender_uid": 2,"receiver_uid": 1,"created": "2018-02-17T18:42:35.252Z","status": 1,"delivered": false,"seen": true,},
{ "message_id": "5a88779b2321141f2864e483","sender_uid": 2,"receiver_uid": 1,"created": "2018-02-17T18:42:35.252Z","status": 1,"delivered": false,"seen": false },
{ "message_id": "5b88779b2321141f2864e483","sender_uid": 2, "receiver_uid": 1, "created": "2018-02-17T18:42:35.252Z", "status": 1,"delivered": false,"seen": false,}
]
}
items = users.messages;
var totalCount = items.reduce((total, obj) => { return (!obj.seen) ? (total +1) : total }, 0);
console.log(totalCount);
_.sumBy would do the trick
const unseenMessages = _.sumBy(users.messages, message => message.seen === false);
I'm am looking for the MediaID of an Instagram image which has been uploaded. It should look like
1234567894561231236_33215652
I have found out the last set of integers are the usersID
For example: this is the link for the image directly, however I see no mediaID in the correct format?
http://distilleryimage11.ak.instagram.com/d33aafc8b55d11e2a66b22000a9f09de_7.jpg
while this is the link
http://instagram.com/p/Y7GF-5vftL/
I don't wish to use the API as all I need the MediaID from a selected image.
Here's a better way:
http://api.instagram.com/oembed?url=http://instagram.com/p/Y7GF-5vftL/
Render as json object and you can easily extract media id from it ---
For instance, in PHP
$api = file_get_contents("http://api.instagram.com/oembed?url=http://instagram.com/p/Y7GF-5vftL/");
$apiObj = json_decode($api,true);
$media_id = $apiObj['media_id'];
For instance, in JS
$.ajax({
type: 'GET',
url: 'http://api.instagram.com/oembed?callback=&url=http://instagram.com/p/Y7GF-5vftL/',
cache: false,
dataType: 'jsonp',
success: function(data) {
try{
var media_id = data[0].media_id;
}catch(err){}
}
});
So the most up-voted "Better Way" is a little deprecated so here is my edit and other solutions:
Javascript + jQuery
$.ajax({
type: 'GET',
url: 'http://api.instagram.com/oembed?callback=&url='+Url, //You must define 'Url' for yourself
cache: false,
dataType: 'json',
jsonp: false,
success: function (data) {
var MediaID = data.media_id;
}
});
PHP
$your_url = "" //Input your url
$api = file_get_contents("http://api.instagram.com/oembed?callback=&url=" . your_url);
$media_id = json_decode($api,true)['media_id'];
So, this is just an updated version of #George's code and is currently working. However, I made other solutions, and some even avoid an ajax request:
Shortcode Ajax Solution
Certain Instagram urls use a shortened url syntax. This allows the client to just use the shortcode in place of the media id if requested properly.
An example shortcode url looks like this: https://www.instagram.com/p/Y7GF-5vftL/
The Y7GF-5vftL is your shortcode for the picture.
Using Regexp:
var url = "https://www.instagram.com/p/Y7GF-5vftL/"; //Define this yourself
var Key = /p\/(.*?)\/$/.exec(url)[1];
In the same scope, Key will contain your shortcode. Now to request, let's say, a low res picture using this shortcode, you would do something like the following:
$.ajax({
type: "GET",
dataType: "json",
url: "https://api.instagram.com/v1/media/shortcode/" + Key + "?access_token=" + access_token, //Define your 'access_token'
success: function (RawData) {
var LowResURL = RawData.data.images.low_resolution.url;
}
});
There is lots of other useful information, including the media id, in the returned RawData structure. Log it or look up the api documentation to see.
Shortcode Conversion Solution
You can actually convert your shortcode to the id fairly easily! Here's a simple way to do it in javascript:
function shortcodeToInstaID(Shortcode) {
var char;
var id = 0;
var alphabet = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_';
for (var i = 0; i < Shortcode.length; i++) {
char = Shortcode[i];
id = (id * 64) + alphabet.indexOf(char);
}
return id;
}
Note: If you want a more robust node.js solution, or want to see how you would convert it back, check out #Slang's module on npm.
Full Page Solution
So what if you have the URL to a full Instagram page like: https://www.instagram.com/p/BAYYJBwi0Tssh605CJP2bmSuRpm_Jt7V_S8q9A0/
Well, you can actually read the HTML to find a meta property that contains the Media ID. There are also a couple other algorithms you can perform on the URL itself to get it, but I believe that requires too much effort so we will keep it simple. Either query the meta tag al:ios:url or iterate through the html. Since reading metatags is posted all over, I'll show you how to iterate.
NOTE: This is a little unstable and is vulnerable to being patched. This method does NOT work on a page that uses a preview box. So if you give it the current HTML when you click on a picture in someone's profile, this WILL break and return a bad Media ID.
function getMediaId(HTML_String) {
var MediaID = "";
var e = HTML_String.indexOf("al:ios:url") + 42; //HTML_String is a variable that contains all of the HTML text as a string for the current document. There are many different ways to retrieve this so look one up.
for (var i = e; i <= e + 100; i++) { //100 should never come close to being reached
if (request.source.charAt(i) == "\"")
break;
MediaID += request.source.charAt(i);
}
return MediaID;
}
And there you go, a bunch of different ways to use Instagram's api to get a Media ID. Hope one fixes your struggles.
Here's an even better way:
No API calls! And I threw in converting a media_id to a shortcode as an added bonus.
Based on slang's amazing work for figuring out the conversion. Nathan's work converting base10 to base64 in php. And rgbflawed's work converting it back the other way (with a modified alphabet). #teameffort
function mediaid_to_shortcode($mediaid){
if(strpos($mediaid, '_') !== false){
$pieces = explode('_', $mediaid);
$mediaid = $pieces[0];
$userid = $pieces[1];
}
$alphabet = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_';
$shortcode = '';
while($mediaid > 0){
$remainder = $mediaid % 64;
$mediaid = ($mediaid-$remainder) / 64;
$shortcode = $alphabet{$remainder} . $shortcode;
};
return $shortcode;
}
function shortcode_to_mediaid($shortcode){
$alphabet='ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_';
$mediaid = 0;
foreach(str_split($shortcode) as $letter) {
$mediaid = ($mediaid*64) + strpos($alphabet, $letter);
}
return $mediaid;
}
Here's a much better way (No Instagram API):
Get the permalink URL of the Instagram image you need the media ID for. http://instagram.com/p/Y7GF-5vftL/ 👀
add ?__a=1 at the end of the permalinkhttp://instagram.com/p/Y7GF-5vftL/?__a=1 👀
Run the link in a browser and Instagram will provide all the metadata of the image in JSON, from which you can easily recover the image ID and other valuable data.
The JSON response will look like this:
{
"graphql": {
"shortcode_media": {
"__typename": "GraphImage",
"id": "448979387270691659",
"shortcode": "Y7GF-5vftL",
"dimensions": {
"height": 612,
"width": 612
},
"gating_info": null,
"fact_check_overall_rating": null,
"fact_check_information": null,
"sensitivity_friction_info": null,
"sharing_friction_info": {
"should_have_sharing_friction": false,
"bloks_app_url": null
},
"media_overlay_info": null,
"media_preview": null,
"display_url": "https://scontent-cdt1-1.cdninstagram.com/v/t51.2885-15/e15/11324452_400723196800905_116356150_n.jpg?_nc_ht=scontent-cdt1-1.cdninstagram.com&_nc_cat=109&_nc_ohc=YQtotj4Ygh0AX9Vqa8s&edm=AABBvjUBAAAA&ccb=7-4&oh=9f8658a873a3e94a462db148bde85b5a&oe=61A49EE6&_nc_sid=83d603",
"display_resources": [
{
"src": "https://scontent-cdt1-1.cdninstagram.com/v/t51.2885-15/e15/11324452_400723196800905_116356150_n.jpg?_nc_ht=scontent-cdt1-1.cdninstagram.com&_nc_cat=109&_nc_ohc=YQtotj4Ygh0AX9Vqa8s&edm=AABBvjUBAAAA&ccb=7-4&oh=9f8658a873a3e94a462db148bde85b5a&oe=61A49EE6&_nc_sid=83d603",
"config_width": 640,
"config_height": 640
},
{
"src": "https://scontent-cdt1-1.cdninstagram.com/v/t51.2885-15/e15/11324452_400723196800905_116356150_n.jpg?_nc_ht=scontent-cdt1-1.cdninstagram.com&_nc_cat=109&_nc_ohc=YQtotj4Ygh0AX9Vqa8s&edm=AABBvjUBAAAA&ccb=7-4&oh=9f8658a873a3e94a462db148bde85b5a&oe=61A49EE6&_nc_sid=83d603",
"config_width": 750,
"config_height": 750
},
{
"src": "https://scontent-cdt1-1.cdninstagram.com/v/t51.2885-15/e15/11324452_400723196800905_116356150_n.jpg?_nc_ht=scontent-cdt1-1.cdninstagram.com&_nc_cat=109&_nc_ohc=YQtotj4Ygh0AX9Vqa8s&edm=AABBvjUBAAAA&ccb=7-4&oh=9f8658a873a3e94a462db148bde85b5a&oe=61A49EE6&_nc_sid=83d603",
"config_width": 1080,
"config_height": 1080
}
],
"accessibility_caption": "Photo by Steven Caelius Thirlwall on May 05, 2013.",
"is_video": false,
"tracking_token": "eyJ2ZXJzaW9uIjo1LCJwYXlsb2FkIjp7ImlzX2FuYWx5dGljc190cmFja2VkIjpmYWxzZSwidXVpZCI6IjFjOTliZDQ5MTU0YzQ2ODY4OGY5MmM4ODgwYWQ4NGQzNDQ4OTc5Mzg3MjcwNjkxNjU5Iiwic2VydmVyX3Rva2VuIjoiMTYzNzY4NDc1NjI4MHw0NDg5NzkzODcyNzA2OTE2NTl8MzExMTA2NDAyfDE2ZGMyNjk3M2M1YWY5YWEzOTNhZTY5YzEzYzU4YjM5NWI0YWQ3MjY1OGQxOTg4YWQ2OWUxYmI3ZjkyNzU5ZDQifSwic2lnbmF0dXJlIjoiIn0=",
"upcoming_event": null,
"edge_media_to_tagged_user": {
"edges": []
},
"edge_media_to_caption": {
"edges": [
{
"node": {
"text": "New ankle biter! #Beagle #pup #shoes #blueisthecolor #cute #iwantone"
}
}
]
},
"can_see_insights_as_brand": false,
"caption_is_edited": false,
"has_ranked_comments": false,
"like_and_view_counts_disabled": false,
"edge_media_to_parent_comment": {
"count": 902,
"page_info": {
"has_next_page": true,
"end_cursor": "QVFBZFlTbmNsVWh1T2dIS1I3Mm8yRl9DdGVQMHV6VXg5cjQxZzlYa0gxQ1NFZGc5a1FfWHhIMTlURU84dlBCcG5QX1I2VXhvVXNpbGRGWlktNG5FTjdRTQ=="
},
"edges": [
{
"node": {
"id": "17916614443887715",
"text": "#h___ep10",
"created_at": 1632633242,
"did_report_as_spam": false,
"owner": {
"id": "7472159900",
"is_verified": false,
"profile_pic_url": "https://scontent-cdg2-1.cdninstagram.com/v/t51.2885-19/s150x150/33736445_386998071786552_2814599361646821376_n.jpg?_nc_ht=scontent-cdg2-1.cdninstagram.com&_nc_cat=100&_nc_ohc=kaD1UHiVnU8AX9oWv0I&edm=AABBvjUBAAAA&ccb=7-4&oh=cabcfaac8d48b63b41f0e9a32bb0282f&oe=61A38CDE&_nc_sid=83d603",
"username": "x._raha.moradi_.x"
},
"viewer_has_liked": false,
"edge_liked_by": {
"count": 0
},
"is_restricted_pending": false,
"edge_threaded_comments": {
"count": 0,
"page_info": {
"has_next_page": false,
"end_cursor": null
},
"edges": []
}
}
},
{
"node": {
"id": "17894221358363984",
"text": "#zahraroshanikia",
"created_at": 1632633244,
"did_report_as_spam": false,
"owner": {
"id": "46440556914",
"is_verified": false,
"profile_pic_url": "https://scontent-cdt1-1.cdninstagram.com/v/t51.2885-19/s150x150/159256912_431734447917250_5641996282890612011_n.jpg?_nc_ht=scontent-cdt1-1.cdninstagram.com&_nc_cat=110&_nc_ohc=y2JgjQ2mc6EAX8U9OnZ&edm=AABBvjUBAAAA&ccb=7-4&oh=95911a34aea9f1fe0f6ae941154de86b&oe=61A4F7B5&_nc_sid=83d603",
"username": "saman.wx68"
},
"viewer_has_liked": false,
"edge_liked_by": {
"count": 0
},
"is_restricted_pending": false,
"edge_threaded_comments": {
"count": 0,
"page_info": {
"has_next_page": false,
"end_cursor": null
},
"edges": []
}
}
},
{
"node": {
"id": "17931125308699029",
"text": "#azarimani55",
"created_at": 1632633244,
"did_report_as_spam": false,
"owner": {
"id": "33210479560",
"is_verified": false,
"profile_pic_url": "https://scontent-cdg2-1.cdninstagram.com/v/t51.2885-19/s150x150/94635563_230560861379228_5419754827787796480_n.jpg?_nc_ht=scontent-cdg2-1.cdninstagram.com&_nc_cat=108&_nc_ohc=7JyeFrDCzcMAX_uDrhk&edm=AABBvjUBAAAA&ccb=7-4&oh=5599a78e5508ca3827b5c580c4e5daf0&oe=61A3CB8E&_nc_sid=83d603",
"username": "alirezaekhteraee"
},
"viewer_has_liked": false,
"edge_liked_by": {
"count": 0
},
"is_restricted_pending": false,
"edge_threaded_comments": {
"count": 0,
"page_info": {
"has_next_page": false,
"end_cursor": null
},
"edges": []
}
}
},
{
"node": {
"id": "18164016367163647",
"text": "#mbahrambagi436",
"created_at": 1632633245,
"did_report_as_spam": false,
"owner": {
"id": "45915987079",
"is_verified": false,
"profile_pic_url": "https://scontent-cdt1-1.cdninstagram.com/v/t51.2885-19/s150x150/148716764_428606351708713_8819828798031017255_n.jpg?_nc_ht=scontent-cdt1-1.cdninstagram.com&_nc_cat=101&_nc_ohc=ZKBGqc8f6xAAX_roxPf&edm=AABBvjUBAAAA&ccb=7-4&oh=0b8ed79236bf5e97dde3a4621a1cc647&oe=61A3B2BD&_nc_sid=83d603",
"username": "xx77llxxrdd"
},
"viewer_has_liked": false,
"edge_liked_by": {
"count": 0
},
"is_restricted_pending": false,
"edge_threaded_comments": {
"count": 0,
"page_info": {
"has_next_page": false,
"end_cursor": null
},
"edges": []
}
}
},
{
"node": {
"id": "17921916424799580",
"text": "#soheila.rezvan",
"created_at": 1632633246,
"did_report_as_spam": false,
"owner": {
"id": "47289012029",
"is_verified": false,
"profile_pic_url": "https://scontent-cdg2-1.cdninstagram.com/v/t51.2885-19/44884218_345707102882519_2446069589734326272_n.jpg?_nc_ht=scontent-cdg2-1.cdninstagram.com&_nc_cat=1&_nc_ohc=uQzgj27XaGsAX_EK6es&edm=AA0lj5EBAAAA&ccb=7-4&oh=11aea858038a83aea909c6a5934ac670&oe=61A4378F&_nc_sid=3add00&ig_cache_key=YW5vbnltb3VzX3Byb2ZpbGVfcGlj.2-ccb7-4",
"username": "ha_midreza2843"
},
"viewer_has_liked": false,
"edge_liked_by": {
"count": 0
},
"is_restricted_pending": false,
"edge_threaded_comments": {
"count": 0,
"page_info": {
"has_next_page": false,
"end_cursor": null
},
"edges": []
}
}
},
{
"node": {
"id": "17907564257125873",
"text": "#paria_niazi80",
"created_at": 1632633247,
"did_report_as_spam": false,
"owner": {
"id": "46492412778",
"is_verified": false,
"profile_pic_url": "https://scontent-cdt1-1.cdninstagram.com/v/t51.2885-19/s150x150/260070060_924734438469169_5591668570031114480_n.jpg?_nc_ht=scontent-cdt1-1.cdninstagram.com&_nc_cat=101&_nc_ohc=fl-bN9uNz9sAX_v_XtR&edm=AABBvjUBAAAA&ccb=7-4&oh=a875da2937ac853d3111499bc32fa452&oe=61A43C46&_nc_sid=83d603",
"username": "ricky_gutierrezz4"
},
"viewer_has_liked": false,
"edge_liked_by": {
"count": 0
},
"is_restricted_pending": false,
"edge_threaded_comments": {
"count": 0,
"page_info": {
"has_next_page": false,
"end_cursor": null
},
"edges": []
}
}
},
{
"node": {
"id": "17922561976794017",
"text": "#memmm.mom",
"created_at": 1632633247,
"did_report_as_spam": false,
"owner": {
"id": "47086299475",
"is_verified": false,
"profile_pic_url": "https://scontent-cdg2-1.cdninstagram.com/v/t51.2885-19/44884218_345707102882519_2446069589734326272_n.jpg?_nc_ht=scontent-cdg2-1.cdninstagram.com&_nc_cat=1&_nc_ohc=uQzgj27XaGsAX_EK6es&edm=AA0lj5EBAAAA&ccb=7-4&oh=11aea858038a83aea909c6a5934ac670&oe=61A4378F&_nc_sid=3add00&ig_cache_key=YW5vbnltb3VzX3Byb2ZpbGVfcGlj.2-ccb7-4",
"username": "izadiizadi2"
},
"viewer_has_liked": false,
"edge_liked_by": {
"count": 0
},
"is_restricted_pending": false,
"edge_threaded_comments": {
"count": 0,
"page_info": {
"has_next_page": false,
"end_cursor": null
},
"edges": []
}
}
},
{
"node": {
"id": "18130172461216294",
"text": "#221bcc",
"created_at": 1632633247,
"did_report_as_spam": false,
"owner": {
"id": "47371753534",
"is_verified": false,
"profile_pic_url": "https://scontent-cdg2-1.cdninstagram.com/v/t51.2885-19/44884218_345707102882519_2446069589734326272_n.jpg?_nc_ht=scontent-cdg2-1.cdninstagram.com&_nc_cat=1&_nc_ohc=uQzgj27XaGsAX_EK6es&edm=AA0lj5EBAAAA&ccb=7-4&oh=11aea858038a83aea909c6a5934ac670&oe=61A4378F&_nc_sid=3add00&ig_cache_key=YW5vbnltb3VzX3Byb2ZpbGVfcGlj.2-ccb7-4",
"username": "karimov_94422"
},
"viewer_has_liked": false,
"edge_liked_by": {
"count": 0
},
"is_restricted_pending": false,
"edge_threaded_comments": {
"count": 0,
"page_info": {
"has_next_page": false,
"end_cursor": null
},
"edges": []
}
}
},
{
"node": {
"id": "17932389193640009",
"text": "#tehran___la",
"created_at": 1632633248,
"did_report_as_spam": false,
"owner": {
"id": "46622156073",
"is_verified": false,
"profile_pic_url": "https://scontent-cdg2-1.cdninstagram.com/v/t51.2885-19/44884218_345707102882519_2446069589734326272_n.jpg?_nc_ht=scontent-cdg2-1.cdninstagram.com&_nc_cat=1&_nc_ohc=uQzgj27XaGsAX_EK6es&edm=AA0lj5EBAAAA&ccb=7-4&oh=11aea858038a83aea909c6a5934ac670&oe=61A4378F&_nc_sid=3add00&ig_cache_key=YW5vbnltb3VzX3Byb2ZpbGVfcGlj.2-ccb7-4",
"username": "rynwrynw627"
},
"viewer_has_liked": false,
"edge_liked_by": {
"count": 0
},
"is_restricted_pending": false,
"edge_threaded_comments": {
"count": 0,
"page_info": {
"has_next_page": false,
"end_cursor": null
},
"edges": []
}
}
},
{
"node": {
"id": "17935588228640366",
"text": "#sepideh.m.i.r",
"created_at": 1632633248,
"did_report_as_spam": false,
"owner": {
"id": "5905800882",
"is_verified": false,
"profile_pic_url": "https://scontent-cdt1-1.cdninstagram.com/v/t51.2885-19/s150x150/160110991_451499282792610_787693123774809640_n.jpg?_nc_ht=scontent-cdt1-1.cdninstagram.com&_nc_cat=106&_nc_ohc=CBgOU0M1MPYAX8m7vvT&edm=AABBvjUBAAAA&ccb=7-4&oh=18a215ed2c3a0cd0e58a905e22cd0c8f&oe=61A489B4&_nc_sid=83d603",
"username": "__mohammad__677"
},
"viewer_has_liked": false,
"edge_liked_by": {
"count": 0
},
"is_restricted_pending": false,
"edge_threaded_comments": {
"count": 0,
"page_info": {
"has_next_page": false,
"end_cursor": null
},
"edges": []
}
}
},
{
"node": {
"id": "17854564814634983",
"text": "#nilooofar5828",
"created_at": 1632633249,
"did_report_as_spam": false,
"owner": {
"id": "46091925856",
"is_verified": false,
"profile_pic_url": "https://scontent-cdg2-1.cdninstagram.com/v/t51.2885-19/44884218_345707102882519_2446069589734326272_n.jpg?_nc_ht=scontent-cdg2-1.cdninstagram.com&_nc_cat=1&_nc_ohc=uQzgj27XaGsAX_EK6es&edm=AA0lj5EBAAAA&ccb=7-4&oh=11aea858038a83aea909c6a5934ac670&oe=61A4378F&_nc_sid=3add00&ig_cache_key=YW5vbnltb3VzX3Byb2ZpbGVfcGlj.2-ccb7-4",
"username": "hsheh6154"
},
"viewer_has_liked": false,
"edge_liked_by": {
"count": 0
},
"is_restricted_pending": false,
"edge_threaded_comments": {
"count": 0,
"page_info": {
"has_next_page": false,
"end_cursor": null
},
"edges": []
}
}
},
{
"node": {
"id": "17907793715125698",
"text": "#oran31201816",
"created_at": 1632633249,
"did_report_as_spam": false,
"owner": {
"id": "44672434922",
"is_verified": false,
"profile_pic_url": "https://scontent-cdg2-1.cdninstagram.com/v/t51.2885-19/s150x150/149881733_183016319827876_8572211010018355650_n.jpg?_nc_ht=scontent-cdg2-1.cdninstagram.com&_nc_cat=104&_nc_ohc=JgjvztBQGrIAX8nLUiM&tn=hRpIRP1GgMkkZ4n7&edm=AABBvjUBAAAA&ccb=7-4&oh=d9e408cf78f195a83f8bb7beec8c22c1&oe=61A360EC&_nc_sid=83d603",
"username": "barcelona10_trol"
},
"viewer_has_liked": false,
"edge_liked_by": {
"count": 0
},
"is_restricted_pending": false,
"edge_threaded_comments": {
"count": 0,
"page_info": {
"has_next_page": false,
"end_cursor": null
},
"edges": []
}
}
}
]
},
"edge_media_to_hoisted_comment": {
"edges": []
},
"edge_media_preview_comment": {
"count": 902,
"edges": []
},
"comments_disabled": false,
"commenting_disabled_for_viewer": false,
"taken_at_timestamp": 1367742535,
"edge_media_preview_like": {
"count": 13823,
"edges": [
{
"node": {
"id": "750983393",
"is_verified": false,
"profile_pic_url": "https://scontent-cdt1-1.cdninstagram.com/v/t51.2885-19/s150x150/245113529_402184758053910_6991076024439577169_n.jpg?_nc_ht=scontent-cdt1-1.cdninstagram.com&_nc_cat=106&_nc_ohc=TPs3jHagdx4AX_JdrO5&tn=hRpIRP1GgMkkZ4n7&edm=AABBvjUBAAAA&ccb=7-4&oh=95f6532e2d737a91e3848fa0525319e4&oe=61A4C0D1&_nc_sid=83d603",
"username": "josepkoray"
}
}
]
},
"edge_media_to_sponsor_user": {
"edges": []
},
"is_affiliate": false,
"is_paid_partnership": false,
"location": null,
"viewer_has_liked": false,
"viewer_has_saved": false,
"viewer_has_saved_to_collection": false,
"viewer_in_photo_of_you": false,
"viewer_can_reshare": true,
"owner": {
"id": "45818965",
"is_verified": false,
"profile_pic_url": "https://scontent-cdg2-1.cdninstagram.com/v/t51.2885-19/s150x150/38792937_2121773964703196_2247098649857228800_n.jpg?_nc_ht=scontent-cdg2-1.cdninstagram.com&_nc_cat=108&_nc_ohc=LyE1N2PfQ3IAX9R25jq&edm=AABBvjUBAAAA&ccb=7-4&oh=29912db673500a2adc9df6ec7241d8c7&oe=61A471D2&_nc_sid=83d603",
"username": "taz4535",
"blocked_by_viewer": false,
"restricted_by_viewer": false,
"followed_by_viewer": false,
"full_name": "Steven Caelius Thirlwall",
"has_blocked_viewer": false,
"is_embeds_disabled": false,
"is_private": false,
"is_unpublished": false,
"requested_by_viewer": false,
"pass_tiering_recommendation": false,
"edge_owner_to_timeline_media": {
"count": 236
},
"edge_followed_by": {
"count": 700
}
},
"is_ad": false,
"edge_web_media_to_related_media": {
"edges": []
},
"coauthor_producers": [],
"edge_related_profiles": {
"edges": []
}
}
}
}
You can use the same ?__a=1 ending even on Instagram user permalinks, for example https://www.instagram.com/taz4535/?__a=1 👀 and you'll get incredibly valuable user data in the reply JSON.
The best is that this is all done without Instagram API authentication!
You can actually derive the MediaId from the last segment of the link algorithmically using a method I wrote about here: http://carrot.is/coding/instagram-ids. It works by mapping the URL segment by character codes & converting the id into a base 64 number.
For example, given the link you mentioned (http://instagram.com/p/Y7GF-5vftL), we get the last segment (Y7GF-5vftL) then we map it into character codes using the base64 url-safe alphabet (24:59:6:5:62:57:47:31:45:11_64). Next, we convert this base64 number into base10 (448979387270691659).
If you append your userId after an _ you get the full id in the form you specified, but since the MediaId is unique without the userId you can actually omit the userId from most requests.
Finally, I made a Node.js module called instagram-id-to-url-segment to automate this conversion:
convert = require('instagram-id-to-url-segment');
instagramIdToUrlSegment = convert.instagramIdToUrlSegment;
urlSegmentToInstagramId = convert.urlSegmentToInstagramId;
instagramIdToUrlSegment('448979387270691659'); // Y7GF-5vftL
urlSegmentToInstagramId('Y7GF-5vftL'); // 448979387270691659
Try the solution from this question:
How can I get an direct Instagram link from a twitter entity?
You can get just the image by appending /media/ to the URL. Using your
You can even specify a size,
One of t (thumbnail), m (medium), l (large). Defaults to m.
So for a thumbnail: http://instagr.am/p/QC8hWKL_4K/media/?size=t
Here is python solution to do this without api call.
def media_id_to_code(media_id):
alphabet = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_'
short_code = ''
while media_id > 0:
remainder = media_id % 64
media_id = (media_id-remainder)/64
short_code = alphabet[remainder] + short_code
return short_code
def code_to_media_id(short_code):
alphabet = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_'
media_id = 0;
for letter in short_code:
media_id = (media_id*64) + alphabet.index(letter)
return media_id
Your media ID is: 448979387270691659_45818965
This is how to get it.
Go to instgram.com/username.
Click the photo you want the id of.
(Chrome instructions) right click on the photo (should be a popup image)
Inspect element
Search through the selected text, you should see something like this photo448979387270691659_45818965
There should be your photo ID.
For some reason, this only seems to work with the popup, and not the actual image URL.
In pure JS (provided your browser can handle XHRs, which every major browser [including IE > 6] can):
function igurlretrieve(url) {
var urldsrc = "http://api.instagram.com/oembed?url=" + url;
//fetch data from URL data source
var x = new XMLHttpRequest();
x.open('GET', urldsrc, true);
x.send();
//load resulting JSON data as JS object
var urldata = JSON.parse(x.responseText);
//reconstruct data as "instagram://" URL that can be opened in iOS app
var reconsturl = "instagram://media?id=" + urldata.media_id;
return reconsturl;
}
Provided this is your goal -- simply opening the page in the Instagram iOS app, which is exactly what this is about -- this should do, especially if you don't want to have to endure licensing fees.
edit
The iOS Instagram app has now registered for regular http links to open in the Instagram app and this deeplink methodology is no longer necessary.
old
Swift 4 short-code parsing solution
private static func instagramDeepLinkFromHTTPLink(_ link: String) -> String? {
guard let shortcode = link.components(separatedBy: "/").last else { return nil }
// algorithm from https://stackoverflow.com/a/37246231/337934
let alphabet = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_"
var mediaId: Int = 0
for (_, char) in shortcode.enumerated() {
guard let index = alphabet.index(of: char) else { continue }
mediaId = (mediaId * 64) + index.encodedOffset
}
return "instagram://media?id=\(mediaId)"
}
Same thing you can implement in Python-
import requests,json
def get_media_id(media_url):
url = 'https://api.instagram.com/oembed/?callback=&url=' + media_url
response = requests.get(url).json()
print(response['media_id'])
get_media_id('MEDIA_URL')
You can use the shortcode media API from instagram. If you use php you can use the following code to get the shortcode from the image's URL:
$matches = [];
preg_match('/instagram\.com\/p\/([^\/]*)/i', $url, $matches);
if (count($matches) > 1) {
$shortcode = $matches[1];
}
Then send a request to the API using your access token (Replace ACCESS-TOKEN with your token)
$apiUrl = sprintf("https://api.instagram.com/v1/media/shortcode/%s?access_token=ACCESS-TOKEN", $shortcode);
Instagram deprecated their legacy APIs in support for Basic Display API during the late 2019
In Basic Display API you are supposed to use the following API endpoint to get the media id. You will need to supply a valid access token.
https://graph.instagram.com/me/media?fields=id,caption&access_token={access-token}
You can read here on how to configure test account and generate access token on Facebook developer portal.
Here is another article which also describes about how to get access token.
Instagram media id to Shortcode
Instagram Shortcode to media id
var bigint = require( 'big-integer' )
var lower = 'abcdefghijklmnopqrstuvwxyz';
var upper = lower.toUpperCase();
var numbers = '0123456789'
var ig_alphabet = upper + lower + numbers + '-_'
var bigint_alphabet = numbers + lower
function toShortcode( longid )
{
var o = bigint( longid ).toString( 64 )
return o.replace(/<(\d+)>|(\w)/g, (m,m1,m2) =>
{
return ig_alphabet.charAt( ( m1 )
? parseInt( m1 )
: bigint_alphabet.indexOf( m2 ) )
});
}
function fromShortcode( shortcode )
{
var o = shortcode.replace( /\S/g, m =>
{
var c = ig_alphabet.indexOf( m )
var b = bigint_alphabet.charAt( c )
return ( b != "" ) ? b : `<${c}>`
} )
return bigint( o, 64 ).toString( 10 )
}
toShortcode( '908540701891980503' ) // s.b. 'ybyPRoQWzX'
fromShortcode( 'ybyPRoQWzX' ) // s.b. '908540701891980503'
Right click on a photo and open in a new tab/window. Right click on inspect element. Search for:
instagram://media?id=
This will give you:
instagram://media?id=############# /// the ID
The full id construct from
photoID_userID
To get the user id, search for:
instapp:owner_user_id Will be in content=