Viewing enriched Twitter post
Game changer for scraping. This repo lets you easily scrape web pages and have the output in LLM-friendly formats (JSON, cleaned HTML, markdown). • Supports crawling multiple URLs simultaneously • Extracts and returns all media tags (Images, Audio, and Video) • Extracts all… https://t.co/bVx1OUeEIB
{
"data": [
{
"id": "1907795226195800064",
"type": "photo",
"url": "https://t.co/bVx1OUeEIB",
"media_url": null,
"media_url_https": "https://pbs.twimg.com/media/GnnZpnmWMAAXQjN.jpg",
"display_url": "pic.x.com/bVx1OUeEIB",
"expanded_url": "https://x.com/LiorOnAI/status/1907795230016856550/photo/1"
}
],
"score": 0.83,
"scored_at": "2025-08-09T13:47:19.521035",
"import_source": "unknown_source",
"links_checked": true,
"checked_at": "2025-08-10T10:33:18.332220"
}{
"tweet": {
"bookmark_count": 463,
"bookmarked": false,
"created_at": "Thu Apr 03 14:00:02 +0000 2025",
"conversation_id_str": "1907795230016856550",
"display_text_range": [
0,
278
],
"entities": {
"hashtags": [],
"media": [
{
"display_url": "pic.x.com/bVx1OUeEIB",
"expanded_url": "https://x.com/LiorOnAI/status/1907795230016856550/photo/1",
"id_str": "1907795226195800064",
"indices": [
279,
302
],
"media_key": "3_1907795226195800064",
"media_url_https": "https://pbs.twimg.com/media/GnnZpnmWMAAXQjN.jpg",
"type": "photo",
"url": "https://t.co/bVx1OUeEIB",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": [
{
"x": 307,
"y": 391,
"h": 44,
"w": 44
}
]
},
"medium": {
"faces": [
{
"x": 307,
"y": 391,
"h": 44,
"w": 44
}
]
},
"small": {
"faces": [
{
"x": 173,
"y": 221,
"h": 24,
"w": 24
}
]
},
"orig": {
"faces": [
{
"x": 307,
"y": 391,
"h": 44,
"w": 44
}
]
}
},
"sizes": {
"large": {
"h": 656,
"w": 1200,
"resize": "fit"
},
"medium": {
"h": 656,
"w": 1200,
"resize": "fit"
},
"small": {
"h": 372,
"w": 680,
"resize": "fit"
},
"thumb": {
"h": 150,
"w": 150,
"resize": "crop"
}
},
"original_info": {
"height": 656,
"width": 1200,
"focus_rects": [
{
"x": 0,
"y": 0,
"w": 1171,
"h": 656
},
{
"x": 0,
"y": 0,
"w": 656,
"h": 656
},
{
"x": 0,
"y": 0,
"w": 575,
"h": 656
},
{
"x": 0,
"y": 0,
"w": 328,
"h": 656
},
{
"x": 0,
"y": 0,
"w": 1200,
"h": 656
}
]
},
"media_results": {
"result": {
"media_key": "3_1907795226195800064"
}
}
}
],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": []
},
"extended_entities": {
"media": [
{
"display_url": "pic.x.com/bVx1OUeEIB",
"expanded_url": "https://x.com/LiorOnAI/status/1907795230016856550/photo/1",
"id_str": "1907795226195800064",
"indices": [
279,
302
],
"media_key": "3_1907795226195800064",
"media_url_https": "https://pbs.twimg.com/media/GnnZpnmWMAAXQjN.jpg",
"type": "photo",
"url": "https://t.co/bVx1OUeEIB",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": [
{
"x": 307,
"y": 391,
"h": 44,
"w": 44
}
]
},
"medium": {
"faces": [
{
"x": 307,
"y": 391,
"h": 44,
"w": 44
}
]
},
"small": {
"faces": [
{
"x": 173,
"y": 221,
"h": 24,
"w": 24
}
]
},
"orig": {
"faces": [
{
"x": 307,
"y": 391,
"h": 44,
"w": 44
}
]
}
},
"sizes": {
"large": {
"h": 656,
"w": 1200,
"resize": "fit"
},
"medium": {
"h": 656,
"w": 1200,
"resize": "fit"
},
"small": {
"h": 372,
"w": 680,
"resize": "fit"
},
"thumb": {
"h": 150,
"w": 150,
"resize": "crop"
}
},
"original_info": {
"height": 656,
"width": 1200,
"focus_rects": [
{
"x": 0,
"y": 0,
"w": 1171,
"h": 656
},
{
"x": 0,
"y": 0,
"w": 656,
"h": 656
},
{
"x": 0,
"y": 0,
"w": 575,
"h": 656
},
{
"x": 0,
"y": 0,
"w": 328,
"h": 656
},
{
"x": 0,
"y": 0,
"w": 1200,
"h": 656
}
]
},
"media_results": {
"result": {
"media_key": "3_1907795226195800064"
}
}
}
]
},
"favorite_count": 321,
"favorited": false,
"full_text": "Game changer for scraping. \n\nThis repo lets you easily scrape web pages and have the output in LLM-friendly formats (JSON, cleaned HTML, markdown).\n\n• Supports crawling multiple URLs simultaneously\n• Extracts and returns all media tags (Images, Audio, and Video)\n• Extracts all… https://t.co/bVx1OUeEIB",
"is_quote_status": false,
"lang": "en",
"possibly_sensitive": false,
"possibly_sensitive_editable": true,
"quote_count": 0,
"reply_count": 14,
"retweet_count": 49,
"retweeted": false,
"user_id_str": "931470139",
"id_str": "1907795230016856550",
"note_tweet": {
"is_expandable": true,
"note_tweet_results": {
"result": {
"id": "Tm90ZVR3ZWV0OjE5MDc3OTUyMjk4ODI2MDk2NjQ=",
"text": "Game changer for scraping. \n\nThis repo lets you easily scrape web pages and have the output in LLM-friendly formats (JSON, cleaned HTML, markdown).\n\n• Supports crawling multiple URLs simultaneously\n• Extracts and returns all media tags (Images, Audio, and Video)\n• Extracts all external and internal links\n• Extracts metadata from the page\n• Custom hooks for authentication, headers, and page modifications before crawling",
"entity_set": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": []
}
}
}
}
},
"user": {
"__typename": "User",
"id": "VXNlcjo5MzE0NzAxMzk=",
"rest_id": "931470139",
"affiliates_highlighted_label": {},
"has_graduated_access": true,
"is_blue_verified": true,
"profile_image_shape": "Circle",
"legacy": {
"can_dm": true,
"can_media_tag": false,
"created_at": "Wed Nov 07 07:19:36 +0000 2012",
"default_profile": false,
"default_profile_image": false,
"description": "Covering the latest in AI development • ML Eng since 2017 • Building @AlphaSignalAI into the #1 source of dev news in AI → At 240k readers.",
"entities": {
"description": {
"urls": []
},
"url": {
"urls": [
{
"display_url": "alphasignal.ai",
"expanded_url": "https://alphasignal.ai",
"url": "https://t.co/AyubevaLcb",
"indices": [
0,
23
]
}
]
}
},
"fast_followers_count": 0,
"favourites_count": 6205,
"followers_count": 103547,
"friends_count": 1587,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 2098,
"location": "SF (let’s hang)",
"media_count": 609,
"name": "Lior⚡",
"normal_followers_count": 103547,
"pinned_tweet_ids_str": [],
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/931470139/1747705414",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1817166841992597504/zLRK5Qx__normal.jpg",
"profile_interstitial_type": "",
"screen_name": "LiorOnAI",
"statuses_count": 3439,
"translator_type": "none",
"url": "https://t.co/AyubevaLcb",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"professional": {
"rest_id": "1621155519586271232",
"professional_type": "Creator",
"category": []
},
"tipjar_settings": {}
},
"views": "20335"
}