šŸ¦ Twitter Post Details

Viewing enriched Twitter post

@_inesmontani

New post: From PDFs to AI-ready structured data šŸ“ƒāœØ A deep dive into document processing, layout analysis and a modular workflow for building end-to-end document understanding and information extraction pipelines using PDFs, Word documents, scans and more. https://t.co/1QGH9NlHao

Media 1
View on Twitter

šŸ“Š Media Metadata

{
  "score": 0.86,
  "scored_at": "2025-08-09T13:46:07.555475",
  "import_source": "network_archive_import",
  "links_checked": true,
  "checked_at": "2025-08-10T10:32:59.330291",
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1863539548581413200/media_0.jpg?",
      "filename": "media_0.jpg"
    },
    {
      "id": "",
      "type": "photo",
      "url": null,
      "media_url": "https://pbs.twimg.com/media/GdyfCgeWQAE1e6h.jpg",
      "media_url_https": null,
      "display_url": null,
      "expanded_url": null
    }
  ],
  "reprocessed_at": "2025-08-12T15:26:59.033011",
  "reprocessed_reason": "missing_media_array",
  "original_structure": "had_both"
}

šŸ”§ Raw API Response

{
  "user": {
    "created_at": "2008-05-02T02:18:57.000Z",
    "default_profile_image": false,
    "description": "šŸ’„ Founder & CEO @explosion_ai\nšŸ‘©ā€šŸ’» Dev @spacy_io & https://t.co/LIBUg29Gm9\n\nšŸ˜ https://t.co/pqYinNyTPm\nšŸŸ¦ https://t.co/RjrWCh1I27ā€¦\nšŸ’¼ https://t.co/gXMmVHWM1m",
    "fast_followers_count": 0,
    "favourites_count": 6041,
    "followers_count": 21553,
    "friends_count": 340,
    "has_custom_timelines": false,
    "is_translator": false,
    "listed_count": 518,
    "location": "Berlin, Germany",
    "media_count": 669,
    "name": "Ines Montani 怰ļø",
    "normal_followers_count": 21553,
    "possibly_sensitive": false,
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/14622002/1562699707",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/762577401574526976/hQjD1Z-F_normal.jpg",
    "screen_name": "_inesmontani",
    "statuses_count": 3684,
    "translator_type": "none",
    "url": "https://t.co/zeTfk0AMPK",
    "verified": false,
    "withheld_in_countries": [],
    "id_str": "14622002"
  },
  "id": "1863539548581413200",
  "conversation_id": "1863539548581413200",
  "full_text": "New post: From PDFs to AI-ready structured data šŸ“ƒāœØ\n\nA deep dive into document processing, layout analysis and a modular workflow for building end-to-end document understanding and information extraction pipelines using PDFs, Word documents, scans and more. https://t.co/1QGH9NlHao",
  "reply_count": 4,
  "retweet_count": 44,
  "favorite_count": 210,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/GdyfCgeWQAE1e6h.jpg",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/_inesmontani/status/1863539548581413200",
  "created_at": "2024-12-02T11:03:45.000Z",
  "#sort_index": "1863539548581413200",
  "view_count": 14702,
  "quote_count": 2,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": false,
  "startUrl": "https://x.com/_inesmontani/status/1863539548581413200"
}