Viewing enriched Twitter post
The final step of the FinePDFs saga is here! The FinePDFs 📃 BOOK We put everything we know about PDFs inside: - How to make the SoTA PDFs dataset? - How much old internet is dead now? - Why we chose RolmOCR for OCR - What is https://t.co/i3PivBI9hh And many more🤗 https://t.co/m8mC0Xjksc
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2008605482328707126/media_0.jpg?",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2008605482328707126/media_0.jpg?",
"type": "photo",
"filename": "media_0.jpg"
}
],
"processed_at": "2026-01-18T19:41:50.159920",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "2008605482328707126",
"url": "https://x.com/HKydlicek/status/2008605482328707126",
"twitterUrl": "https://twitter.com/HKydlicek/status/2008605482328707126",
"text": "The final step of the FinePDFs saga is here!\nThe FinePDFs 📃 BOOK\n\nWe put everything we know about PDFs inside:\n- How to make the SoTA PDFs dataset? \n- How much old internet is dead now?\n- Why we chose RolmOCR for OCR\n- What is https://t.co/i3PivBI9hh\n\nAnd many more🤗 https://t.co/m8mC0Xjksc",
"source": "Twitter for iPhone",
"retweetCount": 16,
"replyCount": 5,
"likeCount": 109,
"quoteCount": 2,
"viewCount": 66655,
"createdAt": "Tue Jan 06 18:23:59 +0000 2026",
"lang": "en",
"bookmarkCount": 91,
"isReply": false,
"inReplyToId": null,
"conversationId": "2008605482328707126",
"displayTextRange": [
0,
267
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "HKydlicek",
"url": "https://x.com/HKydlicek",
"twitterUrl": "https://twitter.com/HKydlicek",
"id": "1470207594727940099",
"name": "Hynek Kydlíček",
"isVerified": false,
"isBlueVerified": false,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/2001409107232763904/TDbrpdja_normal.jpg",
"coverPicture": "",
"description": "",
"location": "Czech Republic",
"followers": 1344,
"following": 454,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Mon Dec 13 01:43:13 +0000 2021",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 664,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 175,
"statusesCount": 760,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1964584936524124645"
],
"profile_bio": {
"description": "Pre-training data @huggingface 🤗\nPrague, CZ\n🇪🇺 eu/acc",
"entities": {
"description": {
"user_mentions": [
{
"id_str": "0",
"indices": [
18,
30
],
"name": "",
"screen_name": "huggingface"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"allow_download_status": {
"allow_download": true
},
"display_url": "pic.twitter.com/m8mC0Xjksc",
"expanded_url": "https://twitter.com/HKydlicek/status/2008605482328707126/photo/1",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": [
{
"h": 110,
"w": 110,
"x": 734,
"y": 238
},
{
"h": 172,
"w": 172,
"x": 827,
"y": 273
}
]
},
"orig": {
"faces": [
{
"h": 110,
"w": 110,
"x": 734,
"y": 238
},
{
"h": 172,
"w": 172,
"x": 827,
"y": 273
}
]
}
},
"id_str": "2008603145371320320",
"indices": [
268,
291
],
"media_key": "3_2008603145371320320",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARvf/esulwAACgACG+AAC0wa0DYAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABG9/96y6XAAAKAAIb4AALTBrQNgAA",
"media_key": "3_2008603145371320320"
}
},
"media_url_https": "https://pbs.twimg.com/media/G9_96y6XAAAUqdY.jpg",
"original_info": {
"focus_rects": [
{
"h": 718,
"w": 1282,
"x": 0,
"y": 0
},
{
"h": 718,
"w": 718,
"x": 205,
"y": 0
},
{
"h": 718,
"w": 630,
"x": 249,
"y": 0
},
{
"h": 718,
"w": 359,
"x": 385,
"y": 0
},
{
"h": 718,
"w": 1328,
"x": 0,
"y": 0
}
],
"height": 718,
"width": 1328
},
"sizes": {
"large": {
"h": 718,
"w": 1328
}
},
"type": "photo",
"url": "https://t.co/m8mC0Xjksc"
}
]
},
"card": null,
"place": {},
"entities": {
"urls": [
{
"display_url": "equibase.com",
"expanded_url": "http://equibase.com",
"indices": [
228,
251
],
"url": "https://t.co/i3PivBI9hh"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
}