91 lines
3.6 KiB
JSON
91 lines
3.6 KiB
JSON
{
|
|
"corpus": "gutenberg-longcontext",
|
|
"created_utc": "2026-10-22T14:21:38Z",
|
|
"documents": [
|
|
{
|
|
"fetched_at_utc": "2026-10-22T14:21:35Z",
|
|
"gutenberg_id": "2600",
|
|
"raw_bytes": 3878334,
|
|
"raw_file": "raw/war_and_peace.html",
|
|
"raw_sha256": "95204a39054713cb9f3bb4468177e64e1cef19f2e60384283aef6403d23ee30e",
|
|
"slug": "war_and_peace",
|
|
"source_url": "https://www.gutenberg.org/cache/epub/2600/pg2600-images.html",
|
|
"title": "War and Peace",
|
|
"txt_bytes": 3476843,
|
|
"txt_file": "txt/war_and_peace.txt",
|
|
"txt_sha256": "6cb9dd25004552dd6362f55f8560d926c2d145d89c192b02884b590ceb8c093b",
|
|
"word_count": 566794
|
|
},
|
|
{
|
|
"fetched_at_utc": "2026-10-22T14:21:34Z",
|
|
"gutenberg_id": "2701",
|
|
"raw_bytes": 1472550,
|
|
"raw_file": "raw/moby_dick.html",
|
|
"raw_sha256": "3e6cb01b2e2a839a50934121f511a2bfffc5695489b7d61ddd7eeae252c0277e",
|
|
"slug": "moby_dick",
|
|
"source_url": "https://www.gutenberg.org/cache/epub/2701/pg2701-images.html",
|
|
"title": "Moby-Dick; or, The Whale",
|
|
"txt_bytes": 1312754,
|
|
"txt_file": "txt/moby_dick.txt",
|
|
"txt_sha256": "9f7e9224bfb6baa821e8e1ff04302e3d5d2e41e716f7f6da1a226b01eeecbd0e",
|
|
"word_count": 216325
|
|
},
|
|
{
|
|
"fetched_at_utc": "2026-10-22T14:21:35Z",
|
|
"gutenberg_id": "1342",
|
|
"raw_bytes": 852590,
|
|
"raw_file": "raw/pride_and_prejudice.html",
|
|
"raw_sha256": "11a120c25838974d55bb542d424df322ee10a9058cd884e1166208d1c0fbfeaa",
|
|
"slug": "pride_and_prejudice",
|
|
"source_url": "https://www.gutenberg.org/cache/epub/1342/pg1342-images.html",
|
|
"title": "Pride and Prejudice",
|
|
"txt_bytes": 771500,
|
|
"txt_file": "txt/pride_and_prejudice.txt",
|
|
"txt_sha256": "7c8f3b9cd10c2324d1308ec99dc5018bc73b5809bf9a1c2dd3107e09d6d5d321",
|
|
"word_count": 130933
|
|
},
|
|
{
|
|
"fetched_at_utc": "2026-10-22T14:21:37Z",
|
|
"gutenberg_id": "1661",
|
|
"raw_bytes": 640229,
|
|
"raw_file": "raw/sherlock_holmes.html",
|
|
"raw_sha256": "26adf6c8ff1384574fca7466df77e226fc048e9ef1eac5c341f0dd997bcb71a4",
|
|
"slug": "sherlock_holmes",
|
|
"source_url": "https://www.gutenberg.org/cache/epub/1661/pg1661-images.html",
|
|
"title": "The Adventures of Sherlock Holmes",
|
|
"txt_bytes": 619475,
|
|
"txt_file": "txt/sherlock_holmes.txt",
|
|
"txt_sha256": "d00a2b51c3a403edf40edc4f5be40d109206cf0b4a83f09f1bc8cebafba30594",
|
|
"word_count": 107654
|
|
},
|
|
{
|
|
"fetched_at_utc": "2026-10-22T14:21:38Z",
|
|
"gutenberg_id": "84",
|
|
"raw_bytes": 468370,
|
|
"raw_file": "raw/frankenstein.html",
|
|
"raw_sha256": "23403a6a3b1cace42a06d6c378a6f1acf8ec97c940c652d12fe3c0d30275e58f",
|
|
"slug": "frankenstein",
|
|
"source_url": "https://www.gutenberg.org/cache/epub/84/pg84-images.html",
|
|
"title": "Frankenstein; or, The Modern Prometheus",
|
|
"txt_bytes": 453921,
|
|
"txt_file": "txt/frankenstein.txt",
|
|
"txt_sha256": "0d113dcfc3a1203f1ab24840a70a804562fbc474c2bf3f5050b614f3abd48406",
|
|
"word_count": 78137
|
|
},
|
|
{
|
|
"fetched_at_utc": "2026-10-22T14:21:37Z",
|
|
"gutenberg_id": "11",
|
|
"raw_bytes": 192539,
|
|
"raw_file": "raw/alice_in_wonderland.html",
|
|
"raw_sha256": "7df9c19e9fccac5b3ae9b1f837b247db1c1da93845dfb9e1903dce85013c43d3",
|
|
"slug": "alice_in_wonderland",
|
|
"source_url": "https://www.gutenberg.org/cache/epub/11/pg11-images.html",
|
|
"title": "Alice's Adventures in Wonderland",
|
|
"txt_bytes": 178232,
|
|
"txt_file": "txt/alice_in_wonderland.txt",
|
|
"txt_sha256": "29d04d721acfd87d176b2931f87c934852268b3fe36ed4259abe9c035ed005b6",
|
|
"word_count": 29673
|
|
}
|
|
],
|
|
"schema": "sphinx-archive/1"
|
|
} |