mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2026-01-06 12:21:30 +00:00
also removes mimetype when base64 is not included in image metadata --------- Co-authored-by: ryannikolaidis <ryannikolaidis@users.noreply.github.com>
815 lines
25 KiB
JSON
815 lines
25 KiB
JSON
[
|
|
{
|
|
"element_id": "1eba9da7f7ba3d80d060f638e240cc2c",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "74d66fc2066f7844294c8d162f443892",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "20c74c9c7e2f03ebdaa0cc475abc461e",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "13be5a443b462adf06733ac5f3c3f821",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "e3c59c23c9a8d3251fbe8c0b8bf06a4f",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "a97244e416b60752f3071e465dd63d41",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "dfd9cc8f70664dc0b785e1f2332a0993",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "d597dda3a2ba146bd314a4d3a92c4aac",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "5e75c9860459e175f1087efd0dc40972",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "c41a8ba74f19172536db4877b5e13f7e",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "29d99bc3b2a5fde6029ddfe8b1604f3a",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "589780ba10ade81f721303579ee9bce0",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "7bc5e9d84b41175c9ff8ad841394c2b3",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "caab6974e98b9e03c78191c02591775e",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2 testtext2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "61525bb0c406b033be2849cb375e9fcd",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"image_url": "https://unstructured-ingest-test.atlassian.net/wiki/download/thumbnails/1802252/image-20230709-015203.png?version=1&modificationDate=1689094907437&cacheVersion=1&api=v2&width=680&height=259",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "",
|
|
"type": "Image"
|
|
},
|
|
{
|
|
"element_id": "7e8cf6622ad36f28966178e194feaad8",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 List Item 1",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "eeb9717b5c634b6bb4b4bb1b83101500",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 List Item 1 Nested Item A",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "c5bc1b1b90fd002ca136bc3d76e3d482",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 List Item 1 Nested Item B",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "9ecb8d523cdd75be94294fa2ca440799",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 List Item 2",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "4909ea47e524d3b8fbac470c0663f589",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 List Item 3",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "ab916d1a2aa844a463b48a24637a8b2d",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 List Item 4",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "a9060bb59dfa0b37c1ec13e97228470a",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 List Item 5",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "0dbff111f50ea5a58eee83c85a1c30b5",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
],
|
|
"link_texts": [
|
|
"This is the link for unstructured . io."
|
|
],
|
|
"link_urls": [
|
|
"https://www.unstructured.io/"
|
|
]
|
|
},
|
|
"text": "This is the link for unstructured . io.",
|
|
"type": "NarrativeText"
|
|
},
|
|
{
|
|
"element_id": "ed95477f3bff4586983201b6387c875b",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 Checklist Item 1",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "260cee6fb6f1562e7b1cb0f7644ea64d",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 Checklist Item 2 (checked)",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "6820bf233e6604b7bd6750d0d2b62192",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 Checklist Item 3",
|
|
"type": "ListItem"
|
|
},
|
|
{
|
|
"element_id": "8f13efbe5d5b289c6ce8eb00e2b5fae2",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "😃 😃 😃 😃 😃 😃 😃 😃 😃 😃 😃 😃",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "ecc13666f56ab3fb01917335016cd9c3",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"emphasized_text_contents": [
|
|
"Testdoc2 bold text"
|
|
],
|
|
"emphasized_text_tags": [
|
|
"b"
|
|
],
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 bold text",
|
|
"type": "NarrativeText"
|
|
},
|
|
{
|
|
"element_id": "93ec1210a0bf6e8b0c6c8504648e7489",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"emphasized_text_contents": [
|
|
"Testdoc2 italic text"
|
|
],
|
|
"emphasized_text_tags": [
|
|
"i"
|
|
],
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 italic text",
|
|
"type": "UncategorizedText"
|
|
},
|
|
{
|
|
"element_id": "f3c0e02138cb55302a075d5508843876",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 Heading 1 Sized Text",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "5bc45f2fc513158f644f2c217cc9e54d",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 Heading 2 Sized Text",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "81bebaf32dff5511a7856e553b526fa3",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 Heading 3 Sized Text",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "833cc590b6815b09fd40d1d73a752420",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 Heading 4 Sized Text",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "bff43fdce7563ccbd5cf3354090e8cf3",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "Testdoc2 Heading 5 Sized Text",
|
|
"type": "Title"
|
|
},
|
|
{
|
|
"element_id": "69b2cf7ade2f1034892b2b38b186fdaa",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
],
|
|
"text_as_html": "<table><tr><td>Testdoc2 Table: Column 1 Row 0</td><td>Testdoc2 Table: Column 2 Row 0</td><td>Testdoc2 Table: Column 3 Row 0</td></tr><tr><td>Testdoc2 Table: Column 1 Row 1</td><td>Testdoc2 Table: Column 2 Row 1</td><td>Testdoc2 Table: Column 3 Row 1</td></tr><tr><td>Testdoc2 Table: Column 1 Row 2</td><td>Testdoc2 Table: Column 2 Row 2</td><td>Testdoc2 Table: Column 3 Row 2</td></tr></table>"
|
|
},
|
|
"text": "Testdoc2 Table: Column 1 Row 0 Testdoc2 Table: Column 2 Row 0 Testdoc2 Table: Column 3 Row 0 Testdoc2 Table: Column 1 Row 1 Testdoc2 Table: Column 2 Row 1 Testdoc2 Table: Column 3 Row 1 Testdoc2 Table: Column 1 Row 2 Testdoc2 Table: Column 2 Row 2 Testdoc2 Table: Column 3 Row 2",
|
|
"type": "Table"
|
|
},
|
|
{
|
|
"element_id": "825a8cbb41eecc2f1b29d4b34cb05c2f",
|
|
"metadata": {
|
|
"data_source": {
|
|
"date_created": "2023-07-11T17:01:39.240000",
|
|
"date_modified": "2023-07-11T17:01:47.340000",
|
|
"record_locator": {
|
|
"page_id": "1802252",
|
|
"url": "https://unstructured-ingest-test.atlassian.net"
|
|
},
|
|
"url": "https://unstructured-ingest-test.atlassian.net/wiki/rest/api/content/1802252",
|
|
"version": "1"
|
|
},
|
|
"filetype": "text/html",
|
|
"image_url": "https://unstructured-ingest-test.atlassian.net/wiki/download/thumbnails/1802252/image-20230709-020021.png?version=1&modificationDate=1689094907442&cacheVersion=1&api=v2&width=475&height=236",
|
|
"languages": [
|
|
"eng",
|
|
"fra"
|
|
]
|
|
},
|
|
"text": "",
|
|
"type": "Image"
|
|
}
|
|
] |