如何在不验证用户身份的情况下从 Instagram 获取用户的媒体？

下面的 nodejs 代码从 Instagram 页面中提取流行图片。 “ ScrapeInstagramPage”函数负责处理后老化效应。

var request = require('parse5');
var request = require('request');
var rp      = require('request-promise');
var $       = require('cheerio'); // Basically jQuery for node.js
const jsdom = require("jsdom");
const { JSDOM } = jsdom;




function ScrapeInstagramPage (args) {
dout("ScrapeInstagramPage for username -> " + args.username);
var query_url = 'https://www.instagram.com/' + args.username + '/';


var cookieString = '';


var options = {
url: query_url,
method: 'GET',
headers: {
'x-requested-with' : 'XMLHttpRequest',
'accept-language'  : 'en-US,en;q=0.8,pt;q=0.6,hi;q=0.4',
'User-Agent'       : 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
'referer'          : 'https://www.instagram.com/dress_blouse_designer/',
'Cookie'           : cookieString,
'Accept'           : '*/*',
'Connection'       : 'keep-alive',
'authority'        : 'www.instagram.com'
}
};




function dout (msg) {
if (args.debug) {
console.log(msg);
}
}


function autoParse(body, response, resolveWithFullResponse) {
// FIXME: The content type string could contain additional values like the charset.
// Consider using the `content-type` library for a robust comparison.
if (response.headers['content-type'] === 'application/json') {
return JSON.parse(body);
} else if (response.headers['content-type'] === 'text/html') {
return $.load(body);
} else {
return body;
}
}


options.transform = autoParse;




rp(options)
.then(function (autoParsedBody) {
if (args.debug) {
console.log("Responce of 'Get first user page': ");
console.log(autoParsedBody);
console.log("Creating JSDOM from above Responce...");
}


const dom = new JSDOM(autoParsedBody.html(), { runScripts: "dangerously" });
if (args.debug) console.log(dom.window._sharedData); // full data doc form instagram for a page


var user = dom.window._sharedData.entry_data.ProfilePage[0].user;
if (args.debug) {
console.log(user); // page user
console.log(user.id); // user ID
console.log(user.full_name); // user full_name
console.log(user.username); // user username
console.log(user.followed_by.count); // user followed_by
console.log(user.profile_pic_url_hd); // user profile pic
console.log(autoParsedBody.html());
}


if (user.is_private) {
dout ("User account is PRIVATE");
} else {
dout ("User account is public");
GetPostsFromUser(user.id, 5000, undefined);
}
})
.catch(function (err) {
console.log( "ERROR: " + err );
});


var pop_posts = [];
function GetPostsFromUser (user_id, first, end_cursor) {
var end_cursor_str = "";
if (end_cursor != undefined) {
end_cursor_str = '&after=' + end_cursor;
}


options.url = 'https://www.instagram.com/graphql/query/?query_id=17880160963012870&id='
+ user_id + '&first=' + first + end_cursor_str;


rp(options)
.then(function (autoParsedBody) {
if (autoParsedBody.status === "ok") {
if (args.debug) console.log(autoParsedBody.data);
var posts = autoParsedBody.data.user.edge_owner_to_timeline_media;


// POSTS processing
if (posts.edges.length > 0) {
//console.log(posts.edges);
pop_posts = pop_posts.concat
(posts.edges.map(function(e) {
var d = new Date();
var now_seconds = d.getTime() / 1000;


var seconds_since_post = now_seconds - e.node.taken_at_timestamp;
//console.log("seconds_since_post: " + seconds_since_post);


var ageing = 10; // valuses (1-10]; big value means no ageing
var days_since_post = Math.floor(seconds_since_post/(24*60*60));
var df = (Math.log(ageing+days_since_post) / (Math.log(ageing)));
var likes_per_day = (e.node.edge_liked_by.count / df);
// console.log("likes: " + e.node.edge_liked_by.count);
//console.log("df: " + df);
//console.log("likes_per_day: " + likes_per_day);
//return (likes_per_day > 10 * 1000);
var obj = {};
obj.url = e.node.display_url;
obj.likes_per_day = likes_per_day;
obj.days_since_post = days_since_post;
obj.total_likes = e.node.edge_liked_by.count;
return obj;
}
));


pop_posts.sort(function (b,a) {
if (a.likes_per_day < b.likes_per_day)
return -1;
if (a.likes_per_day > b.likes_per_day)
return 1;
return 0;
});


//console.log(pop_posts);


pop_posts.forEach(function (obj) {
console.log(obj.url);
});
}


if (posts.page_info.has_next_page) {
GetPostsFromUser(user_id, first, posts.page_info.end_cursor);
}
} else {
console.log( "ERROR: Posts AJAX call not returned good..." );
}
})
.catch(function (err) {
console.log( "ERROR: " + err );
});
}
}




ScrapeInstagramPage ({username : "dress_blouse_designer", debug : false});

试试 给你

例如: 对于给定的 URL‘ https://www.instagram.com/dress_blouse_designer/’，可以调用函数

ScrapeInstagramPage ({username : "dress_blouse_designer", debug : false});

2017年11月11日
由于 Instagram 改变了提供这些数据的方式，以上方法现在都不起作用了。以下是获取用户媒体的新方法:
接通 https://instagram.com/graphql/query/?query_id=17888483320059182&variables={"id":"1951415043","first":20,"after":null}
地点:
永久值: 17888483320059182(注意，将来可能会更改)。
用户的 id-id。它可能会附带用户列表。要获得用户列表，可以使用以下请求: GET https://www.instagram.com/web/search/topsearch/?context=blended&query=YOUR_QUERY
需要获得的项目数量。
如果要从最后一个项目中获取项目，则为该项目的 after-id。

我能够使用以下 API 获得用户的最新媒体，而不需要验证(包括描述、喜欢、评论计数)。

Https://www.instagram.com/apple/?__a=1

例如。

https://www.instagram.com/{username}/?__a=1

这使用一个简单的 ajax 调用和迭代图像路径。

        var name = "nasa";
$.get("https://www.instagram.com/" + name + "/?__a=1", function (data, status) {
console.log('IG_NODES', data.user.media.nodes);
$.each(data.user.media.nodes, function (n, item) {
console.log('ITEMS', item.display_src);
$('body').append(
"<div class='col-md-4'><img class='img-fluid d-block' src='" + item.display_src + "'></div>"
);
});
})

还有一个技巧，通过标签搜索照片:

GET https://www.instagram.com/graphql/query/?query_hash=3e7706b09c6184d5eafd8b032dbcf487&variables={"tag_name":"nature","first":25,"after":""}

地点:

query_hash-永久值(我相信它的哈希值17888483320059182，将来可以更改)

tag_name-标题不言自明

first-数量的项目得到(我不知道为什么，但这个价值不工作的预期。返回的照片的实际数量略大于值乘以4.5(值25大约为110，值100大约为460)

如果要从最后一个项目中获取项目，则为该项目的 after-id。可以在这里使用来自 JSON 响应的 end_cursor值。

JSFiddle

Javascript:

$(document).ready(function(){


var username = "leomessi";
var max_num_items = 5;


var jqxhr = $.ajax( "https://www.instagram.com/"+username+"/?__a=1" ).done(function() {
//alert( "success" );
}).fail(function() {
//alert( "error" );
}).always(function(data) {
//alert( "complete" )
items = data.graphql.user.edge_owner_to_timeline_media.edges;
$.each(items, function(n, item) {
if( (n+1) <= max_num_items )
{
var data_li = "<li><a target='_blank' href='https://www.instagram.com/p/"+item.node.shortcode+"'><img src='" + item.node.thumbnail_src + "'/></a></li>";
$("ul.instagram").append(data_li);
}
});


});


});

HTML:

<ul class="instagram">
</ul>

CSS:

ul.instagram {
list-style: none;
}


ul.instagram li {
float: left;
}


ul.instagram li img {
height: 100px;
}

多亏了 Instagram 不断变化的 API 模式(设计也非常糟糕) ，以上大部分模式到2018年4月将不再有效。

如果您使用 https://www.instagram.com/username/?__a=1方法直接查询各个发布数据的 API，以下是访问这些数据的最新路径。

假设返回的 JSON数据是 $data，您可以使用以下路径示例遍历每个结果:

foreach ($data->graphql->user->edge_owner_to_timeline_media->edges as $item) {


$content_id = $item->node->id;
$date_posted = $item-node->taken_at_timestamp;
$comments = $item->node->edge_media_to_comment->count;
$likes = $item->node->edge_liked_by->count;
$image = $item->node->display_url;
$content = $item->node->edge_media_to_caption->edges[0]->node->text;
// etc etc ....
}

最近变化的主要内容是 graphql和 edge_owner_to_timeline_media。

看起来他们将要为 2018年12月中的非“业务”客户终止这种 API 访问，所以尽可能地利用它。

希望能帮到别人;)

好吧，由于 /?__a=1现在已经停止工作了，所以最好使用 curl 并解析 instagram 页面，就像下面这个答案所写的那样: 生成访问令牌 Instagram API，而不必登录？

您可以使用此 API 检索 instagram 用户的公共信息:

https://api.lityapp.com/instagrams/thebrainscoop?limit=2(编辑: 在2021年2月破坏/恶意链接)

如果不设置限制参数，则文章默认限制在12个

这个 API 是在 SpringBoot 用 htmlUnit 制作的，你可以在代码中看到:

    public JSONObject getPublicInstagramByUserName(String userName, Integer limit) {
String html;
WebClient webClient = new WebClient();
    

try {
webClient.getOptions().setCssEnabled(false);
webClient.getOptions().setJavaScriptEnabled(false);
webClient.getOptions().setThrowExceptionOnScriptError(false);
webClient.getCookieManager().setCookiesEnabled(true);
    

Page page = webClient.getPage("https://www.instagram.com/" + userName);
WebResponse response = page.getWebResponse();
    

html = response.getContentAsString();
} catch (Exception ex) {
ex.printStackTrace();
    

throw new RuntimeException("Ocorreu um erro no Instagram");
}
    

String prefix = "static/bundles/es6/ProfilePageContainer.js";
String suffix = "\"";
String script = html.substring(html.indexOf(prefix));
    

script = script.substring(0, script.indexOf(suffix));
    

try {
Page page = webClient.getPage("https://www.instagram.com/" + script);
WebResponse response = page.getWebResponse();
    

script = response.getContentAsString();
} catch (Exception ex) {
ex.printStackTrace();
    

throw new RuntimeException("Ocorreu um erro no Instagram");
}
    

prefix = "l.pagination},queryId:\"";
    

String queryHash = script.substring(script.indexOf(prefix) + prefix.length());
    

queryHash = queryHash.substring(0, queryHash.indexOf(suffix));
prefix = "<script type=\"text/javascript\">window._sharedData = ";
suffix = ";</script>";
html = html.substring(html.indexOf(prefix) + prefix.length());
html = html.substring(0, html.indexOf(suffix));
    

JSONObject json = new JSONObject(html);
JSONObject entryData = json.getJSONObject("entry_data");
JSONObject profilePage = (JSONObject) entryData.getJSONArray("ProfilePage").get(0);
JSONObject graphql = profilePage.getJSONObject("graphql");
JSONObject user = graphql.getJSONObject("user");
JSONObject response = new JSONObject();
    

response.put("id", user.getString("id"));
response.put("username", user.getString("username"));
response.put("fullName", user.getString("full_name"));
response.put("followedBy", user.getJSONObject("edge_followed_by").getLong("count"));
response.put("following", user.getJSONObject("edge_follow").getLong("count"));
response.put("isBusinessAccount", user.getBoolean("is_business_account"));
response.put("photoUrl", user.getString("profile_pic_url"));
response.put("photoUrlHD", user.getString("profile_pic_url_hd"));
    

JSONObject edgeOwnerToTimelineMedia = user.getJSONObject("edge_owner_to_timeline_media");
JSONArray posts = new JSONArray();
    

try {
loadPublicInstagramPosts(webClient, queryHash, user.getString("id"), posts, edgeOwnerToTimelineMedia, limit == null ? 12 : limit);
} catch (Exception ex) {
ex.printStackTrace();
    

throw new RuntimeException("Você fez muitas chamadas, tente mais tarde");
}
    

response.put("posts", posts);
    

return response;
}
    

private void loadPublicInstagramPosts(WebClient webClient, String queryHash, String userId, JSONArray posts, JSONObject edgeOwnerToTimelineMedia, Integer limit) throws IOException {
JSONArray edges = edgeOwnerToTimelineMedia.getJSONArray("edges");
    

for (Object elem : edges) {
if (limit != null && posts.length() == limit) {
return;
}
    

JSONObject node = ((JSONObject) elem).getJSONObject("node");
    

if (node.getBoolean("is_video")) {
continue;
}
    

JSONObject post = new JSONObject();
    

post.put("id", node.getString("id"));
post.put("shortcode", node.getString("shortcode"));
    

JSONArray captionEdges = node.getJSONObject("edge_media_to_caption").getJSONArray("edges");
    

if (captionEdges.length() > 0) {
JSONObject captionNode = ((JSONObject) captionEdges.get(0)).getJSONObject("node");
    

post.put("caption", captionNode.getString("text"));
} else {
post.put("caption", (Object) null);
}
    

post.put("photoUrl", node.getString("display_url"));
    

JSONObject dimensions = node.getJSONObject("dimensions");
    

post.put("photoWidth", dimensions.getLong("width"));
post.put("photoHeight", dimensions.getLong("height"));
    

JSONArray thumbnailResources = node.getJSONArray("thumbnail_resources");
JSONArray thumbnails = new JSONArray();
    

for (Object elem2 : thumbnailResources) {
JSONObject obj = (JSONObject) elem2;
JSONObject thumbnail = new JSONObject();
    

thumbnail.put("photoUrl", obj.getString("src"));
thumbnail.put("photoWidth", obj.getLong("config_width"));
thumbnail.put("photoHeight", obj.getLong("config_height"));
thumbnails.put(thumbnail);
}
    

post.put("thumbnails", thumbnails);
posts.put(post);
}
    

JSONObject pageInfo = edgeOwnerToTimelineMedia.getJSONObject("page_info");
    

if (!pageInfo.getBoolean("has_next_page")) {
return;
}
    

String endCursor = pageInfo.getString("end_cursor");
String variables = "{\"id\":\"" + userId + "\",\"first\":12,\"after\":\"" + endCursor + "\"}";
    

String url = "https://www.instagram.com/graphql/query/?query_hash=" + queryHash + "&variables=" + URLEncoder.encode(variables, "UTF-8");
Page page = webClient.getPage(url);
WebResponse response = page.getWebResponse();
String content = response.getContentAsString();
JSONObject json = new JSONObject(content);
    

loadPublicInstagramPosts(webClient, queryHash, userId, posts, json.getJSONObject("data").getJSONObject("user").getJSONObject("edge_owner_to_timeline_media"), limit);
}

这是一个反应的例子:

    {
"id": "290482318",
"username": "thebrainscoop",
"fullName": "Official Fan Page",
"followedBy": 1023,
"following": 6,
"isBusinessAccount": false,
"photoUrl": "https://scontent-gru2-1.cdninstagram.com/vp/447ffd0262082f373acf3d467435f130/5C709C77/t51.2885-19/11351770_612904665516559_678168252_a.jpg",
"photoUrlHD": "https://scontent-gru2-1.cdninstagram.com/vp/447ffd0262082f373acf3d467435f130/5C709C77/t51.2885-19/11351770_612904665516559_678168252_a.jpg",
"posts": [
{
"id": "1430331382090378714",
"shortcode": "BPZjtBUly3a",
"caption": "If I have any active followers anymore; hello! I'm Brianna, and I created this account when I was just 12 years old to show my love for The Brain Scoop. I'm now nearly finished high school, and just rediscovered it. I just wanted to see if anyone is still active on here, and also correct some of my past mistakes - being a child at the time, I didn't realise I had to credit artists for their work, so I'm going to try to correct that post haste. Also; the font in my bio is horrendous. Why'd I think that was a good idea? Anyway, this is a beautiful artwork of the long-tailed pangolin by @chelsealinaeve . Check her out!",
"photoUrl": "https://scontent-gru2-1.cdninstagram.com/vp/ab823331376ca46136457f4654bf2880/5CAD48E4/t51.2885-15/e35/16110915_400942200241213_3503127351280009216_n.jpg",
"photoWidth": 640,
"photoHeight": 457,
"thumbnails": [
{
"photoUrl": "https://scontent-gru2-1.cdninstagram.com/vp/43b195566d0ef2ad5f4663ff76d62d23/5C76D756/t51.2885-15/e35/c91.0.457.457/s150x150/16110915_400942200241213_3503127351280009216_n.jpg",
"photoWidth": 150,
"photoHeight": 150
},
{
"photoUrl": "https://scontent-gru2-1.cdninstagram.com/vp/ae39043a7ac050c56d741d8b4355c185/5C93971C/t51.2885-15/e35/c91.0.457.457/s240x240/16110915_400942200241213_3503127351280009216_n.jpg",
"photoWidth": 240,
"photoHeight": 240
},
{
"photoUrl": "https://scontent-gru2-1.cdninstagram.com/vp/ae7a22d09e3ef98d0a6bbf31d621a3b7/5CACBBA6/t51.2885-15/e35/c91.0.457.457/s320x320/16110915_400942200241213_3503127351280009216_n.jpg",
"photoWidth": 320,
"photoHeight": 320
},
{
"photoUrl": "https://scontent-gru2-1.cdninstagram.com/vp/1439dc72b70e7c0c0a3afcc30970bb13/5C8E2923/t51.2885-15/e35/c91.0.457.457/16110915_400942200241213_3503127351280009216_n.jpg",
"photoWidth": 480,
"photoHeight": 480
},
{
"photoUrl": "https://scontent-gru2-1.cdninstagram.com/vp/1439dc72b70e7c0c0a3afcc30970bb13/5C8E2923/t51.2885-15/e35/c91.0.457.457/16110915_400942200241213_3503127351280009216_n.jpg",
"photoWidth": 640,
"photoHeight": 640
}
]
},
{
"id": "442527661838057235",
"shortcode": "YkLJBXJD8T",
"caption": null,
"photoUrl": "https://scontent-gru2-1.cdninstagram.com/vp/dc94b38da679826b9ac94ccd2bcc4928/5C7CDF93/t51.2885-15/e15/11327349_860747310663863_2105199307_n.jpg",
"photoWidth": 612,
"photoHeight": 612,
"thumbnails": [
{
"photoUrl": "https://scontent-gru2-1.cdninstagram.com/vp/c1153c6513c44a6463d897e14b2d8f06/5CB13ADD/t51.2885-15/e15/s150x150/11327349_860747310663863_2105199307_n.jpg",
"photoWidth": 150,
"photoHeight": 150
},
{
"photoUrl": "https://scontent-gru2-1.cdninstagram.com/vp/47e60ec8bca5a1382cd9ac562439d48c/5CAE6A82/t51.2885-15/e15/s240x240/11327349_860747310663863_2105199307_n.jpg",
"photoWidth": 240,
"photoHeight": 240
},
{
"photoUrl": "https://scontent-gru2-1.cdninstagram.com/vp/da0ee5b666ab40e4adc1119e2edca014/5CADCB59/t51.2885-15/e15/s320x320/11327349_860747310663863_2105199307_n.jpg",
"photoWidth": 320,
"photoHeight": 320
},
{
"photoUrl": "https://scontent-gru2-1.cdninstagram.com/vp/02ee23571322ea8d0992e81e72f80ef2/5C741048/t51.2885-15/e15/s480x480/11327349_860747310663863_2105199307_n.jpg",
"photoWidth": 480,
"photoHeight": 480
},
{
"photoUrl": "https://scontent-gru2-1.cdninstagram.com/vp/dc94b38da679826b9ac94ccd2bcc4928/5C7CDF93/t51.2885-15/e15/11327349_860747310663863_2105199307_n.jpg",
"photoWidth": 640,
"photoHeight": 640
}
]
}
]
}

下面是一个 php 脚本，它下载图像并创建一个带有图像链接的 html 文件。信用350D 的 php 版本，这是刚刚阐述。.我会建议把这是一个老古董的工作和解雇无论你需要。截至2019年5月核实工作情况.

<?
$user = 'smena8m';
$igdata = file_get_contents('https://instagram.com/'.$user.'/');
preg_match('/_sharedData = ({.*);<\/script>/',$igdata,$matches);
$profile_data = json_decode($matches[1])->entry_data->ProfilePage[0]->graphql->user;
$html = '<div class="instagramBox" style="display:inline-grid;grid-template-columns:auto auto auto;">';
$i = 0;
$max = 9;
while($i<$max){
$imglink = $profile_data->edge_owner_to_timeline_media->edges[$i]->node->shortcode;
$img = $profile_data->edge_owner_to_timeline_media->edges[$i]->node->thumbnail_resources[0]->src;
file_put_contents('ig'.$i.'.jpg',file_get_contents($img));
$html .= '<a href="https://www.instagram.com/p/'.$imglink.'/" target="_blank"><img src="ig'.$i.'.jpg" /></a>';
$i++;
}
$html .= '</div>';
$instagram = fopen('instagram.html','w');
fwrite($instagram,$html);
fclose($instagram);
?>

我真的需要这个功能，但 WordPress。我适合，它完美地工作

<script>
jQuery(function($){
var name = "caririceara.comcariri";
$.get("https://images"+~~(Math.random()*33)+"-focus-opensocial.googleusercontent.com/gadgets/proxy?container=none&url=https://www.instagram.com/" + name + "/", function(html) {
if (html) {
var regex = /_sharedData = ({.*);<\/script>/m,
json = JSON.parse(regex.exec(html)[1]),
edges = json.entry_data.ProfilePage[0].graphql.user.edge_owner_to_timeline_media.edges;
$.each(edges, function(n, edge) {
if (n <= 7){
var node = edge.node;
$('.img_ins').append('<a href="https://instagr.am/p/'+node.shortcode+'" target="_blank"><img src="'+node.thumbnail_src+'" width="150"></a>');
}
});
}
});
});
</script>

如果希望搜索没有 clientID 和访问令牌的用户:

1: 如果你想搜索所有名字与搜索词相似的用户:

用要搜索的文本替换 SeachName:

Https://www.instagram.com/web/search/topsearch/?query=searchname

2: 如果你想搜索完全相同的名字用户:

将 UserName 替换为所需的搜索名称:

Https://www.instagram.com/username/?__a=1