Разбор комплекса JSON с помощью Kinesis Analytics - PullRequest
Новая
       25

Разбор комплекса JSON с помощью Kinesis Analytics

0 голосов
/ 29 сентября 2018

У меня есть следующий поток JSON, исходящий из Twitter. 

{
  "created_at": "Thu Sep 27 21:02:00 +0000 2018",
  "id": 1045418301336244224,
  "id_str": "1045418301336244224",
  "text": "Conditional Branching Now Supported in AWS Systems Manager Automation - @awscloud #amazon #aws",
  "source": "<a href=\"https://buffer.com\" rel=\"nofollow\">Buffer</a>",
  "truncated": false,
  "in_reply_to_status_id": null,
  "in_reply_to_status_id_str": null,
  "in_reply_to_user_id": null,
  "in_reply_to_user_id_str": null,
  "in_reply_to_screen_name": null,
  "user": {
    "id": 14687423,
    "id_str": "14687423",
    "name": "Casey Becking",
    "screen_name": "caseybecking",
    "location": "Huntington Beach, CA",
    "url": "http://caseybecking.com",
    "description": "I do stuff with computers for @rackspace , geek at heart! play and watch to much hockey, someday I'll make a personal website.",
    "translator_type": "none",
    "protected": false,
    "verified": false,
    "followers_count": 4191,
    "friends_count": 2412,
    "listed_count": 90,
    "favourites_count": 794,
    "statuses_count": 12995,
    "created_at": "Wed May 07 15:03:23 +0000 2008",
    "utc_offset": null,
    "time_zone": null,
    "geo_enabled": true,
    "lang": "en",
    "contributors_enabled": false,
    "is_translator": false,
    "profile_background_color": "000000",
    "profile_background_image_url": "http://abs.twimg.com/images/themes/theme15/bg.png",
    "profile_background_image_url_https": "https://abs.twimg.com/images/themes/theme15/bg.png",
    "profile_background_tile": false,
    "profile_link_color": "ABB8C2",
    "profile_sidebar_border_color": "000000",
    "profile_sidebar_fill_color": "000000",
    "profile_text_color": "000000",
    "profile_use_background_image": false,
    "profile_image_url": "http://pbs.twimg.com/profile_images/981617292546060289/RMX0GQFe_normal.jpg",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/981617292546060289/RMX0GQFe_normal.jpg",
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/14687423/1439137746",
    "default_profile": false,
    "default_profile_image": false,
    "following": null,
    "follow_request_sent": null,
    "notifications": null
  },
  "geo": null,
  "coordinates": null,
  "place": null,
  "contributors": null,
  "is_quote_status": false,
  "quote_count": 0,
  "reply_count": 0,
  "retweet_count": 0,
  "favorite_count": 0,
  "entities": {
    "hashtags": [{
      "text": "amazon",
      "indices": [106, 113]
    }, {
      "text": "aws",
      "indices": [114, 118]
    }],
    "urls": [{
      "url": "",
      "expanded_url": "https://buff.ly/2zwRyBx",
      "display_url": "buff.ly/2zwRyBx",
      "indices": [72, 95]
    }],
    "user_mentions": [{
      "screen_name": "awscloud",
      "name": "Amazon Web Services",
      "id": 66780587,
      "id_str": "66780587",
      "indices": [96, 105]
    }],
    "symbols": []
  },
  "favorited": false,
  "retweeted": false,
  "possibly_sensitive": false,
  "filter_level": "low",
  "lang": "en",
  "timestamp_ms": "1538082120628",
  "emoticons": [],
  "sentiments": "Neutral"
}

Как мне анализировать, анализировать и обрабатывать этот JSON с помощью Kinesis Analytics?

Массивы должны быть сведены, и этоэто очень выполнимо в Hive, но нужно сделать то же самое в Kinesis Analytics.

...