通过主题标签和时间范围查询Instagram帖子-Java 学习之路

我正在尝试通过提供主题标签和时间范围（从日期到日期）来查询Instagram中的帖子 . 我用的是recent tags endpoint .

https://api.instagram.com/v1/tags//media/recent?access_token=ACCESS-TOKEN

我的代码是使用instagram-node库在Node.js中编写的（请参阅内联注释）：

// Require the config file
var config = require('../config.js');

// Require and intialize the instagram instance
var ig = require('instagram-node').instagram();

// Set the access token
ig.use({ access_token: config.instagram.access_token });

// We export this function for public use
// hashtag: the hashtag to search for
// minDate: the since date
// maxDate: the until date
// callback: the callback function (err, posts)
module.exports = function (hashtag, minDate, maxDate, callback) {

  // Create the posts array (will be concated with new posts from pagination responses)
  var posts = [];

  // Convert the date objects into timestamps (seconds)
  var sinceTime = Math.floor(minDate.getTime() / 1000);
  var untilTime = Math.floor(maxDate.getTime() / 1000);

  // Fetch the IG posts page by page
  ig.tag_media_recent(hashtag, { count: 50 }, function fetchPosts(err, medias, pagination, remaining, limit) {

    // Handle error
    if (err) {
      return callback(err);
    }

    // Manually filter by time
    var filteredByTime = medias.filter(function (currentPost) {
      // Convert the created_time string into number (seconds timestamp)
      var createdTime = +currentPost.created_time;

      // Check if it's after since date and before until date
      return createdTime >= sinceTime && createdTime <= untilTime;
    });

    // Get the last post on this page
    var lastPost = medias[medias.length - 1] || {};

    // ...and its timestamp
    var lastPostTimeStamp = +(lastPost.created_time || -1);

    // ...and its timestamp date object
    var lastPostDate = new Date(lastPostTimeStamp * 1000);

    // Concat the new [filtered] posts to the big array
    posts = posts.concat(filteredByTime);

    // Show some output
    console.log('found ' + filteredByTime.length + ' new items total: ' + posts.length, lastPostDate);


    // Check if the last post is BEFORE until date and there are no new posts in the provided range
    if (filteredByTime.length === 0 && lastPostTimeStamp <= untilTime) {
      // ...if so, we can callback!
      return callback(null, posts);
    }

    // Navigate to the next page
    pagination.next(fetchPosts);
  });
};

这将开始获取最新到最近的帖子，并手动过滤 created_time . 这是有效的，但效率非常低，因为如果我们想要从一年前获得帖子，我们必须迭代页面直到那个时候，这将使用大量请求（可能超过5k /小时）这是速率限制） .

有没有更好的方法来进行此查询？如何通过提供标签和时间范围来获取Instagram帖子？

2 回答

我认为这是你正在寻找的基本想法 . 我对Node.js并不是很熟悉，所以这都是普通的javascript . 你必须修改它以满足你的需要，并可能从中做出一个功能 .

我们的想法是将Instagram ID（在此示例中为1116307519311125603）转换为日期，反之亦然，以便您能够快速获取特定时间点，而不是回溯所有结果，直到找到所需的时间戳 . 下划线'_'后面的id部分应该被修剪掉，因为它在某种程度上指的是用户IIRC . 示例中有4个函数，希望对您有所帮助 .

快乐的黑客！

//static
var epoch_hour = 3600,
    epoch_day = 86400,
    epoch_month = 2592000,
    epoch_year = 31557600;

//you'll need to set this part up/integrate it with your code
var dataId = 1116307519311125603,
    range = 2 * epoch_hour,
    count = 1,
    tagName = 'cars',
    access = prompt('Enter access token:'),
    baseUrl = 'https://api.instagram.com/v1/tags/' + 
              tagName + '/media/recent?access_token=' + access;

//date && id utilities
function idToEpoch(n){
  return Math.round((n / 1000000000000 + 11024476.5839159095) / 0.008388608);
}

function epochToId(n){
  return Math.round((n * 0.008388608 - 11024476.5839159095) * 1000000000000);
}

function newDateFromEpoch(n){
  var d = new Date(0);
  d.setUTCSeconds(n);
  return d;
}

function dateToEpoch(d){
  return (d.getTime()-d.getMilliseconds())/1000;
}

//start with your id and range; do the figuring
var epoch_time = idToEpoch(dataId),
    minumumId = epochToId(epoch_time),
    maximumId = epochToId(epoch_time + range),
    minDate = newDateFromEpoch(epoch_time),
    maxDate = newDateFromEpoch(epoch_time + range);

var newUrl = baseUrl + 
             '&count=' + count + 
             '&min_tag_id=' + minumumId + 
             '&max_tag_id=' + maximumId;


//used for testing
/*alert('Start: ' + minDate + ' (' + epoch_time + 
        ')\nEnd: ' + maxDate + ' (' + (epoch_time +
        range) + ')');
window.location = newUrl;*/

回复于 2024-05-03T10:56:06+08:00

为了支持this优秀的答案，通过plpgSQL函数生成一个Instagram ID：

CREATE OR REPLACE FUNCTION insta5.next_id(OUT result bigint) AS $$
DECLARE
    our_epoch bigint := 1314220021721;
    seq_id bigint;
    now_millis bigint;
    shard_id int := 5;
BEGIN
    SELECT nextval('insta5.table_id_seq') %% 1024 INTO seq_id;

    SELECT FLOOR(EXTRACT(EPOCH FROM clock_timestamp()) * 1000) INTO now_millis;
    result := (now_millis - our_epoch) << 23;
    result := result | (shard_id << 10);
    result := result | (seq_id);
END;
$$ LANGUAGE PLPGSQL;

来自Instagram's blog

回复于 2024-05-03T10:56:06+08:00

通过主题标签和时间范围查询Instagram帖子

2 回答

相关问题